Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-12T16:20:32.846517Z
Paper Citation Record · LEDGER
Hymba: A Hybrid-head Architecture for Small Language Models
As of 19 August 2026, this Paper Citation Record lists 100 of 103 outbound references and 43 inbound Pith citation observations for arXiv:2411.13676.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-16T06:04:17.554378Z
A source-named dated measurement, never combined with another source.
Source: pith, observed 2026-08-05T02:28:24.338817Z
Reference resolution
100 of 103 outbound references displayed
- verified exact1
- verified fuzzy14
- unresolved85
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
2
pith, observed 2026-08-05T02:28:24.338817Z
Outbound references
Observation 680b0417-8773-43a0-8e7f-9b09b3a7a5ef · outbound
This paper cites Attention is all you need.Advances in Neural Information Processing Systems, 2017.
Hymba: A Hybrid-head Architecture for Small Language Models Attention is all you need.Advances in Neural Information Processing Systems, 2017
Reference 1
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.284974Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b7babe13-0db6-457e-82c4-2e552c45e11a · outbound
This paper cites Mamba: Linear-Time Sequence Modeling with Selective State Spaces.
Hymba: A Hybrid-head Architecture for Small Language Models Mamba: Linear-Time Sequence Modeling with Selective State Spaces
Reference 2
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.291392Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 89b6ad65-3af9-477f-a3ac-e7c287dcefb3 · outbound
This paper cites Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality.
Hymba: A Hybrid-head Architecture for Small Language Models Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
Reference 3
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.296885Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b6e571fe-5d20-44ee-849c-cfb101d740c9 · outbound
This paper cites An Empirical Study of Mamba-based Language Models.
Hymba: A Hybrid-head Architecture for Small Language Models An Empirical Study of Mamba-based Language Models
Reference 4
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.302339Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ccac880c-419a-4823-9a74-99cfa328a5ef · outbound
This paper cites Simple linear attention language models balance the recall-throughput tradeoff.
Hymba: A Hybrid-head Architecture for Small Language Models Simple linear attention language models balance the recall-throughput tradeoff
Reference 5
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.309050Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 365e0b9a-e682-4f90-99ec-adb327a270a4 · outbound
This paper cites Jamba: A Hybrid Transformer-Mamba Language Model.
Hymba: A Hybrid-head Architecture for Small Language Models Jamba: A Hybrid Transformer-Mamba Language Model
Reference 6
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.314399Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 36a6edb2-9ea8-40f7-8f2a-0ad9df9c4855 · outbound
This paper cites Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling.
Hymba: A Hybrid-head Architecture for Small Language Models Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling
Reference 7
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.321340Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1eab19ac-ab9f-458d-ae84-d9f07161d8e0 · outbound
This paper cites Quantizable transformers: Removing outliers by helping attention heads do nothing.Ad- vances in Neural Information Processing Systems, 36:75067–75096, 2023.
Hymba: A Hybrid-head Architecture for Small Language Models Quantizable transformers: Removing outliers by helping attention heads do nothing.Ad- vances in Neural Information Processing Systems, 36:75067–75096, 2023
Reference 8
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.327340Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d6f7b289-1374-4bd3-a17f-466c8f3a51eb · outbound
This paper cites Attention is off by one.
Hymba: A Hybrid-head Architecture for Small Language Models Attention is off by one
Reference 9
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.332796Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f8d69819-4e30-42c2-9f5e-cb8f74ce3df0 · outbound
This paper cites Efficient Streaming Language Models with Attention Sinks.
Hymba: A Hybrid-head Architecture for Small Language Models Efficient Streaming Language Models with Attention Sinks
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.337908Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation baa5f6ec-1d50-4f0b-9471-2fe7120524d9 · outbound
This paper cites Reducing Transformer Key-Value Cache Size with Cross-Layer Attention.
Hymba: A Hybrid-head Architecture for Small Language Models Reducing Transformer Key-Value Cache Size with Cross-Layer Attention
Reference 11
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.344744Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1ad8a78a-1823-43bd-9217-9601d3c26c4f · outbound
This paper cites Direct preference optimization: Your language model is secretly a reward model.Advances in Neural Information Processing Systems, 36, 2024.
Hymba: A Hybrid-head Architecture for Small Language Models Direct preference optimization: Your language model is secretly a reward model.Advances in Neural Information Processing Systems, 36, 2024
Reference 12
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.351411Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation cf706014-e8d5-4e99-b15d-8b48e360f942 · outbound
This paper cites Dora: Weight- decomposed low-rank adaptation.
Hymba: A Hybrid-head Architecture for Small Language Models Dora: Weight- decomposed low-rank adaptation
Reference 13
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.357034Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation cd50ac20-f563-4bda-b000-3d2fb9916443 · outbound
This paper cites RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models.
Hymba: A Hybrid-head Architecture for Small Language Models RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models
Reference 14
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.362269Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0e9bd003-c636-4f45-b859-121c1be6fdf6 · outbound
This paper cites Repeat After Me: Transformers are Better than State Space Models at Copying.
Hymba: A Hybrid-head Architecture for Small Language Models Repeat After Me: Transformers are Better than State Space Models at Copying
Reference 15
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.368162Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7131e50a-bb25-4aa6-83ab-f318ddd29d06 · outbound
This paper cites Decimamba: Exploring the length extrapolation potential of mamba, 2024.
Hymba: A Hybrid-head Architecture for Small Language Models Decimamba: Exploring the length extrapolation potential of mamba, 2024
Reference 16
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.373999Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0bf35d70-0d9a-4231-82d4-edfbee70b0c8 · outbound
This paper cites Zamba: A Compact 7B SSM Hybrid Model.
Hymba: A Hybrid-head Architecture for Small Language Models Zamba: A Compact 7B SSM Hybrid Model
Reference 17
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.379199Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation abd1283e-8c31-433e-8508-0dd2500a3c4d · outbound
This paper cites Interpreting Key Mechanisms of Factual Recall in Transformer-Based Language Models.
Hymba: A Hybrid-head Architecture for Small Language Models Interpreting Key Mechanisms of Factual Recall in Transformer-Based Language Models
Reference 18
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.384743Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d6726c42-5169-4d68-8ad3-6e22d63dc772 · outbound
This paper cites Talking Heads: Understanding Inter-layer Communication in Transformer Language Models.
Hymba: A Hybrid-head Architecture for Small Language Models Talking Heads: Understanding Inter-layer Communication in Transformer Language Models
Reference 19
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.390532Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d8706e9e-2cf8-4435-8259-39f7b32885db · outbound
This paper cites The Hidden Attention of Mamba Models.
Hymba: A Hybrid-head Architecture for Small Language Models The Hidden Attention of Mamba Models
Reference 20
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.396513Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ff8cedd4-32ed-4362-bb4e-110aeabb4438 · outbound
This paper cites Hellaswag: Can a machine really finish your sentence? InProceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019.
Hymba: A Hybrid-head Architecture for Small Language Models Hellaswag: Can a machine really finish your sentence? InProceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019
Reference 21
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.402349Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ec508037-f6d4-41a1-b849-9ac4e6e33d87 · outbound
This paper cites Longformer: The Long-Document Transformer.
Hymba: A Hybrid-head Architecture for Small Language Models Longformer: The Long-Document Transformer
Reference 22
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.407666Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a54f002f-c183-4e53-88e0-19641b7e1091 · outbound
This paper cites MiniCache: KV Cache Compression in Depth Dimension for Large Language Models.
Hymba: A Hybrid-head Architecture for Small Language Models MiniCache: KV Cache Compression in Depth Dimension for Large Language Models
Reference 23
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.412901Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 616dfada-358d-4b3c-9072-8de28a846d50 · outbound
This paper cites SQuAD: 100,000+ questions for machine comprehension of text.
Hymba: A Hybrid-head Architecture for Small Language Models SQuAD: 100,000+ questions for machine comprehension of text
Reference 24
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.418068Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 88ab6c05-250c-437a-a1af-02dbdfa49a68 · outbound
This paper cites Training Verifiers to Solve Math Word Problems.
Hymba: A Hybrid-head Architecture for Small Language Models Training Verifiers to Solve Math Word Problems
Reference 25
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.423182Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1330a48e-f9b6-4671-b370-e0fb58ba821d · outbound
This paper cites Codeparrot/github-code · datasets at hugging face.
Hymba: A Hybrid-head Architecture for Small Language Models Codeparrot/github-code · datasets at hugging face
Reference 26
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.429431Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 19db1aa1-d488-4222-b898-838bd9e87b48 · outbound
This paper cites Lm-infinite: Zero-shot extreme length generalization for large lan- guage models.
Hymba: A Hybrid-head Architecture for Small Language Models Lm-infinite: Zero-shot extreme length generalization for large lan- guage models
Reference 27
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.434742Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c68a54bb-3d63-4a46-81c4-53fda8165f8b · outbound
This paper cites A framework for few-shot language model evaluation, 12 2023.
Hymba: A Hybrid-head Architecture for Small Language Models A framework for few-shot language model evaluation, 12 2023
Reference 28
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.439564Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2bbaa4bd-2308-4c11-ad31-97bc5337a56e · outbound
This paper cites Simple lin- ear attention language models balance the recall- throughput tradeoff, 2024.
Hymba: A Hybrid-head Architecture for Small Language Models Simple lin- ear attention language models balance the recall- throughput tradeoff, 2024
Reference 29
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.444967Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 90ff8672-6050-444f-8575-294829ebe974 · outbound
This paper cites Vision Transformers Need Registers.
Hymba: A Hybrid-head Architecture for Small Language Models Vision Transformers Need Registers
Reference 30
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.451809Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 56be0203-c52e-44a3-81e0-d720192ebaa3 · outbound
This paper cites Attention if off by one, 2023.
Hymba: A Hybrid-head Architecture for Small Language Models Attention if off by one, 2023
Reference 31
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.457365Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fc87f738-bec5-4b84-9cce-ced81552c1d1 · outbound
This paper cites The Power of Scale for Parameter-Efficient Prompt Tuning.
Hymba: A Hybrid-head Architecture for Small Language Models The Power of Scale for Parameter-Efficient Prompt Tuning
Reference 32
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.463210Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4a05abdf-034d-4bee-9039-8037ad9f7cac · outbound
This paper cites PPT: Pre-trained Prompt Tuning for Few-shot Learning.
Hymba: A Hybrid-head Architecture for Small Language Models PPT: Pre-trained Prompt Tuning for Few-shot Learning
Reference 33
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.469793Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7c9000d7-3e32-42df-96a3-42a970f93439 · outbound
This paper cites The Adventures of Oliver Twist.
Hymba: A Hybrid-head Architecture for Small Language Models The Adventures of Oliver Twist
Reference 34
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.475413Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3061283c-4d28-4fd3-9414-6f5b291602c8 · outbound
This paper cites Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation.
Hymba: A Hybrid-head Architecture for Small Language Models Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation
Reference 35
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.480631Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ab30e457-35f0-4c87-ac38-b0664f91c465 · outbound
This paper cites Dimakis, Yair Carmon, Achal Dave, Ludwig Schmidt, and Vaishaal Shankar.
Hymba: A Hybrid-head Architecture for Small Language Models Dimakis, Yair Carmon, Achal Dave, Ludwig Schmidt, and Vaishaal Shankar
Reference 36
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.487084Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation cae4d716-681c-43bd-8289-73cc594b3cfa · outbound
This paper cites Smollm-corpus, 2024.
Hymba: A Hybrid-head Architecture for Small Language Models Smollm-corpus, 2024
Reference 37
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.491936Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation caf31356-346a-43a1-8f23-506738118c19 · outbound
This paper cites MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies.
Hymba: A Hybrid-head Architecture for Small Language Models MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies
Reference 38
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.496829Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b5d9d355-6f37-489e-be80-50920c2dc077 · outbound
This paper cites The Llama 3 Herd of Models.
Hymba: A Hybrid-head Architecture for Small Language Models The Llama 3 Herd of Models
Reference 39
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.501507Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 296da1dc-63fe-4361-af32-02859fd87607 · outbound
This paper cites JetMoE: Reaching Llama2 Performance with 0.1M Dollars.
Hymba: A Hybrid-head Architecture for Small Language Models JetMoE: Reaching Llama2 Performance with 0.1M Dollars
Reference 40
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.506393Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3df9b504-4256-49ef-879d-38694bac4cb1 · outbound
This paper cites Dynamically scaled rope further increases per- formance of long context llama with zero finetuning, July 2023.
Hymba: A Hybrid-head Architecture for Small Language Models Dynamically scaled rope further increases per- formance of long context llama with zero finetuning, July 2023
Reference 41
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.513029Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a0d2a8e5-58a7-4721-86c3-cd51d1d08bfa · outbound
This paper cites Llama 3.2: Revolutionizing edge AI and vision with open, customizable models.
Hymba: A Hybrid-head Architecture for Small Language Models Llama 3.2: Revolutionizing edge AI and vision with open, customizable models
Reference 42
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.518667Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 05674b16-12c6-4989-90b2-3bc14d7d68d4 · outbound
This paper cites Smollm - blazingly fast and remarkably powerful, 2024.
Hymba: A Hybrid-head Architecture for Small Language Models Smollm - blazingly fast and remarkably powerful, 2024
Reference 43
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.523538Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1ceef134-b3aa-44cc-bede-2b90a580dda4 · outbound
This paper cites Smollm2 - with great data, comes great performance, 2024.
Hymba: A Hybrid-head Architecture for Small Language Models Smollm2 - with great data, comes great performance, 2024
Reference 44
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.528148Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fbcb8e86-336d-4f74-8260-ca0adc84773a · outbound
This paper cites Amd-olmo: A series of 1b language models trained from scratch by amd on amd instinct™ mi250 gpus., October 2024.
Hymba: A Hybrid-head Architecture for Small Language Models Amd-olmo: A series of 1b language models trained from scratch by amd on amd instinct™ mi250 gpus., October 2024
Reference 45
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.532645Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e3896155-8905-435a-9ee9-1aea20503140 · outbound
This paper cites Stable LM 2 1.6B Technical Report.
Hymba: A Hybrid-head Architecture for Small Language Models Stable LM 2 1.6B Technical Report
Reference 46
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.537094Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4e6c3d94-b939-42ac-98bb-d7d51d4ec30d · outbound
This paper cites an unresolved cited work.
Hymba: A Hybrid-head Architecture for Small Language Models Unresolved cited work
Reference 47
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.542119Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation be1b41a3-91d5-4def-997e-10f0fa9990c9 · outbound
This paper cites HuggingFaceTB/cosmo-1b.
Hymba: A Hybrid-head Architecture for Small Language Models HuggingFaceTB/cosmo-1b
Reference 48
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.547512Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b37f3336-fccb-4338-b0c2-fb463294b7c4 · outbound
This paper cites Textbooks Are All You Need II: phi-1.5 technical report.
Hymba: A Hybrid-head Architecture for Small Language Models Textbooks Are All You Need II: phi-1.5 technical report
Reference 49
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.553121Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 033b67d2-727e-4f18-a939-b2ea0cd480fd · outbound
This paper cites H2O-Danube-1.8B Technical Report.
Hymba: A Hybrid-head Architecture for Small Language Models H2O-Danube-1.8B Technical Report
Reference 50
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.559404Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0413a501-64b7-4ce5-8b63-038f12d9bb01 · outbound
This paper cites Openelm: An efficient language model family with open training and infer- ence framework.
Hymba: A Hybrid-head Architecture for Small Language Models Openelm: An efficient language model family with open training and infer- ence framework
Reference 51
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T16:20:34.605592Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 46161be2-7e94-47eb-81a3-a9a7b49db430 · outbound
This paper cites The On-Device Intelligence Update.
Hymba: A Hybrid-head Architecture for Small Language Models The On-Device Intelligence Update
Reference 52
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T16:20:34.589797Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 5f05db3c-05b3-4b1e-8d73-52bf3addbfe6 · outbound
This paper cites Introducing Meta Llama 3: The most capable openly available LLM to date.
Hymba: A Hybrid-head Architecture for Small Language Models Introducing Meta Llama 3: The most capable openly available LLM to date
Reference 53
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T16:20:34.573954Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 15cd0a8d-46ce-4adb-8f68-8c6f1be10571 · outbound
This paper cites The fineweb datasets: Decanting the web for the finest text data at scale, 2024.
Hymba: A Hybrid-head Architecture for Small Language Models The fineweb datasets: Decanting the web for the finest text data at scale, 2024
Reference 54
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T16:20:34.556144Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation f0af0be5-a3eb-465b-b186-2cb0ece0b238 · outbound
This paper cites OpenCeres: When open information extrac- tion meets the semi-structured web.
Hymba: A Hybrid-head Architecture for Small Language Models OpenCeres: When open information extrac- tion meets the semi-structured web
Reference 55
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T16:20:34.537885Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 5ecc7b57-4cab-466a-b602-4555974fedff · outbound
This paper cites Know what you don’t know: Unanswerable questions for squad, 2018.
Hymba: A Hybrid-head Architecture for Small Language Models Know what you don’t know: Unanswerable questions for squad, 2018
Reference 56
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T16:20:34.519467Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 0645f9af-d932-463c-9387-0862a26e8a30 · outbound
This paper cites Scaling Laws of RoPE-based Extrapolation.
Hymba: A Hybrid-head Architecture for Small Language Models Scaling Laws of RoPE-based Extrapolation
Reference 57
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.594000Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b32b6aa2-5522-4e9c-9d22-54a4c927d5c1 · outbound
This paper cites YaRN: Efficient Context Window Extension of Large Language Models.
Hymba: A Hybrid-head Architecture for Small Language Models YaRN: Efficient Context Window Extension of Large Language Models
Reference 58
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.599060Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e016935e-bac5-493b-a86e-0ac1c4da9bef · outbound
This paper cites Inf bench: Extend- ing long context evaluation beyond 100k tokens.
Hymba: A Hybrid-head Architecture for Small Language Models Inf bench: Extend- ing long context evaluation beyond 100k tokens
Reference 59
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T16:20:34.503186Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 31c78362-9544-490e-8e41-50254e2057c0 · outbound
This paper cites Lost in the middle: How language models use long contexts.
Hymba: A Hybrid-head Architecture for Small Language Models Lost in the middle: How language models use long contexts
Reference 60
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T16:20:34.483400Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 53dd1e57-cae1-4b27-8e87-721fafa76a15 · outbound
This paper cites Zephyr: Direct Distillation of LM Alignment.
Hymba: A Hybrid-head Architecture for Small Language Models Zephyr: Direct Distillation of LM Alignment
Reference 61
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.614443Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2409a0ef-cda0-4394-b326-c54fcc136470 · outbound
This paper cites Lmflow: An extensible toolkit for finetuning and inference of large foundation models.
Hymba: A Hybrid-head Architecture for Small Language Models Lmflow: An extensible toolkit for finetuning and inference of large foundation models
Reference 62
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T16:20:34.465379Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 0dcee516-9775-4707-b5fb-406db6415ad2 · outbound
This paper cites RLHF Workflow: From Reward Modeling to Online RLHF.
Hymba: A Hybrid-head Architecture for Small Language Models RLHF Workflow: From Reward Modeling to Online RLHF
Reference 63
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.624660Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c642de7c-5d9c-4e4f-a650-22168a54b64c · outbound
This paper cites Qwen2.5: A party of foundation models, September 2024.
Hymba: A Hybrid-head Architecture for Small Language Models Qwen2.5: A party of foundation models, September 2024
Reference 64
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.630702Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 64695960-143f-4a5e-9ed5-cd415cdc9296 · outbound
This paper cites Patil, Ion Stoica, and Joseph E.
Hymba: A Hybrid-head Architecture for Small Language Models Patil, Ion Stoica, and Joseph E
Reference 65
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T16:20:34.437227Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation a3746c78-2e6c-4896-a81b-4d88e5fffe61 · outbound
This paper cites BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.
Hymba: A Hybrid-head Architecture for Small Language Models BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Reference 66
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.641414Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b756f457-6c40-490f-9ee0-57b8af45360a · outbound
This paper cites an unresolved cited work.
Hymba: A Hybrid-head Architecture for Small Language Models Unresolved cited work
Reference 67
- Resolution
- unresolved
- raw_fallback, observed 2026-08-12T16:20:34.419609Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 772127fc-d81c-482e-a74c-8c86a214e4d9 · outbound
This paper cites Scaling Up Models and Data with $\texttt{t5x}$ and $\texttt{seqio}$.
Hymba: A Hybrid-head Architecture for Small Language Models Scaling Up Models and Data with $\texttt{t5x}$ and $\texttt{seqio}$
Reference 68
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.651174Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 047ad6c2-2cf8-43d1-80bd-7ca9ba659b86 · outbound
This paper cites TransNormerLLM: A Faster and Better Large Language Model with Improved TransNormer.
Hymba: A Hybrid-head Architecture for Small Language Models TransNormerLLM: A Faster and Better Large Language Model with Improved TransNormer
Reference 69
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.657559Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9724b39c-ef0b-4e9d-8b6c-615ab811ea0d · outbound
This paper cites Scaling Laws for Neural Language Models.
Hymba: A Hybrid-head Architecture for Small Language Models Scaling Laws for Neural Language Models
Reference 70
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.662525Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1368313a-1517-4bd9-8dbc-342565407ef3 · outbound
This paper cites Pythia: A suite for analyzing large language models across training and scaling.
Hymba: A Hybrid-head Architecture for Small Language Models Pythia: A suite for analyzing large language models across training and scaling
Reference 71
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T16:20:34.399440Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 24de5703-f677-42d0-a3f8-0c4e18948c10 · outbound
This paper cites GLM: General Language Model Pretraining with Autoregressive Blank Infilling.
Hymba: A Hybrid-head Architecture for Small Language Models GLM: General Language Model Pretraining with Autoregressive Blank Infilling
Reference 72
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.674221Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d38f3495-d6c1-404e-894e-47dc525869ea · outbound
This paper cites OPT: Open Pre-trained Transformer Language Models.
Hymba: A Hybrid-head Architecture for Small Language Models OPT: Open Pre-trained Transformer Language Models
Reference 73
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.681439Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 178da746-bc93-45b6-b9c6-b366210b9a6e · outbound
This paper cites Mistral 7B.
Hymba: A Hybrid-head Architecture for Small Language Models Mistral 7B
Reference 74
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.687367Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 554820f4-fc6b-4b8b-ba72-9e6d399c26ec · outbound
This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.
Hymba: A Hybrid-head Architecture for Small Language Models Llama 2: Open Foundation and Fine-Tuned Chat Models
Reference 75
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.697912Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5c4f27a7-868a-489d-a502-dda45593d24a · outbound
This paper cites Gemma 2: Improving Open Language Models at a Practical Size.
Hymba: A Hybrid-head Architecture for Small Language Models Gemma 2: Improving Open Language Models at a Practical Size
Reference 76
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.703994Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ed7d84d0-6053-4dcd-8a16-0f28dc7cabb4 · outbound
This paper cites GPT-4 Technical Report.
Hymba: A Hybrid-head Architecture for Small Language Models GPT-4 Technical Report
Reference 77
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.711332Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2738873a-0eeb-4cfb-bde8-7bdcc9a3f562 · outbound
This paper cites RWKV: Reinventing RNNs for the Transformer Era.
Hymba: A Hybrid-head Architecture for Small Language Models RWKV: Reinventing RNNs for the Transformer Era
Reference 78
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.717475Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5700e08d-826e-4db2-b63f-f7907257b64c · outbound
This paper cites Retentive Network: A Successor to Transformer for Large Language Models.
Hymba: A Hybrid-head Architecture for Small Language Models Retentive Network: A Successor to Transformer for Large Language Models
Reference 79
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.723486Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6bf116a2-ac4f-44ad-b0c3-78be8e9fcb54 · outbound
This paper cites Gated Linear Attention Transformers with Hardware-Efficient Training.
Hymba: A Hybrid-head Architecture for Small Language Models Gated Linear Attention Transformers with Hardware-Efficient Training
Reference 80
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.731248Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation bfa4a184-e756-450c-8edd-6282fb87788d · outbound
This paper cites Transformers are rnns: Fast autoregressive transformers with linear atten- tion.
Hymba: A Hybrid-head Architecture for Small Language Models Transformers are rnns: Fast autoregressive transformers with linear atten- tion
Reference 81
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T16:20:34.381569Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 7f23ff8e-6b62-4c9d-8e1a-f79088d7ba6a · outbound
This paper cites Efficiently Modeling Long Sequences with Structured State Spaces.
Hymba: A Hybrid-head Architecture for Small Language Models Efficiently Modeling Long Sequences with Structured State Spaces
Reference 82
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.744134Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ff1bf771-e877-43d0-99c0-003eb8e3e7a8 · outbound
This paper cites Combining recurrent, convolutional, and continuous-time models with linear state space layers.Advances in neural information processing systems, 34:572–585, 2021.
Hymba: A Hybrid-head Architecture for Small Language Models Combining recurrent, convolutional, and continuous-time models with linear state space layers.Advances in neural information processing systems, 34:572–585, 2021
Reference 83
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.749783Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 427a0b1a-4761-496c-bc1b-3c27e6828253 · outbound
This paper cites Can Mamba Learn How to Learn? A Comparative Study on In-Context Learning Tasks.
Hymba: A Hybrid-head Architecture for Small Language Models Can Mamba Learn How to Learn? A Comparative Study on In-Context Learning Tasks
Reference 84
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.755868Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 221fdb52-126f-4b54-bf02-399f2e468f51 · outbound
This paper cites Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models.
Hymba: A Hybrid-head Architecture for Small Language Models Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models
Reference 85
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.762403Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9c15ad46-0b6c-42ef-a3f2-853f11c72e3d · outbound
This paper cites Block- state transformers.
Hymba: A Hybrid-head Architecture for Small Language Models Block- state transformers
Reference 86
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T16:20:34.353639Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 1abb3645-4ada-4ffe-9b84-44fbd7aabdc4 · outbound
This paper cites Diag- onal state space augmented transformers for speech recognition.
Hymba: A Hybrid-head Architecture for Small Language Models Diag- onal state space augmented transformers for speech recognition
Reference 87
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T16:20:34.337491Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 13209097-82c5-4c4e-a91b-74485a254335 · outbound
This paper cites Parallelizing Linear Transformers with the Delta Rule over Sequence Length.
Hymba: A Hybrid-head Architecture for Small Language Models Parallelizing Linear Transformers with the Delta Rule over Sequence Length
Reference 88
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.778566Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 01b40957-50f6-4b34-b5f6-444ab50118ab · outbound
This paper cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.
Hymba: A Hybrid-head Architecture for Small Language Models An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Reference 89
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.785778Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ea642133-f126-4478-9e44-bf271734c227 · outbound
This paper cites Memory Transformer.
Hymba: A Hybrid-head Architecture for Small Language Models Memory Transformer
Reference 90
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T16:20:32.792479Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d948f96a-c773-4dc5-8c8b-3a17c9314eac · outbound
This paper cites A framework for few-shot language model evaluation, 07 2024.
Hymba: A Hybrid-head Architecture for Small Language Models A framework for few-shot language model evaluation, 07 2024
Reference 91
- Resolution
- verified exact
- raw_fallback, observed 2026-08-12T16:20:33.077400Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 0f644df1-24e6-4a17-a1c0-472e4ff55e6f · outbound
This paper cites an unresolved cited work.
Hymba: A Hybrid-head Architecture for Small Language Models Unresolved cited work
Reference 92
- Resolution
- unresolved
- raw_fallback, observed 2026-08-12T16:20:34.320092Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 9ea2b237-2054-4c78-bd6b-69498b9596f1 · outbound
This paper cites an unresolved cited work.
Hymba: A Hybrid-head Architecture for Small Language Models Unresolved cited work
Reference 93
- Resolution
- unresolved
- raw_fallback, observed 2026-08-12T16:20:34.304626Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation a9e769b4-4418-4fb2-9c30-200f13ac80a3 · outbound
This paper cites an unresolved cited work.
Hymba: A Hybrid-head Architecture for Small Language Models Unresolved cited work
Reference 94
- Resolution
- unresolved
- raw_fallback, observed 2026-08-12T16:20:34.286627Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 93b27070-6193-4306-97f8-32226790fcb6 · outbound
This paper cites an unresolved cited work.
Hymba: A Hybrid-head Architecture for Small Language Models Unresolved cited work
Reference 95
- Resolution
- unresolved
- raw_fallback, observed 2026-08-12T16:20:34.271386Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation c240863e-5391-4c8f-992a-72e7375d71c2 · outbound
This paper cites an unresolved cited work.
Hymba: A Hybrid-head Architecture for Small Language Models Unresolved cited work
Reference 96
- Resolution
- unresolved
- raw_fallback, observed 2026-08-12T16:20:34.256058Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 27524bd6-e83a-4b79-8182-9f5bbb45d8b9 · outbound
This paper cites an unresolved cited work.
Hymba: A Hybrid-head Architecture for Small Language Models Unresolved cited work
Reference 97
- Resolution
- unresolved
- raw_fallback, observed 2026-08-12T16:20:34.240168Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation e177609c-60b2-4ec8-ba05-bfd6d75b6359 · outbound
This paper cites an unresolved cited work.
Hymba: A Hybrid-head Architecture for Small Language Models Unresolved cited work
Reference 98
- Resolution
- unresolved
- raw_fallback, observed 2026-08-12T16:20:34.221010Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 8146592d-b368-49c7-af4b-0a347ab669e0 · outbound
This paper cites an unresolved cited work.
Hymba: A Hybrid-head Architecture for Small Language Models Unresolved cited work
Reference 99
- Resolution
- unresolved
- raw_fallback, observed 2026-08-12T16:20:34.201109Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation a9cd995e-1094-4218-948d-012d8ccbd4df · outbound
This paper cites an unresolved cited work.
Hymba: A Hybrid-head Architecture for Small Language Models Unresolved cited work
Reference 100
- Resolution
- unresolved
- raw_fallback, observed 2026-08-12T16:20:34.183542Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Pith citing papers
Observation e8dd4dfb-103d-4fdd-ba9e-d44c2d708ff1 · inbound
Titans: Learning to Memorize at Test Time cites this paper.
Titans: Learning to Memorize at Test Time Hymba: A Hybrid-head Architecture for Small Language Models
Reference 31
- Resolution
- verified exact
- arxiv_id, observed 2026-05-14T22:08:15.324590Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 3cf72c39-56e3-4580-92ce-4b5fb40f27dd · inbound
ARWKV: Pretrain is not what we need, an RNN-Attention-Based Language Model Born from Transformer cites this paper.
ARWKV: Pretrain is not what we need, an RNN-Attention-Based Language Model Born from Transformer Hymba: A Hybrid-head Architecture for Small Language Models
Reference 3
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:12:09.285754Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fea57a3b-6a94-4969-a6af-02e7ca4a10e0 · inbound
Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices cites this paper.
Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices Hymba: A Hybrid-head Architecture for Small Language Models
Reference 64
- Resolution
- verified exact
- arxiv_id, observed 2026-05-23T01:05:16.456536Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation f1b3ad46-c1d1-457c-8807-7c1adc1348d9 · inbound
Fine-Grained Fusion: The Missing Piece in Area-Efficient State Space Model Acceleration cites this paper.
Fine-Grained Fusion: The Missing Piece in Area-Efficient State Space Model Acceleration Hymba: A Hybrid-head Architecture for Small Language Models
Reference 2
- Resolution
- verified exact
- arxiv_id, observed 2026-05-22T19:11:57.910134Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation fe8bfa86-92cd-4487-8296-e4d8b474fb52 · inbound
WuNeng: Hybrid State with Attention cites this paper.
WuNeng: Hybrid State with Attention Hymba: A Hybrid-head Architecture for Small Language Models
Reference 2024
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T06:04:17.554378Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation baeac036-1bd8-40a0-aafe-0c79739615b3 · inbound
Recall with Reasoning: Chain-of-Thought Distillation for Mamba's Long-Context Memory and Extrapolation cites this paper.
Recall with Reasoning: Chain-of-Thought Distillation for Mamba's Long-Context Memory and Extrapolation Hymba: A Hybrid-head Architecture for Small Language Models
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T23:56:22.035105Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6e606860-5a8e-47d4-8058-ddd8ec7e988d · inbound
Overflow Prevention Enhances Long-Context Recurrent LLMs cites this paper.
Overflow Prevention Enhances Long-Context Recurrent LLMs Hymba: A Hybrid-head Architecture for Small Language Models
Reference 16
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T22:12:58.603905Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 82ae23a5-1ebd-4d31-bb29-1c836f3c8e44 · inbound
Balancing Computation Load and Representation Expressivity in Parallel Hybrid Neural Networks cites this paper.
Balancing Computation Load and Representation Expressivity in Parallel Hybrid Neural Networks Hymba: A Hybrid-head Architecture for Small Language Models
Reference 2024
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T14:17:23.650165Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d21d9efc-827a-407c-8150-307bcf69d8c2 · inbound
Small Language Models are the Future of Agentic AI cites this paper.
Small Language Models are the Future of Agentic AI Hymba: A Hybrid-head Architecture for Small Language Models
Reference 23
- Resolution
- verified exact
- arxiv_id, observed 2026-05-16T11:55:51.030625Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 3b22685c-af14-40c0-8907-133b90e7a683 · inbound
Towards Efficient Multi-LLM Inference: Characterization and Analysis of LLM Routing and Hierarchical Techniques cites this paper.
Towards Efficient Multi-LLM Inference: Characterization and Analysis of LLM Routing and Hierarchical Techniques Hymba: A Hybrid-head Architecture for Small Language Models
Reference 57
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:56:56.896718Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5d536d28-56ee-48fd-98f7-a858af3525ea · inbound
SeerAttention-R: Sparse Attention Adaptation for Long Reasoning cites this paper.
SeerAttention-R: Sparse Attention Adaptation for Long Reasoning Hymba: A Hybrid-head Architecture for Small Language Models
Reference 16
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:06:32.591124Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 25719a15-1504-4c2e-84f1-b2e79e8d364b · inbound
SparseSSM: Efficient Selective Structured State Space Models Can Be Pruned in One-Shot cites this paper.
SparseSSM: Efficient Selective Structured State Space Models Can Be Pruned in One-Shot Hymba: A Hybrid-head Architecture for Small Language Models
Reference 27
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T04:48:38.651983Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b8137f2f-5bd4-4a54-b85c-6ec7b1077466 · inbound
Routing Mamba: Scaling State Space Models with Mixture-of-Experts Projection cites this paper.
Routing Mamba: Scaling State Space Models with Mixture-of-Experts Projection Hymba: A Hybrid-head Architecture for Small Language Models
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:28:44.573565Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0d34d1ff-41e9-479a-94c8-75fe139c49a6 · inbound
System-performance and cost modeling of Large Language Model training and inference cites this paper.
System-performance and cost modeling of Large Language Model training and inference Hymba: A Hybrid-head Architecture for Small Language Models
Reference 18
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T20:36:00.876438Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4e4c4713-4027-417f-aa9d-b53bbadf77ac · inbound
Falcon-H1: A Family of Hybrid-Head Language Models Redefining Efficiency and Performance cites this paper.
Falcon-H1: A Family of Hybrid-Head Language Models Redefining Efficiency and Performance Hymba: A Hybrid-head Architecture for Small Language Models
Reference 35
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T11:44:04.935445Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 11be0f2c-da88-4262-8e93-b57e802bb9f9 · inbound
SpikingBrain: Spiking Brain-inspired Large Models cites this paper.
SpikingBrain: Spiking Brain-inspired Large Models Hymba: A Hybrid-head Architecture for Small Language Models
Reference 8
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T18:51:45.749016Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 5a8b7ae4-45b6-48a6-93be-61fa93b10ba5 · inbound
Short window attention enables long-term memorization cites this paper.
Short window attention enables long-term memorization Hymba: A Hybrid-head Architecture for Small Language Models
Reference 11
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-18T12:11:21.791249Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 272efa11-27ed-4cf9-b197-38d0d2d85232 · inbound
Hybrid Architectures for Language Models: Systematic Analysis and Design Insights cites this paper.
Hybrid Architectures for Language Models: Systematic Analysis and Design Insights Hymba: A Hybrid-head Architecture for Small Language Models
Reference 13
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T10:21:15.114330Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 2877e21b-05ea-4b5d-99a9-8fb659bc4e14 · inbound
Kimi Linear: An Expressive, Efficient Attention Architecture cites this paper.
Kimi Linear: An Expressive, Efficient Attention Architecture Hymba: A Hybrid-head Architecture for Small Language Models
Reference 22
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T23:49:11.040289Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 50527f6e-efcb-4e44-ac2f-79c9f4ddbb18 · inbound
Gated KalmaNet: A Fading Memory Layer Through Test-Time Ridge Regression cites this paper.
Gated KalmaNet: A Fading Memory Layer Through Test-Time Ridge Regression Hymba: A Hybrid-head Architecture for Small Language Models
Reference 12
- Resolution
- verified exact
- arxiv_id, observed 2026-05-21T18:00:27.018953Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 72f4a784-24bb-4a8d-aaa1-e1595598e1d5 · inbound
Hidden State Poisoning Attacks against Mamba-based Language Models cites this paper.
Hidden State Poisoning Attacks against Mamba-based Language Models Hymba: A Hybrid-head Architecture for Small Language Models
Reference 3
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-16T18:18:14.502702Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 6be18e09-4e1c-4982-a403-69dfe3ce19d0 · inbound
Neural Attention Search Linear: Towards Adaptive Token-Level Hybrid Attention Models cites this paper.
Neural Attention Search Linear: Towards Adaptive Token-Level Hybrid Attention Models Hymba: A Hybrid-head Architecture for Small Language Models
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T04:55:41.380193Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a624811f-df97-43d8-a275-32d8201fa572 · inbound
When to Think Fast and Slow? AMOR: Adaptive Entropy Gate for Hybrid Models cites this paper.
When to Think Fast and Slow? AMOR: Adaptive Entropy Gate for Hybrid Models Hymba: A Hybrid-head Architecture for Small Language Models
Reference 7
- Resolution
- verified exact
- arxiv_id, observed 2026-05-16T11:50:52.833832Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 00fb7d85-b6dd-487d-9948-49c2878c645e · inbound
Beyond Test-Time Memory: State-Space Optimal Control for LLM Reasoning cites this paper.
Beyond Test-Time Memory: State-Space Optimal Control for LLM Reasoning Hymba: A Hybrid-head Architecture for Small Language Models
Reference 9
- Resolution
- unresolved
- no resolver link, observed 2026-07-15T12:09:16.468055Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 15f60ccd-f6c6-456f-89e0-71df9f3af120 · inbound
LPC-SM: Local Predictive Coding and Sparse Memory for Long-Context Language Modeling cites this paper.
LPC-SM: Local Predictive Coding and Sparse Memory for Long-Context Language Modeling Hymba: A Hybrid-head Architecture for Small Language Models
Reference 4
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T11:25:31.076370Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 46ca10e9-ace1-44fb-b446-132a4ae48b7f · inbound
The Hyperscale Lottery: How State-Space Models Have Sacrificed Edge Efficiency cites this paper.
The Hyperscale Lottery: How State-Space Models Have Sacrificed Edge Efficiency Hymba: A Hybrid-head Architecture for Small Language Models
Reference 3
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T06:11:00.959927Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 8bfaa0de-f961-4411-9688-08702050cf8b · inbound
A KL Lens on Quantization: Fast, Forward-Only Sensitivity for Mixed-Precision SSM-Transformer Models cites this paper.
A KL Lens on Quantization: Fast, Forward-Only Sensitivity for Mixed-Precision SSM-Transformer Models Hymba: A Hybrid-head Architecture for Small Language Models
Reference 5
- Resolution
- verified exact
- arxiv_id, observed 2026-05-10T14:25:29.249694Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation c966df19-ca58-42f5-a39a-dbba1d7478aa · inbound
SpikingBrain2.0: Brain-Inspired Foundation Models for Efficient Long-Context and Cross-Platform Inference cites this paper.
SpikingBrain2.0: Brain-Inspired Foundation Models for Efficient Long-Context and Cross-Platform Inference Hymba: A Hybrid-head Architecture for Small Language Models
Reference 12
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T19:21:06.799830Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 4b7653f2-4ada-4594-ba78-d7232a61fe89 · inbound
Echo: KV-Cache-Free Associative Recall with Spectral Koopman Operators cites this paper.
Echo: KV-Cache-Free Associative Recall with Spectral Koopman Operators Hymba: A Hybrid-head Architecture for Small Language Models
Reference 8
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T04:25:56.106800Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation f0f0f8a2-f532-4519-9664-242e3c1996ef · inbound
A Single-Layer Model Can Do Language Modeling cites this paper.
A Single-Layer Model Can Do Language Modeling Hymba: A Hybrid-head Architecture for Small Language Models
Reference 4
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T06:01:25.421310Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 33411379-0fd7-478e-9fe3-057c3e355ed0 · inbound
Asymmetric Virtual Memory Paging for Hybrid Mamba-Transformer Inference cites this paper.
Asymmetric Virtual Memory Paging for Hybrid Mamba-Transformer Inference Hymba: A Hybrid-head Architecture for Small Language Models
Reference 4
- Resolution
- verified exact
- arxiv_id, observed 2026-05-22T07:31:14.110433Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation cdca6b76-ee6b-47b0-a7b0-a94465b616f3 · inbound
Do Language Models Need Sleep? Offline Recurrence for Improved Online Inference cites this paper.
Do Language Models Need Sleep? Offline Recurrence for Improved Online Inference Hymba: A Hybrid-head Architecture for Small Language Models
Reference 20
- Resolution
- verified exact
- arxiv_id, observed 2026-06-29T21:43:59.519478Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 3e582e7f-61ba-4159-8a71-56245017eaf3 · inbound
Forget Attention: Importance-Aware Attention Is All You Need cites this paper.
Forget Attention: Importance-Aware Attention Is All You Need Hymba: A Hybrid-head Architecture for Small Language Models
Reference 7
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T23:06:21.037769Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation b3841260-6ed5-4578-b69f-1fae69a1aa46 · inbound
MOSAIC: Efficient Mixture-of-Agent Scheduling via Adaptive Aggregation and Inference Concurrency cites this paper.
MOSAIC: Efficient Mixture-of-Agent Scheduling via Adaptive Aggregation and Inference Concurrency Hymba: A Hybrid-head Architecture for Small Language Models
Reference 30
- Resolution
- verified exact
- arxiv_id, observed 2026-06-28T11:42:04.506675Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 05a06ea1-e837-4055-bad9-33086f26cb31 · inbound
MOSAIC: A Workload-Driven Simulation and Design-Space Exploration Framework for Heterogeneous NPUs cites this paper.
MOSAIC: A Workload-Driven Simulation and Design-Space Exploration Framework for Heterogeneous NPUs Hymba: A Hybrid-head Architecture for Small Language Models
Reference 7
- Resolution
- verified exact
- arxiv_id, observed 2026-07-02T11:36:55.115884Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation df0f8b44-3048-4a66-82ff-512de8879512 · inbound
Tangram: Unlocking Non-Uniform KV Cache for Efficient Multi-turn LLM Serving cites this paper.
Tangram: Unlocking Non-Uniform KV Cache for Efficient Multi-turn LLM Serving Hymba: A Hybrid-head Architecture for Small Language Models
Reference 8
- Resolution
- verified exact
- arxiv_id, observed 2026-07-02T12:06:56.124721Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation deb35f06-6355-4517-a654-b688b7971bd0 · inbound
Contribution Weights: A Geometrical Analysis of Self-Attention Transformers cites this paper.
Contribution Weights: A Geometrical Analysis of Self-Attention Transformers Hymba: A Hybrid-head Architecture for Small Language Models
Reference 95
- Resolution
- verified exact
- arxiv_id, observed 2026-06-28T23:32:46.637432Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation d2d90e3c-333c-481d-9d6c-ac69050bca9d · inbound
FreqDepthKV: Frequency-Guided Depth Sharing for Robust KV Cache Compression in Long-Context LLM Inference cites this paper.
FreqDepthKV: Frequency-Guided Depth Sharing for Robust KV Cache Compression in Long-Context LLM Inference Hymba: A Hybrid-head Architecture for Small Language Models
Reference 73
- Resolution
- verified exact
- local_arxiv, observed 2026-07-11T00:17:46.087572Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 01e24ed9-e8bc-4d5b-b6bb-4b998673ba42 · inbound
DepthWeave-KV: Token-Adaptive Cross-Layer Residual Factorization for Long-Context KV Cache Compression cites this paper.
DepthWeave-KV: Token-Adaptive Cross-Layer Residual Factorization for Long-Context KV Cache Compression Hymba: A Hybrid-head Architecture for Small Language Models
Reference 85
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-08T03:14:31.609923Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation d8c53253-2a75-4048-a577-8758951f92c0 · inbound
The Capability Convergence Hypothesis: Capability from Access Structure, Not Scale cites this paper.
The Capability Convergence Hypothesis: Capability from Access Structure, Not Scale Hymba: A Hybrid-head Architecture for Small Language Models
Reference 11
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T06:39:21.267463Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ac2f0a18-6a03-484b-8ddc-19bca428c2da · inbound
The Capability Convergence Hypothesis: Capability from Access Structure, Not Scale cites this paper.
The Capability Convergence Hypothesis: Capability from Access Structure, Not Scale Hymba: A Hybrid-head Architecture for Small Language Models
Reference 12
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T02:03:22.922600Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 79aaefee-9a18-4600-b590-70c339f69543 · inbound
Bridging Compute- and Data-Optimal Pretraining cites this paper.
Bridging Compute- and Data-Optimal Pretraining Hymba: A Hybrid-head Architecture for Small Language Models
Reference 63
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T03:02:03.507389Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5b4b4e78-9383-48ee-aba3-01b541d41ce0 · inbound
Memory for Large Language Models cites this paper.
Memory for Large Language Models Hymba: A Hybrid-head Architecture for Small Language Models
Reference 89
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T02:37:54.543725Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.