Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-16T05:19:08.434886Z
Paper Citation Record · LEDGER
As of 18 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 2 inbound Pith citation observations for arXiv:2504.20922.
A citation records a reference. It does not transfer a finding from one paper to another.
Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-16T05:19:08.434886Z
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-15T21:11:55.325064Z
A source-named dated measurement, never combined with another source.
Source: arxiv_reference, observed 2026-05-11T13:26:04.470618Z
44 of 44 outbound references displayed
External citation measurements
No source-named external measurement is stored.
Observation 66af68b4-619b-4a71-9b63-b5de370fb4cb · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures Scaling Autoregressive Multi- Modal Models: Pretraining and Instruction Tuning,
Reference 1
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 036f2e92-fa58-4b94-9a56-570ce4836140 · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures Shall We Pretrain Autoregressive Language Models with Retrieval? A Comprehensive Study,
Reference 2
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 053ce007-934b-46d7-a930-e424b0c3ee98 · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures Attention is All you Need,
Reference 3
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 31287879-6c77-47ca-b8b5-7b341f2268ed · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures LLaMA: Open and Efficient Foundation Language Models,
Reference 4
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 6b3b2330-628f-4fc2-bf50-d50e2b12d60e · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures Mistral 7B,
Reference 5
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 418d4cea-fece-437c-a9ab-6f7431552dee · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures Language models are unsupervised multitask learners,
Reference 6
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3f3dff9b-9cd9-4135-a8bb-ce7b97aec503 · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures Claude 3 model card,
Reference 7
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 3ce85e03-c17a-4894-b6dd-ee340e7f1927 · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures Scaling LLM Test-Time Com- pute Optimally can be More Effective than Scaling Model Parameters,
Reference 8
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation c6a98eda-a311-43cc-9c82-4f0e367cc389 · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures Learning to reason with LLMs,
Reference 9
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 0f63b66d-940b-4a33-9c11-ee18785d82b0 · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures DeepSeek-R1: Incentiviz- ing Reasoning Capability in LLMs via Reinforcement Learning,
Reference 10
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 770dcc2b-1db8-4545-8518-7129f1ad02a9 · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures Mamba: Linear-Time Sequence Modeling with Selective State Spaces,
Reference 11
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation e8584f30-7a55-4121-97ba-62ca7984b3c5 · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures Early exit optimizations for additive machine learned ranking systems,
Reference 12
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation bf0232a2-4326-43a5-aa0a-75141a4f66cf · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures Branchynet: Fast inference via early exiting from deep neural networks,
Reference 13
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 74f20bf4-7766-4de9-af94-8d36ecd0a1ce · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures SkipNet: Learning Dynamic Routing in Convolutional Networks,
Reference 14
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 23c2fe5a-8d63-4a96-bf3f-f4fed8323995 · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures Dynabert: Dynamic bert with adaptive width and depth,
Reference 15
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 29e423ae-c2a5-43e9-a7e1-b2076ebf01cc · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures The Unreasonable Ineffectiveness of the Deeper Layers,
Reference 16
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation c55b1e60-e3a0-4383-8c73-49bd53719d6e · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures BERT: Pre- training of Deep Bidirectional Transformers for Language Understand- ing,
Reference 17
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 401de29b-e747-46ed-8967-a65c4c25e73a · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures AdaViT: Adaptive Tokens for Efficient Vision Transformer,
Reference 18
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 78a758db-2d13-41d1-9bae-4a13fc12c240 · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures Lgvit: Dy- namic early exiting for accelerating vision transformer,
Reference 19
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 2af31bf9-2c5d-4feb-8331-f7fce399a7d5 · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures Nodeformer: A scalable graph structure learning transformer for node classification,
Reference 20
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 6aa2facc-74be-4827-880a-c60f16beff54 · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures Cas- cadeBERT: Accelerating Inference of Pre-trained Language Models via Calibrated Complete Models Cascade,
Reference 21
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 97aae59f-40aa-4acc-aff9-acf29727f179 · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures FastBERT: a Self-distilling BERT with Adaptive Inference Time,
Reference 22
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 94781e21-9d70-48c8-84db-43763c123ce2 · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures Depth-Adaptive Trans- former,
Reference 23
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 2978b015-5263-4165-ab7b-129b27914706 · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures Confident adaptive language modeling,
Reference 24
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a6ff465a-da59-4b63-b178-4a3645dc7ffd · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decodingt5,
Reference 25
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation a84aa94f-cef8-4044-9871-340885f5ace2 · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures EE-LLM: Large-Scale Training and Inference of Early-Exit Large Language Models with 3D Parallelism,
Reference 26
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 90053d09-2dc0-49f0-b7a9-e829d49820d5 · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures Exploring the limits of transfer learning with a unified text-to-text transformer,
Reference 27
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6c88648c-60e8-4fbf-a12b-f0f5c6778d55 · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey,
Reference 28
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 9212d49b-2551-4dae-9f39-0ed3803c980c · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures LoRA: Low-Rank Adaptation of Large Language Models,
Reference 29
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation a3bbab7f-9410-4368-84e7-9464b18e08b4 · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures Transformers are SSMs: Generalized models and efficient algorithms through structured state space duality,
Reference 30
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f9a396e3-c489-4c0f-b2e6-9f7dbe7cdc05 · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures Edanas: Adaptive neural architecture search for early exit neural networks,
Reference 31
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation bcae24a2-8f91-437f-b89a-e33f4159497e · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures Greedy layer- wise training of deep networks,
Reference 32
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 02edd933-81e1-4b18-b648-1d21750080bc · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures Distilling the Knowledge in a Neural Network,
Reference 33
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 967ecd1b-78df-4c31-bcf6-430fe86c182e · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures A survey on deep neural network pruning: Taxonomy, comparison, analysis, and recommendations,
Reference 34
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation db953620-4be8-4d7c-88d7-4edd6dea0c7d · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits,
Reference 35
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 63ac9cb1-d1c4-446a-aac5-4a2bbae414b9 · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures Linformer: Self- Attention with Linear Complexity,
Reference 36
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation c78daf1d-611c-4247-ac06-1de7003e2f8b · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures Longformer: The Long- Document Transformer,
Reference 37
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation e66c4f51-16b3-40a7-abfb-f7a63446175d · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures Codestral mamba,
Reference 38
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 832541d4-d684-4f2e-8f33-387a11322c1c · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures HuggingFace’s Transformers: State-of-the-art Natural Language Processing,
Reference 39
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 0e30cf29-6636-41fc-ac62-aafcc9079ebe · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures Fineweb-edu,
Reference 40
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 4d749746-b4ff-4d44-94af-994808ce1dc7 · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures TruthfulQA: Measuring How Models Mimic Human Falsehoods,
Reference 41
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation f3f5c84b-5b4c-4883-8b56-c510f31db792 · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures Coqa: A conversational question answering challenge,
Reference 42
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7868364a-2296-4942-8085-6af13d11f12e · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehen- sion,
Reference 43
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 6d965324-6b7b-4c00-bd2a-2cf30b819e9b · outbound
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures A framework for few-shot language model evaluation,
Reference 44
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 8dea86c3-65f4-445b-a845-adaba0e2a2cd · inbound
SEAL: Searching Expandable Architectures for Incremental Learning DYNAMAX: Dynamic computing for Transformers and Mamba based architectures
Reference 33
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c3bd16ff-45aa-469d-9104-82357ae88316 · inbound
Variance Is Not Importance: Structural Analysis of Transformer Compressibility Across Model Scales DYNAMAX: Dynamic computing for Transformers and Mamba based architectures
Reference 13
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.