Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-06T10:17:37.530726Z
Paper Citation Record · LEDGER
Representation Shift: Unifying Token Compression with FlashAttention
As of 12 August 2026, this Paper Citation Record lists 78 of 78 outbound references and 0 inbound Pith citation observations for arXiv:2508.00367.
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 2026-08-12T06:34:41.77262+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links
A source-named dated measurement, never combined with another source.
Source: cited_works
Reference resolution
78 of 78 outbound references displayed
- verified exact0
- verified fuzzy70
- unresolved8
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 439c23fc-3dbb-4a25-a11d-eceb4e8a3090 · outbound
This paper cites YOLOv12: A Breakdown of the Key Architectural Features.
Representation Shift: Unifying Token Compression with FlashAttention YOLOv12: A Breakdown of the Key Architectural Features
Reference 1
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T10:17:37.245074Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 834dd77f-01cf-45bb-a053-f8f32f8621d5 · outbound
This paper cites Localizing mo- ments in video with natural language.
Representation Shift: Unifying Token Compression with FlashAttention Localizing mo- ments in video with natural language
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:38.361408Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 3ec508eb-8bdc-4d7a-ae96-85375a974b81 · outbound
This paper cites Longformer: The Long-Document Transformer.
Representation Shift: Unifying Token Compression with FlashAttention Longformer: The Long-Document Transformer
Reference 3
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T10:17:37.253178Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b6b8a5b0-ad36-4e4f-84fe-9b7957fda267 · outbound
This paper cites Token merging: Your vit but faster.
Representation Shift: Unifying Token Compression with FlashAttention Token merging: Your vit but faster
Reference 4
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:38.350081Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation d71c1e61-43be-498a-8385-10f5198ec7ac · outbound
This paper cites The pagerank citation ranking: bringing order to the web.
Representation Shift: Unifying Token Compression with FlashAttention The pagerank citation ranking: bringing order to the web
Reference 5
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:38.339846Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation ef29e2ca-4c00-44d3-a60a-1d7d4d7e708d · outbound
This paper cites Activitynet: A large-scale video benchmark for human activity understanding.
Representation Shift: Unifying Token Compression with FlashAttention Activitynet: A large-scale video benchmark for human activity understanding
Reference 6
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T10:17:37.265113Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fd7f42dc-690b-4017-a3db-a9946bc38b03 · outbound
This paper cites Efficientvit: Multi-scale linear attention for high-resolution dense prediction.
Representation Shift: Unifying Token Compression with FlashAttention Efficientvit: Multi-scale linear attention for high-resolution dense prediction
Reference 7
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:38.322907Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 6c14ae1c-b32f-4002-991d-0488a4d80e32 · outbound
This paper cites End-to- end object detection with transformers.
Representation Shift: Unifying Token Compression with FlashAttention End-to- end object detection with transformers
Reference 8
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:38.313086Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 53992252-77ed-4b3f-91d1-ab9d594450e3 · outbound
This paper cites Scatterbrain: Unifying sparse and low- rank attention.
Representation Shift: Unifying Token Compression with FlashAttention Scatterbrain: Unifying sparse and low- rank attention
Reference 9
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:38.301342Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 6a20e93a-f9c6-4122-97ed-1ed47dc84aed · outbound
This paper cites Collecting highly paral- lel data for paraphrase evaluation.
Representation Shift: Unifying Token Compression with FlashAttention Collecting highly paral- lel data for paraphrase evaluation
Reference 10
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:38.290088Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation c9c62137-8e67-454a-bed1-7b33d7b70be7 · outbound
This paper cites Internvl: Scaling up vision foundation mod- els and aligning for generic visual-linguistic tasks.
Representation Shift: Unifying Token Compression with FlashAttention Internvl: Scaling up vision foundation mod- els and aligning for generic visual-linguistic tasks
Reference 11
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T10:17:37.284773Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation cd7c67bd-1b26-4bd3-bc68-b71bc84b7609 · outbound
This paper cites Per- pixel classification is not all you need for semantic segmen- tation.
Representation Shift: Unifying Token Compression with FlashAttention Per- pixel classification is not all you need for semantic segmen- tation
Reference 12
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:38.272606Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 72b7429e-05d0-4f95-8cbe-937d1f088199 · outbound
This paper cites vid-tldr: Training free token merging for light-weight video transformer.
Representation Shift: Unifying Token Compression with FlashAttention vid-tldr: Training free token merging for light-weight video transformer
Reference 13
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:38.261904Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 52ec060b-295d-4675-9254-d4824dd7a5bb · outbound
This paper cites Rethinking attention with performers.
Representation Shift: Unifying Token Compression with FlashAttention Rethinking attention with performers
Reference 14
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:38.249905Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation c3bf9b5d-c127-4756-80b5-410576ab1ec5 · outbound
This paper cites Twins: Revisiting the design of spatial attention in vision transformers.
Representation Shift: Unifying Token Compression with FlashAttention Twins: Revisiting the design of spatial attention in vision transformers
Reference 15
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:38.238321Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 47e4e8e5-864b-4cfc-ae71-35caf81aaab2 · outbound
This paper cites Flashattention: Fast and memory-efficient exact attention with io-awareness.
Representation Shift: Unifying Token Compression with FlashAttention Flashattention: Fast and memory-efficient exact attention with io-awareness
Reference 16
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:38.227105Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation f3170c15-5aba-4db6-8e51-74fed2f4fcc4 · outbound
This paper cites Vision transformers need registers.ICLR, 2024.
Representation Shift: Unifying Token Compression with FlashAttention Vision transformers need registers.ICLR, 2024
Reference 17
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:38.217026Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 37e4a5f1-6439-4177-9fad-9c1e44f7333f · outbound
This paper cites Imagenet: A large-scale hierarchical image database.
Representation Shift: Unifying Token Compression with FlashAttention Imagenet: A large-scale hierarchical image database
Reference 18
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:38.206538Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 3fd7ee43-b197-4d65-aa39-6838b1efe460 · outbound
This paper cites An image is worth 16x16 words: Trans- formers for image recognition at scale.
Representation Shift: Unifying Token Compression with FlashAttention An image is worth 16x16 words: Trans- formers for image recognition at scale
Reference 19
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:38.196215Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 701bdeec-1175-45bd-802a-7a638a61ac94 · outbound
This paper cites Levit: a vision transformer in convnet’s clothing for faster inference.
Representation Shift: Unifying Token Compression with FlashAttention Levit: a vision transformer in convnet’s clothing for faster inference
Reference 20
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:38.185798Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation ccf354fd-0ee4-4941-8378-b8153f17d1cf · outbound
This paper cites Deep residual learning for image recognition.
Representation Shift: Unifying Token Compression with FlashAttention Deep residual learning for image recognition
Reference 21
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T10:17:37.320934Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 75ed4c45-173c-41f7-9ff2-6d00c2940bd5 · outbound
This paper cites Transformers are rnns: Fast autoregressive transformers with linear attention.
Representation Shift: Unifying Token Compression with FlashAttention Transformers are rnns: Fast autoregressive transformers with linear attention
Reference 22
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:38.169566Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation eeb2938d-1e8d-4039-b27e-6fe95e51e6ea · outbound
This paper cites Groupwise query special- ization and quality-aware multi-assignment for transformer- based visual relationship detection.
Representation Shift: Unifying Token Compression with FlashAttention Groupwise query special- ization and quality-aware multi-assignment for transformer- based visual relationship detection
Reference 23
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:38.159999Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 657f2b3a-b9d0-4357-9602-ffc2c363ff1c · outbound
This paper cites Learned token pruning for transformers.
Representation Shift: Unifying Token Compression with FlashAttention Learned token pruning for transformers
Reference 24
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:38.150594Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation ae01be54-10b8-49e1-9adf-3d4f8cd6f2cd · outbound
This paper cites Re- former: The efficient transformer.
Representation Shift: Unifying Token Compression with FlashAttention Re- former: The efficient transformer
Reference 25
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:38.140460Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 53472f30-1d89-42ba-b682-3f150e4df0e3 · outbound
This paper cites Video-text representation learning via differentiable weak temporal alignment.
Representation Shift: Unifying Token Compression with FlashAttention Video-text representation learning via differentiable weak temporal alignment
Reference 26
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:38.129807Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation bfde008a-917c-4bed-ba23-4b18754fafe0 · outbound
This paper cites Meltr: Meta loss transformer for learning to fine-tune video foun- dation models.
Representation Shift: Unifying Token Compression with FlashAttention Meltr: Meta loss transformer for learning to fine-tune video foun- dation models
Reference 27
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:38.120412Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation b5be7327-bc2d-4442-b79a-7db7aa5ff005 · outbound
This paper cites Vidchain: Chain-of-tasks with metric- based direct preference optimization for dense video caption- ing.
Representation Shift: Unifying Token Compression with FlashAttention Vidchain: Chain-of-tasks with metric- based direct preference optimization for dense video caption- ing
Reference 28
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:38.110961Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 1d995e4e-7879-4f16-894e-71507675aa78 · outbound
This paper cites Multi-criteria token fusion with one-step-ahead attention for efficient vision transformers.
Representation Shift: Unifying Token Compression with FlashAttention Multi-criteria token fusion with one-step-ahead attention for efficient vision transformers
Reference 29
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:38.101194Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 219fafba-d79f-4abb-b72e-d25a5fffc2ac · outbound
This paper cites Ef- ficientvim: Efficient vision mamba with hidden state mixer based state space duality.
Representation Shift: Unifying Token Compression with FlashAttention Ef- ficientvim: Efficient vision mamba with hidden state mixer based state space duality
Reference 30
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:38.090855Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation e4be632f-ca32-442f-9edb-6abe746f56cd · outbound
This paper cites Revealing single frame bias for video-and-language learning.
Representation Shift: Unifying Token Compression with FlashAttention Revealing single frame bias for video-and-language learning
Reference 31
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:38.080579Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 6b884ec1-099f-4670-bdb7-8714a4bd78bd · outbound
This paper cites Unmasked teacher: Towards training-efficient video foundation models.
Representation Shift: Unifying Token Compression with FlashAttention Unmasked teacher: Towards training-efficient video foundation models
Reference 32
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:38.069455Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 7d041539-a0a1-41e9-908f-677c73fb8b66 · outbound
This paper cites Not all patches are what you need: Expediting vision transformers via token reorganiza- tions.
Representation Shift: Unifying Token Compression with FlashAttention Not all patches are what you need: Expediting vision transformers via token reorganiza- tions
Reference 33
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:38.058522Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 1327309f-33c9-42b3-8e6f-d24b9d1ad7f5 · outbound
This paper cites Efficientvit: Memory efficient vision transformer with cascaded group attention.
Representation Shift: Unifying Token Compression with FlashAttention Efficientvit: Memory efficient vision transformer with cascaded group attention
Reference 34
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:38.048055Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 9d727d43-1b07-482d-a29e-9cd6de3af726 · outbound
This paper cites Efficient training of visual trans- formers with small datasets.
Representation Shift: Unifying Token Compression with FlashAttention Efficient training of visual trans- formers with small datasets
Reference 35
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:38.037298Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 8b222a73-4d74-41c1-8cfc-7052ca63de35 · outbound
This paper cites Vmamba: Visual state space model.
Representation Shift: Unifying Token Compression with FlashAttention Vmamba: Visual state space model
Reference 36
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:38.026751Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation c2e19a94-9d08-433b-ae81-c1bb19953063 · outbound
This paper cites Swin transformer: Hierarchical vision transformer using shifted windows.
Representation Shift: Unifying Token Compression with FlashAttention Swin transformer: Hierarchical vision transformer using shifted windows
Reference 37
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:38.015920Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 3d187d7a-25ae-4c0b-9d76-f557a3ecfba2 · outbound
This paper cites A convnet for the 2020s.
Representation Shift: Unifying Token Compression with FlashAttention A convnet for the 2020s
Reference 38
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:38.005742Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 638baeb2-fae5-4184-912c-17fc19bccc55 · outbound
This paper cites Beyond attentive tokens: Incorporating to- ken importance and diversity for efficient vision transform- ers.
Representation Shift: Unifying Token Compression with FlashAttention Beyond attentive tokens: Incorporating to- ken importance and diversity for efficient vision transform- ers
Reference 39
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:37.995803Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 2f42adb5-afef-4565-804d-1d8e0f251dc6 · outbound
This paper cites Mobilevit: light- weight, general-purpose, and mobile-friendly vision trans- former.
Representation Shift: Unifying Token Compression with FlashAttention Mobilevit: light- weight, general-purpose, and mobile-friendly vision trans- former
Reference 40
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:37.984823Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 306f7e7d-a44e-4f34-961c-19a37b616229 · outbound
This paper cites Adavit: Adaptive vision transformers for efficient image recognition.
Representation Shift: Unifying Token Compression with FlashAttention Adavit: Adaptive vision transformers for efficient image recognition
Reference 41
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:37.973859Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 1d9d0bd8-e400-472c-9f51-cdc0d3dca5ad · outbound
This paper cites Dinov2: Learning robust visual features without supervision.
Representation Shift: Unifying Token Compression with FlashAttention Dinov2: Learning robust visual features without supervision
Reference 42
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T10:17:37.399392Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 45a042f0-a349-4328-a1d6-f72c95beeaed · outbound
This paper cites IA-RED 2: Interpretability-aware redundancy reduction for vision trans- formers.
Representation Shift: Unifying Token Compression with FlashAttention IA-RED 2: Interpretability-aware redundancy reduction for vision trans- formers
Reference 43
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:37.956492Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 593486b1-4929-464e-a199-334f7b5c4ccb · outbound
This paper cites Deepvideo-r1: Video reinforcement fine-tuning via difficulty-aware regressive grpo.
Representation Shift: Unifying Token Compression with FlashAttention Deepvideo-r1: Video reinforcement fine-tuning via difficulty-aware regressive grpo
Reference 44
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:37.946986Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation e0dbfeb3-8dfa-44b0-9c93-a4c0d37fd213 · outbound
This paper cites cosformer: Rethinking softmax in attention.
Representation Shift: Unifying Token Compression with FlashAttention cosformer: Rethinking softmax in attention
Reference 45
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:37.936549Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 6827bae3-dc9a-4ac4-b5c3-8b5817b23330 · outbound
This paper cites Dynamicvit: Efficient vision transformers with dynamic token sparsification.
Representation Shift: Unifying Token Compression with FlashAttention Dynamicvit: Efficient vision transformers with dynamic token sparsification
Reference 46
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:37.927045Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 5e5f1771-e94a-49e8-8cd2-510bfb621389 · outbound
This paper cites Movie description.
Representation Shift: Unifying Token Compression with FlashAttention Movie description
Reference 47
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:37.917121Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation da2a2c77-7441-40e7-833f-df36dff6b2d6 · outbound
This paper cites Efficient content-based sparse attention with rout- ing transformers.
Representation Shift: Unifying Token Compression with FlashAttention Efficient content-based sparse attention with rout- ing transformers
Reference 48
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:37.908118Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 29202c4a-b6ac-419c-8f67-6c0f29dbac5f · outbound
This paper cites Segmenter: Transformer for semantic segmenta- tion.
Representation Shift: Unifying Token Compression with FlashAttention Segmenter: Transformer for semantic segmenta- tion
Reference 49
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:37.898403Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation c7180283-0460-4236-84e7-851f202beea2 · outbound
This paper cites Removing rows and columns of tokens in vision transformer enables faster dense prediction without retraining.
Representation Shift: Unifying Token Compression with FlashAttention Removing rows and columns of tokens in vision transformer enables faster dense prediction without retraining
Reference 50
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:37.888076Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 133854c6-c5d6-4a78-b860-33856d269027 · outbound
This paper cites Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training.
Representation Shift: Unifying Token Compression with FlashAttention Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training
Reference 51
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:37.876679Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 6b4eaf69-63d5-4d3e-b039-526076116065 · outbound
This paper cites Training data-efficient image transformers & distillation through at- tention.
Representation Shift: Unifying Token Compression with FlashAttention Training data-efficient image transformers & distillation through at- tention
Reference 52
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:37.865883Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 0bf5102d-bbda-473f-ab54-1960a309c38c · outbound
This paper cites Going deeper with im- age transformers.
Representation Shift: Unifying Token Compression with FlashAttention Going deeper with im- age transformers
Reference 53
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:37.854690Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 14b9665d-5370-42a0-8d22-cc78c25c5580 · outbound
This paper cites Maxvit: Multi-axis vision transformer.
Representation Shift: Unifying Token Compression with FlashAttention Maxvit: Multi-axis vision transformer
Reference 54
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:37.845007Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 9bcea0ea-6be7-44b4-ad3c-ad026ba27559 · outbound
This paper cites Attention is all you need.
Representation Shift: Unifying Token Compression with FlashAttention Attention is all you need
Reference 55
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:37.834387Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 8b041d0c-65c4-4c02-b0e6-f92d2e190a8a · outbound
This paper cites Zero- tprune: Zero-shot token pruning through leveraging of the attention graph in pre-trained transformers.
Representation Shift: Unifying Token Compression with FlashAttention Zero- tprune: Zero-shot token pruning through leveraging of the attention graph in pre-trained transformers
Reference 56
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:37.824802Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 92c44c72-d0c3-4353-91af-75db2571b439 · outbound
This paper cites Linformer: Self-Attention with Linear Complexity.
Representation Shift: Unifying Token Compression with FlashAttention Linformer: Self-Attention with Linear Complexity
Reference 57
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T10:17:37.453396Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ac1b6b9a-036f-4ad8-9d3b-55724f101048 · outbound
This paper cites Pyra- mid vision transformer: A versatile backbone for dense pre- diction without convolutions.
Representation Shift: Unifying Token Compression with FlashAttention Pyra- mid vision transformer: A versatile backbone for dense pre- diction without convolutions
Reference 58
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:37.815080Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 52d4e181-7df8-407f-b927-937d0a47e592 · outbound
This paper cites Pvt v2: Improved baselines with pyramid vision transformer.
Representation Shift: Unifying Token Compression with FlashAttention Pvt v2: Improved baselines with pyramid vision transformer
Reference 59
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:37.805181Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation e619fe51-c297-4566-9ff3-7e3e1acf7f41 · outbound
This paper cites Videocomposer: Compositional video synthesis with motion controllability.
Representation Shift: Unifying Token Compression with FlashAttention Videocomposer: Compositional video synthesis with motion controllability
Reference 60
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:37.795148Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation c115fb94-82ea-4ad6-bca8-04856388ac39 · outbound
This paper cites End-to-end video instance segmentation with transformers.
Representation Shift: Unifying Token Compression with FlashAttention End-to-end video instance segmentation with transformers
Reference 61
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:37.784750Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation af83d3d0-c08e-4df0-801c-d839ffb69237 · outbound
This paper cites InternVideo: General Video Foundation Models via Generative and Discriminative Learning.
Representation Shift: Unifying Token Compression with FlashAttention InternVideo: General Video Foundation Models via Generative and Discriminative Learning
Reference 62
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T10:17:37.471841Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation cc388bdd-0203-455b-9c5d-f843b66e5288 · outbound
This paper cites Anchor detr: Query design for transformer-based object de- tection.
Representation Shift: Unifying Token Compression with FlashAttention Anchor detr: Query design for transformer-based object de- tection
Reference 63
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:37.774169Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation c03a11d8-a1e7-4826-a084-bfd27914e555 · outbound
This paper cites Internvideo2: Scaling foundation models for mul- timodal video understanding.
Representation Shift: Unifying Token Compression with FlashAttention Internvideo2: Scaling foundation models for mul- timodal video understanding
Reference 64
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:37.763834Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 0b896a73-9a0b-4ad8-838b-4919b8b6ed91 · outbound
This paper cites Con- vnext v2: Co-designing and scaling convnets with masked autoencoders.
Representation Shift: Unifying Token Compression with FlashAttention Con- vnext v2: Co-designing and scaling convnets with masked autoencoders
Reference 65
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:37.753286Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation a544daa6-6a46-47fb-acbf-ceaec5123bd7 · outbound
This paper cites Nystr¨omformer: A nystr¨om-based algorithm for approximat- ing self-attention.
Representation Shift: Unifying Token Compression with FlashAttention Nystr¨omformer: A nystr¨om-based algorithm for approximat- ing self-attention
Reference 66
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:37.743887Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 283801d2-fc26-4144-bf9a-8786cb511f53 · outbound
This paper cites Video question answer- ing via gradually refined attention over appearance and mo- tion.
Representation Shift: Unifying Token Compression with FlashAttention Video question answer- ing via gradually refined attention over appearance and mo- tion
Reference 67
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:37.733753Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 0118e699-975c-487d-92b8-f0bc85bc548b · outbound
This paper cites Msr-vtt: A large video description dataset for bridging video and language.
Representation Shift: Unifying Token Compression with FlashAttention Msr-vtt: A large video description dataset for bridging video and language
Reference 68
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:37.722437Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 213a57ad-5390-4905-bb3b-2172a263645b · outbound
This paper cites A-vit: Adaptive tokens for efficient vision transformer.
Representation Shift: Unifying Token Compression with FlashAttention A-vit: Adaptive tokens for efficient vision transformer
Reference 69
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:37.711491Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation fd4d55a3-c0c4-474b-8d74-891b6d95c682 · outbound
This paper cites Tokens-to-token vit: Training vision transformers from scratch on imagenet.
Representation Shift: Unifying Token Compression with FlashAttention Tokens-to-token vit: Training vision transformers from scratch on imagenet
Reference 70
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:37.701378Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 5742a98a-16e4-4110-af82-271f23b7f762 · outbound
This paper cites Efficient trans- former adaptation with soft token merging.
Representation Shift: Unifying Token Compression with FlashAttention Efficient trans- former adaptation with soft token merging
Reference 71
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:37.691182Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation a4c978cc-7625-4211-b0c8-a4824c0a3535 · outbound
This paper cites Shvit: Single-head vision transformer with memory efficient macro design.
Representation Shift: Unifying Token Compression with FlashAttention Shvit: Single-head vision transformer with memory efficient macro design
Reference 72
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:37.679998Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation af6135fd-a25b-4270-ac91-3dd201df9fcc · outbound
This paper cites Big bird: Transformers for longer sequences.
Representation Shift: Unifying Token Compression with FlashAttention Big bird: Transformers for longer sequences
Reference 73
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:37.666727Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 26b174c5-8778-40ff-aaa6-8aab9f4c9bc3 · outbound
This paper cites Exploring token pruning in vision state space models.
Representation Shift: Unifying Token Compression with FlashAttention Exploring token pruning in vision state space models
Reference 74
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:37.653322Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation c9395641-687b-41a5-8db5-3a162b80d17d · outbound
This paper cites Dino: Detr with improved denoising anchor boxes for end-to-end object detection.
Representation Shift: Unifying Token Compression with FlashAttention Dino: Detr with improved denoising anchor boxes for end-to-end object detection
Reference 75
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:37.641483Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation f60e9007-87c7-4010-906c-b1156d1fc016 · outbound
This paper cites Rethinking semantic segmen- tation from a sequence-to-sequence perspective with trans- formers.
Representation Shift: Unifying Token Compression with FlashAttention Rethinking semantic segmen- tation from a sequence-to-sequence perspective with trans- formers
Reference 76
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:37.630756Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation dbfc3aca-161e-40ad-b081-b53ae85b8378 · outbound
This paper cites Vision mamba: Efficient visual representation learning with bidirectional state space model.
Representation Shift: Unifying Token Compression with FlashAttention Vision mamba: Efficient visual representation learning with bidirectional state space model
Reference 77
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:37.620217Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation ae973c5c-838a-490a-9df5-644b8e7818e1 · outbound
This paper cites Deformable detr: Deformable transformers for end-to-end object detection.
Representation Shift: Unifying Token Compression with FlashAttention Deformable detr: Deformable transformers for end-to-end object detection
Reference 78
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T10:17:37.608667Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Pith citing papers
No inbound Pith citation observations are available.