Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-13T02:00:02.786195Z
Paper Citation Record · LEDGER
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs
As of 6 August 2026, this Paper Citation Record lists 65 of 65 outbound references and 0 inbound Pith citation observations for arXiv:2605.11605.
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 2026-08-06T06:34:29.942622+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
65 of 65 outbound references displayed
- verified exact17
- verified fuzzy44
- unresolved1
- parse uncertain0
- malformed identifier1
- metadata mismatch2
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 46427dae-2b9c-497e-a3fe-6b04efb5422f · outbound
This paper cites Flamingo: a Visual Language Model for Few-Shot Learning.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs Flamingo: a Visual Language Model for Few-Shot Learning
Reference 1
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.647472Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 8db28d7e-ab8f-4a5f-bbd6-46f11ec9c95a · outbound
This paper cites Qwen2.5-VL Technical Report.arXiv.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs Qwen2.5-VL Technical Report.arXiv
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.558683Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 4da67932-a6ff-47df-89b8-04d1729db22a · outbound
This paper cites VGGSound: A Large-scale Audio-Visual Dataset.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs VGGSound: A Large-scale Audio-Visual Dataset
Reference 3
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.536785Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation f6005e4a-e121-4901-b81e-a50ca4690868 · outbound
This paper cites Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic
Reference 4
- Resolution
- verified exact
- local_arxiv, observed 2026-05-13T02:02:06.377506Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 28bab313-2f09-48ce-a36f-85bae1915e0c · outbound
This paper cites An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models
Reference 5
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.563568Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 381010d3-a7e7-405f-b127-b642c472fc57 · outbound
This paper cites BEATs: Audio Pre-Training with Acoustic Tokenizers.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs BEATs: Audio Pre-Training with Acoustic Tokenizers
Reference 6
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.621269Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation da416ff9-67f0-474a-a4c1-b6bc865a476f · outbound
This paper cites V AST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs V AST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset
Reference 7
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.511176Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation ec5f479e-00d9-4dd0-a200-e539819b6a52 · outbound
This paper cites StreamingTOM: Streaming Token Compression for Efficient Video Understanding.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs StreamingTOM: Streaming Token Compression for Efficient Video Understanding
Reference 8
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.575821Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 527c5493-22dc-4eff-981d-1df508d70c47 · outbound
This paper cites InternVL: Scaling Up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs InternVL: Scaling Up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks
Reference 9
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.629594Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation a8b010d0-8bcd-4244-88d3-997299a7a457 · outbound
This paper cites VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs
Reference 10
- Resolution
- verified exact
- local_arxiv, observed 2026-05-13T02:02:06.362106Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 5e5f7cbb-4923-4063-9cf1-cbffedce71ab · outbound
This paper cites Meerkat: Audio-Visual Large Language Model for Grounding in Space and Time.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs Meerkat: Audio-Visual Large Language Model for Grounding in Space and Time
Reference 11
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.660046Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation cd6ac54a-e8b6-44aa-866d-5d2882258ed2 · outbound
This paper cites Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Reference 12
- Resolution
- verified exact
- local_arxiv, observed 2026-05-13T02:02:06.342903Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation da58de3f-3268-4dc4-a92d-3b6af83600dc · outbound
This paper cites OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language Models.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language Models
Reference 13
- Resolution
- verified exact
- arxiv_id, observed 2026-05-14T02:56:19.131480Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation c0cd9387-cf1c-4926-8411-c15b44abf422 · outbound
This paper cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Reference 14
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.519927Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation caa110bc-ebb6-4b78-919c-c55326dfc54f · outbound
This paper cites Video-MME: The First-Ever Compre- hensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs Video-MME: The First-Ever Compre- hensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis
Reference 15
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.524633Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 9411a143-83ec-451f-b623-b634ac6ab116 · outbound
This paper cites Gemmeke, Daniel P.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs Gemmeke, Daniel P
Reference 16
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.495135Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation e53fa6ab-5e4a-4b4f-a2f2-98d15ec110bd · outbound
This paper cites EchoingPixels: Aliasing-Resistant Joint Token Reduction for Audio-Visual LLMs.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs EchoingPixels: Aliasing-Resistant Joint Token Reduction for Audio-Visual LLMs
Reference 17
- Resolution
- verified exact
- arxiv_id, observed 2026-06-23T04:13:43.420881Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 8ae23397-ee69-450e-b7c1-5c6a6c4e45a3 · outbound
This paper cites AST: Audio Spectrogram Transformer.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs AST: Audio Spectrogram Transformer
Reference 18
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.498259Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 152b6d51-3fe6-47ea-a2b5-481acfc3cd9d · outbound
This paper cites OneLLM: One Framework to Align All Modalities with Language.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs OneLLM: One Framework to Align All Modalities with Language
Reference 19
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.528855Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation bee92d2e-85e1-4b3b-be17-d9a63bdadcc3 · outbound
This paper cites WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs
Reference 20
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.492104Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 6ca3676d-8686-4580-99ba-1bf0f689ffd3 · outbound
This paper cites Language is Not All You Need: Aligning Perception with Language Models.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs Language is Not All You Need: Aligning Perception with Language Models
Reference 21
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.638217Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 4a52e37a-bf83-473b-bf15-83d521e3d184 · outbound
This paper cites GPT-4o System Card.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs GPT-4o System Card
Reference 22
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-13T02:02:06.333048Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 9ac3acee-bad6-4f77-95f5-92fd9e31f6fb · outbound
This paper cites Multi-Granular Spatio-Temporal Token Merging for Training-Free Acceleration of Video LLMs.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs Multi-Granular Spatio-Temporal Token Merging for Training-Free Acceleration of Video LLMs
Reference 23
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.567710Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 54f8b596-915b-44ee-b959-d5b8867ac574 · outbound
This paper cites STORM: Token-Efficient Long Video Understanding for Multimodal LLMs.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs STORM: Token-Efficient Long Video Understanding for Multimodal LLMs
Reference 24
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.642525Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 851988ae-deea-4a6e-8b7b-4d62c32f3d19 · outbound
This paper cites LLaV A-OneVision: Easy Visual Task Transfer.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs LLaV A-OneVision: Easy Visual Task Transfer
Reference 25
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.670390Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 838e6d47-199d-4410-811c-b9dfff8a762f · outbound
This paper cites Omnivideobench: Towards audio-visual understanding evaluation for omni mllms.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs Omnivideobench: Towards audio-visual understanding evaluation for omni mllms
Reference 26
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T02:02:06.297828Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 10487093-e774-4356-91b5-290f1ce7e967 · outbound
This paper cites BLIP-2: Bootstrapping Language- Image Pre-training with Frozen Image Encoders and Large Language Models.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs BLIP-2: Bootstrapping Language- Image Pre-training with Frozen Image Encoders and Large Language Models
Reference 27
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.545948Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 1d8fc051-5434-4c62-a4ca-94775cbbb317 · outbound
This paper cites VideoChat- Flash: Hierarchical Compression for Long-Context Video Modeling.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs VideoChat- Flash: Hierarchical Compression for Long-Context Video Modeling
Reference 28
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.608600Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 9411bb27-a3a9-462a-9b9a-907b1a0b4bec · outbound
This paper cites Video-LLaV A: Learning United Visual Representation by Alignment Before Projection.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs Video-LLaV A: Learning United Visual Representation by Alignment Before Projection
Reference 29
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.584502Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 32dc153c-abe0-4935-a8aa-2f85ea2928bd · outbound
This paper cites Visual Instruction Tuning.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs Visual Instruction Tuning
Reference 30
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.587896Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 26cbbea0-d15b-44f0-984b-e058915d9b66 · outbound
This paper cites Mixing Importance with Diversity: Joint Optimization for KV Cache Compression in Large Vision-Language Models.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs Mixing Importance with Diversity: Joint Optimization for KV Cache Compression in Large Vision-Language Models
Reference 31
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.600554Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 1dffdf43-1dd2-4240-b85f-02f3f24bb3b2 · outbound
This paper cites Macaw-LLM: Multi-Modal Language Modeling with Image, Audio, Video, and Text Integration.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs Macaw-LLM: Multi-Modal Language Modeling with Image, Audio, Video, and Text Integration
Reference 32
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T02:02:06.307495Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 302028f4-4fd4-48aa-b57e-a31b9ad2f0af · outbound
This paper cites Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models
Reference 33
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.633942Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 1fdfb7a6-5a81-47c0-a436-b1e74a46124e · outbound
This paper cites X-InstructBLIP: A Framework for aligning X-Modal instruction-aware representations to LLMs and Emergent Cross-modal Reasoning.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs X-InstructBLIP: A Framework for aligning X-Modal instruction-aware representations to LLMs and Emergent Cross-modal Reasoning
Reference 34
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T02:02:06.328981Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation f268fcbe-6abb-4f73-b567-aaaa13494a6c · outbound
This paper cites Adapt- Token: Entropy-based Adaptive Token Selection for MLLM Long Video Understanding.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs Adapt- Token: Entropy-based Adaptive Token Selection for MLLM Long Video Understanding
Reference 35
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T02:02:06.338129Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 606d06ea-4a60-4297-a449-7b85aafe8c0a · outbound
This paper cites An LMM for Efficient Video Understanding via Reinforced Compression of Video Cubes.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs An LMM for Efficient Video Understanding via Reinforced Compression of Video Cubes
Reference 36
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T02:02:06.302188Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation aa97041d-52d6-492a-b46b-d3942462140d · outbound
This paper cites Learning Transferable Visual Models From Natural Language Supervision.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs Learning Transferable Visual Models From Natural Language Supervision
Reference 37
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.550241Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation e06d4365-e617-4d24-935b-60af578bbd59 · outbound
This paper cites Robust Speech Recognition via Large-Scale Weak Supervision.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs Robust Speech Recognition via Large-Scale Weak Supervision
Reference 38
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.651937Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 9396f416-d069-437d-a162-89689ff91f90 · outbound
This paper cites LLaV A-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs LLaV A-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models
Reference 39
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.616654Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 63155665-8e18-4e90-842a-cf4fe96392f5 · outbound
This paper cites an unresolved cited work.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs Unresolved cited work
Reference 40
- Resolution
- unresolved
- raw_fallback, observed 2026-05-13T13:57:51.489430Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 4ec4d13e-33cf-4bf4-9f1f-2c8a30f522d2 · outbound
This paper cites HoliTom: Holistic Token Merging for Fast Video Large Language Models.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs HoliTom: Holistic Token Merging for Fast Video Large Language Models
Reference 41
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.541689Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 2e737fa9-64ad-4e62-8cc2-09cc8f167e4e · outbound
This paper cites Video-XL: Extra-Long Vision Language Model for Hour-Scale Video Understanding.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs Video-XL: Extra-Long Vision Language Model for Hour-Scale Video Understanding
Reference 42
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.625379Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation aa610cd1-acad-4834-85b6-0e17081cc188 · outbound
This paper cites video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models
Reference 43
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.674737Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 718c3c65-f48e-41d3-9823-54f62f526fec · outbound
This paper cites TokenCarve: Information-Preserving Visual Token Compression in Multimodal Large Language Models.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs TokenCarve: Information-Preserving Visual Token Compression in Multimodal Large Language Models
Reference 44
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T02:02:06.367035Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation d84ee85f-ea73-4a96-a415-52cfd8bd78d7 · outbound
This paper cites video-SALMONN 2: Caption-enhanced audio-visual large language models.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs video-SALMONN 2: Caption-enhanced audio-visual large language models
Reference 45
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T02:02:06.372567Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation f1ef4fce-7c5b-4824-9b4e-01de9400d0b7 · outbound
This paper cites DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models
Reference 46
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.664257Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation c216012e-e004-4c7c-bdff-4a4b597749f9 · outbound
This paper cites OmniZip: Audio- Guided Dynamic Token Compression for Fast Omnimodal Large Language Models.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs OmniZip: Audio- Guided Dynamic Token Compression for Fast Omnimodal Large Language Models
Reference 47
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.595117Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 97664f33-948d-41dd-a3c3-5e023b1d0c3a · outbound
This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
Reference 48
- Resolution
- verified exact
- local_arxiv, observed 2026-05-13T02:02:06.352132Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 87bb9f0c-cbf7-4397-bc6b-92bff4b09512 · outbound
This paper cites LLaMA: Open and Efficient Foundation Language Models.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs LLaMA: Open and Efficient Foundation Language Models
Reference 49
- Resolution
- verified exact
- local_arxiv, observed 2026-05-13T02:02:06.357482Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation dbf3d468-c410-49d6-b64e-4cd66733f14c · outbound
This paper cites PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction
Reference 50
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.604633Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 7f846117-6b8e-4e01-8233-7e397344da6d · outbound
This paper cites Qwen2.5-Omni Technical Report.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs Qwen2.5-Omni Technical Report
Reference 51
- Resolution
- verified exact
- local_arxiv, observed 2026-05-13T02:02:06.287537Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation cd3c5254-0b18-4755-89c2-4793b69da1f5 · outbound
This paper cites PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models
Reference 52
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.580575Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation f38366e9-d8a8-4b47-8a40-c344eb1ddf9e · outbound
This paper cites A VQA: A Dataset for Audio-Visual Question Answering on Videos.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs A VQA: A Dataset for Audio-Visual Question Answering on Videos
Reference 53
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.612437Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation ba526c80-44e9-4a64-b708-13cb480b510b · outbound
This paper cites VisionZip: Longer is Better but Not Necessary in Vision Language Models.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs VisionZip: Longer is Better but Not Necessary in Vision Language Models
Reference 54
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.515439Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 79822637-f29b-4ac7-8aba-e42ce82ba184 · outbound
This paper cites TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos
Reference 55
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.656044Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 354ce40a-0724-4fc3-a2dd-47afb20ab06b · outbound
This paper cites CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios
Reference 56
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.502615Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 8af86676-dba3-40e7-a6d8-f67db91c3888 · outbound
This paper cites Fit and Prune: Fast and Training-free Visual Token Pruning for Multi-modal Large Language Models.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs Fit and Prune: Fast and Training-free Visual Token Pruning for Multi-modal Large Language Models
Reference 57
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.506746Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation d07c912e-6f1d-469c-9db0-8b7b692b9a32 · outbound
This paper cites RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback
Reference 58
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.571838Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 7262370a-9725-46c9-8304-e10518785462 · outbound
This paper cites AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling
Reference 59
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T02:02:06.312638Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 46ff8bec-d77a-4928-af29-debcd42e5ce9 · outbound
This paper cites Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding
Reference 60
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.591886Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation f7efcaf8-f075-4462-910f-86a11605f658 · outbound
This paper cites p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay
Reference 61
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.532793Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation fc9069bb-08d5-4a77-9a8a-a561fb4fb24d · outbound
This paper cites LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention
Reference 62
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-13T13:57:51.554496Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 9f50a6fc-3ad4-4b69-971b-5fa48ea23872 · outbound
This paper cites ChatBridge: Bridging Modalities with Large Language Model as a Language Catalyst.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs ChatBridge: Bridging Modalities with Large Language Model as a Language Catalyst
Reference 63
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T02:02:06.318077Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 3810f0cd-55ee-4648-8a6d-a09e64088ba7 · outbound
This paper cites Mlvu: Benchmarking multi-task long video understanding.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs Mlvu: Benchmarking multi-task long video understanding
Reference 64
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-13T02:02:06.323895Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 6647d32c-8957-4093-802d-3ef894dd2295 · outbound
This paper cites plucked string instrument music.
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs plucked string instrument music
Reference 65
- Resolution
- malformed identifier
- arxiv_id, observed 2026-05-13T02:02:06.292937Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Pith citing papers
No inbound Pith citation observations are available.