Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-04T23:23:39.127173Z
Paper Citation Record · LEDGER
Allocation Before Ranking: Decoupled Token Compression for OmniLLMs
As of 23 August 2026, this Paper Citation Record lists 19 of 19 outbound references and 0 inbound Pith citation observations for arXiv:2608.01665.
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 2026-08-23T06:30:58.430688+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
19 of 19 outbound references displayed
- verified exact2
- verified fuzzy1
- unresolved16
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation e203ff2e-1c58-439c-963c-e9ac11644da1 · outbound
This paper cites OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language Models.
Allocation Before Ranking: Decoupled Token Compression for OmniLLMs OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language Models
Reference 3
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T23:23:37.653849Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9e43021e-4266-44ad-bea5-45c26c6af657 · outbound
This paper cites Event-vstream: Event-driven real-time understanding for long video streams.arXiv preprint arXiv:2601.15655,.
Allocation Before Ranking: Decoupled Token Compression for OmniLLMs Event-vstream: Event-driven real-time understanding for long video streams.arXiv preprint arXiv:2601.15655,
Reference 6
- Resolution
- verified exact
- arxiv_id, observed 2026-08-04T23:23:39.745127Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 26f457be-4fb0-49da-8fbd-246fdfcb5cf0 · outbound
This paper cites WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs.
Allocation Before Ranking: Decoupled Token Compression for OmniLLMs WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs
Reference 7
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T23:23:38.038522Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation cdcf84f7-48a5-4552-91d9-c05821392a35 · outbound
This paper cites an unresolved cited work.
Allocation Before Ranking: Decoupled Token Compression for OmniLLMs Unresolved cited work
Reference 8
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T23:23:38.125893Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b2e15ce5-88e3-4563-810a-8867e8fe4c14 · outbound
This paper cites URLhttps://arxiv.org/abs/2503.04130.
Allocation Before Ranking: Decoupled Token Compression for OmniLLMs URLhttps://arxiv.org/abs/2503.04130
Reference 9
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T23:23:38.234159Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 27e54a3e-1f0d-40a1-bc3e-f1a0a6cf8394 · outbound
This paper cites 2601.13143.
Allocation Before Ranking: Decoupled Token Compression for OmniLLMs 2601.13143
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T23:23:38.297534Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 995e80ce-76f8-42a4-83b1-e293a54cfab9 · outbound
This paper cites DASH: Dynamic Audio-Driven Semantic Chunking for Efficient Omnimodal Token Compression.
Allocation Before Ranking: Decoupled Token Compression for OmniLLMs DASH: Dynamic Audio-Driven Semantic Chunking for Efficient Omnimodal Token Compression
Reference 11
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T23:23:38.428177Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fc042c54-46ec-4b4f-97a2-ad3f36087706 · outbound
This paper cites Kele Shao, Keda Tao, Can Qin, Haoxuan You, Yang Sui, and Huan Wang.
Allocation Before Ranking: Decoupled Token Compression for OmniLLMs Kele Shao, Keda Tao, Can Qin, Haoxuan You, Yang Sui, and Huan Wang
Reference 12
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T23:23:38.494676Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d1bde1cf-a489-465a-a9cd-f7dfb3337742 · outbound
This paper cites Huyu Wu, Meng Tang, Xinhan Zheng, and Haiyun Jiang.
Allocation Before Ranking: Decoupled Token Compression for OmniLLMs Huyu Wu, Meng Tang, Xinhan Zheng, and Haiyun Jiang
Reference 13
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T23:23:38.577322Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1292bf7c-cbee-4843-8715-43181321eafc · outbound
This paper cites When Language Overrules: Revealing Text Dominance in Multimodal Large Language Models.
Allocation Before Ranking: Decoupled Token Compression for OmniLLMs When Language Overrules: Revealing Text Dominance in Multimodal Large Language Models
Reference 14
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T23:23:38.657616Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 309f69c9-7ce8-47e5-ade7-a89946606132 · outbound
This paper cites PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction.
Allocation Before Ranking: Decoupled Token Compression for OmniLLMs PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction
Reference 15
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T23:23:38.724029Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c42d391e-0024-4f16-b4d2-b10cbc4723e4 · outbound
This paper cites Qwen2.5-Omni Technical Report.
Allocation Before Ranking: Decoupled Token Compression for OmniLLMs Qwen2.5-Omni Technical Report
Reference 16
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T23:23:38.847802Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6b8813a0-05ca-4779-8278-e01d2d41057c · outbound
This paper cites LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models.
Allocation Before Ranking: Decoupled Token Compression for OmniLLMs LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models
Reference 17
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T23:23:38.908542Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2428e129-1e3e-41a7-a55b-7e035829ebef · outbound
This paper cites MLLMs are Deeply Affected by Modality Bias.
Allocation Before Ranking: Decoupled Token Compression for OmniLLMs MLLMs are Deeply Affected by Modality Bias
Reference 18
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T23:23:39.041606Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e3706b11-782e-4d0f-bb5b-e200c1b17737 · outbound
This paper cites The ratio∆ v/∆a measures whether video or audio readout is more sensitive to probe-layer choice.
Allocation Before Ranking: Decoupled Token Compression for OmniLLMs The ratio∆ v/∆a measures whether video or audio readout is more sensitive to probe-layer choice
Reference 19
- Resolution
- verified exact
- arxiv_id, observed 2026-08-04T23:23:39.429064Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation a575452c-6a33-43de-86b2-59c5805eb4d1 · outbound
This paper cites Liang Chen, Haozhe Zhao, Tianyu Liu, Shuai Bai, Junyang Lin, Chang Zhou, and Baobao Chang.
Allocation Before Ranking: Decoupled Token Compression for OmniLLMs Liang Chen, Haozhe Zhao, Tianyu Liu, Shuai Bai, Junyang Lin, Chang Zhou, and Baobao Chang
Reference 2023
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-04T23:23:39.988358Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation d5893ffd-1c19-4210-a32d-a87daa2f0fba · outbound
This paper cites FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning.
Allocation Before Ranking: Decoupled Token Compression for OmniLLMs FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning
Reference 2024
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T23:23:37.539387Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 70c59f4e-51a2-44fa-bca1-f081081e2100 · outbound
This paper cites ARC-Hunyuan-Video-7B: Structured Video Comprehension of Real-World Shorts.
Allocation Before Ranking: Decoupled Token Compression for OmniLLMs ARC-Hunyuan-Video-7B: Structured Video Comprehension of Real-World Shorts
Reference 2025
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T23:23:37.839045Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4b77c009-9588-4157-823d-53606e59ef2f · outbound
This paper cites OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language Models.
Allocation Before Ranking: Decoupled Token Compression for OmniLLMs OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language Models
Reference 2026
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T23:23:37.735203Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Pith citing papers
No inbound Pith citation observations are available.