Paper Citation Record · LEDGER

HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models

As of 6 August 2026, this Paper Citation Record lists 34 of 34 outbound references and 0 inbound Pith citation observations for arXiv:2604.23717.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2604.23717 v1

Coverage vector

measured 34 of 34 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-08T05:20:30.823304Z

measured 34 of 34 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

34 of 34 outbound references displayed

verified exact19
verified fuzzy13
unresolved2
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation e9899b37-44e8-40af-bc00-b577a5b281de · outbound

This paper cites Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs.

HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-11T22:22:28.302846Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 40b8f34b-e6e2-4bc5-8920-3e93ce848b28 · outbound

This paper cites Towards audio token compression in large audio language models.

HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models Towards audio token compression in large audio language models

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:31:14.401725Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e7da7269-9919-49d9-b7b2-3dfc5f8da75e · outbound

This paper cites Variation-aware vision token dropping for faster large vision-language models.

HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models Variation-aware vision token dropping for faster large vision-language models

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:31:14.378072Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation bffe711f-3c2e-4c92-8dfd-f944ff110020 · outbound

This paper cites An image is worth 1/2 tokens after layer 2: Plug-and-play inference acceleration for large vision-language models.

HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models An image is worth 1/2 tokens after layer 2: Plug-and-play inference acceleration for large vision-language models

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T19:57:56.584029Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a4295657-bb6c-4941-aba1-af5d483ec599 · outbound

This paper cites Voxdialogue: Can spoken dialogue systems un- derstand information beyond words? InThe Thirteenth International Conference on Learn- ing Representations.

HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models Voxdialogue: Can spoken dialogue systems un- derstand information beyond words? InThe Thirteenth International Conference on Learn- ing Representations

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T19:57:56.580751Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c8d85341-555c-4be0-953b-0748dc9289fc · outbound

This paper cites Recent advances in speech language models: A survey.

HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models Recent advances in speech language models: A survey

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T19:57:56.561749Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 898ff85c-2a31-40b3-87bd-2926c7790446 · outbound

This paper cites OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language Models.

HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language Models

Reference 7

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 2026-08-05T06:32:48.257954+00:00.

Observation bf4b9018-0016-4edd-9b2e-362ec6250864 · outbound

This paper cites Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities.

HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:31:14.370153Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7e9353d4-a18d-4699-8b73-dc728fa74740 · outbound

This paper cites Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models.

HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-15T03:42:46.422993Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1bdcfb75-9d0e-476a-a9a3-133515f91b67 · outbound

This paper cites Filter, correlate, compress: Training-free token reduc- tion for mllm acceleration.

HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models Filter, correlate, compress: Training-free token reduc- tion for mllm acceleration

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T19:57:56.546365Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 870262c2-a8e2-4446-bb81-0c36ca06ccc8 · outbound

This paper cites Audiomarathon: A comprehensive benchmark for long-context audio understanding and efficiency in audio llms.

HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models Audiomarathon: A comprehensive benchmark for long-context audio understanding and efficiency in audio llms

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:31:14.497205Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a6acffad-05ba-4093-9044-286feb5b7a2b · outbound

This paper cites MMAU-Pro: A Challenging and Comprehensive Benchmark for Holistic Evaluation of Audio General Intelligence.

HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models MMAU-Pro: A Challenging and Comprehensive Benchmark for Holistic Evaluation of Audio General Intelligence

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:31:14.474889Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f1e50845-3222-4a47-8073-11ba80d34beb · outbound

This paper cites V-cast: Video curvature- aware spatio-temporal pruning for efficient video large language models.

HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models V-cast: Video curvature- aware spatio-temporal pruning for efficient video large language models

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:31:14.657167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3ed66fc0-294a-4000-92d7-9c28a980e6fb · outbound

This paper cites Mixing importance with diversity: Joint optimization for kv cache compression in large vision-language models.

HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models Mixing importance with diversity: Joint optimization for kv cache compression in large vision-language models

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:31:14.513215Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d1b026d1-b1ba-4b27-8ef1-ec175ea69ae7 · outbound

This paper cites Video compression commander: Plug-and-play inference acceleration for video large language models.

HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models Video compression commander: Plug-and-play inference acceleration for video large language models

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T19:57:56.543532Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 724a5910-bc5a-4ec1-af1e-9354d78a695a · outbound

This paper cites Shifting AI efficiency from model-centric to data-centric compression.

HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models Shifting AI efficiency from model-centric to data-centric compression

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:31:14.445030Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9a3c33ad-a0d5-4bb6-8cb6-bac34ef25363 · outbound

This paper cites Global compression commander: Plug-and-play infer- ence acceleration for high-resolution large vision- language models.

HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models Global compression commander: Plug-and-play infer- ence acceleration for high-resolution large vision- language models

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T19:57:56.540450Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4abbffd3-3d25-46c2-915b-804f12f3f2cf · outbound

This paper cites Librispeech: an asr corpus based on public domain audio books.

HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models Librispeech: an asr corpus based on public domain audio books

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T19:57:56.565167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 93ba1f1d-8a84-43b4-a904-e48ecd18bedf · outbound

This paper cites Robust speech recognition via large- scale weak supervision.

HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models Robust speech recognition via large- scale weak supervision

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T19:57:56.568263Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 196c0e02-1f11-4ace-bc2f-a081d44e7b7f · outbound

This paper cites Sound event detec- tion in synthetic domestic environments.

HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models Sound event detec- tion in synthetic domestic environments

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T19:57:56.571169Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9ac3f73f-d49c-48d9-9ee1-8ec2c911da9f · outbound

This paper cites SALMONN: Towards Generic Hearing Abilities for Large Language Models.

HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models SALMONN: Towards Generic Hearing Abilities for Large Language Models

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-18T02:29:46.683133Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6490c2f1-061b-4704-8000-a1ef2e463553 · outbound

This paper cites MMSU: A Massive Multi-task Spoken Language Understanding and Reasoning Benchmark.

HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models MMSU: A Massive Multi-task Spoken Language Understanding and Reasoning Benchmark

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-17T17:21:50.902611Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d4cc5161-b3a8-481d-a543-b82fb78afeba · outbound

This paper cites Accelerating streaming video large language models via hierarchical token compression.

HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models Accelerating streaming video large language models via hierarchical token compression

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:31:14.616290Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation aa111c45-fffc-4065-9216-d52c541ee86d · outbound

This paper cites AudioKV: KV Cache Eviction in Efficient Large Audio Language Models.

HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models AudioKV: KV Cache Eviction in Efficient Large Audio Language Models

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-05-11T21:31:14.567879Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2e4ba5d4-df3d-4e55-bf62-beaf4520ba1e · outbound

This paper cites an unresolved cited work.

HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models Unresolved cited work

Reference 25

Resolution: unresolved; raw_fallback, observed 2026-05-26T19:57:56.574187Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 87e75540-5bb3-45b4-8336-5a01d0f862ca · outbound

This paper cites Stolfo, A., Balachandran, V ., Yousefi, S., Horvitz, E., and Nushi, B.

HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models Stolfo, A., Balachandran, V ., Yousefi, S., Horvitz, E., and Nushi, B

Reference 26

Resolution: verified exact; doi, observed 2026-05-08T23:54:25.288601Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation da6e42db-0295-4223-988a-5f90513ce6f6 · outbound

This paper cites emnlp-main.505/.

HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models emnlp-main.505/

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T19:57:56.555479Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2f88fd74-413b-4689-8ad8-4320184c52af · outbound

This paper cites Efficient Streaming Language Models with Attention Sinks.

HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models Efficient Streaming Language Models with Attention Sinks

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-05-11T21:31:14.455362Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d73c1422-ffbb-4461-b29d-c7bb9b415b41 · outbound

This paper cites Qwen2.5-Omni Technical Report.

HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models Qwen2.5-Omni Technical Report

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-05-11T21:31:14.582887Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6f2d9c7d-3566-48b9-a27e-059812bf89cd · outbound

This paper cites an unresolved cited work.

HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models Unresolved cited work

Reference 30

Resolution: unresolved; raw_fallback, observed 2026-05-26T19:57:56.549274Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c366e5e3-4d9e-4f67-b605-74aa33839a66 · outbound

This paper cites Qwen3-Omni Technical Report.

HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models Qwen3-Omni Technical Report

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-05-11T21:31:14.628554Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f7619b2c-54b2-4cff-9a80-91ea556c21eb · outbound

This paper cites Sakura: On the multi-hop rea- soning of large audio-language models based on speech and audio information.

HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models Sakura: On the multi-hop rea- soning of large audio-language models based on speech and audio information

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T19:57:56.552201Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation bfb51d97-cd5c-4b7d-9233-2c771ac3d228 · outbound

This paper cites Visionzip: Longer is better but not nec- essary in vision language models.

HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models Visionzip: Longer is better but not nec- essary in vision language models

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T19:57:56.558681Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0f42a7df-0ab8-44c7-b7e7-0de8d6793826 · outbound

This paper cites Speechgpt: Empowering large language models 12 with intrinsic cross-modal conversational abili- ties.

HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models Speechgpt: Empowering large language models 12 with intrinsic cross-modal conversational abili- ties

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T19:57:56.577294Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Pith citing papers

No inbound Pith citation observations are available.