AVLLMs encode audio semantics in middle layers but suppress them in final text outputs when audio conflicts with vision, due to training that largely inherits from vision-language base models.
hub
video-salmonn: Speech-enhanced audio-visual large language models.arXiv preprint arXiv:2406.15704
14 Pith papers cite this work. Polarity classification is still indexing.
14
Pith papers citing it
hub tools
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
Sandboxed coding agents with text+image access match or outperform native omnimodal models on audio-video benchmarks by converting tasks into code-driven retrieval and processing.
MTSS replaces monolithic video captions with factorized streams and relational grounding, yielding reported gains in understanding benchmarks and generation consistency.
AV-SpeakerBench is a new speaker-centered benchmark showing that top multimodal models still struggle with fine-grained audiovisual speech understanding, with Gemini 2.5 Pro leading but open models lagging on fusion.
XModBench is a tri-modal benchmark that systematically measures cross-modal consistency, modality disparities, and directional imbalances in omni-language models across five task families and all modality combinations.
R1-VL uses StepGRPO with rule-based StepRAR and StepRVR rewards to let MLLMs learn step-by-step reasoning beyond imitation of positive paths.
WorldSense provides the first benchmark requiring synergistic audio-video-text understanding on 1,662 real-world videos and 3,172 QA pairs, where the best current multimodal LLM reaches only 65.1% accuracy.
V-LynX integrates novel modalities into frozen Video LLMs by aligning to an internalized continuous token manifold using unpaired unimodal data and attention/statistical matching.
EmoMM benchmark reveals Video Contribution Collapse in MLLMs for emotion recognition under modality conflict and missingness, mitigated by CHASE head-level attention steering.
OmniZip introduces an audio-guided dynamic token compression framework that achieves 3.42X inference speedup and 1.4X memory reduction for omnimodal LLMs without any training.
OmniRefine introduces alignment-aware chunk refinement via similarity and dynamic programming followed by modality-cooperative token compression, achieving near-baseline accuracy at 44% token retention on WorldSense.
Qwen2.5-Omni presents a multimodal model with block-wise encoders, TMRoPE position embeddings, and a Thinker-Talker architecture that enables simultaneous text and streaming speech generation while matching text performance on reasoning benchmarks.
VideoLLaMA3 uses a vision-centric training paradigm and token-reduction design to reach competitive results on image and video benchmarks.
VITA-1.5 integrates vision and speech into a single LLM through multi-stage training, delivering competitive benchmark results on image, video, and speech tasks with near real-time response speed.
citing papers explorer
-
Do Audio-Visual Large Language Models Really See and Hear?
AVLLMs encode audio semantics in middle layers but suppress them in final text outputs when audio conflicts with vision, due to training that largely inherits from vision-language base models.
-
Sandboxed Coding Agents are Competitive Omni-modal Task Solvers
Sandboxed coding agents with text+image access match or outperform native omnimodal models on audio-video benchmarks by converting tasks into code-driven retrieval and processing.
-
Script-a-Video: Deep Structured Audio-visual Captions via Factorized Streams and Relational Grounding
MTSS replaces monolithic video captions with factorized streams and relational grounding, yielding reported gains in understanding benchmarks and generation consistency.
-
See, Hear, and Understand: Benchmarking Audiovisual Human Speech Understanding in Multimodal Large Language Models
AV-SpeakerBench is a new speaker-centered benchmark showing that top multimodal models still struggle with fine-grained audiovisual speech understanding, with Gemini 2.5 Pro leading but open models lagging on fusion.
-
XModBench: Benchmarking Cross-Modal Capabilities and Consistency in Omni-Language Models
XModBench is a tri-modal benchmark that systematically measures cross-modal consistency, modality disparities, and directional imbalances in omni-language models across five task families and all modality combinations.
-
R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization
R1-VL uses StepGRPO with rule-based StepRAR and StepRVR rewards to let MLLMs learn step-by-step reasoning beyond imitation of positive paths.
-
WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs
WorldSense provides the first benchmark requiring synergistic audio-video-text understanding on 1,662 real-world videos and 3,172 QA pairs, where the best current multimodal LLM reaches only 65.1% accuracy.
-
V-LynX: Token Interface Alignment for Video+X LLMs
V-LynX integrates novel modalities into frozen Video LLMs by aligning to an internalized continuous token manifold using unpaired unimodal data and attention/statistical matching.
-
EmoMM: Benchmarking and Steering MLLM for Multimodal Emotion Recognition under Conflict and Missingness
EmoMM benchmark reveals Video Contribution Collapse in MLLMs for emotion recognition under modality conflict and missingness, mitigated by CHASE head-level attention steering.
-
OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models
OmniZip introduces an audio-guided dynamic token compression framework that achieves 3.42X inference speedup and 1.4X memory reduction for omnimodal LLMs without any training.
-
OmniRefine: Alignment-Aware Cooperative Compression for Efficient Omnimodal Large Language Models
OmniRefine introduces alignment-aware chunk refinement via similarity and dynamic programming followed by modality-cooperative token compression, achieving near-baseline accuracy at 44% token retention on WorldSense.
-
Qwen2.5-Omni Technical Report
Qwen2.5-Omni presents a multimodal model with block-wise encoders, TMRoPE position embeddings, and a Thinker-Talker architecture that enables simultaneous text and streaming speech generation while matching text performance on reasoning benchmarks.
-
VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding
VideoLLaMA3 uses a vision-centric training paradigm and token-reduction design to reach competitive results on image and video benchmarks.
-
VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction
VITA-1.5 integrates vision and speech into a single LLM through multi-stage training, delivering competitive benchmark results on image, video, and speech tasks with near real-time response speed.