12 papers · 1 filter
LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMs
Keda Tao, Yuhua Zheng, Jia Xu +13
Recent advancements in omnimodal large language models (OmniLLMs) have significantly improved the comprehension of audio and video inputs. However, current evaluations primarily fo…
StreamingAssistant: Efficient Visual Token Pruning for Accelerating Online Video Understanding
Xinqi Jin, Hanxun Yu, Bohan Yu +8
Online video understanding is essential for applications like public surveillance and AI glasses. However, applying Multimodal Large Language Models (MLLMs) to this domain is chall…
Active Perception Agent for Omnimodal Audio-Video Understanding
Keda Tao, Wenjie Du, Bohan Yu +3
Omnimodal large language models have made significant strides in unifying audio and visual modalities; however, they often face challenges in fine-grained cross-modal understanding…
OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models
Keda Tao, Kele Shao, Bohan Yu +3
Omnimodal large language models (OmniLLMs) have attracted increasing research attention of late towards unified audio-video understanding. However, the high computational cost of p…
StreamingTOM: Streaming Token Compression for Efficient Video Understanding
Xueyi Chen, Keda Tao, Kele Shao +1
Unlike offline processing, streaming video vision-language models face two fundamental constraints: causality and accumulation. Causality prevents access to future frames that offl…
Revisiting MLLM Token Technology through the Lens of Classical Visual Coding
Jinming Liu, Junyan Lin, Yuntao Wei +7
Classical visual coding and Multimodal Large Language Model (MLLM) token technology share the core objective - maximizing information fidelity while minimizing computational cost.…
TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs
Kejia Zhang, Keda Tao, Zhiming Luo +3
Multimodal large language models (MLLMs) are prone to hallucinations, generating plausible but visually ungrounded outputs, partly because direct preference optimization (DPO) over…
A Survey of Token Compression for Efficient Multimodal Large Language Models
Kele Shao, Keda Tao, Kejia Zhang +7
Multimodal large language models (MLLMs) have made remarkable strides, largely driven by their ability to process increasingly long and complex contexts, such as high-resolution im…
HoliTom: Holistic Token Merging for Fast Video Large Language Models
Kele Shao, Keda Tao, Can Qin +3
Video large language models (video LLMs) excel at video comprehension but face significant computational inefficiency due to redundant video tokens. Existing token pruning methods…
Plug-and-Play 1.x-Bit KV Cache Quantization for Video Large Language Models
Keda Tao, Haoxuan You, Yang Sui +2
Video large language models (VideoLLMs) have demonstrated the capability to process longer video inputs and enable complex reasoning and analysis. However, due to the thousands of…
Poison as Cure: Visual Noise for Mitigating Object Hallucinations in LVMs
Kejia Zhang, Keda Tao, Jiasheng Tang +1
Large vision-language models (LVMs) extend large language models (LLMs) with visual perception capabilities, enabling them to process and interpret visual information. A major chal…
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models
Keda Tao, Can Qin, Haoxuan You +2
Video large language models (VLLMs) have significantly advanced recently in processing complex video content, yet their inference efficiency remains constrained because of the high…