3 citations · 3 across the 20 of their papers we have counts for
22 papers
OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and Understanding
Xuyang Liu, Shihao Wang, Xinyu Wei +5
With the rapid development of multimodal large language models (MLLMs), evaluating their video understanding capabilities has become increasingly important. Existing video understa…
Look Ahead Before You Distill: Future Trajectory Validation of Teacher Guidance for Agentic On-Policy Distillation
Chishui Chen, Yaoyou Fan, Te Sun +11
On-policy distillation (OPD) provides teacher supervision on states visited by the student, reducing the distribution gap between training and inference. However, in multi-turn age…
Where to Place the Query? Unveiling and Mitigating Positional Bias in In-Context Learning for Diffusion LLMs via Decoding Dynamics
Zhengheng Li, Panrui Li, Xuyang Liu +1
While In-Context Learning (ICL) is extensively studied in Autoregressive (AR) LLMs, its mechanism within Diffusion Large Language Models (dLLMs) remains largely unexplored. Unlike…
EvoStreaming: Your Offline Video Model Is a Natively Streaming Assistant
Zichen Wen, Boxue Yang, Junlong Ke +5
Streaming video understanding demands more than watching longer videos: assistants must decide when to speak in real time, balancing responsiveness against verbosity. Yet most vide…
HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models
Peize He, Yaodi Luo, Xiaoqian Liu +7
Recent large audio language models (LALMs) demonstrate remarkable capabilities in processing extended multi-modal sequences, yet incur high inference costs. Token compression is an…
STDec: Spatio-Temporal Stability Guided Decoding for dLLMs
Yuzhe Chen, Jiale Cao, Xuyang Liu +3
Diffusion Large Language Models (dLLMs) have achieved rapid progress, viewed as a promising alternative to the autoregressive paradigm. However, most dLLM decoders still adopt a gl…
AudioKV: KV Cache Eviction in Efficient Large Audio Language Models
Yuxuan Wang, Peize He, Xiyan Gui +5
Large Audio-Language Models (LALMs) have set new benchmarks in speech processing, yet their deployment is hindered by the memory footprint of the Key-Value (KV) cache during long-c…
V-CAST: Video Curvature-Aware Spatio-Temporal Pruning for Efficient Video Large Language Models
Xinying Lin, Xuyang Liu, Yiyu Wang +2
Video large language models (VideoLLMs) show strong capability in video understanding, yet long-context inference is still dominated by massive redundant visual tokens in the prefi…
Bridging Visual Representation and Reinforcement Learning from Verifiable Rewards in Large Vision-Language Models
Yuhang Han, Yuyang Wu, Zhengbo Jiao +6
Reinforcement Learning from Verifiable Rewards (RLVR) has substantially enhanced the reasoning capabilities of large language models in abstract reasoning tasks. However, its appli…
Flash-Unified: A Training-Free and Task-Aware Acceleration Framework for Native Unified Models
Junlong Ke, Zichen Wen, Boxue Yang +6
Native unified multimodal models, which integrate both generative and understanding capabilities, face substantial computational overhead that hinders their real-world deployment.…
Where and How to Prune: An Empirical Study of Visual Token Pruning for GUI Agent Navigation
Daiqiang Li, Zihao Pan, Zeyu Zhang +8
In recent years, GUI agents have demonstrated strong potential in navigation tasks. However, preserving complete historical screenshots introduces substantial computational overhea…
IPCV: Information-Preserving Compression for MLLM Visual Encoders
Yuan Chen, Zichen Wen, Yuzhou Wu +6
Multimodal Large Language Models (MLLMs) deliver strong vision-language performance but at high computational cost, driven by numerous visual tokens processed by the Vision Transfo…
Accelerating Streaming Video Large Language Models via Hierarchical Token Compression
Yiyu Wang, Xuyang Liu, Xiyan Gui +5
Streaming Video Large Language Models (VideoLLMs) have demonstrated impressive performance across various video understanding tasks, but they face significant challenges in real-ti…
AI for Service: Proactive Assistance with AI Glasses
Zichen Wen, Yiyu Wang, Chenfei Liao +10
In an era where AI is evolving from a passive tool into an active and adaptive companion, we introduce AI for Service (AI4Service), a new paradigm that enables proactive and real-t…
Mixing Importance with Diversity: Joint Optimization for KV Cache Compression in Large Vision-Language Models
Xuyang Liu, Xiyan Gui, Yuchao Zhang +1
Recent large vision-language models (LVLMs) demonstrate remarkable capabilities in processing extended multi-modal sequences, yet the resulting key-value (KV) cache expansion creat…
Prune2Drive: A Plug-and-Play Framework for Accelerating Vision-Language Models in Autonomous Driving
Minhao Xiong, Zichen Wen, Zhuangcheng Gu +9
Vision-Language Models (VLMs) have emerged as a promising paradigm in autonomous driving (AD), providing a unified framework for perception and decision-making. However, their real…
The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs
Zichen Wen, Jiashu Qu, Zhaorun Chen +13
Diffusion-based large language models (dLLMs) have recently emerged as a powerful alternative to autoregressive LLMs, offering faster inference and greater interactivity via parall…
Shifting AI Efficiency From Model-Centric to Data-Centric Compression
Xuyang Liu, Zichen Wen, Shaobo Wang +14
The advancement of large language models (LLMs) and multi-modal LLMs (MLLMs) has historically relied on scaling model parameters. However, as hardware limits constrain further mode…
Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models
Xuyang Liu, Yiyu Wang, Junpeng Ma +1
Video large language models (VideoLLM) excel at video understanding, but face efficiency challenges due to the quadratic complexity of abundant visual tokens. Our systematic analys…
Seeing Sarcasm Through Different Eyes: Analyzing Multimodal Sarcasm Perception in Large Vision-Language Models
Junjie Chen, Xuyang Liu, Subin Huang +2
With the advent of large vision-language models (LVLMs) demonstrating increasingly human-like abilities, a pivotal question emerges: do different LVLMs interpret multimodal sarcasm…
Global Compression Commander: Plug-and-Play Inference Acceleration for High-Resolution Large Vision-Language Models
Xuyang Liu, Ziming Wang, Junjie Chen +6
Large vision-language models (LVLMs) excel at visual understanding, but face efficiency challenges due to quadratic complexity in processing long multi-modal contexts. While token…
Gnothi Seauton: Empowering Faithful Self-Interpretability in Black-Box Transformers
Shaobo Wang, Hongxuan Tang, Mingyang Wang +5
The debate between self-interpretable models and post-hoc explanations for black-box models is central to Explainable AI (XAI). Self-interpretable models, such as concept-based net…