collaborators

21 papers

cs.CL2026

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…

cs.CV2026

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…

cs.CL2026

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…

cs.SD2026

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…

cs.CV2026

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…

cs.SD2026

AudioKV: KV Cache Eviction in Efficient Large Audio Language Models

Yuxuan Wang, Peize He, Xiyan Gui +6

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…