3 papers
cs.CV2026
Thinking in Streaming Video
Zikang Liu, Longteng Guo, Handong Li +7
Real-time understanding of continuous video streams is essential for interactive assistants and multimodal agents operating in dynamic environments. However, most existing video re…
cs.LG2025
Prefix Grouper: Efficient GRPO Training through Shared-Prefix Forward
Zikang Liu, Tongtian Yue, Yepeng Tang +5
Group Relative Policy Optimization (GRPO) enhances policy learning by computing gradients from relative comparisons among candidate outputs that share a common input prefix. Despit…
cs.AI2025
VRoPE: Rotary Position Embedding for Video Large Language Models
Zikang Liu, Longteng Guo, Yepeng Tang +6
Rotary Position Embedding (RoPE) has shown strong performance in text-based Large Language Models (LLMs), but extending it to video remains a challenge due to the intricate spatiot…