4 papers
Knowledge-Preserved Model Tuning in Null-Space for Robust Spatio-Temporal Video Grounding
Haoxuan Chen, Xianqin Liu, Jian-Fang Hu
Spatio-Temporal Video Grounding aims to localize object tubes based on textual queries. While recent methods have achieved remarkable success, they mainly focus on high-quality(HQ)…
Breaking : Cooperative Policy Optimization Improves Diverse LLM Reasoning
Haoxuan Chen, Tianming Liang, Wei-Shi Zheng +1
Reinforcement learning with verifiers (RLVR) has become a central paradigm for improving LLM reasoning, yet popular group-based optimization algorithms like GRPO often suffer from…
Null-LoRA: Low-Rank Adaptation on Null Space
Yi Zhang, Yulei Kang, Haoxuan Chen +2
Parameter-efficient fine-tuning methods have gained considerable popularity for adapting large-scale models to downstream tasks, particularly LoRA and its variants. Existing method…
Image-to-Video Transfer Learning based on Image-Language Foundation Models: A Comprehensive Survey
Jinxuan Li, Chaolei Tan, Haoxuan Chen +4
Image-Language Foundation Models (ILFMs) have demonstrated remarkable success in vision-language understanding, providing transferable multimodal representations that generalize ac…