5 papers
DRIFT: Difficulty Routing Self-DIstillation with Rhythm-Gated Exploration and Success BuFfer Training
Haisen Luo, Yiwei Liu, Haoning Wang +13
Enabling large language models to achieve stable self-improvement without external expert supervision remains a central challenge in complex reasoning tasks. Existing self-distilla…
UAV-VL-R1: Generalizing Vision-Language Models via Supervised Fine-Tuning and Multi-Stage GRPO for UAV Visual Reasoning
Jiajin Guan, Haibo Mei, Bonan Zhang +3
Recent advances in vision-language models (VLMs) have demonstrated strong generalization in natural image tasks. However, their performance often degrades on unmanned aerial vehicl…
Causal-Tune: Mining Causal Factors from Vision Foundation Models for Domain Generalized Semantic Segmentation
Yin Zhang, Yongqiang Zhang, Yaoyue Zheng +2
Fine-tuning Vision Foundation Models (VFMs) with a small number of parameters has shown remarkable performance in Domain Generalized Semantic Segmentation (DGSS). Most existing wor…
Extreme Model Compression with Structured Sparsity at Low Precision
Dan Liu, Nikita Dvornik, Xue Liu
Deep neural networks (DNNs) are used in many applications, but their large size and high computational cost make them hard to run on devices with limited resources. Two widely used…
Pinpointing crucial steps: Attribution-based Credit Assignment for Verifiable Reinforcement Learning
Junxi Yin, Haisen Luo, Zhenyu Li +4
While Reinforcement Learning with Verifiable Rewards (RLVR) enhances complex reasoning in LLMs, current methods struggle to balance exploration and exploitation. This leads to crit…