15 papers
REOPD: Reliability-Adaptive Reward Extrapolation for On-Policy Distillation
Yang Sun, Lichao Ma, Houyuan Qin +5
On-policy distillation (OPD) trains a student on its own trajectories under dense token-level supervision from a teacher. Reward-extrapolation methods such as ExOPD amplify the tea…
Distill Where You Fail: Recovering Learning Signals of Negative RL-Groups from Adaptive Teacher Guidance
Zhuowen Han, Jinwei Xiao, Zhengxi Lu +9
Reinforcement learning with verifiable rewards (RLVR) has become a standard paradigm for post-training large language models (LLMs). While Group Relative Policy Optimization (GRPO)…
RRS-10K: A Multitask Vision-Language Model Benchmark for Rare Remote Sensing Image Interpretation
Yuqiao Lai, Jiancheng Qi, Fei Wang +5
Vision-language models (VLMs) have achieved strong performance on general remote sensing tasks. However, their capability for rare scenes remains insufficiently understood, because…
TextGaze: Prompting Gaze Target Estimation with Textual Scene Cues
Junhui She, Fei Wang, Kun Li +4
Gaze target estimation aims to infer the position of a person's gaze within a scene. Within mainstream design logic, multi-branch methods require extra supervision and annotations,…
Rethinking the Role of Feature Engineering and Learning Strategies in Few-Shot Hidden Emotion Recognition
Xiaochuan Guo, Jihao Gu, Haixu Liu +6
In this paper, we present the solution developed by our team, XInsight Lab, which achieved first place in Track 3 of the 4th EI-MIGA-IJCAI Challenge with a test accuracy of 0.76923…
Finding the Evidence: Discovering Decision-Supporting Tokens for On-Policy Reasoning Distillation
Jinwei Xiao, Zhuowen Han, Yueqing Sun +6
On-policy distillation transfers reasoning ability through dense token-level supervision, yet the nature of the transferable signal remains unclear. We discover that reasoning chai…