6 papers
Teacher-Student Gaps Are Not Enough: Outcome-Guided On-Policy Distillation for Multi-Turn Autonomous Agents
Tong Zhang, Zhou Liu, Yihao Liu +8
On-policy distillation (OPD) trains a student on its own trajectories with dense teacher supervision. Recent work on OPD for multi-turn autonomous agents often treats large teacher…
Beyond Sparse Rewards: A New Benchmark and Structure-Aware Graph Alignment for Micro-Drama Understanding
Yixin Qin, Shi-Zhe Chen, Zhiqi Yu +4
Micro-dramas, characterized by ultra-short durations and hyper-dense storylines, pose unique challenges for video understanding that conventional benchmarks fail to address. To bri…
HyLaR: Hybrid Latent Reasoning with Decoupled Policy Optimization
Tao Cheng, Shi-Zhe Chen, Hao Zhang +3
Chain-of-Thought (CoT) reasoning significantly elevates the complex problem-solving capabilities of multimodal large language models (MLLMs). However, adapting CoT to vision typica…
Vision-Language Reasoning for Geolocalization: A Reinforcement Learning Approach
Biao Wu, Meng Fang, Ling Chen +3
Recent advances in vision-language models have opened up new possibilities for reasoning-driven image geolocalization. However, existing approaches often rely on synthetic reasonin…
Patho-R1: A Multimodal Reinforcement Learning-Based Pathology Expert Reasoner
Wenchuan Zhang, Penghao Zhang, Jingru Guo +6
Recent advances in vision language models (VLMs) have enabled broad progress in the general medical field. However, pathology still remains a more challenging subdomain, with curre…
Geolocation with Real Human Gameplay Data: A Large-Scale Dataset and Human-Like Reasoning Framework
Zirui Song, Jingpu Yang, Yuan Huang +6
Geolocation, the task of identifying an image's location, requires complex reasoning and is crucial for navigation, monitoring, and cultural preservation. However, current methods…