Shuo Wang

C$^2$GSPG: Confidence-calibrated Group Sequence Policy Gradient towards Self-aware Reasoning

ForesightKV: Optimizing KV Cache Eviction for Reasoning Models by Learning Long-Term Contribution

Process Reinforcement through Implicit Rewards

SurveyBench: How Well Can LLM(-Agents) Write Academic Surveys?

Query Routing over Multimodal Knowledge Bases for Retrieval-Augmented Reasoning

Enhancing Delta Compression in LLMs via SVD-based Quantization Error Minimization

RoMA: Scaling up Mamba-based Foundation Models for Remote Sensing

A*-Thought: Efficient Reasoning via Bidirectional Compression for Low-Resource Settings

RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards

VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents