Latest
- ReviewGrounder: Improving Review Substantiveness with Rubric-Guided Tool-Integrated Agents
- SciImpact: A Multi-Dimensional Multi-Field Benchmark for Scientific Impact Prediction
- In-the-Flow Agentic System Optimization for Effective Planning and Tool Use
- Curriculum Reinforcement Learning from Easy to Hard Tasks Improves LLM Reasoning
- RM-R1: Reward Modeling as Reasoning
- Knowledge Homophily in Large Language Models
- Protein Large Language Models: A Comprehensive Survey
- Internal and External Impacts of Natural Language Processing Papers
- A Unified Taxonomy-Guided Instruction Tuning Framework for Entity Set Expansion and Taxonomy Expansion
- Chain-of-Factors Paper-Reviewer Matching