LLM4Impact: Integrating Heterogeneous Information for Scientific Impact Prediction
Research
Research News
New papers, breakthroughs and academic AI research
Beyond Outcome Rewards: Constructing and Assigning Retrieval Credit for Search Agents
Research
Learning to Act with Task Progress: Distilling Small Agents from Compact Teacher Supervision
Research
Evaluating Trajectory Features for Routing Final-Layer Attention
Research
Twist Flow for Inverse Problems
Research
Self-attention summary networks for subsurface velocity-model building from common-image gathers
Research
LeCuration: A Tiny World Model as a Data Curation Multi-Tool
Research
RewardWeaver: Long-Horizon Interactive Learning for Language Agents via Self-Evolving Reward Adaptation
Research
Benign Overfitting under Heterogeneous Input Fusion
Research
Before They Can Solve: Predicting Post-Training Coding-Agent Performance from Base Models
Research
EngramEdit: Decoupled Knowledge Updates in LLMs through Conditional Memory
Research
Large-scale Repository Engineering via Agent-Native Reusable Code Primitives
Research