How Is Automated Research Evaluated? A Survey of Benchmarks and Evaluation Practices
Research
Research News
New papers, breakthroughs and academic AI research
An Interpretable Approach to PDE Solution Discovery via Structural Experience Distillation
Research
V-CoLA: Vision Token Compression with Linear Attention
Research
MemTrial: Learning When to Trust Memory in LLM Portfolio Agents
Research
LR-V2X: Loss-Resilient Collaborative Perception under Low-Bandwidth Communication
Research
Adapting English Quality Classifiers for Multilingual LLM Pretraining Data Selection
Research
When Scene Text Hijacks the Scene: Uncovering, Exploiting, and Mitigating Rendered-Text Semantic Leakage in Image Generation Models
Research
TRACE: Diagnosing Verifier Brittleness in Agentic Evaluation
Research
Measuring Cultural Alignment Beyond the Average: A Framework for Evaluating Maternal-Health LLM Interactions in Indian Contexts
Research
Memento 3: Model-Based Recursive Self-Improvement through Reflective Rulebooks
Research
MetaOPD: Meta-Learned Token Weighting for On-Policy Distillation
Research
Scalable AI Uncertainty Quantification via Generalized Laplace Active Subspaces
Research