Mixture of Decoders for Diverse Dialog Response Generation
Research
Research News
New papers, breakthroughs and academic AI research
Lingtai: What Concept Geometry Reveals--and Does Not Reveal--About LLM Inference
Research
CompMat-Bench: Benchmarking AI Agents for Computational Materials Science
Research
When More Data Is Not Enough: The Context-Sufficiency Frontier in Generative AI Personalization
Research
Self-Evolving Coding Rules for AI Coding Agents
Research
PhysicsMate: A Curriculum-Grounded Bengali Benchmark for Secondary Physics QA with Small-Model Adaptation
Research
Agent Evaluation Reliability: More Tasks Won't (Always) Fix An Agent Leaderboard
Research
A Simple Doxastic Deontic Logic for Norm-Guided Decision Making
Research
Large Language Bayes Is Not Reparameterisation-Invariant
Research
Coupling Perception and Reasoning in Federated Multimodal Graph Foundation Models
Research
PhysVista: Benchmarking Physical Intelligence in VLMs via a Perception-Reasoning-Assessment Loop
Research
The Null Is the Hard Part: Exact Tests for Memorization in Generative Models
Research