My FAULT: Self-Diagnosis as Credit Assignment in Self-Evolving Agentic Reinforcement Learning
Research
Research News
New papers, breakthroughs and academic AI research
Temporally-Resolved Token Attribution Reveals the Generation Dynamics of Diffusion Language Models
Research
ASCRIBE: Atomic and Significance-Based Reasoning for Thai Clinical SOAP Note Generation
Research
Evaluating the Robustness of Japanese LLMs to IME-Related and Typographical Errors
Research
SpikeMoE: Brain-Inspired Competitive Routing for Flexible Spiking Mixture-of-Experts
Research
Rethinking Probability-Based Reinforcement Learning From Posterior Concentration
Research
PRISM: A Category-Theoretic Framework for Measuring and Refining Multimodal Analogies
Research
Contrastive Attention Mitigates Spectral Bias in Spiking Transformers
Research
A Deterministic and Auditable AI Security Risk Assessment Framework with ATLAS Aligned Executable Rules and Formal Verification
Research
AiSearch: Interactive Multi-Modal Search with VLMs
Research
Beyond Memory: Harnessing Long-Horizon Agents with Explicit Belief States
Research
A Multi-Agent LLM Framework for Personalized Health Checkup Interpretation and Guidance
Research