AI
CDRL: Certification-Driven Reinforcement Learning for Neutrino Flavor Model Discovery
A new AI approach called Certification-Driven Reinforcement Learning (CDRL) has been developed to he...
AI
VortexChat: An agentic framework for autonomous multi-objective integrated photonic design
Researchers have developed VortexChat, an AI system that can autonomously design complex integrated ...
AI
DirEAG: Dirichlet Evidence Aggregation for Calibrating Verbalized Confidence in Mathematical Reasoning
Researchers propose a new method called DirEAG to improve confidence estimation in large language mo...
AI
Calibrating Criterion Revision in LLM Agents: Failure Modes and a Trace-Anchored Protocol
Researchers have been working on improving language models by allowing them to adapt and learn from ...
AI
ForeTime-VLA: Causal Future-Token Distillation from a World Action Model for Conveyor-Belt Manipulation
Researchers have developed a new AI model called ForeTime-VLA that can predict a...
AI
Continuous-Time Quantum Walks based Graph Neural Network
Researchers have proposed a new type of Graph Neural Network (GNN) called CTQW-G...
AI
Is Multimodal Speculative Decoding Ready for Diffusion-Based Parallel Drafting? A Survey and Empirical Diagnosis
Researchers Yantao Li and colleagues have conducted a survey to determine if mul...
AI
Natural-Language-Guided Generator-Agnostic Shortlisting for Protein Binder Design
Researchers have developed a method to use language models to rank and shortlist...