Completion-Aware Cross-Fidelity Offline-to-Online Reinforcement Learning for Multi-Line Bus Holding
Research
Research News
New papers, breakthroughs and academic AI research
Group Preference Collapse in Personalized Multimodal Large Language Models
Research
3D Software Synthesis Driven by Constraint-Expressive Intermediate Representation
Research
GrammarRL: Effective Grammar-Constrained Decoding via Reinforcement Learning
Research
Single-turn emergency psychiatric triage across 15 frontier AI chatbots
Research
Efficient Expert-Parallel Communication on PCIe-Connected Consumer GPUs
Research
ConflictGuide: AutoResearch Improves When Competing Behaviors Are Made Visible
Research
DiDA: Video Object Segmentation with Distillation Learning of Deformable Attention
Research
Fast LapSum: Exact Differentiable Top-$k$ at Million Scale
Research
FoCLIP: A Feature-Space Misalignment Framework for CLIP-Based Image Manipulation and Detection
Research
Coverage Before Control: Route-Instruction Grounding and Steering for Controllable Retrosynthesis
Research
Less is more: error-distance scaling relation for data-efficient kilometer-scale downscaling of extreme heat
Research