Provably Efficient Reinforcement Learning in Continuous-Time Episodic MDPs with Poisson Decision Epochs
Research
Research News
New papers, breakthroughs and academic AI research
Error-Supervised Synthetic Learner Writing for Automated Essay Scoring
Research
Neural Residual Modeling for Scientific Data Compression under Guaranteed Error Bounds
Research
VGGT-Prime: Compute-Adaptive Mixture-of-Heads for Efficient Visual Geometry Transformers
Research
OnlineWM: Causality-Aware Active Online Learning for Effective World Modeling
Research
Ask for Any Appliance: A Prompt-Programmable Foundation Model for Non-Intrusive Load Monitoring
Research
On the Efficiency-Safety Dilemma in Large Reasoning Models
Research
VISTA: Video-Injected Stylized Text-to-Animation
Research
Lifted Bellman Linear Programming for Offline Reinforcement Learning
Research
RAILS: Retrieval-Augmented Incremental LLM Clustering at Scale
Research
PixelDiT2: Representation-Grounded Pixel Diffusion Transformers
Research
Layer-Aware Position Embeddings for Visual Token Pruning in Multimodal Large Language Models
Research