PickMoment: Continuous-Time Single-Image-to-Video via Learning Deblurring and Blur-to-Video
Research
Research News
New papers, breakthroughs and academic AI research
Misalignment of Low-Loss Regions Causes Grokking
Research
RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations
Research
Can LLMs Reliably Annotate Bioassay Metadata to Improve Data Readiness?
Research
ShelfChange3D: Object-Level 3D Change Detection for Retail Shelf Monitoring
Research
Learning Linear Systems under Heavy-Tailed Noise: A Non-Asymptotic Analysis from A Single Trajectory
Research
ODDR: One-Step Deshadow Diffusion via Reward Guidance
Research
ORBIT-FMIB: Tracking Order-Resolved Epistatic Information Through ESM-2
Research
MWOP: Modality-aware Width-wise Operation Pruning for Efficient MLLMs
Research
Learning the identity: a case study of how SGD selects among functional decompositions
Research
VideoEvolve: Evolving Agent Harnesses for Video Temporal Grounding
Research
LineupRL: Verifiable Reinforcement Learning for Time Series Captioning via Caption-to-Series Identification
Research