Post-Training Semantic Lifting for 3D Gaussian Splatting: Separating Detector, Lifting and Representation Error
Research
Research News
New papers, breakthroughs and academic AI research
Backend-Agnostic Sparse Attention for Fast High-Resolution Visual Generation
Research
Data Leakage in Patch-Based Hyperspectral Image Classification: Quantifying the Impact of Spatial Overlap
Research
World Models' Last Exam in Physics
Research
Variance-Averse $n$-Step Offline Reinforcement Learning for Sparse Long-Horizon Environments
Research
Toward Alignment Scaling Laws: A Framework and First Preregistered Measurements
Research
Privileged Context as Drift in On-Policy Self-Distillation
Research
Generalized Matheron Variational Implicit Processes
Research
SquidAgent: Parallelize Wisely, Coordinate Efficiently
Research
A Decision-Focused Neural Optimization Framework for Personalized Route Reproduction from Vehicle Trajectories
Research
FC-SWE: Failure-Conditioned RL for Long-Horizon Software Engineering Agents
Research
Align, Then Correct: Training-Free Two-Stage Low-Rank Compensation for Extremely Quantized Large Language Models
Research