Learning from Runtime Feedback through Failure-Bank Self-Evolution for Vision-Language-Action Models
Research
Research News
New papers, breakthroughs and academic AI research
Hybrid Methods for Robust Tabular Data Imputation
Research
StreamRig: Exploiting Intra-Rig Geometry for Streaming Multi-Camera Odometry
Research
Mitigating Representation Gaps in Amortized Bayesian Inference with Auxiliary Supervision
Research
Learning Skills from Historical Action Trajectories: Action Experience Dictionary for World Action Models
Research
CATCH: A Controllable Analysis Testbed for Reward Hacking in Coding RL
Research
LOCI: Spatial Linear Memory for Streaming World Models
Research
GLARE: Generating Listening Heads with Appropriate Reactions
Research
Towards Better Exploration in Sequential Test-Time Scaling
Research
Ghost in the Encoder: Decodable Artist Identity Representations in Lyrics-to-Song Generation
Research
ComputerSD: Online Self-Distillation from Real-Time Feedback for Computer-Use Agents
Research
BayesNDE: Bayesian Generative Modeling for Neural Density Estimation
Research