VepAgent: Bridging Causal-Transition via Tool-Augmented Reinforcement Learning for Video Event Prediction
Research
Research News
New papers, breakthroughs and academic AI research
Joint Class-Time Learning for Video Classification with Multi-Instance Partial-Label Learning
Research
Readout Blindness: VLM Scores Miss the Spatial Direction Their Frozen Encoders Retain
Research
Reading the Mood: Emotion-Guided Book-to-Music Recommendation via CGANs and LLMs
Research
Hierarchical Time-aware Bootstrapping for Off-Policy Subgoal Value Learning
Research
Paradee: Distilling Kokoro-82M into an 8M-Parameter Single-Voice Text-to-Speech Model
Research
Groupwise Distortion Guarantees for Preference-Based Alignment
Research
Recursive Video In-Context Learning for Agentic Robot
Research
VERA: Verdict-Conditioned Reliability for Adaptive LLM Judges
Research
Base Models Can Reason By Taking a Cue From Training Data
Research
Three tiers of computation in transformers and in brain architectures
Research
Universality and Convergence of Generative Flows
Research