Pretext: Defeating Malicious Skill Detection Frameworks for AI Agents
Research
Research News
New papers, breakthroughs and academic AI research
VR-JEPA: Learning Contrastive-State Latent Guidance for Generation-based Video Reasoning
Research
ChorusTIC: Training-Free Multivariate Time Series Classification via Chorus In-Context Learning
Research
Free Everywhere, Exact on Trees: PPO's Dropped Correction Buys Sample Efficiency Under Aggressive Reuse
Research
Zero-Compute Cross-Lingual Transferability Estimation Using Typological Feature Proxies
Research
DiffWAM: A Fast and Efficient Navigation World Action Model
Research
SEPAL: Separated Expert Pairs with Answer-Level Fusion for Reliable LLM Collaboration
Research
Probabilistic Adversarial Training
Research
RoboCoach: World Models as Active Coaches for Compositional Robot Skills
Research
Diffusion-Augmented Markov Decision Processes for Maximum Entropy Reinforcement Learning
Research
DAMP: Decay-Aware Mixed-Precision Recurrent-State Quantization
Research
GFD-OPD: Guidance-Folded On-Policy Distillation of Diffusion Models Across Scales
Research