Variance-Optimal Control Variates for Learning with Black-box Feedback
Research
Research News
New papers, breakthroughs and academic AI research
RoMod: Temporal Routing Modulation via Mixture-of-Experts for Video Anomaly Detection
Research
MMPostTrainBench: Benchmarking Autonomous Research for Multimodal Post-Training
Research
Learning Discriminative Geometry for Drifting Models
Research
FoSeRL: Formal Sequential Robustness Certification for Reinforcement Learning Policies
Research
AI Safety via Debate is Compromised by Cognitive Biases
Research
Hallucination Across the Reasoning Lifecycle: Interface Visibility, Causal Evidence, and Release Control in Large Reasoning Models
Research
Differentiable Bit-Widths: Co-optimizing Pruning and Quantization via SVD for Ultra-Efficient LLM Compression
Research
LightMTP: Lightweight Latent Multi-Token Prediction
Research
DASH: Fast, Valid Counterfactuals for Deep Networks via Batched Directional Search
Research
Anatomy of LLM Sycophancy: What a Flip Rate Hides
Research
TrustMI: Causally controlling how assistants trust their users
Research