TF-PRVR: Training-Free Partially Relevant Video Retrieval
Research
Research News
New papers, breakthroughs and academic AI research
CCDF: A Benchmark Dataset for Deepfake Detection in Real-World Surveillance Footage
Research
Site Is Decodable Before Pretraining: Negative Controls for Probing Frozen Brain-MRI Foundation Models
Research
Selective Critique for Cost-Aware LLM Agents in Long-Horizon Decision Making
Research
RELACE: retrospective likelihood-based action credit estimation for long-horizon language agents
Research
Multigroup Fairness and Omniprediction: Separations and Equivalences
Research
Dynamic Alignment and Calibration for Multimodal Learning
Research
The AI Accountability Ecosystem in the Era of Language Models
Research
Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization
Research
TRACE: Training-time Report-guided and Clinically Ordered Concept Editing
Research
Weight Oracles: Reading Neural Network Weights with Language Models
Research
Stepped MoE: Segment-Level Routing with Configurable Inference Complexity
Research