Hard, Yet Reducible: Controlled Forward Transfer for Synthetic Degradation Curation
Research
Research News
New papers, breakthroughs and academic AI research
Lightweight and Versatile Learned Optimization by Recombination of Gradient History
Research
When does a network's training history predict its future learning better than its current state? Evidence from a response probe and a forecasting screen
Research
PAIR: Bridging Perception and Action in Vision-Language-Action Models
Research
Personalize at Test Time: Learning User Preferences for Image Generation
Research
TopoCurve: Geometry-Aware Topology Reasoning via B\'ezier Curves in Autonomous Driving
Research
Not Every Call Needs a Frontier Model: Per-Call-Site Evaluation of Small Language Models in a Deployed Agentic Home-Automation System
Research
RippleCP: Measuring Counterfactual Checkpoint Advantage in Coding Agents
Research
Beyond Explanation: Debugging Medical Imaging Models via Concept Intervention
Research
PHRBench: A Behavioral Evaluation of Post-Hallucination Reasoning in LLMs
Research
Phoneme-Guided Initialization for LLM-based Speech Recognition
Research
Talking with Language Models
Research