Recurrent Self-Improvement: Dynamic Cross-Loop On-Policy Distillation for Looped Language Models
Research
Research News
New papers, breakthroughs and academic AI research
MESSENGER: Memory-Enhanced Sequential Scene Flow Estimation via Autoregressive Next-Frame Forecasting
Research
Enabling Preference-driven Unlearning in Few-step Distilled Text-to-Image Diffusion Models
Research
LinSlot: Exploiting Linear Representation hypothesis for unsupervised attribute discovery from slot based object representation
Research
Distillation for Incrimination and Distillation for Capabilities
Research
AgentHorizon: Evaluating Agentic Judges for Long-Horizon Computer-Use Tasks
Research
Beyond Imitation: A Framework and Benchmark for LLM-Assisted Peer Review
Research
OpenProblemBench: Benchmarking AI on Open Problems in the Foundational Theoretical Sciences
Research
Visible Reasoning Is Not a Universal Optimizer: Persona- and Thinking-Dependent Effects in Analytics Code Generation
Research
When Interfaces Speak: Data-Aware Generative UI Harness for Active Interaction
Research
Coverage-Aware Reasoning with Medical Tokens for Diagnosis Prediction
Research
What to Admit and How to Present: Governing Persistent Memory in LLM Agents
Research