Verifiable, Articulable, and Tacit Components of Preference
Research
Research News
New papers, breakthroughs and academic AI research
MOF-VERIFY: A Failure-Aware Agentic Harness for MOF Hypothesis Verification
Research
RIFAR: Reliability and Forgetting-Aware Replay for Continual Robot Learning
Research
SoftGene: Protein Language Model-Enhanced Soft Prompting for Interpretable Gene Set Annotation
Research
hacktrace: behavior-supervised detection of reward hacking during code generation
Research
Keeping JEPA World Models Plannable When Little of the Frame Moves
Research
Uncertainty as a Proxy for Semantic Correctness in Diffusion-Based Medical Image Synthesis
Research
Writerslogic at the CLEF 2026 SimpleText Track: Multi-Candidate LLM Simplification and Stacked Complexity Spotting
Research
EmbPASS: Towards Cross-Embodiment Open Panoramic Segmentation
Research
FALCON: A Model and Dataset Agnostic Framework for Synthetic Data Generation for NL2SQL Pairs
Research
COSMI: COmpositional Synthesis of Multi-object Interactions
Research
Language Models that Play Chess and Explain Their Moves
Research