How Humans and LLMs Read Gender into "Gender-Neutral" Physical Descriptions
Research
Research News
New papers, breakthroughs and academic AI research
Rollback the World, Keep the Reflection: Rollback-Induced Reflection for Long-Horizon LLM Agents
Research
FedVideoMAE: Efficient Federated Video Moderation with Differential Privacy and Secure Aggregation
Research
ArtNVG: Content-Style Separated Artistic Neighboring-View Gaussian Stylization
Research
FORGE: Forensic Reasoning with Grounded Evidence
Research
Monocular Visual Odometry without Calibration or Test-time Optimization
Research
Unexplored flaws in multiple-choice VQA make benchmarking unreliable
Research
MUSE: A Theory-Harnessed Story Engine for Vibe Narrativizing
Research
Verifiable by Construction: Claim-Level Evaluation of Verbatim Citation in Clinical Question Answering
Research
RiskChainBench: A Benchmark for Obfuscated Platform Message Restoration and Evidence-Grounded Web Investigation
Research
SEA-LION-v4.8: A Technical Report
Research
Redemption Score: A Multi-Modal Evaluation Framework for Image Captioning via Distributional, Perceptual, and Linguistic Signal Triangulation
Research