Beyond Dyadic Memory: Interaction-Aware Multimodal Memory with Adaptive Agentic Retrieval for Multi-Party Spoken Conversations
Research
Research News
New papers, breakthroughs and academic AI research
Groupwise Agentic Grading and Advantage Redistribution for Code Agent RL
Research
Pinned and Still Unstable: Within-Judge Verdict Variance and the Noise Floor of LLM-as-Judge Leaderboards
Research
MixBench-TS: A Multivariate Time Series Forecasting Benchmark Where Channel Mixing Pays Off
Research
The Alignment Paradox: How Post-Training Amplifies Confident Hallucinations in Language Models
Research
Prediction Limits and Koopman Closure of Geometry-Induced Soft State Abstractions
Research
ControlGS: Conditioning Neural Gaussians for Downstream-Processing-Aware XR Rendering
Research
Amnesia by Design, Memory By Necessity: Persistent State for Document Intelligence
Research
Learning from a Thoughtful Teacher: Adaptive On-Policy Self-Distillation for Mathematical Reasoning
Research
Does CoT-Pass@k Really Check the CoT? A Multilingual Mathematical Audit
Research
ScreenHaystack: Finding Blind Zones in GUI Grounding
Research
OneSign: Unifying Sign Language Understanding Tasks with One Model
Research