Larry Caused the Car to Stop, But the Model Didn't Notice: Transformer Blindness to the M-Heuristic
Research
Research News
New papers, breakthroughs and academic AI research
The Rashomon Wikipedia: A Data-Perspectivist Analysis of Divergent Historical Narratives
Research
Who Warmed the Archives? LLMs Overestimate Historical Warmth
Research
From Dissonance to Orchestration: Teacher Intervention in On-Policy Distillation
Research
SCALE: Synthetic Calibration via Agreement Labeling in Embedding Space
Research
Routing Probes Can Improve Without New Information: An Exact-Null Audit of Uncertainty Beyond Model Outputs
Research
When Order Matters: First-Speaker Bias and Mitigation through Personality in Sequential Multi-Agent Debate
Research
RealWorldShop: Benchmarking and Improving Conversational Shopping Agents in Real-World E-commerce
Research
BELIEFRAG: Making Adaptive RAG State-Aware under Evolving Evidence
Research
MADBench: Benchmarking the Security of Multi-Agent Debate
Research
Evaluating Agents Across Runtime Contracts: When Mismatch Costs Efficiency or Quality
Research
Hard-Region Supervision: #1 on the Waymo Open Dataset 2D Video Panoptic Segmentation Leaderboard
Research