AcademiClaw: When Students Set Challenges for AI Agents
Paper • 2605.02661 • Published • 17
Valentin Lafargue
ValentinLAFARGUE
·
AI & ML interests
Bias, Fairness, Auditing.
Organizations
upvoted a paper 2 months ago
upvoted 8
papers 3 months ago
The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents
Paper • 2604.10577 • Published • 27
Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation
Paper • 2604.10098 • Published • 82
Paper Reconstruction Evaluation: Evaluating Presentation and Hallucination in AI-written Papers
Paper • 2604.01128 • Published • 15
Reasoning Shift: How Context Silently Shortens LLM Reasoning
Paper • 2604.01161 • Published • 32
Regulating AI Agents
Paper • 2603.23471 • Published • 5
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
Paper • 2402.03300 • Published • 148
MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification
Paper • 2603.15726 • Published • 187
AI Can Learn Scientific Taste
Paper • 2603.14473 • Published • 431