13 posts published in the last hour
- 06:36Low-Rank Hierarchical Merging for Efficient Long-to-Short Reasoning
- 06:35El Agente F\’armaco: A Scalable AI Scientist for Drug Discovery
- 06:35Reasoning is topologically simple
- 06:35Tencent WeVisOne-VL Unifies Detection, OCR, Segmentation and Matting
- 06:34LaplaceDiag: Fault Diagnosis through Changes in Learned Actuator Effects
- 06:34Building AI for Lawyers – Jacob Lauritzen, CTO of Legora
- 06:34VagueBench: Benchmarking the Robustness of Embodied Agents on Ambient Context Illusions
- 06:06Training LLM Agents to Automate LLM Post-Training with RSI-Dojo
- 06:06EMBERS: Empirically Motivated Robustness Testing of Deep Research Systems via Defect-Guided Fuzzing
- 06:05From Logs to Faults: Reference-Free Fault Localization for Retrieval-Augmented Generation Pipelines
- 06:05Unsatz: Evaluating Scientific Discovery Without a Given Ansatz
- 06:05Anthropic warns that it’s very close to RSI capability, aka self-building AI
- 06:05Counterexample-driven autonomous research with application to excess radiated energy in a Z-pinch