14 posts published in the last hour
- 20:33Can a Dynamic Internal Field Govern a Transformer’s Cognition? Certifiability, not Superiority, in Homeostatic Compute Control
- 20:33Benchmarking LLM Judges for Voice-Agent Evaluation: Reliability, Calibration, and Human Oversight
- 20:32SonarLLM: A Native Sonar–Optical Multimodal Large Language Model for Underwater Perception
- 20:32Cohere Releases Parse 5 (parse-v5.0): A 2.3B Vision Language Model That Turns Enterprise Documents Into Markdown
- 20:32Selective Regenerative Decoding: Trajectory-Level Intervention for Inference-Time Reasoning
- 20:32Can You Defend What Your AI Just Did?
- 20:32The Handoff Tax: Continuing Non-Native Trajectories in LLM Agents
- 20:03OPDSearch+: On-Policy Distillation with RL Refinement for Search-Augmented Reasoning
- 20:03Eating for a Sustainable Planet: Personalized Sustainable Diet Recommendation via Constraint-Aware Decision-Making Modeling
- 20:03ReproAgent: Contract-Guided Paper-to-Code Reproduction
- 20:03Expanding our support for scientists
- 20:02RePolicy: Reinforcement Learning for Safety-Policy Invocation in Agent Safeguards
- 20:02Barret Zoph, the Thinking Machines co-founder who defected to OpenAI, is now at Google
- 20:02VideoHarness-RSI: Recursive Harness Self-Improvement for Long-Video Understanding with Frozen Vision-Language Models
