14 posts published in the last hour
- 08:35AlgoPilot: Cross-Paradigm Reasoning in Language Models via Strategy Selection and Guidance
- 08:34Look Before You Launch: Learned Throughput Prediction for Hardware Selection in a Production Training Fleet
- 08:34Query-based Submodular Data Selection for Efficient Instruction Tuning
- 08:34Harvey to Bring Jus Mundi’s Arbitration Agent Into Legal Workflows
- 08:34On the Primacy Bias in RLVR Training
- 08:33llm 0.37
- 08:33The Agent Board: Kanban for Machines; Durable Coordination for Agents That Outlive the Conversation
- 08:06Exploit or conform? How norm utility prompting changes the way LLMs use community beliefs
- 08:05ROCm InferaSim: Cut LLM Serving Trial Costs and Deploy the Best Configuration
- 08:05HybridSpec: Throughput-Aware Speculative Decoding for Hybrid GDN-MoE Models
- 08:05Scaling Git at OpenAI
- 08:05Forgetting to Improve: Principled Data Removal in Active Learning
- 08:04Rack-scale AI: How Dell and AMD are building infrastructure
- 08:04Recursa: Toward Recursively Self-Improving Foundation Model Systems