paper-buf

• LLM safety
  • LLM360 K2: Scaling up 360-open-source large language models
  • NOTES
  • Risk-averse fine-tuning of large language models
  • NOTES
• Reasoning
  • Multiagent finetuning: Self improvement with diverse reasoning chains, code
  • The lessons of developing process reward models in mathematical reasoning
  • O1 replication journey - Part 2: Surpassing O1-preview through simple distillation, big progress or bitter lesson?
  • O1 replication journey - Part 3: Inference-time scaling for medical reasoning
• LLM
  • LongProc: Benchmarking long-context language models on long procedural generation
  • NOTES
  • Step-by-step mastery: Enhancing soft constraint following ability of large language models
• Agent
  • WebWalker: Benchmarking llms in web traversal