paper ,  foundation-model ,  llm-generalization ,  reinforcement-learning ,  supervised-fine-tuning ,  sft-memorizes-rl-generalizes

google-ai-studio ,  gemini ,  google-gemini ,  gemini-2-0-flash-thinking

llm-analytics ,  klarity ,  uncertainty-analysis ,  klara-labs

openai ,  deep-research ,  openai-deep-research

paper ,  top-ml-papers-of-the-week ,  test-time-compute ,  o3-mini ,  qwen-2-5-1m ,  janus-pro ,  divpo ,  shortcomings-of-rl-strategies ,  docling ,  rag-through-multi-agent-rl ,  mmoa-rag ,  tensorllm ,  tokenverse ,  multi-concept-personalization

text-to-music ,  lyrics-to-song ,  yue

openai ,  o3-mini ,  o3-mini-high ,  o3 ,  reasoning-effort-option ,  deliberative-alignment

rust ,  llm-c ,  from-scratch ,  llm-from-scratch ,  llm-rust

zero-3 ,  deepseek-r1 ,  open-r1 ,  minimal-r1 ,  long-cot

nipa ,  un-sdg ,  sustainable-development-goals ,  ai-for-good-innovate-for-imp

llm-applications ,  desktop-app ,  notate

ai-engineering ,  machine-learning-in-production ,  cmu

java ,  jlama ,  jlama-langchain4j ,  langchain4j ,  vector-api

pytorch ,  pytorch-release ,  pytorch-2-6 ,  torch-compiler-set_stance ,  torch-library-triton_op ,  python-3-13 ,  pt2-archive ,  dim-auto ,  flexattention

ollama ,  local-llm ,  llm-in-research ,  research-automation ,  llm-researcher ,  deepseek-r1 ,  automated-ai-web-researcher ,  ollama-deep-researcher ,  web-researcher

llm-reasoning ,  open-thoughts ,  bespoke-labs ,  datacomp ,  openthoughts-114k ,  openthinker-7b ,  bespoke-stratos-17k ,  bespoke-stratos-32b ,  bespoke-stratos-7b ,  reasoning-dataset

apache-20-license ,  agent-framework ,  speechagents ,  multi-agent-framework ,  livekit ,  livekit-agents

deepseek ,  llm-distillation ,  deepseek-r1 ,  deepseek-r1-zero ,  distilled-models

webgpu ,  llm-on-browser ,  local-llm ,  browser-ai

huggingface ,  deepseek-r1 ,  deepseek-r1-zero ,  huggingface-open-r1 ,  open-r1 ,  r1-distill

paper ,  top-ml-papers-of-the-week ,  survey-paper ,  algorithm-of-thought ,  ai-in-drug-development ,  deepseek-r1 ,  intellagent ,  humanitys-last-exam ,  kimi ,  chain-of-agents ,  test-time-compute ,  agentic-rag ,  behavioral-self-awareness

typescript ,  model-context-protocol ,  easy-mcp ,  fast-mcp

video-editing ,  web-browser-based ,  ai-video-starter-kit ,  fal-ai

rope ,  power-attention ,  symmetric-power-transformer ,  symmetric-power-embeddings