읽을거리&정보공유

geeknews ,  ai-startup

text-to-video ,  ltx-2

amazon ,  smart-glasses ,  digital-twin ,  blue-jay ,  project-eluna ,  delivery-glasses

agent-memory-module ,  memory-framework ,  agent-memory ,  long-term-memory ,  llm-memory ,  lightmem ,  sensory-memory ,  short-term-memory

google ,  podcast ,  open-notebook ,  notebook-lm

character-ai ,  yale-university ,  ovi ,  twin-backbone-cross-modal-fusion ,  video-audio-multimodal-generation ,  text-to-audio-video ,  image-to-audio-video ,  text-to-image-to-video ,  spatial-temporal-consistency

ray ,  pytorch-foundation ,  anyscale ,  distributed-framework ,  pytorch-ecosystem

파이토치 ,  llm-agent ,  multimodal ,  nanovlm

openai ,  web-ai ,  aria ,  chromium ,  atlas ,  chatgpt-atlas ,  chatgpt-memory ,  web-browser ,  wai-aria

ocr ,  datalab ,  chandra-ocr ,  chandra

code-agent ,  task-master ,  claude-task-master

ocr ,  deepseek ,  document-image-to-text ,  deepseek-ocr

anthropic ,  claude-code ,  claude-code-web ,  sandbox ,  sandboxing

apple-silicon ,  cli-tools ,  amd-gpu ,  nvidia-gpu ,  intel-gpu ,  gpu-monitoring ,  gpu-kill ,  kagehq

pytorch ,  torchvision ,  flash-decoding ,  pytorch-release ,  torchcodec ,  flexattention ,  pytorch-2-9 ,  torchaudio ,  symmetric-memory ,  libtorch-abi

paper ,  survey-paper ,  rl-with-verifiable-rewards ,  ai-ml-papers-of-the-week ,  self-improving-agents ,  scaling-reinforcement-learning-for-llms ,  agentic-reinforcement-learning ,  reinforcement-learning-in-vision ,  webscale-rl ,  agentic-context-engineering ,  pacs ,  generalized-relative-advantage-policy-evolution ,  autonomous-tools-integrated-reasoning ,  tool-integrated-reasoning ,  taarofbench ,  mind-your-tone

agentic-framework ,  kayba-ai ,  agentic-context-engine ,  contextual-learning ,  self-learning-agent

anthropic ,  claude-code ,  skills ,  claude-skills ,  agent-skills ,  claude-apps ,  claude-api

google ,  gemma ,  yale-university ,  cell2sentence-scale ,  cell2sentence-scale-27b ,  c2s-scale ,  antigen-presentation ,  immune-context

anthropic ,  model-context-protocol ,  claude-code ,  plugin ,  claude-code-plugin ,  subagent

code-agent ,  fleetcode

google-chrome ,  coding-assistant ,  model-context-protocol ,  mcp-server ,  chrome-devtools-mcp

stanford ,  agentflow ,  search-r1 ,  flow-based-collaboration ,  flow-grpo ,  modular-agentic-system

figure ,  humanoid-robot ,  vision-language-action-model ,  helix ,  figure-03 ,  botq

chatgpt ,  andrej-karpathy ,  nanogpt ,  from-scratch ,  llm-from-scratch ,  nanochat

comfyui

llm-inference ,  inference-framework ,  llm-inference-serving ,  haif ,  hyperswarm-rpc-ai-inference-framework

paper ,  multivariate-time-series ,  agi ,  agentflow ,  test-time-compute ,  ai-ml-papers-of-the-week ,  hrm-hierarchical-reasoning-model ,  trm-tiny-recursive-model ,  paper2video ,  papertalker ,  coral-protocol ,  matpo ,  multi-agent-tool-integrated-policy-optimization ,  opentslm ,  learning-to-parallel ,  learn2pd ,  end-of-text-prediction ,  reasoning-llm ,  tpt-thinking-augmented-pre-training