paper

agent ,  alignment ,  paper ,  llm ,  anthropic ,  safety ,  red-teaming

deep-learning ,  paper ,  reinforcement-learning ,  neuroscience ,  sakana-ai ,  credit-assignment ,  biologically-plausible

alignment ,  paper ,  llm ,  anthropic ,  claude ,  safety ,  values-in-the-wild ,  value ,  value-axes

technical-report ,  paper ,  diffusion ,  multimodal ,  avatar ,  video-generation ,  real-time

pretraining ,  opensource ,  long-context ,  mamba ,  paper ,  mixture-of-experts ,  llm

inference-optimization ,  paper ,  reinforcement-learning ,  llm ,  speculative-decoding ,  llada ,  diffusion-llm ,  research ,  diffusiongemma

ai-ml-papers-of-the-week ,  context-engineering ,  paper ,  survey-paper ,  self-improving-agents ,  r3-reject-as-resource-retriever ,  geospatial-foundation-models ,  geospatial-reasoning ,  llm-based-recommender-systems ,  prismata ,  vs-bench ,  visualswap ,  llm-in-cybersecurity ,  llm-in-privacy ,  proofagent-harness ,  diffusiongemma ,  variable-transparency ,  algorithmic-transparency ,  mathematics-of-data-science

quantization ,  paper ,  llm ,  edge-ai ,  speculative-decoding ,  on-device ,  prismml

agent ,  benchmark ,  robotics ,  paper ,  vla ,  llm ,  anthropic ,  safety ,  embodied-ai ,  robot ,  physical-ai ,  embody-benchmark

agent ,  robotics ,  paper ,  code-generation ,  llm ,  continual-learning ,  nvidia ,  aspire ,  self-improvement

agent ,  paper ,  foundation-model ,  self-supervised-learning ,  google ,  wearable ,  digital-health ,  google-deepmind ,  llm-for-healthcare ,  google-research

pose-estimation ,  computer-vision ,  paper ,  foundation-model ,  nvidia ,  3d-reconstruction ,  human-object-interaction

agent ,  reasoning ,  paper ,  llm ,  google ,  time-series ,  forecasting ,  timesfm ,  tsfm

ai-ml-papers-of-the-week ,  paper ,  nexus ,  mtia ,  time-series-forecasting ,  agentic-framework ,  gen4u-generation-for-understanding ,  crux-collaborative-research-for-updating-ai-expect ,  napmem ,  kernelevolve ,  dlrm-deep-learning-recommendation-model ,  egagent ,  agent-interoperability-protocols ,  time-series-foundation-model ,  metacognition ,  rlmf-rl-with-metacognitive-feedback ,  single-rollout-asynchronous-optimization ,  openclaw-skill ,  collective-skill-tree-search

pytorch ,  computer-vision ,  paper ,  3d ,  nvidia ,  graphics ,  human-body-model ,  differentiable ,  soma

sim-to-real ,  humanoid ,  robot-learning ,  paper ,  reinforcement-learning ,  nvidia ,  video-generation

humanoid ,  robotics ,  paper ,  reinforcement-learning ,  vla ,  nvidia ,  motion-tracking

fine-tuning ,  agent ,  paper ,  llm ,  meta ,  brain-computer-interface ,  meg

interpretability ,  alignment ,  paper ,  llm ,  anthropic ,  ai-safety

paper ,  reinforcement-learning ,  diffusion ,  icml ,  ai-safety ,  best-paper-awards ,  icml-2026 ,  test-of-time

agent-skills ,  agent ,  retrieval ,  paper ,  llm ,  coding-agent ,  skillcomposer

agent ,  automation ,  technical-report ,  paper ,  labor-market ,  llm ,  anthropic ,  anthropic-economic-index ,  economic-index

agent ,  rag ,  paper ,  reinforcement-learning ,  llm ,  microsoft ,  knowledge-graph ,  agentic-memory

ai-ml-papers-of-the-week ,  paper ,  self-improving-agents ,  flow-matching ,  automem ,  memora ,  experience-graphs ,  preact ,  bineval ,  reasonrec ,  meta-memory ,  generative-skill-composition ,  is-one-layer-enough ,  flowwm ,  skillcomposer ,  paper-assistant-tool

hugging-face ,  opensource ,  paper ,  llm ,  collaboration ,  empirical-study

agent ,  benchmark ,  technical-report ,  paper ,  llm ,  bytedance ,  scaling-law ,  evaluation ,  research

paper ,  embeddings ,  nlp ,  representation-learning ,  graph ,  recipe ,  food ,  food-ingredient-embedding ,  computational-gastronomy

distillation ,  theorem-proving ,  paper ,  reinforcement-learning ,  llm ,  meta ,  lean

computer-use ,  agent ,  benchmark ,  paper ,  llm ,  safety ,  osworld ,  cua ,  osworld-2-0

test-time-training ,  agent ,  reasoning ,  inference-optimization ,  paper ,  llm ,  test-time-scaling