paper

paper ,  time-series ,  multimodal-agent ,  visual-reasoning ,  llm-benchmark ,  chain-of-agents ,  ai-ml-papers-of-the-week ,  computerrl ,  embedding-search-limitations ,  survey ,  timemaster ,  time-r1 ,  compositional-visual-reasoning ,  m3-agent ,  agent-fine-tuning ,  meta-clip2

paper ,  chain-of-thought ,  ai-ml-papers-of-the-week ,  deepconf ,  test-time-routing-ensemble ,  avengers-pro ,  rag-with-lean-lm ,  llm-persona ,  gepa ,  glimpse ,  infinite-video-understanding ,  inductive-bias ,  wall-confronting-llm ,  persona-vectors

google ,  paper ,  datacenter ,  gemini ,  energy-efficient ,  energy-consumption ,  environmental-footprint ,  energy-innovation

paper ,  ai-ml-papers-of-the-week ,  self-evolving-agents ,  dino-v3 ,  fourier-vlm ,  efficient-llm-architectures ,  rl-for-llm-reasoning ,  the-agent-company ,  deepfleet ,  visionthink ,  rag-mcp

paper ,  mem0 ,  ai-ml-papers-of-the-week ,  long-term-memory ,  efficient-agents ,  graph-r1 ,  tura ,  self-evolving-agents ,  reagan ,  memtool ,  agentic-web ,  trading-agents ,  workflow-graphs ,  ai-agents-efficiency ,  graph-knowledge-representation

paper ,  ai-ml-papers-of-the-week ,  kimi-k2 ,  hierarchical-reasoning-model ,  iw-sft ,  rrvf ,  dino-world ,  rlcr ,  cort ,  sem ,  hierarchical-reasoning ,  ml-intergration ,  model-synthesis-architecture ,  iterated-random-computation ,  multimodal-learning

paper ,  seal ,  survey-paper ,  continual-learning ,  benchmark ,  reinforcement-learning ,  rl-with-verifiable-rewards ,  grpo ,  ai-ml-papers-of-the-week ,  inverse-scaling ,  ttd-dr ,  pt-moe ,  one-shot-rlvr ,  tree-rl ,  absencebench ,  verbalization-finetuning ,  multimodal-multilingual-model

paper ,  test-time-compute ,  test-time-scaling ,  inference-time-scaling ,  inverse-scaling ,  inverse-scaling-in-test-time-compute

paper ,  survey-paper ,  vision-language-action-model ,  rl-with-verifiable-rewards ,  ai-ml-papers-of-the-week ,  mixture-of-recursions ,  ai-monitorability ,  dreamvla ,  vq-vla ,  temporal-chain-of-thought ,  reinforcement-learned-teachers ,  data-approximation-from-weights ,  evaluation-awareness ,  vision-language-integration ,  adaptive-computation

paper ,  ai-security ,  survey-paper ,  small-llm ,  llm-benchmark ,  multi-agent-orchestration ,  ai-ml-papers-of-the-week ,  embodied-web-agents ,  deep-research-bench ,  llm-agent-communication ,  math-reasoning-transferability ,  ai4research ,  ab-mcts ,  ai-collaboration

conference ,  paper ,  ai-agent ,  agents4science ,  openreview

paper ,  vision-language-action-model ,  block-diffusion ,  ai-ml-papers-of-the-week ,  mercury ,  transformers-are-gnns ,  show-o2 ,  scene-r1 ,  univla ,  worldvla ,  diffusion-steering-rl ,  rl-in-robotics ,  vla-post-training

paper ,  survey-paper ,  mllm ,  visual-reasoning ,  ai-ml-papers-of-the-week ,  seedance ,  revisit ,  video-world-model ,  llm-surrogates ,  locate-3d ,  llama-nemotron ,  nemo ,  nemo-aligner ,  megatron-lm ,  agent-protocols ,  agent-survey ,  doomarena ,  darwin-godel-machine ,  self-improving-agents

paper ,  top-ml-papers-of-the-week ,  survey-paper ,  llm-reasoning ,  attention-sink ,  rare ,  command-a ,  paperbench ,  codescientist ,  llm-first-token ,  multi-agent-simulations ,  medagentsim ,  open-deep-search ,  z1 ,  test-time-scaling-with-code ,  inside-out

paper ,  ai-ability ,  metr ,  hcast ,  re-bench ,  software-atomic-actions ,  50-percentage-task-completion-time-horizon

paper ,  top-ml-papers-of-the-week ,  synthetic-data ,  qwen-2-5-omni ,  time-aligned-multimodal-rope ,  tracing-the-thoughts-of-llms ,  agentrxiv ,  neural-alignment-via-speech-embeddings ,  chain-of-tools ,  cotools ,  meminsight ,  play2prompt ,  synthetic-data-generation ,  llm-for-knowledge-work

paper ,  diffusion-language-model ,  top-ml-papers-of-the-week ,  survey-paper ,  llm-survey ,  gemma-3 ,  gemini-robotics ,  traveling-waves ,  dyt ,  dynamic-tanh ,  promoting-obfuscation ,  obfuscated-reward-hacking ,  plan-and-act ,  planning-long-horizon-task ,  search-r1 ,  llm-auditing ,  llm-post-training-survey ,  bd3-lm ,  block-diffusion

paper ,  top-ml-papers-of-the-week ,  survey-paper ,  llm-survey ,  gnn ,  scaling-law ,  deepseek ,  reasoning-strategies ,  efficient-reasoning ,  stop-overthinking ,  a-mem ,  agentic-memory ,  deepmesh ,  deep-learning-is-not-so-mysterious-or-different ,  flora-bench

paper ,  llm-evaluation ,  factorio ,  factorio-learning-envionment

prompt-engineering ,  prompt ,  paper ,  chain-of-thought ,  chain-of-draft

paper ,  top-ml-papers-of-the-week ,  survey-paper ,  llm-survey ,  multi-agent-framework ,  gpt-4-5 ,  protein-llm-survey ,  prompt-optimization ,  automatic-prompt-optimization ,  lightthinker ,  metal ,  plangen ,  fast-fourier-transform ,  emergent-misalignment ,  chain-of-draft ,  claude-3-7-sonnet

paper ,  deep-research ,  surveyx ,  academic-survey-automation ,  survey-framework

paper ,  top-ml-papers-of-the-week ,  swe-agent ,  ai-co-scientist ,  inner-thinking-transformers ,  danger-of-overthinking ,  moba ,  open-reasoner-zero ,  compound-ai ,  model-selection ,  swe-lancer ,  llada ,  native-sparse-attention ,  ai-cuda-engineer

google ,  multi-agent ,  llm-in-medicine ,  llm-in-research ,  gemini-2-0 ,  ai-co-scientist ,  llm-in-science ,  llm-based-multi-agents ,  paper

paper ,  top-ml-papers-of-the-week ,  llm-reasoning ,  test-time-compute ,  long-cot ,  latent-recurrent-depth-transformer ,  brain-to-text-decoding ,  brain2qwerty ,  reinforcement-learning-via-self-play ,  large-reasoning-models ,  competitive-programming ,  reasoning-efficiently ,  lm2 ,  large-memory-models ,  prompt-caching ,  step-back-to-leap-forward ,  solomon ,  semiconductor-designing ,  reasonflux ,  hierarchical-llm-reasoning

foundation-model ,  text-to-image ,  bytedance ,  rectified-flow ,  image-to-video ,  text-to-video ,  goku ,  flow-based ,  gentron ,  paper

paper ,  top-ml-papers-of-the-week ,  survey-paper ,  mixture-of-agents ,  dataset-survey ,  long-cot ,  s1 ,  text-data-augmentation ,  advancing-reasoning ,  agentic-supernet ,  maas ,  syntriever ,  chain-of-associated-thoughts ,  limo ,  omnihuman-1

paper ,  longer-reasoning ,  reasoning-dataset ,  test-time-scaling ,  s1 ,  s1k-dataset ,  budget-forcing ,  sequential-scaling ,  parallel-scaling

tool ,  chrome-extension ,  paper ,  google-chrome ,  google-scholar ,  pdf-reader

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