paper

nvidia ,  stanford ,  deepmind ,  reinforcement-learning ,  test-time-compute ,  alphaevolve ,  ttt-discover ,  learning-to-discover-at-test-time ,  test-time-training ,  scientific-discovery ,  ai4science ,  best-of-n ,  predictor-upper-confidence-bound-applied-to-trees ,  state-reuse ,  entropic-objective ,  adaptive-beta-scheduling ,  the-bitter-lesson ,  paper

paper ,  ai-ml-papers-of-the-week ,  ttt-discover ,  test-time-training ,  organizational-intelligence ,  agent-drift ,  g2rl ,  deep-delta-learning ,  toolorchestra ,  agentic-tool-calling ,  llm-inference-hardware ,  multi-agent-models ,  delta-operator ,  reward-forcing ,  ema-sink ,  rewarded-distribution-matching-distillation ,  gradient-guided-reinforcement-learning ,  drope

paper ,  mtia ,  electronic-design-automation ,  computer-use-agent ,  ai-ml-papers-of-the-week ,  multi-agent-system ,  agentic-search ,  agentic-reasoning ,  agentic-r ,  tritorx ,  agentic-eda ,  self-evolution ,  evocua ,  unified-fine-tuning ,  stem ,  confucius-code-agent ,  universal-rag ,  pytorch-opinfo ,  confucius-sdk ,  reinforcement-fine-tuning

paper ,  deepseek ,  engram ,  n-gram ,  context-aware-gating ,  conditional-memory ,  new-axis-of-sparsity ,  tokenizer-compression

paper ,  multi-agent-framework ,  agent-laboratory ,  agentrxiv ,  ai-research-agent ,  ai-for-science-research ,  agent-for-science-research ,  collaborative-autonomous-research ,  autonomous-research-agents

paper ,  knowledge-graph ,  llm-as-a-judge ,  ai-ml-papers-of-the-week ,  agent-survey ,  multi-agent-system ,  mattrl ,  uarl ,  foresight-learning ,  agent-as-a-judge ,  agentic-search ,  latent-action-world-models ,  causal-rl ,  llm-empowered-kg ,  test-time-reinforcement-learning ,  rl-based-agentic-search ,  distribution-aligned-sequence-distillation ,  exploration-collapse ,  uniqueness-aware-reinforcement-learning ,  visual-instruction-based-editor

paper ,  text-to-image ,  bytedance ,  image-editing ,  self-correction ,  nextflow ,  editcanvas ,  prefix-tuning-grpo ,  optional-diffusion-decoder ,  loss-reweighting ,  multiscale-3d-rope ,  visual-auto-regrressive ,  fixed-computation-budget-packing

paper ,  ai-security ,  small-llm ,  benchmark ,  world-model ,  ai-ml-papers-of-the-week ,  dlcm ,  relayllm ,  photon ,  robust-r1 ,  infiagent ,  mmgr ,  datbench ,  deepresearch ,  dynamic-large-concept-models ,  spo ,  dynamic-reasoning-depth-scaling ,  4-δ-bound ,  multi-modal-generative-reasoning ,  artemis

paper ,  rl-with-verifiable-rewards ,  stepfun ,  ai-ml-papers-of-the-week ,  vibe-coding ,  manifold-constrained-hyper-connections ,  hyper-connections ,  science-context-protocol ,  step-deepresearch ,  attention-is-not-what-you-need ,  grassmann-flows ,  reponavigator ,  sophia ,  system-3-architecture ,  vl-jepa ,  joint-embedding-predictive-architecture ,  universal-reasoning-model ,  universal-transformers ,  ai-agent-use-for-coding

paper ,  survey-paper ,  self-supervised ,  ai-ml-papers-of-the-week ,  worldplay ,  jacobi-forcing ,  qttt ,  4d-rgpt ,  nepa ,  quco-rag ,  dynamic-rag ,  perceptual-4d-distillation ,  h-neurons ,  model-first-reasoning-llm-agents ,  reasoning-agent ,  stabilizing-reinforcement-learning ,  causal-parallel-decoding ,  multi-token-generation ,  llm-harms ,  model-first-reasoning

data-centric ,  paper ,  data-pipeline ,  data-platform ,  data-framework ,  dataflow ,  data-workflow

prompt-engineering ,  paper ,  chain-of-thought ,  vibe-coding ,  wharton-school ,  generative-ai-labs ,  prompting-science-report-series ,  emotional-incentives ,  expert-persona-prompting ,  myth-busting

paper ,  diffusion-language-model ,  rag ,  agentic-ai ,  ai-ml-papers-of-the-week ,  agent-memory ,  lmcache ,  context-engineering ,  continuous-latent-reasoning ,  salient-compressor-pretraining ,  visual-tokenizer ,  visual-tokenizer-pretraining ,  refusion ,  scaling-agent-system ,  aigne-framework ,  efficient-dlm ,  adaptation-of-agentic-ai

paper ,  survey-paper ,  diffusion-transformer ,  test-time-scaling ,  ai-ml-papers-of-the-week ,  agentic-llm ,  latentmas ,  ontoaxiom ,  ontology-learning ,  axiom-by-axiom ,  pixeldit ,  onethinker ,  ema-grpo ,  agents-in-production ,  beaver ,  deterministic-llm-verifier ,  terrain-diffusion ,  perlin-noise

neurips ,  paper ,  neurips-2025 ,  artificial-hivemind ,  gated-attention ,  self-supervised-rl ,  why-diffusion-models-dont-memorize ,  best-paper-awards ,  runners-up-papers

paper ,  agent-framework ,  out-of-distribution ,  ai-ml-papers-of-the-week ,  agent0 ,  agent0-vl ,  matrix ,  z-image ,  z-image-edit ,  dip ,  diffusion-in-pixel-space ,  implicit-dynamical-regularization ,  learning-to-reason ,  deep-reinforcement-image-feature-tracking ,  codevision

paper ,  survey-paper ,  ai-ml-papers-of-the-week ,  self-evolving-agents ,  context-engineering ,  diffusion-llm ,  tidar ,  agent0 ,  eggroll ,  evolution-strategies ,  grpo-verif ,  robust-reasoning ,  nemotron-elastic ,  many-in-one-reasoning ,  mamba-attention ,  slicing-is-all-you-need ,  principles-of-diffusion-models ,  maker ,  rynnvla-002 ,  massively-decomposed-agentic-processes

paper ,  speech-to-text ,  speech-to-speech ,  test-time-compute ,  test-time-scaling ,  rl-with-verifiable-rewards ,  step-audio ,  stepfun ,  mgrd ,  inverted-scaling ,  stepfun-audio ,  format-reward ,  self-cognition-error ,  textual-surrogate-reasoning ,  audio-llm

paper ,  hallucination ,  scaling-law ,  openevolve ,  ai-ml-papers-of-the-week ,  agentevolver ,  fundamental-limits-of-llm ,  scaling-laws-for-efficient-mixture-of-experts ,  ai-driven-research-for-systems ,  difference-in-differences ,  ai-assisted-coding ,  intelligence-per-watt ,  model-native-agentic-ai ,  nemotron-nano-v2-vl ,  mamba-transformer ,  efficient-video-sampling ,  ring-1t ,  ai-agents-economy

paper ,  web-agent ,  ai-ml-papers-of-the-week ,  omnilingual-asr ,  from-lazy-agents-to-deliberation ,  agent-data-protocol ,  agent-dataset ,  scaling-agent-learning ,  experience-synthesis ,  dreamgym ,  marag-r1 ,  emergent-coordination ,  reasoningbank ,  reasoning-memory ,  agentic-organization ,  asyncthink ,  matts

paper ,  calm ,  ai-ml-papers-of-the-week ,  ring-linear ,  continuous-autoregressive-language-models ,  llms-encode-how-difficult-problems-are ,  kosmos ,  ai-scientist-for-autonomous-discovery ,  train-for-truth-keep-the-skills ,  binary-retrieval-augmented-reward ,  graph-based-agent-planning ,  cache-to-cache ,  direct-semantic-communication ,  beyond-a-million-tokens ,  beam ,  from-memorization-to-reasoning ,  spectrum-of-loss-curvature

dataset ,  paper ,  survey-paper ,  large-reasoning-models ,  ai-ml-papers-of-the-week ,  vibe-coding ,  recode ,  deep-reasoning-dataset ,  sipit ,  real-deep-research ,  entropylong ,  dr-llm ,  lookahead-routing ,  fast-dllm-v2

paper ,  react ,  agent-framework ,  react-agent ,  recode ,  recode-agent ,  agent-with-planner ,  recursive-code-generation ,  hierarchical-decision-making ,  scienceworld ,  webshop ,  alfworld

paper ,  benchmark ,  ai-ml-papers-of-the-week ,  brain-rot ,  beyond-seeing ,  optpipe ,  pipeline-parallelism ,  dragon-hatchling ,  hybrid-reinforcement ,  hybrid-ensemble-reward-optimization ,  reasoning-over-task-execution ,  chunkllm ,  diffusion-llm ,  parallel-decoding ,  fast-dllm ,  elastic-cache ,  visualtoolbench ,  the-space-of-ai ,  ais-impact-on-developers

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

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

vision-language ,  paper ,  survey-paper ,  continual-learning ,  agent2agent ,  ai-ml-papers-of-the-week ,  multi-agent-system ,  tool-use-mixture ,  tumix ,  reverse-speculative-decoding ,  truthful-text-summarization ,  agentmaster ,  knowledge-infusion-scaling-law ,  bifrost-1 ,  agents-research-environments ,  federation-of-agents

paper ,  survey-paper ,  reinforcement-learning ,  deep-research ,  large-reasoning-models ,  ai-ml-papers-of-the-week ,  universal-deep-research ,  alphaagents ,  multi-agent-consensus-alignment ,  1-bit-is-all-we-need ,  time-series-foundation-models ,  parathinker ,  parallel-thinking ,  retrieval-and-structuring-augmented-generation ,  parallel-r1 ,  paper2agent

paper ,  ai-ml-papers-of-the-week

paper ,  hallucination ,  vision-language-action-model ,  rl-with-verifiable-rewards ,  ai-ml-papers-of-the-week ,  llm-embeddings ,  rstar2-agent ,  grpo-roc ,  ugmm-nn ,  gaussian-mixture-model ,  hierarchy-aware-credit-assignment ,  openvision-2 ,  backprompting ,  depth-breadth-synergy-in-rlvr ,  flowvla ,  visual-chain-of-thought ,  episodic-memory ,  video-episodic-memory-representation