Open Models Almanac
Methodspost-training

methods · pipeline stage 5 of 6

post-training

506 methods filed at this node or below it, from the sources of 40 models.

In this branch 506

Everything filed at this node or below it, with one collapsible heading per child node.

filed here 28

post-training core · 3 sources · 4 quotes
Scalable RL at Agent Scale core · 3 sources · 3 quotes
Scalable reinforcement learning post-training core · 2 sources · 2 quotes
Task-specific post-training core · 2 sources · 2 quotes
Specialized teacher training used · 4 sources · 4 quotes
22 single mentions
Matched-quantity context masking core · 1 source · 1 quote
Multi-stage training strategy core · 1 source · 1 quote
Pretraining on general manipulation data core · 1 source · 1 quote
Three-phase audio model training core · 1 source · 1 quote
Three-stage post-training pipeline core · 1 source · 2 quotes
Three-stage VLA training pipeline core · 1 source · 1 quote
Extended post-training used · 1 source · 1 quote
Post-training on diverse domains used · 1 source · 1 quote
Post-training optimization used · 1 source · 1 quote
Reasoning-effort labeling used · 1 source · 1 quote
Specialize-then-rehearse training used · 1 source · 1 quote
Three-stage Thinker post-training strategy used · 1 source · 1 quote
Full post-training using TRL optional · 1 source · 1 quote
Post-training with real or synthetic data optional · 1 source · 1 quote

supervised fine-tuning 110

Supervised fine-tuning core · 23 sources · 27 quotes
Low-Rank Adaptation core · 11 sources · 12 quotes
Two-stage supervised fine-tuning core · 4 sources · 5 quotes
Full-model fine-tuning core · 3 sources · 3 quotes
Embodiment-specific fine-tuning core · 2 sources · 3 quotes
German-language reasoning post-training core · 2 sources · 2 quotes
Fine-tuning used · 6 sources · 6 quotes
Assistant-only loss used · 2 sources · 2 quotes
End-to-end fine-tuning used · 2 sources · 2 quotes
Imitation learning used · 2 sources · 2 quotes
Multitask fine-tuning used · 2 sources · 2 quotes
Parameter-efficient fine-tuning used · 2 sources · 2 quotes
Rejection sampling used · 2 sources · 2 quotes
Self-correction cold start used · 2 sources · 2 quotes
SFT bootstrapping with synthetic data used · 2 sources · 2 quotes
Single-GPU fine-tuning optional · 2 sources · 2 quotes
93 from one source, or only mentioned as not used
Depth-token noise during fine-tuning core · 1 source · 1 quote
Frozen Qwen3-VL-4B instruction encoder core · 1 source · 1 quote
Frozen video encoder for camera frames core · 1 source · 1 quote
Optimized Fine-Tuning core · 1 source · 1 quote
Action-focused second-stage training used · 1 source · 1 quote
Adversarial fine-tuning used · 1 source · 1 quote
Cold-started supervised fine-tuning model used · 1 source · 1 quote
Context-grounded abstention training used · 1 source · 1 quote
Embodied specialization stage used · 1 source · 1 quote
Evaluation-based early stopping during SFT used · 1 source · 1 quote
Fine-tuning on downstream robot tasks used · 1 source · 1 quote
Fine-tuning with high-quality data used · 1 source · 1 quote
Frozen-backbone action-expert fine-tuning used · 1 source · 1 quote
Instruction hierarchy training used · 1 source · 1 quote
Instruction-following fine-tuning used · 1 source · 1 quote
Joint multimodal supervised fine-tuning used · 1 source · 1 quote
Joint policy adaptation used · 1 source · 1 quote
Lightweight speaker fine-tuning used · 1 source · 1 quote
Mask tool responses from the SFT loss used · 1 source · 1 quote
Post-training on the DROID Dataset used · 1 source · 1 quote
Post-training on the LIBERO Dataset used · 1 source · 1 quote
Rank-32 Low-Rank Adaptation used · 1 source · 1 quote
Reasoning-data system prompt used · 1 source · 1 quote
Robot-only fine-tuning used · 1 source · 1 quote
Single-stage supervised fine-tuning used · 1 source · 1 quote
Specialist training used · 1 source · 1 quote
Token-budget-based SFT data blending used · 1 source · 1 quote
Use 100% SFT data for final QAD used · 1 source · 1 quote
Domain-specific post-training optional · 1 source · 1 quote
Fine-tuning action heads for a new embodiment optional · 1 source · 1 quote
Fine-tuning on traces from Mistral Large 4 optional · 1 source · 1 quote
Frozen-backbone projection-layer adaptation optional · 1 source · 1 quote
Local fine-tuning for specialization optional · 1 source · 1 quote
Action-expert-only fine-tuning evaluated · 1 source · 1 quote
Experimental agentic SFT blend evaluated · 1 source · 1 quote
Fine-tuning on BridgeData V2 only evaluated · 1 source · 1 quote
Freeze the vision encoder during fine-tuning evaluated · 1 source · 2 quotes
Joint fine-tuning across multiple embodiments evaluated · 1 source · 1 quote
Last-layer and token-embedding fine-tuning evaluated · 1 source · 1 quote
Long-context SFT data ablation evaluated · 1 source · 1 quote
Loss masking in supervised fine-tuning evaluated · 1 source · 1 quote
Reasoning-effort assignment in SFT evaluated · 1 source · 1 quote
Sandwich fine-tuning evaluated · 1 source · 1 quote
Shortened supervised fine-tuning ablation recipe evaluated · 1 source · 1 quote
Task-specific fine-tuning of a multitask policy evaluated · 1 source · 1 quote
Heterogeneous Low-Rank Adaptation not used · 1 source · 1 quote

reinforcement learning algorithm 75

Group Relative Policy Optimization core · 16 sources · 18 quotes
Mixed-domain reinforcement learning core · 5 sources · 5 quotes
Groupwise Advantage Redistribution core · 3 sources · 4 quotes
Chain-of-thought reinforcement learning core · 2 sources · 2 quotes
Group-relative advantage estimation core · 2 sources · 2 quotes
Dropping zero-advantage rollout groups default · 2 sources · 2 quotes
Reinforcement learning used · 20 sources · 23 quotes
Abstention training used · 2 sources · 2 quotes
IcePop used · 2 sources · 3 quotes
Keep Sampling Mask used · 2 sources · 2 quotes
Off-Policy Sequence Masking used · 2 sources · 3 quotes
Rollout Routing Replay used · 2 sources · 3 quotes
59 single mentions
CISPO-style REINFORCE objective core · 1 source · 1 quote
Difficulty-bucket and pass-rate curriculum core · 1 source · 1 quote
Keep Routing core · 1 source · 1 quote
Merlin and Morgana masking algorithms core · 1 source · 1 quote
Penalty Module core · 1 source · 1 quote
Advantage shaping used · 1 source · 1 quote
Checkpoint merging for successive RL runs used · 1 source · 1 quote
Concatenated routing replay used · 1 source · 1 quote
Direct Double-sided Importance Sampling used · 1 source · 2 quotes
Domain-specialized RL experts used · 1 source · 1 quote
Domain-specific GRPO training used · 1 source · 1 quote
Dynamic abstention-reward calibration used · 1 source · 1 quote
End-to-end GRPO on agentic tasks used · 1 source · 1 quote
Group-based rollout sampling used · 1 source · 1 quote
Group-relative length penalty used · 1 source · 1 quote
Group-wise policy optimization used · 1 source · 1 quote
GRPO with masked importance sampling used · 1 source · 1 quote
GSPO used · 1 source · 1 quote
Hierarchical penalty escalation used · 1 source · 1 quote
Incremental reinforcement learning used · 1 source · 1 quote
Interaction-Aligned RL used · 1 source · 1 quote
Length-based RL reward adjustment used · 1 source · 1 quote
Mask re-rendered context during training used · 1 source · 1 quote
Off-policy drift reduction used · 1 source · 1 quote
Omitting advantage normalization used · 1 source · 1 quote
PivotRL used · 1 source · 2 quotes
PPO-style policy-ratio clipping used · 1 source · 1 quote
Progressively complex task distributions used · 1 source · 1 quote
Quality-weighted advantage redistribution used · 1 source · 1 quote
Reinforcement-learning pipeline used · 1 source · 1 quote
RL with rubric and claims graders used · 1 source · 1 quote
RLCEF used · 1 source · 1 quote
SAO with compaction used · 1 source · 1 quote
SFT and GRPO for domain specialization used · 1 source · 1 quote
SFT checkpoint initialization for RL used · 1 source · 1 quote
Single mixed-domain RL run used · 1 source · 1 quote
Single-harness reinforcement learning used · 1 source · 1 quote
Tool-error step penalty used · 1 source · 1 quote
Moonlight scaling optional · 1 source · 1 quote

reward modelling 68

Groupwise Agentic Grading core · 3 sources · 4 quotes
Groupwise Reward Synthesis core · 3 sources · 4 quotes
Generative Reward Model used · 6 sources · 7 quotes
Adversarial-agent reward-hacking audit used · 4 sources · 4 quotes
Length penalty used · 4 sources · 4 quotes
Language-consistency reward used · 3 sources · 3 quotes
Reasoning-length penalty used · 2 sources · 2 quotes
Verifier cross-checking used · 2 sources · 2 quotes
59 single mentions
Binary task verifier core · 1 source · 1 quote
Deterministic reward-checking chain core · 1 source · 1 quote
p-norm aggregation of format signals core · 1 source · 1 quote
Per-source composite reward functions core · 1 source · 1 quote
Role-centered reward baselines core · 1 source · 1 quote
Role-conditioned Merlin–Arthur rewards core · 1 source · 1 quote
Sparse terminal-verifier reward core · 1 source · 1 quote
Conservative failure attribution default · 1 source · 1 quote
Abstention-aware factual QA reward used · 1 source · 1 quote
Agentic Generative Reward Model used · 1 source · 1 quote
Auxiliary tool-use reward used · 1 source · 1 quote
Behavior rubrics used · 1 source · 1 quote
Binary answer-correctness reward used · 1 source · 1 quote
Continuous tracking-quality reward used · 1 source · 1 quote
Deterministic task-verifier rewards used · 1 source · 2 quotes
Fail-to-pass test verifier construction used · 1 source · 1 quote
Group-relative length bonus used · 1 source · 1 quote
Hybrid reward system used · 1 source · 1 quote
Matched think-block format validation used · 1 source · 2 quotes
Monitoring-only penalty strategy used · 1 source · 1 quote
Multi-level reward formulation used · 1 source · 1 quote
Multiplicative p-norm format reward used · 1 source · 1 quote
Outcome Reward Model used · 1 source · 1 quote
Pairwise rewards with groupwise penalties used · 1 source · 1 quote
Per-token tool-error reward shaping used · 1 source · 1 quote
Public and hidden verifier pairing used · 1 source · 1 quote
Reasoning reward from LRM feedback used · 1 source · 1 quote
Reasoning-action consistency reward used · 1 source · 2 quotes
Reasoning-to-action verification used · 1 source · 1 quote
Regression-adjusted test-pass reward used · 1 source · 1 quote
Reward-scale calibration used · 1 source · 1 quote
Rule-based outcome reward used · 1 source · 1 quote
Rule-based verifiers used · 1 source · 1 quote
Safety reward used · 1 source · 1 quote
Scientific-tool answer cross-checking used · 1 source · 1 quote
Segment-level behavioral penalties used · 1 source · 1 quote
Solution-quality rubrics used · 1 source · 1 quote
Test-case pass-fraction reward used · 1 source · 1 quote
Test-difficulty-driven code reward used · 1 source · 1 quote
Trajectory-quality reward used · 1 source · 1 quote

preference optimization 8

7 single mentions
Offline direct preference alignment core · 1 source · 1 quote
Budget-based verbosity control used · 1 source · 1 quote
Deliberative alignment used · 1 source · 1 quote
Direct Preference Optimization (DPO) used · 1 source · 1 quote
Fixed-reference response comparison used · 1 source · 1 quote

policy distillation 32

Multi-Teacher On-Policy Distillation core · 21 sources · 29 quotes
On-Policy Distillation core · 6 sources · 8 quotes
Prefix-Conditioned On-Policy Distillation used · 3 sources · 6 quotes
Specialist Distillation used · 3 sources · 3 quotes
Distillation from a Larger Nemotron 3 Model used · 2 sources · 2 quotes
Distillation from Nemotron 3 Ultra Base used · 2 sources · 2 quotes
On-Policy Self-Distillation used · 2 sources · 4 quotes
24 from one source, or only mentioned as not used
Dual-Query Distillation core · 1 source · 1 quote
Token-Local Distillation Update core · 1 source · 1 quote
Autonomous Student Rollouts used · 1 source · 1 quote
Behavior–Proximal Policy Decoupling used · 1 source · 1 quote
Distillation on MiMo-Generated Data used · 1 source · 1 quote
Frozen Student Self-Anchor used · 1 source · 1 quote
IcePop Token-Level Loss Masking used · 1 source · 1 quote
Model Distillation used · 1 source · 1 quote
Multi-Teacher Capability Consolidation used · 1 source · 1 quote
Multiple-Teacher Distillation used · 1 source · 1 quote
On-Policy Cross-Stage Distillation used · 1 source · 2 quotes
Reasoning-Prefill Distillation used · 1 source · 3 quotes
Remote Teacher Infrastructure used · 1 source · 1 quote
Off-Policy Distillation not used · 1 source · 1 quote

rollout & RL infrastructure 98

Asynchronous reinforcement learning core · 14 sources · 18 quotes
Partial rollout used · 3 sources · 5 quotes
Adaptive Rollout Concurrency used · 2 sources · 2 quotes
Co-located rollout and training used · 2 sources · 2 quotes
On-policy rollout generation used · 2 sources · 2 quotes
Seamless Rollout Engine used · 2 sources · 2 quotes
SLIME used · 2 sources · 3 quotes
Token-in-Token-out (TITO) used · 2 sources · 3 quotes
88 from one source, or only mentioned as not used
Agent Loop core · 1 source · 1 quote
Agent-centric rollout execution core · 1 source · 1 quote
Compute-node sharding into scale units core · 1 source · 1 quote
Hierarchical trajectory data organization core · 1 source · 1 quote
One rollout worker per non-controller node core · 1 source · 1 quote
Payload Porter core · 1 source · 1 quote
Persistent multi-tenant harness pool core · 1 source · 2 quotes
Predictive Rollout Dispatch core · 1 source · 2 quotes
Sample-level dispatch default · 1 source · 1 quote
Adaptive Rollout Scheduling used · 1 source · 1 quote
Autoscaling rollout actors used · 1 source · 1 quote
Autoscaling supporting services used · 1 source · 1 quote
Bounding off-policy sample ratio used · 1 source · 1 quote
Capping trajectory staleness used · 1 source · 1 quote
Centralized trajectory bin-packing used · 1 source · 1 quote
Data re-sampling strategy used · 1 source · 1 quote
Data Scheduler used · 1 source · 2 quotes
Decoupled control plane and data plane used · 1 source · 2 quotes
Dialogue prefix matching used · 1 source · 1 quote
Distributed rollout workers used · 1 source · 1 quote
Fixed-usable-trajectory-count batching used · 1 source · 1 quote
Heterogeneous Agent Harnesses used · 1 source · 1 quote
Incremental multimodal-delta transfer used · 1 source · 1 quote
Independent parallel agent rollouts used · 1 source · 1 quote
Long-horizon rollout budgets used · 1 source · 1 quote
Maximum-staleness replay-buffer eviction used · 1 source · 1 quote
Mixed-task rollout infrastructure used · 1 source · 1 quote
Mixing tasks and harnesses in one RL batch used · 1 source · 1 quote
Multi-harness rollouts used · 1 source · 1 quote
Multi-Task Rollout Orchestrator used · 1 source · 1 quote
Multimodal metadata/payload separation used · 1 source · 1 quote
Overlapped RDMA weight-transfer writes used · 1 source · 1 quote
Per-dataset rollout concurrency limits used · 1 source · 1 quote
Per-step NCCL weight updates used · 1 source · 1 quote
Preserving the environment sampling mix used · 1 source · 1 quote
Provider failover routing used · 1 source · 1 quote
Replay-buffer shared-prefix deduplication used · 1 source · 1 quote
Routed-Expert Replay used · 1 source · 1 quote
Sample Mixer used · 1 source · 1 quote
Sample replay used · 1 source · 1 quote
Sample-grained garbage collection used · 1 source · 1 quote
Shared composable interface for RL tasks used · 1 source · 1 quote
Teacher-generated rollout trajectories used · 1 source · 1 quote
Token-level interruption of generation used · 1 source · 1 quote
Tool Manager used · 1 source · 2 quotes
Toolbox used · 1 source · 2 quotes
Asynchronous group-wise grading optional · 1 source · 1 quote
Discarding early-returned short samples optional · 1 source · 1 quote
Deficit-corrected scheduling evaluated · 1 source · 2 quotes
Batch-level rollout dispatch not used · 1 source · 1 quote
Prompt-level rollout dispatch not used · 1 source · 1 quote

agentic post-training 69

Agentic reinforcement learning core · 8 sources · 8 quotes
Merlin–Arthur protocol core · 2 sources · 4 quotes
Multi-environment reinforcement learning core · 2 sources · 2 quotes
Agentic post-training used · 2 sources · 2 quotes
Agentic tool-use post-training used · 2 sources · 2 quotes
62 single mentions
Common agent-environment interaction loop core · 1 source · 1 quote
Durable peer-mailbox communication core · 1 source · 1 quote
End-to-end project development core · 1 source · 1 quote
Weighted environment sampling core · 1 source · 1 quote
Autonomous Execution Tasks used · 1 source · 1 quote
Concurrent multi-environment post-training used · 1 source · 1 quote
Container-level network isolation used · 1 source · 1 quote
Crash-as-failure trajectory handling used · 1 source · 1 quote
Generate-verify-refine loop used · 1 source · 1 quote
German-language RL training environments used · 1 source · 1 quote
Harness randomization for agentic training used · 1 source · 1 quote
Harness-optimized training used · 1 source · 1 quote
Morgana adversarial context hiding used · 1 source · 1 quote
Multi-harness reinforcement learning used · 1 source · 3 quotes
Multi-turn collaboration simulator used · 1 source · 1 quote
Per-episode configuration randomization used · 1 source · 1 quote
Prompt typo injection used · 1 source · 1 quote
Python-tool use during chain-of-thought used · 1 source · 1 quote
Re-post-training for agentic capabilities used · 1 source · 1 quote
Reinforcement learning with self-feedback used · 1 source · 1 quote
Seed-based terminal-task generation used · 1 source · 1 quote
Self-hosted user simulator used · 1 source · 1 quote
Unified white-box RL environment used · 1 source · 1 quote
Fresh or snapshot-based teammate initialization optional · 1 source · 1 quote
RL restricted to search and code environments evaluated · 1 source · 1 quote

mid-training & continual pretraining 18

Long-context extension via continued pretraining core · 12 sources · 16 quotes
Mid-training core · 5 sources · 6 quotes
Continued pretraining used · 4 sources · 4 quotes
Indic continued pretraining used · 4 sources · 4 quotes
Long-context recovery training used · 4 sources · 6 quotes
Software-engineering mid-training used · 4 sources · 5 quotes
12 single mentions
Agent-centric mid-training used · 1 source · 1 quote
Broad robot-data pretraining used · 1 source · 1 quote
Human-video pretraining used · 1 source · 1 quote
Joint text-and-audio mid-training used · 1 source · 1 quote
Mid-training on the MolmoAct Dataset used · 1 source · 1 quote
Multimodal mid-training used · 1 source · 1 quote
Physical-AI-focused pretraining used · 1 source · 1 quote

By model

Which of this branch's methods each model's own documents describe, and how strongly. Under each model: its strongest treatment anywhere in the branch.

Modelfiled heresupervised fine-tuningreinforcement learning algorithmreward modellingpreference optimizationpolicy distillationrollout & RL infrastructureagentic post-trainingmid-training & continual pretraining
DeepSeek-V4.1-Flash-1017 core———————End-to-end project development coreReinforcement learning with self-feedback used——
DeepSeek-V4.1-Flash coreSFT followed by reinforcement learning and on-policy distillation used——Checkpoint merging for successive RL runs usedConcatenated routing replay usedEffort-conditioned subgroup reward centering usedReinforcement learning mentioned—Reasoning-length penalty used——Dynamic Post-Training Recipe Reconfiguration usedFull-Vocabulary On-Policy Distillation with Heterogeneous Teachers usedSFT–RL–On-Policy Distillation Post-Training Recipe used—Asynchronous reinforcement learning coreCompute-node sharding into scale units coreSample-level dispatch defaultAsynchronous reinforcement learning on synthesized tasks usedBounding off-policy sample ratio usedCo-located rollout and training usedDecoupled sandbox and worker-container architecture for RL rollouts usedPer-dataset rollout concurrency limits usedReuse of persisted rollout state without re-prefilling usedSample-grained garbage collection usedScaffold-agnostic rollout control and trajectory normalization usedState-preserving suspension and resumption of rollouts usedToken-granular persistence of rollout state usedToken-level interruption of generation usedDiscarding early-returned short samples optionalBatch-level rollout dispatch not usedPrompt-level rollout dispatch not used—Durable peer-mailbox communication coreCollaborative multi-agent construction of coding environments usedCrash-as-failure trajectory handling usedFailure replay and targeted reinforcement learning usedGenerating real-workflow agent environments from feedback and failure cases usedIndependent multi-agent testing and inspection of coding environments usedIsolated-container environment setup and packaging usedIterative agent-led environment repair and reverification usedLifecycle monitoring and quality re-auditing of RL tasks usedMocked-tool construction for real-world interfaces usedMulti-objective reinforcement-learning reward for agent collaboration usedFresh or snapshot-based teammate initialization optional——
GLM-5.3 corepost-training coreExtended post-training used——SAO with compaction used—————Environment scaling for realistic training tasks used——
DeepSeek-V4-Flash-0731 usedPost-training optimization used———————Re-post-training for agentic capabilities used——
Hy3 usedJoint supervised fine-tuning and reinforcement learning used—Supervised fine-tuning usedFine-tuning optional—Group Relative Policy Optimization usedReinforcement learning used———————
MiMo-V2.6-Flash core—SFT checkpoint intended as an RL starting point coreSelf-correction cold start usedSupervised fine-tuning on MiMo-generated task data used—Asynchronous Group Relative Policy Optimization coreGroupwise Advantage Redistribution corePenalty Module coreDropping zero-advantage rollout groups defaultAdvantage shaping usedDomain-specific GRPO training usedDynamic sampling of informative rollout groups usedFlagged-token advantage penalty and masking usedFreezing the MoE router during reinforcement learning usedGroup-relative length penalty usedHierarchical penalty escalation usedQuality-weighted advantage redistribution usedReplay top-k/top-p sampling candidate sets during training usedRollout Routing Replay usedSingle-harness reinforcement learning usedZero-reward correction for externally supported trajectories used—Groupwise Agentic Grading coreGroupwise Reward Synthesis coreAdversarial-agent reward-hacking audit usedBehavior rubrics usedFive-dimension comparative grading of passing patches usedMonitoring-only penalty strategy usedMultiplicative reward synthesis from test and rubric scores usedNegative rubric checks for unintended side effects usedOffline trajectory auditing for reward hacking usedRule-based or model-judged trajectory error detection usedSegment-level behavioral penalties usedSolution-quality rubrics usedVerifier cross-checking used——Autonomous Student Rollouts usedDistillation on MiMo-Generated Data usedModel Distillation usedMulti-Prefix Multi-Teacher On-Policy Distillation usedPrefix-Conditioned On-Policy Distillation usedStandard Multi-Teacher On-Policy Distillation used—Agent Loop coreAgent-centric rollout execution coreAsynchronous reinforcement learning coreHierarchical trajectory data organization corePayload Porter corePersistent multi-tenant harness pool corePredictive Rollout Dispatch coreAdaptive Rollout Concurrency usedAdaptive Rollout Scheduling usedBackground-thread offloading of blocking rollout work usedComposite early-stop strategy that zeroes reward and masks affected contexts usedDecoupled control plane and data plane usedDialogue prefix matching usedDuration- and acceptance-adjusted per-source oversampling usedHeterogeneous Agent Harnesses usedIncremental multimodal-delta transfer usedIsolated resettable sandboxes for agent rollouts usedMixed-task rollout infrastructure usedMultimodal metadata/payload separation usedPartial rollout usedPer-source priors for rollout length estimation usedSample Mixer usedSample replay usedTraining–inference consistency mechanisms usedAsynchronous group-wise grading optionalDeficit-corrected scheduling evaluated—Agentic reinforcement learning coreContainer-level network isolation usedEnvironment hardening during reinforcement learning usedEnvironment preparation to prevent solution leakage usedMulti-harness reinforcement learning usedUnified trajectory representation for agentic RL used—Agent-centric mid-training usedMid-training alignment data from reward-hacking cases used—
NVIDIA-Nemotron-3-Ultra-550B-A55B core—Light supervised fine-tuning on teacher-distribution data coreRejection sampling usedSupervised fine-tuning usedToken-budget-based SFT data blending used—Abstention training usedDynamic abstention-reward calibration usedGroup Relative Policy Optimization usedIcePop usedNegative-advantage penalties for malformed reasoning and tool calls usedPivotRL usedPPO-style policy-ratio clipping usedReinforcement learning usedReinforcement learning from verifiable rewards used—Generative Reward Model usedLength penalty usedPrinciple-conditioned generative reward model used—Reinforcement Learning from Human Feedback (RLHF) used—Multi-Teacher On-Policy Distillation coreAsynchronous Multi-Teacher On-Policy Distillation usedBehavior–Proximal Policy Decoupling usedIcePop Token-Level Loss Masking usedOff-Policy Distillation not used—One-step off-policy asynchronous reinforcement learning coreAsynchronous reinforcement learning usedOn-policy rollout generation used—Concurrent multi-environment post-training usedMulti-environment reinforcement learning used—Continued pretraining usedLong-context extension via continued pretraining used—
DeepSeek-V4-Flash core——Group Relative Policy Optimization used—Direct RL optimization of a generative reward model usedGenerative Reward Model used——Multi-Teacher On-Policy Distillation coreOn-Policy Distillation used————
Alpamayo 1.5 / 2 Super coreMulti-stage training strategy coreThree-stage VLA training: action-modality injection, CoC reasoning SFT, and RL post-training core—Supervised fine-tuning on Chain of Causation data core—RL-based post-training framework with complementary rewards coreGroup Relative Policy Optimization usedReinforcement learning used—Reasoning reward from LRM feedback usedReasoning-action consistency reward usedSafety reward usedTrajectory-quality reward used—————Physical-AI-focused pretraining used—
DeepSeek-V3.2 coreScalable reinforcement learning post-training core—Prompt-based cold start for reasoning with tool use usedReasoning-data system prompt used—Group Relative Policy Optimization coreKeep Routing coreMixed-domain reinforcement learning coreImportance-sampling-corrected unbiased KL estimate usedKeep Sampling Mask usedOff-Policy Sequence Masking usedReinforcement learning used—Generative Reward Model usedLanguage-consistency reward usedLength penalty usedRule-based outcome reward used——Specialist Distillation used——Generate-verify-refine loop usedLarge-scale reinforcement learning on synthetic agentic data usedTraining agentic policies with real-world tools usedRL on synthetic agentic tasks in non-thinking mode evaluatedRL restricted to search and code environments evaluated—Continued pretraining used—
DeepSeek-V4-Flash-Vision-Exp corePost-training optimization used————————Continued training for visual understanding core—
DeepSeek-V4-Pro core—Specialist training usedSupervised fine-tuning used—Group Relative Policy Optimization usedReinforcement learning used—Direct RL optimization of a generative reward model usedGenerative Reward Model used——Multi-Teacher On-Policy Distillation coreOn-Policy Distillation core—Preemptible rollout service with write-ahead logging used——Mid-training used—
DeepSeek-V4-Pro-0813 usedPost-training optimization used—————————
FLUX 3 Action core—Frozen Qwen3-VL-4B instruction encoder coreFrozen video encoder for camera frames coreAction-focused second-stage training usedFine-tuning for video-game and simulated-drone control usedRobot-specific fine-tuning with a small demonstration set usedFine-tuning action heads for a new embodiment optional————————
GLM-5.2 used—Rejection sampling used—Direct Double-sided Importance Sampling usedGroup Relative Policy Optimization usedGroup-wise policy optimization usedIcePop used—Hybrid reward system usedMulti-level reward formulation used——On-Policy Cross-Stage Distillation used—Asynchronous Agent Reinforcement Learning algorithms usedAsynchronous reinforcement learning usedMulti-Task Rollout Orchestrator usedSLIME usedToken-in-Token-out (TITO) used———
GR00T N1.7 usedPost-training with real or synthetic data optional—Fine-tuning video generation models on robot teleoperation data usedFreeze language and visual backbones during fine-tuning usedFreeze the language component of the vision-language backbone usedLow-Rank Adaptation usedPost-training on the Bridge Dataset in SimplerEnv usedPost-training on the DROID Dataset usedPost-training on the Fractal Dataset in SimplerEnv usedPost-training on the LIBERO Dataset usedSingle-embodiment post-training fine-tuning usedFine-tuning on custom embodiments with LeRobot-format datasets optional———————Human-video pretraining used—
Gemma 4 31B mentioned—Fine-tuning mentioned————————
Inkling corePost-training on diverse domains used—Low-Rank Adaptation coreSafety training to an internal specification usedSFT bootstrapping with synthetic data used—Reinforcement learning usedRL for calibration with proper scoring rules usedRL with rubric and claims graders used—Abstention-aware factual QA reward used——Distillation-Based Post-Training Data Generation used—Asynchronous reinforcement learning core———
Kimi K3 coreThree-stage post-training with SFT, RL, and multi-teacher on-policy distillation core—Supervised fine-tuning used—Multi-domain, multi-effort reinforcement learning coreDomain-specialized RL experts used—Agentic Generative Reward Model usedPublic and hidden verifier pairing usedWeb-development reward with deterministic checks and model judging used—Budget-based verbosity control used—Multi-Teacher On-Policy Distillation corePer-Token On-Policy Distillation Reward with Clipping used—Co-located million-token agentic RL system with resumable sandboxes usedCo-located rollout and training usedPartial rollout used—Training on verifiable problems in agentic environments coreAutonomous Execution Tasks usedMock applications for personal-assistant RL usedUnified white-box RL environment used——
Kolibri-1 coreMatched-quantity context masking coreDataset-specific reference groups for reasoning-effort labeling usedReasoning-effort labeling usedSeeded soft effort-label sampling around bucket boundaries used—German-language reasoning post-training coreAssistant-only loss usedContext-grounded abstention training usedFine-tuning a specialist model for each dataset cluster usedInclude English and German safety datasets in SFT usedLong-context post-training with document question answering usedMask loss on incorrect tool calls and terminal actions usedMask loss on invalid or repeated tool calls usedSafety refusal training with appropriate partial answers usedSFT refusal training for PII extraction attacks usedSupervised fine-tuning usedLong-context SFT data ablation evaluatedLoss masking in supervised fine-tuning evaluatedReasoning-effort assignment in SFT evaluatedShortened supervised fine-tuning ablation recipe evaluated—Difficulty-bucket and pass-rate curriculum coreGroup-relative advantage estimation coreMerlin and Morgana masking algorithms coreDynamic sampling of informative rollout groups usedLarge-scale reinforcement learning for long-horizon tasks usedMask re-rendered context during training usedOmitting advantage normalization used—Environment-specific output-format reward signals coreMultiplicative aggregation of format signals corep-norm aggregation of format signals coreReinforcement Learning with Verifiable Rewards coreRole-centered reward baselines coreRole-conditioned Merlin–Arthur rewards coreFormat reward conditioned on positive environment reward usedHallucination mitigation through abstention and context-sensitive RL usedKillable, time-limited verifier process pool usedLanguage-consistency reward usedMerlin–Arthur correctness and abstention reward usedMerlin–Arthur hallucination and abstention example construction usedMultiplicative p-norm format reward usedReasoning-to-action verification usedRegression-adjusted test-pass reward usedTest-case pass-fraction reward used——On-Policy Self-Distillation usedReasoning-Prefill Distillation used—Asynchronous reinforcement learning coreOne rollout worker per non-controller node coreRouting sequences to the same inference replica coreAsynchronous batching of parallel retrieval queries usedCapacity allocation balancing trainer and inference throughput usedDistributed rollout workers usedIsolated resettable sandboxes for agent rollouts usedMaximum-staleness replay-buffer eviction usedNon-blocking weight synchronization to inference usedOverlapped RDMA weight-transfer writes usedPreserving the environment sampling mix usedRDMA weight distribution through one replica per node usedReplay-buffer shared-prefix deduplication usedRouted-Expert Replay used—Environment sampling proportional to sampling and curriculum weights coreMerlin–Arthur protocol corePrompt sampling by difficulty bucket and evaluation recency coreRandomization of RL environments and prompts coreRetrieval-augmented question-answering training coreWeighted environment sampling coreAgentic retrieval environments for RAG training usedGerman-language RL training environments usedHarness randomization for agentic training usedLong-context question-answering RL environment usedMorgana adversarial context hiding usedPer-episode configuration randomization usedPer-group randomization of system prompt, coding harness, and user request usedPrompt typo injection usedRandomized preservation of reasoning traces across turns usedRandomized reasoning-effort level per rollout group usedRandomized retrieval setup and task language usedRandomized training environments for real-world robustness usedRL environments for political balance, copyright, and safety usedSelf-hosted user simulator usedSeparate abstention-only environment for unanswerable questions usedTool-calling and terminal-environment post-training usedTraining environments that simulate real-world use cases used—Long-context extension via continued pretraining used—
LFM3-1.7B coreThree-phase audio model training coreThree-stage post-training pipeline coreFull post-training using TRL optional—Supervised fine-tuning coreCross-category integration of multilingual samples in SFT data usedEnd-to-end fine-tuning usedFine-tuned skill monitor for robot recovery usedJoint multimodal supervised fine-tuning usedRank-32 Low-Rank Adaptation usedTask-specific fine-tuning for wind-turbine blade defect detection usedFrozen-backbone projection-layer adaptation optionalLocal fine-tuning for specialization optionalSingle-GPU fine-tuning optional—Mixed-domain reinforcement learning usedSFT and GRPO for domain specialization used—Length penalty used—Length-normalized direct preference alignment coreOffline direct preference alignment coreContrastive Learning from AI Revisions (CLAIR) used—Multi-Teacher On-Policy Distillation used——Agentic post-training usedAgentic reinforcement learning used—Joint text-and-audio mid-training usedLong-context extension via continued pretraining usedMid-training usedMid-training with lower-quality SFT datasets usedMultimodal mid-training usedContinued pretraining optional—
Laguna-S-2.1 coreTwo-stage post-training pipeline (SFT then RL) core—Evaluation-based early stopping during SFT usedFrozen-network warmup for new special tokens usedInstruction-following fine-tuning usedSFT bootstrapping with synthetic data used—CISPO with length-weighted leave-one-out group-relative advantages coreAgentic RL task mix with a shared tool-use API usedRLCEF usedTool-error step penalty usedMoonlight scaling optional—Binary task verifier coreDeterministic reward-checking chain coreSparse terminal-verifier reward corePer-token tool-error reward shaping used———Blocking in-flight rollout steps during weight updates usedCapping trajectory staleness usedClosed-loop multi-turn synthetic-data rollout usedExact rollout-to-production chat-template alignment assertion usedLong-horizon rollout budgets usedMulti-harness rollouts usedRL sandboxing with selective network blocking and artifact caching usedToken-in-Token-out (TITO) used—Agentic reinforcement learning coreProduction-harness-matched reinforcement learning coreMulti-harness trajectory training with native behavior preservation usedSeed-based terminal-task generation used—Long-context extension via continued pretraining used—
LingBot-VLA 2.0 core—————Dual-Query Distillation core————
MiMo-V2.5 core—Cold-started supervised fine-tuning model usedSupervised fine-tuning used—Group Relative Policy Optimization usedReinforcement learning usedRollout Routing Replay used—Outcome Reward Model usedRule-based verifiers usedTest-difficulty-driven code reward used——Multi-Teacher On-Policy Distillation coreOn-Policy Distillation used—Continuous rollout with asynchronous rewards and early termination usedData re-sampling strategy usedData Scheduler usedPartial rollout usedSeamless Rollout Engine usedStaleness-aware truncated importance sampling usedTool Manager usedToolbox used—Agentic post-training usedAgentic reinforcement learning used——
MiMo-V2.5-Pro core—Cold-started supervised fine-tuning model usedSupervised fine-tuning used—Reinforcement learning used—Rule-based verifiers usedTest-difficulty-driven code reward used——Multi-Teacher On-Policy Distillation core—Continuous rollout with asynchronous rewards and early termination usedData re-sampling strategy usedSeamless Rollout Engine used—Agentic post-training usedAgentic reinforcement learning used——
MiMo-V2.6-Pro core—SFT checkpoint intended as an RL starting point coreSelf-correction cold start usedSupervised fine-tuning on MiMo-generated task data used—Penalty Module coreDropping zero-advantage rollout groups defaultAdvantage shaping usedAsynchronous Group Relative Policy Optimization usedDomain-specific GRPO training usedDynamic sampling of informative rollout groups usedFlagged-token advantage penalty and masking usedFreezing the MoE router during reinforcement learning usedGroup-relative length penalty usedGroupwise Advantage Redistribution usedHierarchical penalty escalation usedQuality-weighted advantage redistribution usedReplay top-k/top-p sampling candidate sets during training usedRollout Routing Replay usedSingle mixed-domain RL run usedSingle-harness reinforcement learning usedZero-reward correction for externally supported trajectories used—Groupwise Agentic Grading coreAdversarial-agent reward-hacking audit usedBehavior rubrics usedFive-dimension comparative grading of passing patches usedGroupwise Reward Synthesis usedMonitoring-only penalty strategy usedMultiplicative reward synthesis from test and rubric scores usedNegative rubric checks for unintended side effects usedOffline trajectory auditing for reward hacking usedRule-based or model-judged trajectory error detection usedSegment-level behavioral penalties usedSolution-quality rubrics usedVerifier cross-checking used——Autonomous Student Rollouts usedDistillation on MiMo-Generated Data usedModel Distillation usedMulti-Prefix Multi-Teacher On-Policy Distillation usedPrefix-Conditioned On-Policy Distillation usedStandard Multi-Teacher On-Policy Distillation used—Agent Loop coreAgent-centric rollout execution coreAsynchronous reinforcement learning coreHierarchical trajectory data organization corePayload Porter corePersistent multi-tenant harness pool corePredictive Rollout Dispatch coreAdaptive Rollout Concurrency usedAdaptive Rollout Scheduling usedBackground-thread offloading of blocking rollout work usedComposite early-stop strategy that zeroes reward and masks affected contexts usedDecoupled control plane and data plane usedDialogue prefix matching usedDuration- and acceptance-adjusted per-source oversampling usedHeterogeneous Agent Harnesses usedIncremental multimodal-delta transfer usedIsolated resettable sandboxes for agent rollouts usedMixed-task rollout infrastructure usedMixing tasks and harnesses in one RL batch usedMultimodal metadata/payload separation usedPartial rollout usedPer-source priors for rollout length estimation usedSample Mixer usedSample replay usedTraining–inference consistency mechanisms usedAsynchronous group-wise grading optionalDeficit-corrected scheduling evaluated—Agentic reinforcement learning coreContainer-level network isolation usedEnvironment hardening during reinforcement learning usedEnvironment preparation to prevent solution leakage usedMulti-agent task decomposition and coordination usedMulti-harness reinforcement learning usedUnified trajectory representation for agentic RL used—Agent-centric mid-training usedMid-training alignment data from reward-hacking cases used—
MiniMax-M3 used———————Multi-turn collaboration simulator used——
Mistral-Large-4 core—Assistant-only loss usedFreeze the vision encoder during pretraining and unfreeze for SFT usedLow-Rank Adaptation usedSupervised fine-tuning usedFine-tuning optionalFine-tuning on traces from Mistral Large 4 optional—CISPO-style REINFORCE objective coreImportance weighting for asynchronous policy lag coreKeep importance-weighted tokens in the objective corePer-token weight normalization by rollout group coreStop-gradient upper-clipped importance weighting coreDropping zero-advantage rollout groups usedGroup-based rollout sampling usedGroup-centered batch-wide advantage normalization usedGroup-relative advantage estimation usedMiMo-style segment-level advantage correction usedOff-policy drift reduction usedReinforcement learning usedReinforcement-learning pipeline usedSFT checkpoint initialization for RL used—Per-source composite reward functions coreConservative failure attribution defaultAdversarial-agent reward-hacking audit usedComposable multi-method reward verification usedExploit-neutralization and regression-free patch reward usedFail-to-pass test verifier construction usedGroup-relative length bonus usedPairwise rewards with groupwise penalties usedQuantized group-relative rollout-length bonus usedReward-scale calibration usedScientific-tool answer cross-checking usedReinforcement Learning with Verifiable Rewards optional——Multi-Teacher On-Policy Distillation usedMultiple-Teacher Distillation usedRemote Teacher Infrastructure usedThree-Teacher Distillation for Reasoning-Effort Modes used—Asynchronous reinforcement learning coreShared environment implementation across RL, evaluation, and synthetic data generation coreActor-pool orchestration for asynchronous RL usedAdaptive Rollout Concurrency usedAutoscaling rollout actors usedAutoscaling supporting services usedBackpressure- and concurrency-controlled rollout admission usedCentralized trajectory bin-packing usedDiscarding infrastructure-failure rollouts in RL usedExcluding auxiliary environment-model calls from training usedFixed-usable-trajectory-count batching usedLow-staleness optimization for long-trajectory RL usedPause and resume in-flight rollouts across policy updates usedPer-step NCCL weight updates usedPrioritizing sibling rollouts from started groups usedProvider failover routing usedRemote teacher hidden-state transfer with trainer-side logit reconstruction usedShared composable interface for RL tasks usedSubmission-only termination for environments with a submit tool optional—Common agent-environment interaction loop coreTerminal-task difficulty calibration using solver pass rates used——
MolmoAct 2 corepost-training coreThree-stage VLA training pipeline corePost-training for multi-embodiment robot control usedSpecialize-then-rehearse training used—Depth-token noise during fine-tuning coreEmbodiment-specific fine-tuning coreFull-model fine-tuning coreEmbodied specialization stage usedFine-tuning on target-embodiment demonstrations usedFine-tuning on the combined LIBERO training suites usedLow-Rank Adaptation usedRobot-only fine-tuning usedSeparate single-task policies for bimanual YAM tasks usedFine-tuning for a target robot embodiment or benchmark optionalAction-expert-only fine-tuning evaluatedFlow-loss updates through action-expert conditioning not usedFreeze added-token input embeddings during embodiment fine-tuning not used———————Mid-training coreMid-training on the MolmoAct Dataset used—
NVIDIA-Nemotron-3.5-Lightning-30B-A3B coreSpecialized teacher training used—Capability-targeted second-stage supervised fine-tuning usedLow-Rank Adaptation usedMask tool responses from the SFT loss usedRandom-budget truncation of reasoning traces usedSingle-stage supervised fine-tuning usedSupervised fine-tuning usedSupervised fine-tuning at 256k sequence length usedTwo-stage supervised fine-tuning usedUse 100% SFT data for final QAD usedExperimental agentic SFT blend evaluatedFine-tuning with demographically balanced datasets mentioned—Abstention training usedAsynchronous Group Relative Policy Optimization usedClipped-range importance weighting with stale-token masking usedEnd-to-end GRPO on agentic tasks usedGroup Relative Policy Optimization usedGRPO with masked importance sampling usedLength-based RL reward adjustment usedReinforcement learning from verifiable rewards used—Auxiliary tool-use reward usedBinary answer-correctness reward usedContinuous tracking-quality reward usedCorrect-response-only soft length preference usedDeterministic task-verifier rewards usedMatched think-block format validation usedReasoning-length penalty usedReinforcement Learning with Verifiable Rewards used—Reinforcement Learning from Human Feedback (RLHF) coreFixed-reference response comparison used—Token-Local Distillation Update coreDistillation from a Larger Nemotron 3 Model usedFrozen Student Self-Anchor usedMulti-Teacher On-Policy Distillation usedProximal-Teacher Trust-Region Policy Distillation usedTwo-Stage Multi-Teacher On-Policy Distillation used—Asynchronous reinforcement learning usedIndependent parallel agent rollouts usedOn-policy rollout generation usedOne-step-stale asynchronous response generation usedTeacher-generated rollout trajectories used—Multi-environment reinforcement learning coreFinance-agent environment with consistent tools across training stages usedHarness-optimized training usedTraining agentic teachers on sandboxed executable tasks used—Long-context extension via continued pretraining coreMid-training coreIndic continued pretraining usedLong-context recovery training usedSoftware-engineering mid-training used—
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B coreSpecialized teacher training used—Two-stage supervised fine-tuning coreCapability-targeted second-stage supervised fine-tuning usedMask tool responses from the SFT loss usedPost-training on organization-specific data usedRandom-budget truncation of reasoning traces usedSingle-stage supervised fine-tuning usedSupervised fine-tuning usedUse 100% SFT data for final QAD usedDomain-specific post-training optionalLow-Rank Adaptation optionalExperimental agentic SFT blend evaluated—Abstention training usedAsynchronous Group Relative Policy Optimization usedClipped-range importance weighting with stale-token masking usedEnd-to-end GRPO on agentic tasks usedLength-based RL reward adjustment usedReinforcement learning usedReinforcement learning from verifiable rewards used—Auxiliary tool-use reward usedBinary answer-correctness reward usedContinuous tracking-quality reward usedCorrect-response-only soft length preference usedDeterministic task-verifier rewards usedMatched think-block format validation usedReasoning-length penalty usedReinforcement Learning with Verifiable Rewards used—Reinforcement Learning from Human Feedback (RLHF) coreFixed-reference response comparison used—Token-Local Distillation Update coreDistillation from a Larger Nemotron 3 Model usedDistillation from Nemotron 3 Ultra Base usedFrozen Student Self-Anchor usedMulti-Teacher Capability Consolidation usedMulti-Teacher On-Policy Distillation usedProximal-Teacher Trust-Region Policy Distillation usedTwo-Stage Multi-Teacher On-Policy Distillation used—Independent parallel agent rollouts usedOn-policy rollout generation usedOne-step-stale asynchronous response generation usedTeacher-generated rollout trajectories used—Finance-agent environment with consistent tools across training stages usedTraining agentic teachers on sandboxed executable tasks used—Long-context extension via continued pretraining coreMid-training coreContinued pretraining with natural and synthetic data usedIndic continued pretraining usedLong-context recovery training usedSoftware-engineering mid-training used—
OpenVLA / OpenVLA-OFT core—Fine-tuning a vision-language model to predict robot actions coreFine-tuning all model parameters including the vision backbone coreOptimized Fine-Tuning coreVision-encoder fine-tuning during VLA training coreEnd-to-end fine-tuning usedFine-tuning with setup-specific demonstrations usedFull-model fine-tuning usedImitation learning usedLow-Rank Adaptation usedParameter-efficient fine-tuning usedSupervised fine-tuning on target-task demonstrations usedFine-tuning with demonstration data for new tasks and robot setups optionalFine-tuning on BridgeData V2 only evaluatedFreeze the vision encoder during fine-tuning evaluatedLast-layer and token-embedding fine-tuning evaluatedSandwich fine-tuning evaluated————————
Qwen3.5-397B-A17B coreScalable RL at Agent Scale coreThree-stage Thinker post-training strategy used—Lightweight speaker fine-tuning used—GSPO usedInteraction-Aligned RL usedProgressively complex task distributions used——Direct Preference Optimization (DPO) used—On-Policy Distillation usedSpecialist Distillation used—Asynchronous RL framework for large-scale agent scaffolds and environment orchestration used——Continued pretraining used—
Qwen3.6-35B-A3B coreScalable RL at Agent Scale core—————————
SmolVLA corePretraining on general manipulation data coreTask-specific post-training core—Fine-tuning usedFrozen-backbone action-expert fine-tuning usedImitation learning usedMultitask fine-tuning used—————Asynchronous reinforcement learning evaluated———
VLA Foundry (Foundry-VLA-1.7B) used—Task-specific fine-tuning of a multitask policy evaluated———————Sequential LLM-to-VLM-to-VLA training pipeline used—
X-VLA used—Embodiment-specific fine-tuning usedJoint policy adaptation usedPeriodic policy training with failure-targeted demonstration collection usedPrompt warm-up with the pretrained backbone frozen usedJoint fine-tuning across multiple embodiments evaluatedLow-Rank Adaptation evaluatedHeterogeneous Low-Rank Adaptation not used————————
Xiaomi-Robotics-1 corePre-training followed by post-training for robot policies core—————————
gpt-oss-120b core—Adversarial fine-tuning usedInstruction hierarchy training usedFine-tuning optional—Chain-of-thought reinforcement learning coreHelpful-only adversarial reinforcement learning usedIncremental reinforcement learning used——Deliberative alignment used———Agentic tool-use post-training usedPython-tool use during chain-of-thought used——
π0.5 corePre-training followed by post-training for robot policies corepost-training usedTask-specific post-training used—Adaptation of vision-language models using robot data usedFine-tuning on downstream robot tasks usedFine-tuning with high-quality data usedFull-model fine-tuning usedFine-tuning optionalLow-Rank Adaptation optionalTraining a downstream policy only on high-quality task data evaluated———————Broad robot-data pretraining used—

Proposed children

Paths the corpus wanted and the taxonomy does not have. A human promotes them into the outline; the extraction cannot.

robotics action representation & controlaction chunking, continuous action generation, robot policy execution, action-sp
↑