Flux Matching generalizes score-based generative modeling by using a weaker objective that admits infinitely many non-conservative vector fields with the data as stationary distribution, enabling new design choices beyond traditional score matching.
hub Canonical reference
Imitating human behaviour with dif- fusion models
Canonical reference. 100% of citing Pith papers cite this work as background.
19
Pith papers citing it
Background
100% of classified citations
hub tools
citation-role summary
background 7
citation-polarity summary
roles
background 7polarities
background 7representative citing papers
Test-time sparsity with a parallel pipeline and omnidirectional feature reuse accelerates action diffusion by 5x to 47.5 Hz while cutting FLOPs 92% with no performance loss.
Flow map policies enable fast one-step inference for flow-based RL policies, and FMQ provides an optimal closed-form Q-guided target for offline-to-online adaptation under trust-region constraints, achieving SOTA performance.
Action Images turn robot arm motions into interpretable multiview pixel videos, letting video backbones serve as zero-shot policies for end-to-end robot learning.
A Bayesian expert selection framework with variational Bayesian last layers and lower confidence bounds improves diffusion policies for active multi-target tracking.
RoboDreamer factorizes video generation using language primitives to achieve compositional generalization in robot world models, outperforming monolithic baselines on unseen goals in RT-X.
Diffusion-QL uses conditional diffusion models as expressive policies in offline RL by coupling behavior cloning with Q-value maximization, achieving SOTA on most D4RL tasks.
FGO guides diffusion policy generation via expanding spectral bands on sub-frequency manifolds to improve action smoothness on 15 robotic manipulation tasks.
FA-OPD co-trains a flow-matching teacher and MLP student via adversarial dual on-policy distillation, improving robustness over baselines on six robot benchmarks with noisy or limited demonstrations.
Generative sequence models for physical tasks exhibit physical misgeneralization where local prediction errors propagate through physical measurements to distort aggregate distributions over quantities like distance or energy; a data deviation kernel explains and predicts the shifts and supports a内核
OGPO enables sample-efficient full-finetuning of generative control policies via off-policy critics and modified PPO, achieving SOTA on robot manipulation tasks while rescuing poorly initialized behavior cloning policies without expert data.
FingerViP equips each finger with a miniature camera and trains a multi-view diffusion policy that achieves 80.8% success on real-world dexterous tasks previously limited by wrist-camera occlusion.
Legato trains flow-based VLA policies with schedule-shaped action-noise mixtures and randomized conditions to achieve smoother trajectories and ~10% faster task completion than real-time chunking across five real-world manipulation tasks.
Real-time chunking (RTC) allows diffusion- and flow-based action chunking policies to execute smoothly and asynchronously, maintaining high success rates on dynamic tasks even with significant inference latency.
HybridVLA unifies diffusion and autoregression in a single VLA model via collaborative training and ensemble to raise robot manipulation success rates by 14% in simulation and 19% in real-world tasks.
CogACT is a new VLA model that uses a conditioned diffusion action transformer to achieve over 35% higher average success rates than OpenVLA in simulation and 55% in real-robot experiments while generalizing to new robots and objects.
DPPO fine-tunes diffusion policies via policy gradients and outperforms prior RL approaches for diffusion policies and PG-tuned alternatives on robot benchmarks while enabling stable training and hardware deployment.
LP-DS improves generative policies for imitation and RL by optimizing latent noise perturbations with a constrained Lagrangian objective, showing up to 25% better returns on manipulation and locomotion tasks.
GAM framework uses arc-length parameterization for temporal invariance and schema-affine factorization for geometric invariance to build a covariant action manifold integrated into VLA models for improved generalization from sparse data.
citing papers explorer
-
Generative Modeling with Flux Matching
Flux Matching generalizes score-based generative modeling by using a weaker objective that admits infinitely many non-conservative vector fields with the data as stationary distribution, enabling new design choices beyond traditional score matching.
-
Test-time Sparsity for Extreme Fast Action Diffusion
Test-time sparsity with a parallel pipeline and omnidirectional feature reuse accelerates action diffusion by 5x to 47.5 Hz while cutting FLOPs 92% with no performance loss.
-
Aligning Flow Map Policies with Optimal Q-Guidance
Flow map policies enable fast one-step inference for flow-based RL policies, and FMQ provides an optimal closed-form Q-guided target for offline-to-online adaptation under trust-region constraints, achieving SOTA performance.
-
Action Images: End-to-End Policy Learning via Multiview Video Generation
Action Images turn robot arm motions into interpretable multiview pixel videos, letting video backbones serve as zero-shot policies for end-to-end robot learning.
-
Diffusion Policy with Bayesian Expert Selection for Active Multi-Target Tracking
A Bayesian expert selection framework with variational Bayesian last layers and lower confidence bounds improves diffusion policies for active multi-target tracking.
-
RoboDreamer: Learning Compositional World Models for Robot Imagination
RoboDreamer factorizes video generation using language primitives to achieve compositional generalization in robot world models, outperforming monolithic baselines on unseen goals in RT-X.
-
Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning
Diffusion-QL uses conditional diffusion models as expressive policies in offline RL by coupling behavior cloning with Q-value maximization, achieving SOTA on most D4RL tasks.
-
Frequency-Guided Action Diffusion via Sub-Frequency Manifold Traversal
FGO guides diffusion policy generation via expanding spectral bands on sub-frequency manifolds to improve action smoothness on 15 robotic manipulation tasks.
-
Adversarial Dual On-Policy Distillation from Expressive Teacher
FA-OPD co-trains a flow-matching teacher and MLP student via adversarial dual on-policy distillation, improving robustness over baselines on six robot benchmarks with noisy or limited demonstrations.
-
Mechanisms of Misgeneralization in Physical Sequence Modeling
Generative sequence models for physical tasks exhibit physical misgeneralization where local prediction errors propagate through physical measurements to distort aggregate distributions over quantities like distance or energy; a data deviation kernel explains and predicts the shifts and supports a内核
-
OGPO: Sample Efficient Full-Finetuning of Generative Control Policies
OGPO enables sample-efficient full-finetuning of generative control policies via off-policy critics and modified PPO, achieving SOTA on robot manipulation tasks while rescuing poorly initialized behavior cloning policies without expert data.
-
FingerViP: Learning Real-World Dexterous Manipulation with Fingertip Visual Perception
FingerViP equips each finger with a miniature camera and trains a multi-view diffusion policy that achieves 80.8% success on real-world dexterous tasks previously limited by wrist-camera occlusion.
-
Learning Native Continuation for Action Chunking Flow Policies
Legato trains flow-based VLA policies with schedule-shaped action-noise mixtures and randomized conditions to achieve smoother trajectories and ~10% faster task completion than real-time chunking across five real-world manipulation tasks.
-
Real-Time Execution of Action Chunking Flow Policies
Real-time chunking (RTC) allows diffusion- and flow-based action chunking policies to execute smoothly and asynchronously, maintaining high success rates on dynamic tasks even with significant inference latency.
-
HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model
HybridVLA unifies diffusion and autoregression in a single VLA model via collaborative training and ensemble to raise robot manipulation success rates by 14% in simulation and 19% in real-world tasks.
-
CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation
CogACT is a new VLA model that uses a conditioned diffusion action transformer to achieve over 35% higher average success rates than OpenVLA in simulation and 55% in real-robot experiments while generalizing to new robots and objects.
-
Diffusion Policy Policy Optimization
DPPO fine-tunes diffusion policies via policy gradients and outperforms prior RL approaches for diffusion policies and PG-tuned alternatives on robot benchmarks while enabling stable training and hardware deployment.
-
Lagrangian Perturbation Diffusion Steering: Latent Reinforcement Learning for Generative Policies
LP-DS improves generative policies for imitation and RL by optimizing latent noise perturbations with a constrained Lagrangian objective, showing up to 25% better returns on manipulation and locomotion tasks.
-
General Covariant Action Modeling: Constructing Generalized Manifolds via Spatio-Temporal Decoupling
GAM framework uses arc-length parameterization for temporal invariance and schema-affine factorization for geometric invariance to build a covariant action manifold integrated into VLA models for improved generalization from sparse data.