JEDI is the first online end-to-end latent diffusion world model that trains latents from denoising loss rather than reconstruction, achieving competitive Atari100k results with 43% less VRAM and over 3x faster sampling than pixel diffusion baselines.
hub Canonical reference
Planning with Diffusion for Flexible Behavior Synthesis
Canonical reference. 73% of citing Pith papers cite this work as background.
49
Pith papers citing it
Background
73% of classified citations
abstract
Model-based reinforcement learning methods often use learning only for the purpose of estimating an approximate dynamics model, offloading the rest of the decision-making work to classical trajectory optimizers. While conceptually simple, this combination has a number of empirical shortcomings, suggesting that learned models may not be well-suited to standard trajectory optimization. In this paper, we consider what it would look like to fold as much of the trajectory optimization pipeline as possible into the modeling problem, such that sampling from the model and planning with it become nearly identical. The core of our technical approach lies in a diffusion probabilistic model that plans by iteratively denoising trajectories. We show how classifier-guided sampling and image inpainting can be reinterpreted as coherent planning strategies, explore the unusual and useful properties of diffusion-based planning methods, and demonstrate the effectiveness of our framework in control settings that emphasize long-horizon decision-making and test-time flexibility.
hub tools
citation-role summary
background 13
baseline 1
method 1
citation-polarity summary
representative citing papers
CoDi decomposes the multi-agent diffusion score into pre-trained single-agent policies plus a gradient-free cost guidance term to generate coordinated behavior from single-agent data alone.
Muninn accelerates diffusion trajectory planners up to 4.6x by spending an uncertainty budget to decide when to cache denoiser outputs, preserving performance and certifying bounded deviation from full computation.
Path-Coupled Bellman Flows use source-consistent Bellman-coupled paths and a lambda-parameterized control-variate to learn return distributions via flow matching, improving fidelity and stability over prior DRL approaches.
SDGD uses cost-conditioned classifier-free guidance plus reward guidance with feasible trajectory relabeling to generate safe high-reward trajectories that adapt to changing safety budgets in offline RL.
Being-H0.7 adds future-aware latent reasoning to direct VLA policies via dual-branch alignment on latent queries, matching world-model benefits at VLA efficiency.
PRISM lets pre-trained text-to-image models handle long prompts by breaking them into compositional parts, predicting noise separately, and merging outputs via energy-based conjunction, matching fine-tuned models while generalizing better to prompts over 500 tokens.
ScoRe-Flow achieves decoupled mean-variance control in stochastic flow matching by deriving a closed-form score for drift modulation plus learned variance, yielding faster RL convergence and higher success rates on locomotion and manipulation benchmarks.
Advantage-guided diffusion (SAG and EAG) steers sampling in diffusion world models to higher-advantage trajectories, enabling policy improvement and better sample efficiency on MuJoCo tasks.
ReV is a referring-aware visuomotor policy using coupled diffusion heads for real-time trajectory replanning in robotic manipulation, trained solely via targeted perturbations to expert demonstrations and achieving higher success rates in simulated and real tasks.
GeCO replaces time-dependent flow matching with time-unconditional optimization, enabling adaptive inference and intrinsic OOD detection for robotic imitation learning.
DARE performs sample-level constraint relaxation in offline-to-online RL by conditioning on behavioral consistency with a behavior model via posterior-induced exchange, yielding improved fine-tuning stability and performance on D4RL benchmarks.
Frictional Q-Learning encodes supported actions as tangent directions on an action manifold using a contrastive variational autoencoder to reduce extrapolation errors in off-policy reinforcement learning.
MIMIC-D enables multi-modal multi-agent coordination via joint training of decentralized diffusion policies using only local information.
BeyondMimic combines compact motion tracking with a unified guided latent diffusion model to master diverse agile behaviors from human demos and solve unseen downstream tasks via test-time classifier guidance.
DSRL steers pretrained diffusion policies for robotics by applying RL to their latent noise inputs, achieving sample-efficient real-world adaptation with only black-box access.
BiTrajDiff augments offline RL datasets by running independent forward and backward diffusion processes from intermediate states, yielding higher performance than prior one-directional data-augmentation baselines on D4RL.
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.
SOM is an actor-critic algorithm that constructs the target velocity field for one-step MeanFlow policies directly from the Q-function via score estimation and probability flow ODE, achieving claimed SOTA on locomotion tasks with reduced training and inference time.
CARV amortizes upstream diffusion teacher costs over noise resamples with timestep importance sampling and stratified-inverse-CDF sampling, delivering 2-3x effective compute gains in text-to-3D experiments and order-of-magnitude variance cuts in single-step distillation.
Recasts sampling-based nonconvex optimization as smoothed gradient descent to obtain non-asymptotic convergence guarantees and introduces the DIDA annealed algorithm that converges to the global optimum.
Ada-Diffuser is a causal diffusion model that jointly learns observed interaction structure and underlying latent dynamics from minimal observations for adaptive planning and policy learning.
TFGN is an architectural overlay for transformers enabling task-free, replay-free continual pre-training across heterogeneous domains at LLM scale with near-zero backward transfer and high gradient orthogonality.
citing papers explorer
-
JEDI: Joint Embedding Diffusion World Model for Online Model-Based Reinforcement Learning
JEDI is the first online end-to-end latent diffusion world model that trains latents from denoising loss rather than reconstruction, achieving competitive Atari100k results with 43% less VRAM and over 3x faster sampling than pixel diffusion baselines.
-
Coordinated Diffusion: Generating Multi-Agent Behavior Without Multi-Agent Demonstrations
CoDi decomposes the multi-agent diffusion score into pre-trained single-agent policies plus a gradient-free cost guidance term to generate coordinated behavior from single-agent data alone.
-
Muninn: Your Trajectory Diffusion Model But Faster
Muninn accelerates diffusion trajectory planners up to 4.6x by spending an uncertainty budget to decide when to cache denoiser outputs, preserving performance and certifying bounded deviation from full computation.
-
Path-Coupled Bellman Flows for Distributional Reinforcement Learning
Path-Coupled Bellman Flows use source-consistent Bellman-coupled paths and a lambda-parameterized control-variate to learn return distributions via flow matching, improving fidelity and stability over prior DRL approaches.
-
Decoupled Guidance Diffusion for Adaptive Offline Safe Reinforcement Learning
SDGD uses cost-conditioned classifier-free guidance plus reward guidance with feasible trajectory relabeling to generate safe high-reward trajectories that adapt to changing safety budgets in offline RL.
-
Being-H0.7: A Latent World-Action Model from Egocentric Videos
Being-H0.7 adds future-aware latent reasoning to direct VLA policies via dual-branch alignment on latent queries, matching world-model benefits at VLA efficiency.
-
Long-Text-to-Image Generation via Compositional Prompt Decomposition
PRISM lets pre-trained text-to-image models handle long prompts by breaking them into compositional parts, predicting noise separately, and merging outputs via energy-based conjunction, matching fine-tuned models while generalizing better to prompts over 500 tokens.
-
ScoRe-Flow: Complete Distributional Control via Score-Based Reinforcement Learning for Flow Matching
ScoRe-Flow achieves decoupled mean-variance control in stochastic flow matching by deriving a closed-form score for drift modulation plus learned variance, yielding faster RL convergence and higher success rates on locomotion and manipulation benchmarks.
-
Advantage-Guided Diffusion for Model-Based Reinforcement Learning
Advantage-guided diffusion (SAG and EAG) steers sampling in diffusion world models to higher-advantage trajectories, enabling policy improvement and better sample efficiency on MuJoCo tasks.
-
Referring-Aware Visuomotor Policy Learning for Closed-Loop Manipulation
ReV is a referring-aware visuomotor policy using coupled diffusion heads for real-time trajectory replanning in robotic manipulation, trained solely via targeted perturbations to expert demonstrations and achieving higher success rates in simulated and real tasks.
-
Generative Control as Optimization: Time Unconditional Flow Matching for Adaptive and Robust Robotic Control
GeCO replaces time-dependent flow matching with time-unconditional optimization, enabling adaptive inference and intrinsic OOD detection for robotic imitation learning.
-
From Static Constraints to Dynamic Adaptation: Sample-Level Constraint Relaxation for Offline-to-Online Reinforcement Learning
DARE performs sample-level constraint relaxation in offline-to-online RL by conditioning on behavioral consistency with a behavior model via posterior-induced exchange, yielding improved fine-tuning stability and performance on D4RL benchmarks.
-
Frictional Q-Learning
Frictional Q-Learning encodes supported actions as tangent directions on an action manifold using a contrastive variational autoencoder to reduce extrapolation errors in off-policy reinforcement learning.
-
MIMIC-D: Multi-modal Imitation for MultI-agent Coordination with Decentralized Diffusion Policies
MIMIC-D enables multi-modal multi-agent coordination via joint training of decentralized diffusion policies using only local information.
-
BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusion
BeyondMimic combines compact motion tracking with a unified guided latent diffusion model to master diverse agile behaviors from human demos and solve unseen downstream tasks via test-time classifier guidance.
-
Steering Your Diffusion Policy with Latent Space Reinforcement Learning
DSRL steers pretrained diffusion policies for robotics by applying RL to their latent noise inputs, achieving sample-efficient real-world adaptation with only black-box access.
-
BiTrajDiff: Bidirectional Trajectory Generation with Diffusion Models for Offline Reinforcement Learning
BiTrajDiff augments offline RL datasets by running independent forward and backward diffusion processes from intermediate states, yielding higher performance than prior one-directional data-augmentation baselines on D4RL.
-
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.
-
Score-Based One-step MeanFlow Policy Optimization
SOM is an actor-critic algorithm that constructs the target velocity field for one-step MeanFlow policies directly from the Q-function via score estimation and probability flow ODE, achieving claimed SOTA on locomotion tasks with reduced training and inference time.
-
Variance Reduction for Expectations with Diffusion Teachers
CARV amortizes upstream diffusion teacher costs over noise resamples with timestep importance sampling and stratified-inverse-CDF sampling, delivering 2-3x effective compute gains in text-to-3D experiments and order-of-magnitude variance cuts in single-step distillation.
-
Global Convergence of Sampling-Based Nonconvex Optimization through Diffusion-Style Smoothing
Recasts sampling-based nonconvex optimization as smoothed gradient descent to obtain non-asymptotic convergence guarantees and introduces the DIDA annealed algorithm that converges to the global optimum.
-
Ada-Diffuser: Latent-Aware Adaptive Diffusion for Decision-Making
Ada-Diffuser is a causal diffusion model that jointly learns observed interaction structure and underlying latent dynamics from minimal observations for adaptive planning and policy learning.
-
TFGN: Task-Free, Replay-Free Continual Pre-Training Without Catastrophic Forgetting at LLM Scale
TFGN is an architectural overlay for transformers enabling task-free, replay-free continual pre-training across heterogeneous domains at LLM scale with near-zero backward transfer and high gradient orthogonality.
-
Policy-DRIFT: Dynamic Reward-Informed Flow Trajectory Steering
Policy-DRIFT combines conditional flow matching with terminal reward guidance and decoupled DRL to achieve 49% drag reduction in Re_tau=180 channel flow, 16% above DRL benchmarks and with 37 times less actuation energy.
-
Enforcing Constraints in Generative Sampling via Adaptive Correction Scheduling
Adaptive correction scheduling for hard constraints in generative sampling recovers 71% of stepwise projection benefits using 75% fewer corrections by focusing on trajectory-perturbing steps.
-
OGPO: Sample Efficient Full-Finetuning of Generative Control Policies
OGPO is a sample-efficient off-policy method for full finetuning of generative control policies that reaches SOTA on robotic manipulation tasks and can recover from poor behavior-cloning initializations without expert data.
-
Lucid-XR: An Extended-Reality Data Engine for Robotic Manipulation
Lucid-XR uses XR-headset physics simulation and physics-guided video generation to create synthetic data that trains robot policies transferring zero-shot to unseen real-world manipulation tasks.
-
Fisher Decorator: Refining Flow Policy via a Local Transport Map
Fisher Decorator refines flow policies in offline RL via a local transport map and Fisher-matrix quadratic approximation of the KL constraint, yielding controllable error near the optimum and SOTA benchmark results.
-
CMP: Robust Whole-Body Tracking for Loco-Manipulation via Competence Manifold Projection
CMP projects actions onto a learned competence manifold using a frame-wise safety scheme and isomorphic latent space to achieve up to 10x better survival in out-of-distribution scenarios with under 10% tracking loss.
-
Equivariant Asynchronous Diffusion: An Adaptive Denoising Schedule for Accelerated Molecular Conformation Generation
EAD is an equivariant diffusion model with adaptive asynchronous denoising that achieves state-of-the-art 3D molecular conformation generation.
-
SeedPolicy: Horizon Scaling via Self-Evolving Diffusion Policy for Robot Manipulation
SeedPolicy introduces self-evolving gated attention to extend the temporal horizon of diffusion policies, yielding 36.8% and 169% relative gains over standard DP on clean and randomized RoboTwin 2.0 tasks.
-
How Does the Lagrangian Guide Safe Reinforcement Learning through Diffusion Models?
ALGD augments the Lagrangian to locally convexify the energy landscape in diffusion models, stabilizing safe RL training and generation without changing optimal policies.
-
DAWM: Diffusion Action World Models for Offline Reinforcement Learning via Action-Inferred Transitions
DAWM introduces a modular diffusion world model with an inverse dynamics model to produce complete synthetic transitions that improve conservative offline RL algorithms like TD3BC and IQL on D4RL 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.
-
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.
-
IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies
IDQL generalizes IQL into an actor-critic framework and uses diffusion policies for robust policy extraction, outperforming prior offline RL methods.
-
Scaling Robot Learning with Semantically Imagined Experience
Augmenting robot datasets via diffusion-based semantic inpainting enables manipulation policies to solve unseen tasks with new objects and improves robustness to novel distractors.
-
Diverse Yet Consistent: Context-Guided Diffusion with Energy-Based Joint Refinement for Multi-Agent Motion Prediction
A context-guided diffusion model with energy-based joint refinement improves both marginal and joint metrics for multi-agent motion prediction on standard benchmarks.
-
Jointly Learning Predicates and Actions Enables Zero-Shot Skill Composition
PACTS jointly model action trajectories and predicate belief trajectories in a single generative policy, enabling zero-shot skill composition via symbolic planning without retraining.
-
SWEET: Sparse World Modeling with Image Editing for Embodied Task Execution
SWEET is a one-shot sparse visual planning framework that progressively generates manipulation keyframes via image editing conditioned on language and spatial guidance, then converts them to actions with a diffusion predictor, showing better fidelity and lower cost than video models on DROID and Rob
-
Behavioral Mode Discovery for Fine-tuning Multimodal Generative Policies
Unsupervised behavioral mode discovery combined with mutual information rewards enables RL fine-tuning of multimodal generative policies that achieves higher success rates without losing action diversity.
-
Insider Attacks in Multi-Agent LLM Consensus Systems
A malicious agent in multi-agent LLM consensus systems can be trained via a surrogate world model and RL to reduce consensus rates and prolong disagreement more effectively than direct prompt attacks.
-
Efficient Hierarchical Implicit Flow Q-learning for Offline Goal-conditioned Reinforcement Learning
Proposes mean flow policies and LeJEPA loss to overcome Gaussian policy limits and weak subgoal generation in hierarchical offline GCRL, reporting strong results on OGBench state and pixel tasks.
-
VGAS: Value-Guided Action-Chunk Selection for Few-Shot Vision-Language-Action Adaptation
VGAS uses best-of-N selection with a geometrically grounded critic and explicit regularization to improve success rates of few-shot VLA policies under limited data and distribution shifts.
-
HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds
HY-World 2.0 generates and reconstructs high-fidelity navigable 3D Gaussian Splatting worlds from text, images, or videos via upgraded panorama, planning, expansion, and composition modules, with released code claiming open-source SOTA performance.
-
Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models
The paper reviews the background, technology, applications, limitations, and future directions of OpenAI's Sora text-to-video generative model based on public information.
- Rectified Schr\"odinger Bridge Matching for Few-Step Visual Navigation