Multi-robot trajectory planning is a fundamental problem in multi-robot coordination but remains computationally challenging due to its nonconvex, multimodal, and high-dimensional nature. This work builds upon D4orm, a dynamics-aware diffusion-denoising framework, and develops a family of planning architectures for diverse operational requirements. Unlike conventional numerical optimization methods, D4orm employs sampling-based optimization to generate solution trajectories through massively parallel sampling, leveraging modern computing architectures such as GPUs. Its diffusion-denoising structure iteratively optimizes deformations to candidate control trajectories, providing an efficient and versatile paradigm for generating kinodynamically feasible and conflict-free trajectories. Using D4orm as the building block for advanced planners, we present a decoupled planner for improved scalability, an online receding-horizon planner with feedback control, and a distributed planner for resource-constrained settings. Evaluations with differential-drive and holonomic robots in 2D and 3D environments demonstrate that D4orm-based approaches find high-quality solutions faster and more reliably than other sampling-based optimization methods, such as MPPI, as well as a learned diffusion-model-based method. We further demonstrate zero-shot deployment on ten real quadrotors with obstacles, large-scale deconfliction with 100 simulated robots, and fully onboard distributed `lifelong' operation with six ground robots. Overall, these results establish diffusion denoising as a scalable and reliable framework for multi-robot coordination. Code and video: this https URL
https://arxiv.org/abs/2609.35651
Recent advancements in audio generation have been largely driven by Transformer-based diffusion models. However, these models suffer from quadratic complexity of self-attention, severely bottlenecking the long-form audio synthesis. To overcome this limitation, we propose MFlowAudio, a novel latent audio generation framework that synergizes the continuous-time dynamics of Flow Matching with a custom-designed TCMamba backbone. TCMamba uses an innovative dual-scan mechanism: a TimeMamba module to capture long-range causal dependencies with linear complexity, and a ChannelMamba module to model cross-channel correlations such as harmonic structures. Exploiting this structural foundation, we formulate the Stateful Flow Matching (SFM) paradigm. This framework inherently enables chunk-wise training and streaming generation, maintaining an $\mathcal{O}(1)$ caching complexity without incurring extra computational overhead. To enable fine-grained controllable synthesis, we devise a novel guidance mechanism that neutralizes vector field collisions precipitated by on-the-fly semantic transitions of prompts. Comprehensive empirical evaluations confirm that MFlowAudio yields generative fidelity on par with state-of-the-art baselines while establishing significant computational efficiency, achieving above $14.5$% acceleration in generation and facilitating perceptually seamless streaming synthesis with a constant latency of $1.8$ seconds. Demo: this https URL
https://arxiv.org/abs/2610.41852
Deep neural networks for time series classification (TSC) are trained almost exclusively by error backpropagation, which imposes update locking and the weight-transport problem. Backpropagation-free learning rules such as Direct Feedback Alignment (DFA), Direct Random Target Projection (DRTP), and the diffusion-inspired NoProp relax these constraints but have been evaluated almost exclusively on 2D image benchmarks. We adapt these three learners to univariate TSC with 1D convolutional architectures and present the first systematic study of them across 112 datasets from the UCR time series archive, with one hyperparameter-optimized configuration per method. The optimized learners reach mean F1 scores of 0.76 to 0.79, below ROCKET (0.83) and InceptionTime (0.84). We propose an analysis framework that relates the per-dataset gap to InceptionTime to dataset properties and tests convolutional feature learning by replacing the flatten readout with global average pooling, measured as a difference-in-differences (DD) against a backpropagation control on the identical architecture. Intra-class temporal variability is the dataset property most consistently associated with the gap for all three learners (partial Spearman $\rho$ from $0.28$ to $0.40$). Pooling harms DFA and DRTP more than backpropagation (DD $-0.025$ and $-0.055$), consistent with near-random convolutional features, whereas NoProp tolerates pooling as backpropagation does (DD $+0.013$). Relative to backpropagation on the same architectures, DRTP reduces training floating-point operations (FLOPs) by 33% and trains faster only on series longer than about 700 time steps, DFA yields no computational reduction, and NoProp reduces peak memory by 38% at the cost of 48% longer training.
https://arxiv.org/abs/2610.41805
Diffusion and flow matching visuomotor policies require iterative denoising or numerical integration for multimodal action generation, introducing latency and execution mismatch. We instead consider a different formulation: conditioned on vision and proprioception, demonstrated bimanual action chunks concentrate in a structured observation-dependent region of joint-action space, making the action target more direct to model than the generative process. Based on this view, we propose the Direct Manifold Action Transformer (DMAT), which reformulates action generation as the direct modeling of clean, observation-conditioned joint-space action chunks from stochastic interpolants, thereby enabling single-step inference without relying on iterative generative inference or auxiliary trajectory-straightening procedures. Within DMAT, local 3D geometry anchors predictions to spatial structure, while State-Consistent Spectral-Time Refinement (STR) reconciles predicted chunks with proprioception and suppresses high-frequency residuals. Across 567 standard and out-of-distribution (OOD) trials per method, DMAT outperformed Improved 3D Diffusion Policy (IDP3) and DiTFlow3D in aggregate success rate, achieving relative improvements of 129.1% and 95.7%, respectively, while generating action chunks 2.06x and 1.34x faster and remaining robust under repeated 50 N interventions. These results pave the way for a novel generative paradigm for efficient and robust bimanual manipulation.
https://arxiv.org/abs/2610.41643
The quality of image generation models trained with diffusion or flow matching is largely fixed by the training budget: at inference, the only available lever is the number of sampling steps, and additional steps improve quality only up to a point. We present a training recipe, Scout-Refine-Correct (SRC), that instead gives a flow-matching generator a genuine inference-time refinement capability. At each sampling step the model takes a scout rollout -- $K$ steps ahead along its own trajectory -- extrapolates a full-sample estimate, and feeds that estimate back to itself as a self-conditioning signal before taking the real step. This can be repeated for $R$ refinement rounds. Two correction losses, applied during training at states the model's own rollouts actually reach rather than only on the ground-truth path, teach the model to use this signal to reach new samples instead of collapsing to a suboptimal one. On ImageNet-256, SRC improves LightningDiT-B from FID~14.5 to FID~7.26 at NFE~550, matching a privileged best-of-$N$ baseline that uses an oracle FID verifier to choose among samples. SRC uses no external verifier, no reward signal, and, after ablation, almost no extra parameters over the base architecture. Combining SRC with best-of-$N$ improves the result further, to FID~3.81 at NFE~4400, showing that the two axes are complementary. We ablate the main design choices -- the architectural pathway for the scout signal, the scout horizon, each correction loss, and the training schedule to demonstrate key working components of training.
https://arxiv.org/abs/2610.41598
Unlike autoregressive (AR) models, diffusion language models (DLMs) permit parallel token updates, flexible generation, and bidirectional attention, but leading systems rely on costly pretraining or full-model fine-tuning. We present Build Your Own DLM (BYOD), a generalizable LoRA-only recipe for parameter-efficient AR-to-DLM conversion. Without architecture-specific tuning, BYOD induces diffusion generation in Gemma 2 9B, Llama 3.1 8B, Qwen2.5 7B, and Ministral 8B; to our knowledge, this is the first reported AR-to-DLM conversion of a Mistral model. The adapters comprise 4.1-5.8% of final parameters while every base-model parameter remains frozen; each 25,000-iteration conversion needs at most 102.4M tokens, processed in 3.1-4.0 hours on one Google Colab GPU. All four models generate from fully masked sequences, use bidirectional context in a controlled attention test, and retain substantial parent-model knowledge. BYOD-Gemma is the strongest BYOD conversion on our nine-task evaluation, reaching 50.6% average accuracy compared with 51.9% for LLaDA 8B Instruct in the same harness. Open-generation quality at low network function evaluation (NFE) budgets remains the principal limitation: BYOD perplexity is 8.3-11.1 versus 4.1 for LLaDA and 2.2-3.0 for the AR parents when generating 128 tokens in 64 steps. To enable further experimentation and inspection, we provide a standalone training and evaluation implementation and interactive demos for all four conversions. BYOD thus provides a practical route for extending diffusion generation to other existing model families while identifying the gap that efficient conversion must next close.
https://arxiv.org/abs/2610.41574
Decentralized federated learning (DFL) has emerged as a scalable alternative to centralized federated learning, removing the single point of failure and communication bottleneck at the server. However, most existing decentralized approaches rely on full-neighborhood broadcasting, where each client transmits its model update to all of its neighbors in each communication round. While effective, this results in significant communication overhead and high energy consumption. This paper applies spectral graph tools as lightweight client selection methods that leverage the graph topology by analyzing the spectral properties of the graph Laplacian over a fixed communication graph. Specifically, we exploit eigenvector embeddings and heat/diffusion kernel similarities to guide each client in selecting only a subset of structurally relevant neighbors, i.e., those that are most beneficial for the convergence of the federation process. This topology aware randomization matches or outperforms uniform neighborhood subsampling and approaches the accuracy of full broadcasting. The largest gains, about $3$ percentage points, emerge under strong data heterogeneity on larger, structurally rich graphs, while the total number of transmitted messages is reduced by $50\%$ compared to naive broadcasting.
https://arxiv.org/abs/2610.41570
Text-to-image diffusion models can reproduce memorized training content within localized image regions, making precise localization essential for targeted mitigation. However, curvature observations at a single denoising state can contain transient responses, while spatially uniform mitigation may disrupt prompt-relevant content. We present Trajectory-Aware Curvature Observation (TACO), a unified framework for local memorization detection and mitigation in diffusion models. Our empirical analysis reveals that memorization-related curvature becomes pronounced during late-stage denoising and persists at consistent spatial locations across neighboring states. Motivated by these observations, TACO aggregates prompt-dependent curvature responses along the late denoising trajectory and applies latent-guided spatial refinement to improve spatial coherence. The resulting memorization map serves both as a localization signal and as a spatial control signal for mitigation. Specifically, TACO uses this map to steer existing inference-time interventions toward memorization-related regions through spatial reweighting and localized guidance correction. Extensive experiments demonstrate that TACO consistently outperforms competing localization methods, and improves the Pareto trade-off between memorization suppression, semantic alignment, and perceptual quality. These results establish trajectory-aware spatial analysis as an effective link between memorization localization and targeted mitigation.
https://arxiv.org/abs/2610.41520
Long-context diffusion repeatedly pays for both token interaction and feed-forward computation. We formulate these costs as two separate budgets: the edges available to an attention graph and the experts activated for each token. This view connects local, dilated, and global attention with conditional expert computation without assuming that sparsity alone preserves document-level information. We specify normalized masked attention, distinguish denoising depth from sampling iterations, and derive graph and compute bounds. A reported sparse-expert configuration, denoted DualBudget, is analyzed across scientific summarization, multi-hop question answering, dialogue, and sentence-pair prediction. All supplied table measurements are retained. The length study shows gains over the listed baselines through 16K, together with measurable degradation as length increases. Ablations reveal mixed changes across the three reported scores, while the cost record indicates a 20% reduction relative to DiffuSeq under an unspecified timing convention. The analysis separates these observations from unmeasured claims about training speed, absorbing states, global coherence, and deployment memory.
https://arxiv.org/abs/2610.41487
Embodied world models should not only imagine plausible futures, but also perceive the geometric, semantic, and motion structure of the evolving world. We present GenSight, a unified embodied world model that brings future video generation and dense perception into a single pretrained video diffusion transformer. GenSight uses a unified spatiotemporal representation for video, depth, embodiment segmentation, and first-frame-relative 2D flow. Built on a shared DiT backbone, GenSight uses lightweight task modulation to predict all modalities within the same architecture. All tasks are jointly optimized within a unified velocity prediction space. At inference, GenSight supports two complementary modes: multi-step future video generation with aligned dense predictions and single-step dense perception from an observed video. By unifying modality representation, model architecture, and prediction space, GenSight avoids separate modality-specific pipelines and couples appearance, geometry, semantics, and motion in a shared representation. It promotes cross-modal consistency and allows dense perception to benefit from the spatiotemporal priors learned through video generation. Trained on embodied manipulation data spanning multiple robot embodiments and human-hand interactions, GenSight demonstrates strong performance in both video generation and dense 4D perception, highlighting the effectiveness of unifying seeing and imagining for embodied world modeling.
https://arxiv.org/abs/2610.39232
General humanoid motion trackers typically rely on deterministic policies that cannot adapt online without brittle reference editing or costly retraining. We present DiffWBC, shifting whole-body control to a generative paradigm via a one-step diffusion model. By modeling distributions over future trajectories, DiffWBC unifies general tracking, test-time steering, and simulation-free failure discovery within a single controller: (1) Generative general tracking: DiffWBC requires a single forward pass per 50 Hz control step and can be distilled from an RL teacher or trained from scratch via model-based RL, achieving the lowest local tracking error among six general trackers on held-out benchmarks (20.1 mm on BONES) and deploying on a physical Unitree G1. (2) Zero-shot test-time steering: differentiable cost gradients and body-group masks modulate the frozen controller online, substantially outperforming kinematic reference editing (0.84 clean pass at 1.25 m ceiling vs. 0.10) and zero-shot generalizing across hurdles, spatial reaching, actuator faults, and tray balancing. (3) Simulation-free failure discovery: plan dispersion across generation noise effectively identifies physical tracking failures (91% precision in top 2%) without physics simulations; targeted fine-tuning on flagged clips resolves 50% of failure cases. Videos and interactive demonstrations are available at this https URL.
https://arxiv.org/abs/2610.41354
Motion planning in clutter is embodiment-specific: the feasible free space and reachable commands depend on each robot's geometry and dynamics. Existing cross-embodiment policies output normalized commands that disregard these differences, or compensate through per-robot training and distillation. World models can in principle pool cross-embodiment data, yet command-conditioned models bind their latent dynamics to a single action space, while pose-conditioned models omit the mapping from commands to body-specific motion. On flat ground, however, embodiment affects the planner's observations only through the camera ego-motion. This letter proposes Hourglass, an hourglass-shaped architecture that factorizes cross-embodiment motion planning at this interface: a body-agnostic world model and each robot's differentiable ego-dynamics, which map commands to that ego-motion, are coupled only through it. The world model is trained on data pooled across embodiments and camera mounts; each robot's ego-dynamics is a reduced-order template with identified physical parameters. A generalist parameter-conditioned policy is learned once at this junction: each imagined step rolls out the template and then the world model, and imagination training through each robot's template makes the policy body-aware. On seven simulated robots of five locomotion types, the generalist policy outperforms imitation-learning and diffusion-policy baselines on the same world model by 3.8--10.6 percentage points in success rate and matches per-robot specialists without dedicated training, while approaching its parameter-conditioned MPPI teacher within 1.4--2.8 points without an online map. After three minutes of teleoperated driving for identification, the synthetic-data-trained model transfers zero-shot to a real skid-steer robot unseen in training, navigating unseen indoor scenes.
https://arxiv.org/abs/2610.41330
Generating small molecules to target protein-protein interactions (PPIs) remains one of the most challenging yet high-reward frontiers in drug discovery. Unlike traditional small-molecule drugs that bind to deep, well-defined pockets, PPI interfaces often comprise broad, shallow binding surfaces. A natural strategy is to leverage known peptide-target interactions, as peptide ligands provide rich interface-level constraints. However, a major algorithmic challenge is that rigid atom-level conditioning on peptide structures can over-constrain the generative space and exclude valid small-molecule solutions. To address this challenge, we present PIFT (Peptide InterFace Transfer), a novel framework that transfers peptide-target interaction patterns to small molecules through joint sampling-time guidance of masked discrete diffusion and continuous flow matching. PIFT first maps peptide-target and small-molecule-target interfaces into a shared, target-conditioned interaction space, capturing transferable interface information across molecular modalities. The resulting peptide-derived reference then jointly steers building-block logits and 3D coordinates toward peptide-compatible molecules while preserving a strong adapted molecular prior. Extensive experiments across diverse PPI targets show that the learned representation captures cross-modal interaction compatibility, while peptide guidance improves interface recovery and achieves strong docking performance and favorable molecular properties.
https://arxiv.org/abs/2610.41322
Existing sketch generation methods often rely on image guidance and are largely limited to individual objects or simplified scenes, leaving text-guided complex scene sketching underexplored. We present SketchDirector, an agentic framework that mimics the human sketching workflow for automatic multi-concept scene sketching. Given a scene-level text prompt, SketchDirector first employs a large language model~(LLM) to decompose the scene into multiple draft assets, where each is represented by a set of Bézier curves. Then, an agentic reasoning loop iteratively plans and executes their spatial arrangement, guided by self-evolving memory. Finally, a detail refinement module leverages diffusion priors to enhance sketch quality while preserving geometric structure. To support future research and applications in multi-concept scene sketch generation, we further introduce the \textit{MCSketch8K} dataset, comprising editable vector assets, compositional layouts, and object-level manipulation annotations. Extensive experiments show that SketchDirector outperforms state-of-the-art baselines in semantic and compositional quality while effectively preserving overall contour organization during refinement. The project page is: \href{this https URL}{this https URL}.
https://arxiv.org/abs/2610.41260
Monocular depth estimation is a fundamental capability for 3D spatial perception in robotic and intelligent systems. While data-driven discriminative methods have achieved compelling performance for monocular depth estimation, generative approaches can reconstruct fine structural details with stronger generalization. However, most existing generative diffusion models suffer from low inference efficiency caused by multi-step sampling, whereas single-step diffusion models struggle to recover high-fidelity depth maps. To mitigate these drawbacks, this paper presents FlowMoDE, a coarse-to-fine flow-matching-based framework for efficient, structure-aware monocular depth estimation supporting sim-to-real and cross-scene generalization. The core architecture first conducts coarse-level decoding conditioned on diffused features extracted from a pre-trained semantic encoder, and subsequently restores fine-grained structural patterns via expanded decoding layers. Trained exclusively on a single synthetic indoor dataset, our proposed method outperforms prior methods across five real-world indoor and outdoor datasets, yielding an average 14.1% reduction in relative error against state-of-the-art works as well as 9.9\% reduction in chamfer distance for point cloud reconstruction. We further validate the generalization capability of FlowMoDE on realistic robotic scenes, with qualitative comparisons against state-of-the-art methods. The project page is this https URL
https://arxiv.org/abs/2610.41190
Synthesizing realistic tumors on medical images helps address data scarcity for clinical AI. Existing diffusion-based methods, however, lack fine-grained attribute-level controllability, closed-loop quality verification, and awareness of which morphological patterns are underrepresented in the target distribution. We present MATS, a multi-agent framework for text-controllable, cross-organ tumor synthesis. Given a target disease, MATS first profiles its morphological distribution over a fine-grained attribute space covering tumor geometry and appearance, and constructs a generation plan that amplifies underrepresented subtypes while keeping common ones dominant. It then localizes the target organ, proposes anatomically valid placement, and executes two-stage diffusion to produce the tumor mask and render texture, each conditioned on the corresponding attributes. A closed-loop reflective mechanism verifies attribute alignment at three checkpoints throughout synthesis and provides targeted feedback to guide re-generation when misalignment is detected. Trained exclusively on a single-source pancreatic neuroendocrine tumor dataset, MATS consistently improves downstream segmentation both in-domain and across LiTS, KiTS, and MSD-Pancreas benchmarks, whereas most prior generative augmentation methods fall below real-only training.
https://arxiv.org/abs/2610.41159
Computer vision models learn hand action only from its visual consequences, without access to the underlying embodied motor signals. We address this absence with MotorSense, the first large-scale paired egocentric video and surface electromyography (EMG) dataset. MotorSense pairs bimanual EMG bands with egocentric video and yields synchronized video, bimanual EMG and IMU, and audio across 100 hours of unscripted manipulation. EMG offers a powerful scalable alternative to manual annotation: it captures finger movement, hand configuration, and the forces exerted between hand and environment as a dense signal free of occlusion and labeler bias, whereas manual annotation is costly, subjective, and unreliable under occlusion. We use MotorSense to learn sensorimotor alignment, producing an organization of action that is shared across the visual and motoric spaces, through cross-modal pre-training between video and EMG. The resultant vision models are then transferred to downstream tasks that benefit from sensorimotor alignment: in this case, action recognition, 3D hand reconstruction, and 3D contact reconstruction. We further demonstrate a generative application in which EMG motor signals are used to condition a video diffusion model, yielding videos of fine-grained hand manipulation. Across four action-centric computer vision tasks and eight popular video datasets, we demonstrate that sensorimotor alignment provides a stronger foundation for visual representation learning than conventional self-supervised learning methods over video, outperforming every baseline across all tasks and datasets evaluated.
https://arxiv.org/abs/2610.41127
Recent diffusion-based methods have substantially advanced image editing, yet parametric 3D control at the part level remains challenging. Existing approaches either operate on whole objects with manual rigging, or revert to 2D handles at the part level. They also struggle to model appearance and texture under large transformations, leading to unrealistic outputs in geometry-intensive edits. To address these limitations, we introduce RADI3N, a framework for semantically-grounded part-aware object manipulation with parametric 3D control. Our CS-ARAP deformation module suppresses rotation-field discontinuities at part boundaries via neighborhood covariance smoothing, producing structurally consistent deformations under complex part-level edits. We further introduce an inversion-free selective texture transfer mechanism that suppresses high-frequency positional biases and scales up low-frequency semantic cues within cross-image attention. This eliminates strict spatial bias and supports semantic matching, allowing source appearance to follow the edited part onto its new geometry. Experiments demonstrate that RADI3N achieves state-of-the-art performance in geometric fidelity, viewpoint consistency, and controllability.
https://arxiv.org/abs/2610.40973
Training acceleration methods for diffusion transformers, such as REPA and dispersive regularization, are commonly explained by additional supervision, spatial-structure priors, or improved feature geometry. We revisit this view and uncover a striking internal change: the AdaLN-Zero residual gate $\alpha$, which directly controls how conditioned updates enter the residual stream, is substantially reorganized by these methods. This observation motivates our hypothesis that acceleration arises, at least in part, from reshaping the residual gating pathway rather than solely from the feature structures explicitly imposed by auxiliary objectives. Supporting this view, accelerated models are markedly more sensitive to perturbations of $\alpha$, and their gate geometry reflects semantic relationships among classes. We further introduce the normalized participation ratio (nPR) to characterize the channel-wise organization of the gates and find that, across REPA teachers, projector architectures, and radial-objective targets, broader gate participation accompanies better generation quality. Guided by this insight, we propose a simple teacher-free radial objective that promotes broader gate participation through feature-norm regularization, without pairwise feature comparisons. On ImageNet $256\times256$ with SiT-B/2, our method improves FID over dispersive loss while increasing mean gate participation over timesteps and classes, further supporting the link between gate organization and training acceleration. Our results identify residual-gate reorganization as a measurable axis of diffusion training acceleration and suggest a simple direction for further acceleration.
https://arxiv.org/abs/2610.40914
Continuous diffusion language models (CDLMs) and speculative drafters offer efficient language generation but are typically evaluated differently: CDLMs generate independently through iterative refinement, whereas drafters propose text for target-model verification and correction. We compare their architectures without verification, using LangFlow for CDLMs and adapting DSpark's Markov and recurrent-head architectures for standalone generation. All models are trained from scratch for unconditional, single-block OpenWebText generation at lengths 16, 128, and 1024, without target features or verification, using common preprocessing, backbone dimensions, and training-update budgets. We evaluate generation perplexity (GenPPL) with an external language model and distributional similarity to reference text with MAUVE. With default denoising steps equal to sequence length, LangFlow outperforms both DSpark variants on both metrics at lengths 128 and 1024, while DSpark-RNN leads at 16. A conditional KL analysis characterizes dependencies excluded by the Markov head's previous-token conditioning. Recurrent memory removes this restriction and improves both metrics, but the longer-sequence gap persists. Teacher probability matching further lowers Markov GenPPL without observed MAUVE gains. Increasing LangFlow's denoising steps at fixed weights improves both metrics at lengths 16 and 128, changing the length-128 ordering relative to DSpark-RNN. These results establish LangFlow's longer-sequence advantage under the evaluated budgets and highlight iterative full-sequence refinement as a route to improving standalone generation beyond gains from recurrent head memory.
https://arxiv.org/abs/2610.40847