animation software developers

Abstract: Large-scale vision, language, and video pretraining has substantially improved the perception and generalization capabilities of robotic manipulation models, but action generation for complex dexterous manipulation remains constrained by the scarcity of robot demonstrations. Limited robot demonstrations must be used to learn both action representations and task-conditioned action distributions, making it difficult to adequately learn action representations and, in turn, limiting the ability of downstream generative models to generate complex dexterous actions. To address this limitation, we propose ARPG (Action Representation Pretraining and Generation), which explicitly separates action representation learning from action generation: we first pretrain an action representation encoder on large-scale human manipulation data. We then freeze the encoder and train a compact generative backbone (130M parameters) to learn task-conditioned action distributions in the encoder's representation space. Experimental results show that ARPG achieves state-of-the-art performance on the DexJoCo benchmark and improves the average success rate on bimanual dexterous manipulation from 10.1% for $π_{0.5}$ to 44.7%. Scaling experiments further show that broader coverage of human manipulation behaviors effectively improves downstream performance. These results indicate that action representation pretraining provides an independent scaling dimension for improving complex dexterous manipulation capabilities.

Abstract: We introduce TrackTok, an efficient video tokenization framework that produces object-centric tokens, i.e., tokens that consistently encode the same semantic objects across time, even as it moves, deforms, or undergoes partial occlusion. Conventional patch-based or existing holistic tokenizers produce token identities often tied to fixed image locations. In contrast, our approach learns temporally persistent object-centric representations that bind visual features across frames into stable semantic units. This enables substantially more compact, continuous latent video representations, reducing the number of tokens required for downstream generative modeling with state-of-the-art flow models, while preserving the semantic structure needed for high-quality synthesis. Our tokenizer offers a favorable quality-efficiency trade-off. TrackTok achieves comparable class-conditional generative FVD on UCF-101 dataset at 8 times fewer latent tokens and better latency, and outperforms existing 1D tokenization baselines on frame prediction task on Kinetics-600 across low token budgets. These results suggest that object-aligned and temporally persistent tokenization is a promising direction for scalable video generation, where reducing latent token counts is critical for efficient modeling. Our code for this work is available at https://github.com/phamleyennhi/tracktok.

Abstract: Long-horizon video generation requires retaining an ever-expanding history, but conditioning on its growing token sequence is costly. Existing methods restrict or compress historical context, potentially losing information needed for future generation. This work proposes ReCam, which groups local spatiotemporal blocks of historical latents into vectors and projects them directly into the high-dimensional hidden space of a Diffusion Transformer. The model learns to use the resulting memory tokens through native self-attention, reducing token count while retaining block-level access to the full history. To mitigate temporal drift during autoregressive rollout, we further introduce dual-pointer denoising with separate noise schedules for recent context and target frames. Among the evaluated methods, ReCam achieves the highest VBench-Long overall score of 80.1 and competitive static-scene revisitation performance on R2M-Bench. It also leads on all four consistency metrics for off-screen subject reappearance, including clothing consistency of 4.09 versus 3.03 for the best baseline.

Abstract: Trajectory optimization methods, from sampling-based zero-order to gradient-based first- and second-order approaches, require many evaluations of dynamical system functions, i.e., functions derived from a robot's dynamical model, such as forward kinematics and their Jacobians and Hessians. These evaluations are largely independent, e.g., across sampled trajectories or time steps, and can thus be evaluated in parallel as a batch. When used to make decisions online, these methods require low latency, i.e., each batch must complete in as little wall-clock time as possible. Existing frameworks utilize modern GPU hardware primarily to parallelize across batch instances, thereby optimizing throughput but not latency. We present CusADi2, a software library that reduces the batch evaluation latency by additionally parallelizing computation within each batch instance. We benchmark forward kinematics, Jacobians, and Hessians for all 67~robots in the MuJoCo Menagerie, including arms, hands, quadrupeds, humanoids, and biomechanical models, against MuJoCo XLA, MuJoCo Warp, frax, CusADi, and CasADi. CusADi2 achieves lower latency than all baselines at batch sizes of 64 to 4096, while matching them at larger batch sizes. We also demonstrate the performance advantage of CusADi2 in a sampling-based control application. All code is open-source at: https://github.com/johnviljoen/cusadi2

Abstract: A shared latent space is often assumed to make representations from different schemas directly interchangeable, yet sharing parameters, dimensionality, or a prior does not determine how corresponding instances are expressed in latent coordinates. We show that this assumption conflates recoverable correspondence, direct compatibility, and decoder reuse. In a controlled multi-schema motion VAE on HumanML3D, even identical inputs yield only $5.9$--$17.7\%$ raw Recall@1 and $0.221$--$0.484$ paired-token cosine, despite correspondence being almost perfectly recoverable after linear calibration. Cycle consistency strengthens recoverability but still leaves direct retrieval and token agreement near zero. In contrast, only $64$ paired clips raise raw Recall@1 to $88.4$--$90.3\%$ and token cosine to approximately $0.82$, making most post-hoc alignment unnecessary, although crossed decoding remains substantially worse than native reconstruction. We further find that reducing measured marginal discrepancy does not imply schema invariance. These results show that a shared backbone or prior does not ensure directly compatible latent coordinates, while limited paired correspondence can substantially improve direct compatibility in the tested setting.

Abstract: Regression-based RL for flow models mandates sampling \emph{without} classifier-free guidance (CFG) to align the rectification target with the reference marginal velocity. Extending Advantage-Weighted Rectification (AWR), which dynamically scales this regression target based on reward, to video generation encounters a cold-start pathology: unguided rollouts collapse into low-fidelity regions where intra-group reward gaps remain wide but no longer track perceptual quality, rendering the optimization target arbitrary. Conversely, utilizing guided rollouts to restore fidelity, while keeping the regression target tied to the guided sampling distribution, provably triggers a geometric guidance blow-up under exponential-moving-average (EMA) updates. We propose \textbf{VideoAWR}, which resolves this tension by untying sampling from the optimization anchor. An EMA reference policy generates \emph{guided} rollouts to restore reward separability, while the trainable policy is rectified against the \emph{unguided} conditional anchor. We prove this decoupled objective is mathematically exact: the centered advantage cancels the anchor in expectation, filtering out the reward-neutral guidance offset and retaining only the reward-correlated covariance increment. Consequently, inference runs single-branch and CFG-free, yet inference-time CFG preserves its original semantics. Furthermore, we introduce \emph{Decoupled Timestep Rectification}, supervising each rollout at an independently sampled timestep without bias to improve sample efficiency. Experiments on Wan2.1-1.3B and 14B demonstrate stable optimization and superior visual and motion quality in \emph{both} CFG-free and CFG-enabled regimes. Code is available at \pdfstartlink attr{/Border [0 0 0]} user{/Subtype /Link /A << /S /URI /URI (https://github.com/Fuzm7/FlowAWR) >>}% \textcolor{pearDark}{VideoAWR}\pdfendlink.

Abstract: Physics-based human-object interaction has achieved robust single-agent manipulation skills, yet extending them to multi-agent cooperative tasks remains challenging. Existing approaches typically adapt interaction policies through task-specific fine-tuning, which entangles low-level contact-rich execution with high-level coordination and limits reuse across object geometries, interaction types, and team sizes. We propose a hierarchical framework that converts a single-agent HOI policy into a reusable Object-oriented Motion Skill. Specifically, we reinterpret teacher rollouts as object-oriented action supervision by extracting short-horizon object-proxy motions from executed trajectories, and distill task-specific teachers into a low-level skill operating in an Object-oriented Action Space. For downstream tasks, the distilled skill is frozen as a reusable executor, while a high-level policy coordinates multiple agents by generating region-wise object-oriented actions conditioned on the shared object, task goal, agent states, and local manipulation regions. This formulation shifts multi-agent HOI learning from direct contact-rich full-body control to compact object-level proxy-motion coordination. Experiments on diverse HOI tasks show that the distilled Object-oriented Motion Skill supports robust proxy-motion execution and enables composable policy learning across different interaction types, object geometries, and team sizes.

Abstract: Despite recent advances in video generation, motion customization remains challenging due to content leakage, where appearance attributes from the reference video unintentionally propagate into the generated output. We identify this issue as a consequence of the generative process collapsing toward the reference video, which arises from formulating the learning objective as a direct regression on the reference. To address this, we propose Control-based Motion Customization (CMC), a principled training framework that is structurally robust to content leakage. Our key idea is to steer generative dynamics toward desired motion while avoiding collapse toward the reference video, which we formalize using Stochastic Optimal Control (SOC). Under this formulation, customized videos acquire the target motion yet remain within the pre-trained model's prompt-conditional distribution, where appearance is determined by the text prompt rather than the reference video. Furthermore, to improve efficiency, we tailor the SOC formulation to motion customization by eliminating the need for an explicit reward and introducing a timestep-adaptive motion cost that focuses only on early generative stages, accelerating training by 2.5 times. Extensive experiments demonstrate that CMC effectively mitigates content leakage and achieves competitive motion fidelity while preserving the diversity of the base model across diverse scenarios.

Abstract: In this paper, we present trajectory-aware reuse and adaptive correction (TRAC), a training-free framework for efficient autoregressive (AR) video generation. Existing acceleration methods mainly target single-trajectory generation with bidirectional attention. AR video generation, by contrast, sequentially couples chunk-level denoising trajectories. Consequently, approximation errors accumulate and propagate through the generation process. TRAC addresses this challenge with three components, including robust cumulative scheduling (RCS), autoregressive trajectory-aware guidance scheduling (ATGS), and spectral structure correction (SSC). RCS selects cache reuse schedules by cumulative rollout error and cross-chunk/prompt variation. ATGS coordinates CFG refreshes along the global AR trajectory. SSC restores low-frequency structure of the first chunk to correct long-term structural loss. Experiments on SkyReels-V2 and FramePack-F1 show that, compared with existing methods, TRAC achieves both the highest inference efficiency and the best generation quality for AR video generation.

Abstract: Legged robots can learn expressive whole-body skills from the motions of humans and animals. Due to the morphology gap between the source and the robot, however, the motion must be tailored to the dynamic properties of the robot. In particular, dynamic motions such as a jump require careful adjustment, since their timing and control are interdependent. We propose dense temporal motion retargeting (DTMR), which jointly optimizes timing and control within a single optimization, where dense means that the timing is adjusted for every control step. This dense formulation enables DTMR to deform only the parts of the motion that need a change in timing. The problem is solved with sampling-based model predictive control (MPC) in parallel on a GPU. We evaluate DTMR against baselines on two hours of human motion with four humanoid robots, where the results show that DTMR outperforms baseline methods, particularly on dynamic motions. We also show that allowing more temporal deformation yields more precise retargeting. We further compare DTMR with a baseline that optimizes the temporal dimension, where the result shows that DTMR retargets more precisely under the same deformation budget while being ~19x faster. Lastly, policies trained on our references transfer to a real humanoid robot.

Abstract: Cross-skeleton motion generation trains generative models to carry action structure and motion intention from one body to another. Yet a target motion that shows the right action has two explanations that the training data cannot tell apart: the model transferred the source clip, or it recovered a typical motion for the requested action. We show that this ambiguity is structural rather than incidental: under standard generative objectives, the source-conditioned retargeting map is non-identifiable in sparse heterogeneous motion domains. Unpaired distribution matching yields gauge non-identifiability: the latent spaces of different skeletons can be transformed relative to one another without changing the training evidence, so different source-conditioned maps fit it equally well. Sparse paired supervision admits the complementary failure mode, \emph{conditional-mean degeneration}: when clips are paired only by action, squared-error training converges to an average target motion that ignores the source clip. To make the missing evidence observable, we introduce Source-Instance Fidelity (SIF), a diagnostic that tests whether outputs differ from one another the way their source clips do, with the target skeleton and action held fixed. Under this diagnostic, methods that succeed at the standard action-level test on animal motion data often sit at the source-blind floor, while the methods that rise above it retain only a partial relational signal. Retargeting therefore needs objectives and evaluations that can identify the source-conditioned map it claims to learn. Project page: https://cross-skeleton-retargeting.netlify.app/.

Abstract: In constrained motion planning problems, task and loop-closure constraints restrict a robot's motion to a curved, lower-dimensional submanifold of its configuration space. Planners measure path length with a metric, which sets the cost of moving in each direction. Under the Euclidean metric, this cost is the same everywhere, whereas under a general Riemannian metric, such as the kinetic-energy metric, the cost can vary with direction and configuration. Existing methods often describe the submanifold either implicitly, as a constraint level set, or explicitly, through a parameterization. The implicit representation is typically combined with the Euclidean metric of the configuration space, and the explicit representation with the parameter domain, so the path length that a planner minimizes depends on the representation. Instead, we measure path length with the induced metric, which the submanifold inherits from a Riemannian metric on the configuration space. The implicit and explicit representations yield the same induced metric, expressed in different coordinates, and hence the same geometry. This result holds for any Riemannian metric on the configuration space, not only the Euclidean one. The choice of metric is therefore independent of the choice of representation. Using this result, we extend planning under a Riemannian metric from unconstrained spaces to constraint submanifolds by applying the induced metric in both a sampling-based planner and a trajectory optimizer. For an explicit representation, the induced metric also accounts for the distortion that the parameterization introduces. In experiments on a bimanual manipulation setup with two Franka arms under end-effector task constraints, we compare the Euclidean and kinetic-energy metrics.

Abstract: Learning a motion prior requires a reward that guides a policy from its current behavior toward demonstrated motion. Adversarial Motion Priors (AMP) provide such a reward with a discriminator. However, adversarial objectives can become uninformative when policy and expert supports are far apart. A naive use of optimal transport (OT) averages matched expert successors into a barycentric target. Averaging across gait phases can weaken the target's joint motion. We introduce Flow-Matched Motion Priors (FMP), an online scalar reward learned from paths connecting current rollout histories to an expert motion bank. Entropic OT supplies the coupling. Before each policy update, we train a neural potential with flow matching (FM) along the rollout-to-expert paths, endpoint-gradient supervision, and relative-value calibration. The actor receives only physical observations and the reward remains a scalar, as in AMP. Controlled reward-model experiments show substantially better generalization beyond the fitting rollout than value-only or endpoint-only fitting. On Unitree G1, matched 50-million-transition experiments compare FMP with AMP, a barycentric OT reward, and nested ablations under demonstration and fixed-pose initialization. FMP produces stable forward walking at 0.727 m/s from demonstration resets and 0.338 m/s from a fixed default pose. In the fixed-pose condition, it incurs 129 falls versus 243 for the endpoint-only control. Against a static score-gradient teacher, dynamic FM reduces score-increment error at interpolation fractions 0.25 and 0.50 while using 29% less offline fitting time.