Tracking
-
GRASP: Gradient-Guided Sampling for Contact-Rich Physics-Based Motion Retargeting
2026-11-03 23:53:22Yang Liu, Tong Wang, Yiming Bao, Heng YangAbstract
We study physics-based retargeting of human demonstrations for robot learning: finding robot controls that reproduce reference motions under contact dynamics. We propose GRASP (Gradient Recovery from Archived Samples for Proposals), which combines sampling-based exploration with gradient-guided refinement without requiring a differentiable simulator. GRASP-TO extends tempered sequential Monte Carlo by fitting local quadratic cost models to archived rollouts and using their gradients to guide Markov chain Monte Carlo rejuvenation. Metropolis-Hastings correction preserves the target distribution for each fixed proposal kernel, and a population analysis connects the recovered gradients to Gaussian smoothing. GRASP-MPC scales this optimizer to long demonstrations through warm-started receding-horizon planning. Experiments on dexterous hands and humanoids show accurate retargeting with a shared tracking objective and no task-specific contact rewards, including 92.8% success on 1352 bimanual OakInk2 demonstrations. The refined references improve PPO tracking in pen spinning and humanoid-object interaction. We also demonstrate dexterous manipulation and whole-body humanoid motion on real hardware.
Abstract (translated)
URL
https://arxiv.org/abs/2611.05754
PDF
-
Anchored Slice Propagation with Boundary Transport for 3D CT Segmentation from Three Orthogonal Annotated Slices
2026-11-03 22:21:39Tushar Kataria, Md Rakibul Haque, Shireen Y. ElhabianAbstract
Sli2Vol propagates a binary mask through affinities between adjacent slices, but an error can persist because each prediction becomes the input to the next step. Three orthogonal annotations reduce dependence on any one chain, yet they offer more than three starting masks: where a chain crosses another annotated plane, the correct label is already known. Those labels could correct drift during propagation and indicate how much to trust each chain at fusion. Between annotated planes, the information carried by the chain may matter as well. A binary mask records foreground membership but discards distance to the boundary, a cue that could help follow gradual shape changes between this http URL address these two sources of error with a fixed pretrained affinity backbone. We anchor each chain by correcting its prediction where it crosses another annotated plane, then use its agreement with those labels to weight fusion. We compare this anchored mask with two ways of transporting boundary geometry: a truncated signed-distance field (SDF) propagated by dense affinity averaging, and a contour whose vertices follow motion cues from the same affinity. The contour tracker starts from a hand-crafted rule and learns a motion correction from supervoxel pseudo-objects in 506 CT volumes, without manual organ labels. On 2,091 held-out structure instances from approximately 403 CT scans spanning 17 abdominal structures, anchoring raises mean Dice from 0.737 with orthogonal mask propagation to 0.769 and improves every structure. Beyond the anchored mask, learned contour tracking improves Dice by 5.7\% for the esophagus and 5.9\% for the postcava, while SDF transport improves right-adrenal Dice by 2.8\%. The anchored methods have similar mean Dice (0.769--0.772); contour tracking performs worse on the kidneys, stomach, and hepatic vessel tree.
Abstract (translated)
URL
https://arxiv.org/abs/2611.05693
PDF
-
When to Ask, When to Answer: Strategic Clarification for Ambiguous Reference Resolution in Dialogue
2026-11-03 19:14:42Ibrahim Khebour, Nikhil KrishnaswamyAbstract
For humans, referential disambiguation is a collaborative process involving clarification questions asked when they will meaningfully change the outcome. However, large language models (LLMs) have been shown to be biased toward premature answering, preferring definite single-turn responses over more clarification exchanges. In this paper, we study the problem of "strategic clarification" -- asking clarification questions in a reference game when their answers will narrow the set of candidate referents. We construct a controlled test environment from the SIMMC 2.1 dataset that records how many questions each ambiguous reference needs to be successfully resolved, and examine how baseline LLM behavior and common post-training methods ask clarifying questions vs. attempt to answer the referent. We also propose BACE (Belief-Aware Critic with Epistemic tracking), a lightweight action chooser method on top of a frozen LM backbone, and show that BACE more consistently chooses the optimal number of clarifying questions than methods such as GRPO and ArCHer.
Abstract (translated)
URL
https://arxiv.org/abs/2611.05517
PDF
-
Ctrl-F: Force as an Interface for Humanoid Loco-Manipulation
2026-11-03 19:04:27Mengjie Zhao, Yuxin Chen, Yiyang Shao, Chuye Hong, Jiakang Chen, Koushil Sreenath, Masayoshi TomizukaAbstract
Humanoid motion tracking has scaled to general policies that reproduce diverse human motion, but the resulting behavior is in free-space: the tracker knows where the body should be, not how it should interact with the environment. Other work makes the object part of the objective, yet abstracts that interaction to contact or geometry, which leaves the demanding cases under-explored. We argue that force is a natural command channel between motion imitation and object interaction, one that specifies not just where to make contact but how hard. We present Ctrl-F, a hierarchical motion-force framework that augments motion tracking with an explicit force command, a 3-D force at each designated contact body such as a hand or a foot. The hierarchical framework comprises: (1) A unified motion-force controller tracks the reference motion while applying the commanded force to the world. (2) A high-level force planner that issues a force command online based on object state and proprioception observations. In simulation and on hardware, Ctrl-F completes loco-manipulation that demands large, sustained interaction force and adjusts its command online as the load changes, both out of reach of a force-blind tracker. On hardware, Ctrl-F demonstrates hand-based dragging, pushing, and lifting, as well as foot-based kicking, successfully manipulating boxes weighing up to 20kg in pushing and kicking tasks where the force-blind baseline fails, while adapting online to additional loads introduced mid-task.
Abstract (translated)
URL
https://arxiv.org/abs/2611.05507
PDF
-
Specification-Guided Generation for Large Language Models
2026-11-02 11:15:06Alessandro Previti, Konstantinos Vandikas, Mario Alviano, Mats Carlsson, Albin Larsson Forsberg, Alexandros Nikou, Athanasios Karapantelakis, Aneta VulgarakisAbstract
Large language models (LLMs) can generate structured outputs, but existing constrained-decoding methods mainly enforce syntax and cannot directly enforce satisfaction of a formal specification. We introduce a neuro-symbolic, specification-guided decoding framework that combines LLM generation with symbolic reasoning. At each step, the framework refines the decoding grammar by filtering out values that cannot be extended to an output satisfying the specification. We present a forward-only variant that guarantees specification satisfaction by construction, and a backtracking variant that revises earlier feasible choices when their downstream consequences leave only values that the LLM itself judges unsuitable. The framework is model-agnostic, requires no retraining, and builds on existing grammar-constrained decoding mechanisms. Experiments on configuration and constraint-solving benchmarks show that the forward-only variant reliably produces specification-compliant outputs while reducing repeated LLM inference compared with rejection sampling and incurring modest symbolic-reasoning overhead. The backtracking variant further reduces cases in which the model is forced to select values that it has itself judged unsuitable, thereby substantially improving adherence to the LLM's stated interpretation of the prompt.
Abstract (translated)
URL
https://arxiv.org/abs/2610.41511
PDF
-
A State Change Is Local, Its Consequences Are Not: Dependency-Aware State Revision for Long-Term Agent Memory
2026-11-02 10:44:02Yiqi Wang, Tongyuan Zhao, Jiaqi Zhang, Yiqun Duan, Zhangkai Wu, Mingkai Zheng, Taotao CaiAbstract
Long-lived agents rely on persistent memory of users, tasks and decisions, and this memory must stay consistent with a world that keeps changing. When an upstream fact changes, however, memory systems can revise the contradicted memory itself while the beliefs, plans and actions derived from it remain accepted, even though they have lost their support. We therefore formulate dependency-aware state revision, which asks not only what changed but also which dependent states should no longer be trusted. To address it, StateGraph maintains an evolving state dependency graph whose edges are recovered from interaction histories. Its core design is counterfactual verification: each candidate edge is tested by asking whether the dependent state would survive the loss of its premise, which separates support dependence from semantic relatedness, and revision then invalidates a dependent state only when a strict dependency fails and no independent support path survives. To test this design, we introduce StateChangeBench, a controlled benchmark of 50 author-constructed cases annotated with cascade depth, hard negatives and action consequences. On it, StateGraph's Impact-F1 margin over a CUPMem reimplementation is 6.9 percentage points at depth 1 and 26.0 at depth 3+. On public long-term memory benchmarks, its point estimates are comparable to or higher than those of the evaluated baselines on most datasets. These results provide initial evidence that explicit dependency tracking can improve selective memory revision under changing conditions.
Abstract (translated)
URL
https://arxiv.org/abs/2611.02912
PDF
-
MicroMouse: Masking Harmful Supervision in Long CoT via Relative Potential
2026-11-02 08:03:52Xiaowei Zhu, Hengzhu Tang, Zhenyu Zhang, Shuohuan Wang, Yubing Ren, Yanan CaoAbstract
Even successful long CoTs may contain harmful supervision, motivating the need for methods that can automatically identify and mask such signals during SFT. Inspired by the MicroMouse maze-solving process, we view a long CoT as a search trajectory from the input problem toward the target answer. This perspective motivates maintaining a goal-relative measure, analogous to a MicroMouse's spatial coordinates, to quantify how close the current reasoning state is to the target answer. Building on this perspective, we propose MicroMouse, an automated selective-SFT framework for masking harmful supervision in long CoTs. In MicroMouse we introduce a Relative Potential (REP) to measure how closely each reasoning state supports the gold answer. Unlike the perplexity of the gold answer alone, REP measures relative support by contrasting the gold answer with a matched foil. This contrast cancels likelihood variations shared by the pair, yielding a more stable signal of progress toward the target answer. By tracking the REP trajectory, MicroMouse identifies consecutive potential decreases as erroneous exploration and post-peak reasoning as redundant wandering, and masks these harmful supervision during SFT. Extensive experiments across multiple student model scales and reasoning benchmarks show that MicroMouse consistently outperforms Full-CoT SFT and existing selective-SFT baselines, yielding average relative gains of 5.5% in greedy accuracy and 2.6% in Pass@1 relative to Full-CoT SFT. Meanwhile, MicroMouse improves reasoning efficiency by reducing average output length by 8.8%, while identifying harmful supervision in only 1.7 seconds per long CoT on average.
Abstract (translated)
URL
https://arxiv.org/abs/2611.02710
PDF
-
TrackMem: Tracking Evolving Beliefs in Long-Horizon Financial Dialogue
2026-11-01 15:43:41Austin M. Y. Cheung, Harsh Vardhan Gupta, Go Nam Lui, Lok Kan Chan, Ginny Y. Wong, Simon SeeAbstract
Memory systems for LLM agents are evaluated mostly on social dialogue, where facts accumulate and rarely change, so remembering reduces largely to finding the turn in which something was said. Financial dialogue breaks this assumption: figures are revised, stances shift without being restated, rules stated once govern later questions, and a single company is discussed under several analytical lenses. Memory systems that retrieve the passages most similar to a question, or the most recent ones, therefore return superseded values, miss rules that share no wording with the question, and cannot recover a stance spread across sessions. We present TrackMem, a per-speaker graph memory that tracks the history of figures, separates perspectives by entity and lens, and preserves each speaker's actions in chronological order. To evaluate it, we introduce FinLoCoMo, a benchmark of 15 long-horizon investment conversations with 765 questions in two splits: one following the LoCoMo categories and one targeting four failure modes. With two readers, TrackMem outperforms existing memory systems on both splits. On the failure-mode split it reaches 73.9% macro accuracy against 69.4% for the strongest baseline, with the largest gains on questions about revised figures (86.5% against 73.4%).
Abstract (translated)
URL
https://arxiv.org/abs/2611.02001
PDF
-
LF-VideoQA: Evaluating Long-Video Understanding with Long-Form Theory-of-Mind Questions
2026-10-30 21:05:36Shaden Shaar, Bradon Thymes, Majd Aldaye, Claire Cardie, Bharath HariharanAbstract
The hardest part of understanding a long video is not pinpointing any one moment but synthesizing many, e.g., answering a question that requires tracking what develops across hours of content and articulating how the pieces fit together. To date, most long-video QA datasets require only a short answer or a multiple-choice selection, oversimplifying the long-video understanding task to retrieval. We introduce LF-VideoQA, a dataset for long-form, open-ended question answering over long narrative videos built on theory-of-mind questions: a character's belief depends on everything they have seen or been told, so each question demands assembling and reasoning from evidence distributed across the video. The dataset contains more than 6,300 questions on 94 recent films; each requires reasoning over scenes spanning an average of 23 minutes and comes with a question-specific rubric for recall and precision scoring. The dataset is created entirely automatically by annotating screenplays with scene events and each character's first-order beliefs and meta-beliefs, then generating (question, answer, rubric) triples through LLM-based question generation and verification; human studies validate their quality. We evaluate four families of state-of-the-art open-source VLMs across three settings and find the task highly challenging: (i) even an oracle with access to the screenplay falls well short of complete answers; (ii) the best non-oracle model attains barely half of the recall level of the oracle; (iii) unlike on prior long-video benchmarks, captions and subtitles underperform the video itself, indicating that the questions need visual evidence; and (iv) recall is the predominant bottleneck, with answers omitting many required rubric claims.
Abstract (translated)
URL
https://arxiv.org/abs/2611.00383
PDF
-
MEMENTO: Learning Context Management for Long Context Processing Agents
2026-10-30 18:25:08Yunfan Zhang, Taehoon Hwang, Kathleen McKeown, Smaranda MuresanAbstract
LLM agents that operate over long inputs must perform context management: deciding what to retain in a fixed-size context window. A common approach is compaction, where the model replaces its history with a self-generated note. Yet off-the-shelf agentic models, including GPT-5.5 and GLM-5.3, often write ineffective notes, and reinforcement learning (RL) alone rarely discovers useful note-taking behavior. We present MEMENTO, a long-context agent built on Qwen3-8B and trained to manage its context through compaction. We first bootstrap note-taking by fine-tuning on synthetic trajectories annotated with notes generated in hindsight, then reinforce it with RL using a reward that combines answer correctness, note-quality heuristics, and confidence calibration. Although trained only to compact into a fresh window, MEMENTO extends at test time to strategies such as context folding and confidence-based backtracking. On book-level question answering across four benchmarks, with books of up to 2.5M tokens, MEMENTO raises Qwen3-8B's accuracy from 36.9% to 67.8% while never holding more than 20K tokens in context. It outperforms GPT-5.5 agent in the same harness (13.1%) and full book context (56.7%) at less than 1/50 the cost. It also nearly matches a ~100x larger GLM-5.3 agent (69.3%) at 1/9 the cost, and comes within 6.4 points of GLM-5.3 full context at 1/26 the cost.
Abstract (translated)
URL
https://arxiv.org/abs/2611.00244
PDF
-
ReLift: Dense 3D Tracking as Lifted Trajectory Repair
2026-10-30 17:58:33Assaf Singer, Maroun Khriesh, Noam Rotstein, Yoni Kasten, Or LitanyAbstract
Dense 3D tracking from monocular video requires establishing point correspondences over time, estimating their depth, and inferring their trajectories during occlusion. Existing methods typically learn these tasks jointly, a demanding objective given the scarcity of 4D supervision. We show that strong pretrained 2D trackers and 3D geometry models provide an effective foundation: lifted trajectories, with occluded segments simply interpolated, already rival dedicated 3D trackers using the same geometry. However, lifted trajectories inherit correspondence and depth errors, and under occlusion, their depth comes from the occluder rather than the tracked point. We introduce ReLift, an efficient feed-forward framework that recasts dense 3D tracking as geometric trajectory repair and completion. At its core, a trajectory corrector alternates attention along and across trajectories to preserve reliable observations, repair corrupted positions, and complete missing motion. Using only geometric inputs allows us to train directly on 3D trajectories with simulated lifting errors, decoupling training from images and from any specific tracker or geometry model. Concentrating 4D supervision on trajectory refinement yields a reusable model that consistently improves lifted trajectories across trackers and geometry providers without retraining, so it benefits directly from future advances in either component. On WorldTrack, ReLift achieves state-of-the-art mean accuracy, improving on the strongest baselines by 2.1 APD on all points and 3.0 on dynamic points, with faster configurations remaining competitive with leading 3D trackers while running faster than 4RC. Visit our supplementry page for more examples and code.
Abstract (translated)
URL
https://arxiv.org/abs/2610.42136
PDF
-
Think in 360{deg}: Benchmarking and Bootstrapping Panoramic Video Reasoning
2026-10-30 17:35:02Lidong Lu, Lidong Zou, Xinyi Mao, Jiaxin Lv, Zhenquan Li, Liangrui Dong, Tong Lu, Guo ChenAbstract
A panoramic video captures all directions around the camera, but relevant evidence can appear in different directions and at different times. Understanding it requires models to connect observations across the viewing sphere and time. We introduce PanoVideoBench, the first manually annotated benchmark for comprehensive panoramic video understanding. Its 1,000 questions span five categories and 15 question types, with diagnostic annotations for target search and panoramic capabilities. Evaluation of 11 proprietary, open-source, and panoramic-specialized models identifies cross-view tracking and sphere-time evidence integration as their weakest capabilities. To strengthen these capabilities, we construct PanoVideoCoT, the first reasoning dataset grounded in real panoramic video, through sphere-time-grounded synthesis that converts verified panoramic observations and successful agentic explorations into 13,465 QA-CoT pairs. Starting from a general video MLLM, PanoVideoReasoner learns from this corpus through Panoramic CoT SFT and Evidence-Privileged On-Policy Self-Distillation, a panoramic instantiation of Vision-OPD's OPSD in which the teacher uses verified perspective views to guide student-generated trajectories. It reaches 55.7% on PanoVideoBench, improving the backbone by 12.5 points and the previous SOTA by 2.6. The gains concentrate on the same spatial, cross-view, and temporal capabilities exposed by the benchmark, showing that grounded sphere-time supervision can equip a general video MLLM with panoramic reasoning.
Abstract (translated)
URL
https://arxiv.org/abs/2610.42082
PDF
-
Online Learning of Heterogeneous Locomotion Dynamics under Reinforcement Learning Policies for Precise Loco-Manipulation
2026-10-30 15:34:35Tianlin Zhang, Weipeng Xia, Lingwei Zhang, Yiyang Shao, Zhongyu Li, Yun-Hui LiuAbstract
How to reuse a pretrained locomotion policy for precise loco-manipulation is still an open problem. We propose an online method to learn the closed-loop dynamics under a frozen locomotion policy. The learned model predicts floating-base motion and improves loco-manipulation accuracy. However, unobserved latent conditions of the policy introduce heterogeneous responses, meaning that the same observed state will lead to different motions. Direct learning without accounting for this heterogeneity introduces bias and fluctuations into dynamics estimates, degrading floating-base prediction and end-effector tracking. To address this problem, a contaminated Gaussian model is proposed to approximate the effects of latent conditions. The model uses two Gaussian components to approximate predictable and unpredictable responses under the same observed state. Then, the contaminated Gaussian model is combined with a Gaussian process to construct an online learner using random Fourier features (RFFs). The learner estimates each response's probability of belonging to the predictable component and uses it to weight online updates, capturing predictable responses while reducing bias and fluctuations caused by heterogeneous observations. With consistent and unbiased dynamics estimates, model predictive control (MPC) predicts floating-base motion accurately and enables precise loco-manipulation. A finite-sample error bound is established to ensure uniform convergence in online learning. Simulation and hardware experiments demonstrate consistent end-effector tracking across different manipulator configurations and tasks, with errors of 0.01 m.
Abstract (translated)
URL
https://arxiv.org/abs/2610.41892
PDF
-
Iterated Integrals as Lexical Fingerprints: Path Signature Embeddings for Lexical Similarity
2026-10-30 15:11:18Raj Shekhar Singh, Pratham AgarwalAbstract
While sentence embeddings are primarily designed for semantic generalization, their latent geometry implicitly encodes surface-level lexical properties, a relationship that remains poorly understood. Shallow pooling methods discard word order, while deep Transformer models obscure these lexical alignments behind computational complexity and uninterpretable spaces. We propose constructing sentence embeddings via the path signature of Word2Vec trajectories, leveraging the iterated integrals of rough path theory to create representations that explicitly capture sequential and lexical structure in a geometrically tractable manner. Through extensive ablations spanning Word2Vec dimensions, signature depths, and PCA compression, we correlate embedding distances against five lexical string metrics: Levenshtein, Jaro-Winkler, word Jaccard, phoneme Levenshtein, and character TF-IDF. We reveal that while average pooling almost entirely fails to capture character-level edit distances, path signatures strongly align with them, with depth 2 signatures optimally balancing character and word-level sensitivities. Furthermore, we demonstrate that the critical lexical variance is concentrated in a highly compact PCA subspace, and unlike pooling, signatures structurally preserve and quantify word order. These findings establish path signatures not as semantic generalizers, but as rigorous mathematical lenses that explicitly encode discrete lexical structures and word order, offering an interpretable alternative to opaque deep learning for lexical tracking.
Abstract (translated)
URL
https://arxiv.org/abs/2610.41855
PDF
-
Higher-Order Kinematic Derivatives for Aspect-Preserving Real-Time Numerical Inverse Kinematics
Abstract
This paper leverages the higher-order kinematic derivatives of serial robots to achieve efficient, aspect-preserving real-time inverse kinematics. First, a family of higher-order solvers is derived, with a necessary orientation-error correction map, yielding the QuIK4 and QuIK5 methods with fourth- and fifth-order convergence. Second, an aspect-preserving step limiter extrapolates the Jacobian determinant along the step to predict and avoid singularities, shortening steps only when they head toward a singularity rather than when the current iterate is ill-conditioned. Third, a Hermite-interpolation certifier verifies the aspect of each answer, and a certified restart algorithm recovers failures from proven same-aspect seeds. The proposed methods are shown to outperform prior methods, reducing failures by up to four orders of magnitude and nearly eliminating aspect switching at tracking-level errors. A C++ library is released with ROS 2 integration.
Abstract (translated)
URL
https://arxiv.org/abs/2610.41752
PDF
-
Biomechanics do not predict perceptual and cognitive consequences of force augmentation
2026-10-30 12:47:21Maria Molina-Sanchez, Francesco Missiroli, Viktorija Pavalkyte, Mabel Ziman, Julien Russ, Maggie Szymanska, Noham Wolpe, Rani Moran, Lorenzo Masia, Tamar R. MakinAbstract
Wearable force-augmentation technologies, including exoskeletons and soft exosuits, are being developed for occupational and rehabilitation settings to enhance performance by reducing the muscular demands of movements. Yet enhanced performance also requires users to perceive the environment accurately, adapt to changing conditions, and decide whether actions are worth their physical cost. We used an elbow-assisting exosuit to investigate the physiological, perceptual and cognitive consequences of force augmentation during lifting. We assessed weight perception, adaptation in a volatile environment, and effort-based decision-making with and without assistance. While assistance reduced muscle activity, its behavioural outcomes did not simply reflect this biomechanical change. Assistance reduced perceived weight, but this effect was strongly shaped by participants' initial experience. Assistance also selectively reduced adaptation to changing environmental contingencies. Finally, reducing the muscular demands of lifting did not translate straightforwardly into how demanding the action felt or whether participants chose to perform it: differences in effort-based decisions were shaped by initial experience rather than simply tracking reductions in muscle activity or perceived fatigue. Together, we show that the perceptual and cognitive consequences of force augmentation cannot be inferred from its biomechanical benefits alone. Effective augmentation therefore requires perceptual and cognitive outcomes to be evaluated alongside physical performance.
Abstract (translated)
URL
https://arxiv.org/abs/2610.41679
PDF
-
$nabla$Mimic: Ultra-Efficient Humanoid Control with Differentiable Simulation
Abstract
Robot policy learning is dominated by zeroth-order methods such as PPO, which treat the simulator as a black box and pay for it with enormous sample counts. First-order policy learning differentiates through the dynamics, but on contact-rich whole-body control it has rarely worked: its gradients explode. A recent world-model method showed that derivative information can make humanoid motion tracking far more efficient, using surrogate gradients of a learned model. We show that exact gradients of the simulator itself do better, once two obstacles are removed. Exact gradients contain rare unbounded samples, because contact dynamics is not differentiable everywhere and its derivative diverges near some events; and they are expensive, because the simulator's adjoint has to replay the contact solve. $\nabla$Mimic bounds these samples with median-relative per-sample gradient clipping at every step of the backward pass, and reuses each costly simulated window by multistep regression onto gradient-derived action targets, which bounds every action target independently of the gradient scale. NablaEngine, a differentiable GPU simulation engine for the Unitree G1, removes the cost: it computes MuJoCo's full contact dynamics with fused per-world kernels and the adjoint of a whole control step as a single megakernel, with analytic gradients that match float64 finite differences, $11.5\times$ faster than the available MuJoCo Warp adjoint. On whole-body tracking of all 40 LAFAN1 clips with one policy on one GPU, $\nabla$Mimic reaches the score reported by the state-of-the-art world-model method, 0.82, in 20 minutes instead of 1.2 h, and 0.874 in 1.8 h. SHAC, the standard first-order baseline, stops on exploding gradients within minutes. We release NablaEngine and $\nabla$Mimic as open-source infrastructure for first-order humanoid policy learning.
Abstract (translated)
URL
https://arxiv.org/abs/2610.41654
PDF
-
DrawSplat: Atlanta World-Guided Implicit Gaussian SLAM for Indoor Reconstruction
2026-10-30 11:35:14Fan Zhu, Zhisong Xu, Ziyu Chen, Zhenjun Zhao, Takayuki OkataniAbstract
RGB-D SLAM requires accurate online tracking, high-quality rendering, and geometrically consistent reconstruction. Existing Gaussian SLAM methods mainly optimize Gaussian primitives with photometric, depth, or local frame-to-model constraints, which are often insufficient in indoor scenes with weak textures, large planar structures, noisy depth, and long trajectories. The resulting maps may suffer from pose drift, surface thickness artifacts, noisy normals, and blurred structural boundaries. We propose DrawSplat, an Atlanta World-guided implicit Gaussian SLAM framework for indoor reconstruction. DrawSplat follows a drawing-like process: explicit point-line geometry first sketches the structural layout, and implicit neural Gaussians then fill in high-fidelity appearance and continuous geometric details. It estimates camera poses, sparse geometry, and gravity direction through point-line joint tracking, infers structural planes from tracked lines using the shared-gravity component of the Atlanta World prior, and converts them into differentiable regularization terms on Gaussian centers and normals. To improve compactness and efficiency, DrawSplat further combines an anchor-based implicit neural Gaussian representation with adaptive structural sampling, which allocates Gaussian capacity to structurally informative regions. Experiments on multiple datasets show that DrawSplat achieves robust tracking, high-fidelity rendering, and strong geometric reconstruction among Gaussian-based SLAM systems, while maintaining a practical balance among quality, efficiency, and model size.
Abstract (translated)
URL
https://arxiv.org/abs/2610.41602
PDF
-
DiffWBC: Unlocking Steerable General Humanoid Motion Tracking via One-Step Diffusion Whole-Body Control
2026-10-30 07:16:01Yifei Huang, Yazhao Yang, Weijia Li, Zhiheng Ma, Dian ShenAbstract
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.
Abstract (translated)
URL
https://arxiv.org/abs/2610.41354
PDF
-
HIPC: Humanoid Iterative Planning and Control via Goal-Conditioned Motion Closure
2026-10-30 06:48:20Yi Han, Xingyu Chen, Zixuan Lang, Qianyang Wu, Yuhang Lin, Ji Ma, Liang Li, Dongting Li, Xinpeng Liu, Ruoli Dai, Hesheng Wang, Renjing Xu, Lei HanAbstract
Recent generative models are widely used to provide whole-body motion for humanoid tracking. Current methods combine motion generators with controllers in an open-loop paradigm, which leads to critical issues: tracking errors can accumulate into spatial drift, and the planner cannot adapt to unexpected physical disturbances without feedback from physical execution. However, directly feeding realized states back to the planner in a closed loop can cause discontinuities, resulting in physical jitter and even falls, since such states are out of distribution during training. To bridge this gap, we propose HIPC, a real-time Humanoid Iterative Planning and Control framework that couples a generative model with motion tracking into a unified planning-and-control paradigm. HIPC introduces a goal-conditioned motion planning trained with a canonical motion representation that avoids gimbal-lock singularities under extreme orientations and supports motion generation on diverse geometric and semantic conditions. Then, HIPC adopts two strategies, deviation-decayed recovery and history re-anchoring, to mitigate the out-of-distribution shift caused by realized-state feedback. Finally, HIPC operates a real-time asynchronous planning-and-control system, with latency compensation to reduce temporal mismatch for inference delay. Extensive experiments confirm the effectiveness of HIPC under switching and composition of diverse conditions. Results show that HIPC achieves state-of-the-art goal-reaching accuracy among existing methods while simultaneously demonstrating robustness to physical perturbations and the ability to recover from falls.
Abstract (translated)
URL
https://arxiv.org/abs/2610.41334
PDF
