arXiv subjects

Hang Zhao

Publications and source records attributed to Hang Zhao.

At least 19 recordsLinked to original sources

arXiv2026

CereVLA: Cerebellum-Inspired Consequence-Aware Residual Governance for Efficient Vision-Language-Action Execution

Action-chunked vision-language-action (VLA) policies improve inference efficiency, but limited feedback within committed action chunks can lead to accumulated execution errors. Residual adaptation can correct such deviations without retraining the VLA; however, existing corrections are typically optimized for reference-action consistency without explicitly considering their downstream consequences. To address this limitation, we present Cerebellum-Inspired Consequence-Aware Residual Governance (CereVLA), a unified framework that integrates lightweight residual refinement and predictive consequence evaluation into frozen VLA execution. Corrective actions are first generated by flow-based residual refinement, and their short- and interval-horizon consequences are then evaluated by a recurrent state-space model and a history-aware classifier. Residual corrections predicted to be unfavorable are selectively suppressed by a lightweight governor. Comparisons with state-of-the-art methods on LIBERO-10 and LIBERO-GOAL demonstrate the effectiveness of CereVLA. On SO-101, CereVLA increases task success from 57.5% to 90.0% and reduces mean control steps by 19.6% among successful trials, relative to the frozen SmolVLA baseline.

cs.CV↗

arXiv2026

MSK-Bench: Benchmarking Full-Body Musculoskeletal Motor Control Across Tasks, Control Paradigms, and Physiological Metrics

Musculoskeletal (MSK) humanoids provide a physiologically grounded embodiment for studying full-body motor control, but their high-dimensional muscle actuation, delayed activation dynamics, and redundant muscle--tendon structures make learning substantially harder than torque-driven humanoid control. Existing MSK benchmarks remain fragmented across gait, prosthetics, dexterous hands, or challenge-specific tracks, leaving full-body muscle-actuated control insufficiently evaluated under standardized tasks, methods, and metrics. We introduce MSK-Bench, a benchmark of 22 full-body motor-control tasks organized into three progressively challenging categories: postural stabilization, common locomotor behaviors, and contact-rich environmental interaction. Under unified task protocols and robustness perturbations, MSK-Bench evaluates 5 representative control paradigms, including reward-based RL, agentic reward tuning, latent-action RL, imitation-prior control, and residual adaptation over imitation priors. Beyond task success and reward, MSK-Bench further reports robustness analysis and physiology-oriented diagnostics, including activation cost, joint smoothness, and EMG-envelope similarity. Our empirical study shows that embodiment-aware exploration and structured action representations improve task coverage in high-dimensional muscle spaces, imitation priors enhance reference-compatible stabilization and locomotion but degrade under contact-rich terrain mismatch, and residual adaptation can recover successful behaviors when fixed references fail. We further find that improved task success does not necessarily imply improved physiological agreement, highlighting the importance of evaluating task performance, robustness, and physiological behavior jointly. MSK-Bench provides a task--method--metric testbed for full-body muscle-actuated humanoid control.

cs.RO↗

arXiv2026

Task-Oriented Co-Design and Optimization of Geared Actuators for Robotic Applications

Different tasks performed by legged robots impose distinct torque and speed requirements on actuators. Existing robotic actuators are generally optimized at the component level for metrics such as torque or power density, without explicit task guidance. System-level optimization across components such as motors, gearboxes, and sensors is challenging because of the high computational cost and coupling among mechanical, electrical, and electromagnetic behaviors. Consequently, improvements in individual components may not translate into better robot performance in a specific task. To this end, we present a systematic optimization framework for task-oriented co-design of actuator hardware and control. First, surrogate models are employed to accelerate motor evaluation and support global exploration of the coupled design space. Then, a hierarchical mixed-variable optimization strategy is adopted, combining discrete enumeration with continuous search over dimensions and real-valued indices. These indices are rounded to select admissible values for the remaining discrete choices before each evaluation. Within this search, rated output torque density and task performance are jointly optimized, with Bezier-parameterized joint torque profiles determined for each hardware candidate. Finally, the effectiveness of the proposed framework is validated through actuator fabrication and experiments on a two-degree-of-freedom jumping leg. Based on its measured mass, the fabricated prototype achieves a nominal rated output torque density of 35.7 N m/kg, approximately 60% higher than that of a widely used commercial geared joint actuator, while being 18.6% lighter. Under matched bench conditions, it achieves 12.0% greater jump height at twice-rated torque. Together, these results demonstrate a systematic route from task requirements to actuator design and control.

cs.RO↗

arXiv2026

SkelWAM: A Skeleton-Guided World-Action Model for Zero-Shot Cross-Embodiment Manipulation

Reusing manipulation experience across robot embodiments is important for scaling robot learning and reducing repeated task-specific data collection. However, changes in embodiment alter visual appearance, action dimensionality and semantics, and the whole-body configurations that can realize the same tool pose. We present SkelWAM, a skeleton-guided world-action model that couples perception and control through one explicit geometric representation for single-source cross-embodiment manipulation. Arm centerline geometry, tool-center-point (TCP) pose, and parallel-jaw commands form a shared 25-D state. The same definition underlies canonical third-person and wrist observations and future whole-body action targets. Trained with predictive visual supervision, a video-action mixture of transformers predicts canonical skeleton action chunks, which embodiment-specific constrained decoders convert into joint or continuum-robot controls. This formulation requires no one-to-one joint correspondence and uses no target-task demonstrations or target policy updates. We introduce LIBERO-Cross10, a source-only cross-embodiment transfer benchmark covering ten tasks and ten target embodiments across four morphological groups. On this benchmark, Franka-trained SkelWAM achieves 43.3% success over 1,000 episodes, exceeding the best-performing evaluated baseline by 36.2 percentage points. We further deploy a JAKA mini2-trained policy on the Feagine A03 continuum robot for three tabletop manipulation tasks, illustrating the approach's potential for real-world cross-embodiment manipulation. Project page: http://www.liukepku.com/skelwam/index.html

cs.RO↗

arXiv2026

COIN-GP: Cooperative Online Learning in Networked Distributed Systems with Partial Measurements via Gaussian Process Regression

In this paper, we tackle the problem of jointly estimating the system states and partially unknown dynamics within distributed sensor-equipped networks, particularly in scenarios where only partial state observations are available. To address this issue, we propose an observer-based dynamic cooperative learning framework incorporating online distributed Gaussian Process (GP) regression, which enables accurate estimation despite incomplete in measurements and deficient GP models. In addition, a novel data collection strategy is introduced, with theoretical conditions ensuring feasible data acquisition. Moreover, we also derive an error upper bound encompassing state estimation and model estimation, leveraging the deterministic error bounds of GPs. Empirical simulations demonstrate the superiority of our approach compared to existing distributed GP-based methods.

cs.LG↗

arXiv2026

Retrieval-Augmented Multi-Prompt Ensemble for Minor-Grain Breeding Information Extraction

This paper presents our system for CCL2026-Eval Task 5: Minor-Grain Breeding Information Extraction (MGBIE), which jointly extracts 12 entity types and 6 relation types from minor-grain breeding literature. We propose RAME (Retrieval-Augmented Multi-Prompt Ensemble), a training-free framework that elicits multiple LLM outputs under controlled diversity and aggregates them by majority voting to obtain high-confidence predictions. RAME combines (i) retrieval-augmented few-shot selection via a hybrid BM25-embedding retriever, (ii) a three-prompt ensemble (Strict, Relaxed, Balanced) spanning the precision to recall spectrum, and (iii) large-scale repeated sampling with majority voting to filter noisy predictions. Built on DeepSeek-V4-Flash, RAME achieves a Total Score of 0.499 (NER 0.730, RE 0.346) on the leaderboard, ranking 1st and surpassing the official Track-A baseline powered by GPT-5.5 (0.448), representing an 11.4% relative improvement. Code is available at https://github.com/king-wang123/CCL26-RAME.

cs.CL↗

arXiv2026

OpenWAM: An Open, Modular Exploration Towards Systematic World-Action Model Pretraining

World-Action Models inherit world knowledge from video-generative priors, and channel it into executable control signals through embodied experience. Existing systems, however, are monolithic: the generative backbone, visual representation, architecture, information flow, inference procedure, and training data are tightly coupled, obscuring which design choices matter and why. We introduce OpenWAM, an open research stack that turns world-action pretraining into a controlled experimental program. OpenWAM-Infra factorizes the WAM design space into composable modules with unified training, inference, deployment, and evaluation. On this substrate, OpenWAM-Study examines three questions through controlled experiments: what to inherit, how world and action learning interact, and how their synergy scales; and distills three principles: upstream knowledge transfers through a sufficiently capable generative backbone and a compact, information-rich latent space; world-action synergy requires dedicated action capacity, explicit world-to-action information flow, and synchronized joint denoising; and embodied pretraining principally improves out-of-domain generalization, with one-stage co-training over egocentric and robot data integrating world coverage and action grounding. Composing these principles, we build OpenWAM-α, an open WAM pretrained on roughly 6,400 hours of egocentric human and robot data and evaluated across simulation and real-world benchmarks. Across the eight simulation benchmarks and the real-robot experiments, which together span embodiments from single-arm and bimanual manipulation to dexterous hands, OpenWAM-α delivers consistently excellent performance, sustaining its top-tier standing from simulation to the physical world. We release the full stack, including infrastructure, evaluation protocols, pretrained models, and data recipes, to facilitate future research.

cs.RO↗

arXiv2026

Generic Zero-Entropy Optimization for Finitely Generated Nonlacunary Actions on the Circle

Let $T_n(x)=nx\pmod 1$ on $\T=\mathbb R/\mathbb Z$, and let $Σ\subset\mathbb N$ be a finitely generated nonlacunary multiplicative semigroup. We prove that, for every $1\le s\le\infty$, there is an open dense set of potentials $f\in W^{1,s}(\T)$ such that every measure that maximizes or minimizes $\int f\,dμ$ over the $Σ$-invariant probability measures satisfies $h_μ(T_r)=0$ for all $r\inΣ\setminus\{1\}$. For each fixed $s$, a single dense $G_δ$ subset of $W^{1,s}(\T)$ works simultaneously for all finitely generated nonlacunary multiplicative semigroups. The proof combines Rudolph--Johnson entropy rigidity with periodic-grid perturbations that generically exclude Haar measure from the optimizing faces. In particular, without any uniqueness assumption, the result applies to simultaneous $T_p,T_q$-invariance whenever $p,q\ge2$ are multiplicatively independent.

math.DS↗

arXiv2026

Explicit exposure of Haar measure

We solve the problem of explicitly constructing a continuous function whose unique maximizing measure for the doubling map is Lebesgue measure. More generally, given a nontrivial compact metrizable abelian group and a continuous surjective endomorphism for which normalised Haar measure is ergodic, we explicitly construct a continuous function on the group for which Haar measure is the unique invariant maximizing measure. The function is the uniform limit of a recursively defined sequence of trigonometric polynomials with rational coefficients; every parameter of the recursion is given by a closed formula, every step is exact, and the rate of convergence is explicit. In specific cases, we further obtain a uniformly convergent Fourier expansion in the classical frequency order, each of whose coefficients is rational and computable exactly, by a finite procedure.

math.DS↗

arXiv2026

ORV: 4D Occupancy-centric Robot Video Generation

Recent embodied intelligence suffers from data scarcity, while conventional simulators lack visual realism. Controllable video generation is emerging as a promising data engine, yet current action-conditioned methods still fall short: generated videos are limited in fidelity and temporal consistency, poorly aligned with controls, and often constrained to singleview settings. We attribute these issues to the representational gap between sparse control inputs and dense pixel outputs. Thus, we introduce ORV, a 4D occupancy-centric framework for robot video generation that couples action priors with occupancy-derived visual priors. Concretely, we align chunked 7-DoF actions with video latents via an Action-Expert AdaLN modulation, and inject 2D renderings of 4D semantic occupancy into the generation process as soft guidance. Meanwhile, a central obstacle is the lack of occupancy data for embodied scenarios; we therefore curate ORV-Data, a large-scale, high-quality 4D semantic occupancy dataset of robot manipulation. Across BridgeV2, DROID, and RT-1, ORV improves video generation quality and controllability, achieving 18.8% lower FVD than state of the art, +3.5% success rate on visual planning, and +6.4% success rate on policy learning. Beyond singleview generation, ORV natively supports multiview consistent synthesis and enables simulation-to-real transfer despite significant domain gaps. Code, models, and data are at: https://orangesodahub.github.io/ORV

cs.CV↗

arXiv2026

G0.5: One Autoregressive Stream for Robot Reasoning and Action

The prevailing recipe for Vision-Language-Action (VLA) models couples a pretrained VLM with a separately trained flow-matching action expert. This makes the VLM a context encoder rather than a decision-maker. We introduce G0.5, a pretrained autoregressive VLA in which a single transformer decoder emits reasoning and action tokens under a single objective. Three components make this tractable at foundation-model scale: a learnable cross-embodiment action tokenizer that maps heterogeneous robot actions into a shared vocabulary; a native chain-of-thought stream interleaving task decomposition, object grounding, and action hints with action tokens; and a visual memory module that injects multi-second history through the vision encoder. Because reasoning and action share a single set of weights, the pretrained VLM's capabilities carry over to physical behavior: the model follows instructions closely, and prompts directly steer action granularity, task horizon, and out-of-distribution scene handling without further training. Pretrained on a large collection of robot datasets together with VQA samples, G0.5 surpasses state-of-the-art models across 7 independent regimes: real-world fine-tuning on R1lite and R1pro robots (76.7\% vs.\ 53.3\% for $π_{0.5}$ and 24.4\% for GR00T-N1.7), the 2025 BEHAVIOR Challenge on 50 long-horizon household mobile manipulation tasks using a generalist policy (31.4\% vs.\ 26.3\% for $π_{0.5}$ and 26.1\% for the challenge winner), DROID post-training followed by zero-shot transfer to an unseen environment and objects (82.5\%), a language-following Pick-and-Place benchmark, LIBERO (98.9\%), RoboTwin 2.0 (93.3\%), and SimplerEnv-Bridge (87.3\%).

cs.RO↗

arXiv2026

SLAMFormer-$\infty$: Infinite SLAM Transformer for Unbounded Frontend and Backend Processing

We introduce the Infinite SLAM Transformer (SLAMFormer-$\infty$), the first geometric transformer capable of supporting both long-range frontend and backend processing without an explicit distance bound. Instead of relying on a first-frame-anchored formulation, SLAMFormer-$\infty$ employs memory conditions to define flexible coordinate systems and scales for input frames, enabling more expressive structural conditioning. Built upon this formulation, the frontend preserves efficient local computation, while the backend jointly optimizes long-range trajectories and scene geometry in a globally consistent manner. Experimental results demonstrate that SLAMFormer-$\infty$ achieves superior or highly competitive performance in both trajectory estimation and scene reconstruction across large-scale datasets. Notably, SLAMFormer-$\infty$ generalizes to extremely long trajectories, successfully operating on sequences exceeding $17\mathrm{km}$.

cs.CV↗

arXiv2026

Sparse Weight Decomposition for Efficient Circuit Extraction

Dense pretrained transformers do not naturally expose interpretable units for circuit extraction. Existing approaches obtain such units by learning auxiliary sparse representations or training sparse models, incurring substantial additional computation while potentially introducing a fidelity gap between the representation being analyzed and the original pretrained model. We propose Sparse Weight Decomposition (SWD), which reparameterizes pretrained linear projections by factorizing each weight matrix into two sparse factors whose shared intermediate coordinates serve as individually addressable circuit units. Without training a separate replacement network, this parametric representation supports the same scoring, selection, and ablation circuit extraction workflow used for methods that learn sparse features. Across single-matrix replacements, SWD matches the held-out fidelity achieved by Transcoder and other strong baselines while using less than 1% of the data that those baselines use to train their replacements. For matched replacement fidelity, SWD reaches the same circuit sufficiency and necessity targets with fewer active read/write edges and selected units across tasks on GPT-2, Qwen2.5, and Qwen3.5-27B. We further show that SWD remains effective for full-model replacement of all attention and MLP weight matrices after fine-tuning the nonzero factor values. Finally, SWD also features a zero-data variant, allowing broader use of mechanistic interpretability analysis (e.g., per-step analysis).

cs.LG↗

arXiv2026

On Automorphism Groups of (1,2)-Surfaces

Let S be a minimal surface of general type with K_S^2 = 1 and p_g(S) = 2, commonly referred to as a (1,2)-surface. The automorphism groups of such surfaces have been classified by David Wen using algebraic methods via the canonical ring, establishing the bound |Aut(S)| <= 200. In this paper, we provide a geometric recovery of this bound from the double cover of the Hirzebruch surface Sigma_2. We compute the automorphisms of Sigma_2 from its Cox ring and analyze the induced action on the base P^1 together with its vertical kernel. Applying this to automorphisms preserving the branch divisor R = Delta_0 + R_0, R_0 in |5 Delta_0 + 10 Gamma|, gives a geometric framework for the vertical and horizontal parts of the automorphism group and recovers Wen's bound |Aut(S)| <= 200.

math.AG↗

arXiv2026

SLAM-Former: Putting SLAM into One Transformer

We present SLAM-Former, a neural approach that integrates full SLAM capabilities into a single transformer. Similar to traditional SLAM systems, SLAM-Former comprises both a frontend and a back-end that operate in tandem. The frontend processes sequential monocular images in real-time for incremental mapping and tracking, while the backend performs global refinement to ensure a geometrically consistent result. This alternating execution allows the frontend and back-end to mutually promote one another, enhancing overall system performance. Comprehensive experimental results demonstrate that SLAM- Former achieves superior or highly competitive performance compared to state-of-the-art dense SLAM methods.

cs.CV↗

arXiv2026

Orca: The World is in Your Mind

We introduce Orca, an initial instantiation of a general world foundation model. Orca learns a unified world latent space from multimodal world signals and exposes it through multimodal readout interfaces. Rather than optimizing isolated next-token, next-frame, or next-action prediction, we are centered on Next-State-Prediction modeling, offering a unified state-transition modeling route toward understanding, predicting, and acting upon the world. Orca learns through two complementary paradigms: unconscious learning captures dense natural state transitions from continuous videos, and conscious learning models sparse meaningful state transitions by language-described events and VQA supervision. For pre-training, we construct a large-scale world-learning inventory data, including 125K hours of video data and 160M event annotations. After pre-training, Orca learns a unified world latent space. To examine whether the learned latent supports downstream, we evaluate it by three representative downstream readouts: text generation, image prediction, and embodied action generation. Orca's backbone is frozen, and only the lightweight modality-specific decoders are trainable. Experiments show the scalability of the proposed paradigm and verify that stronger world latent enables stronger downstream readouts. Orca outperforms similar-sized specialized baselines. These results show that Orca, as a general world foundation model, presents a promising approach to understanding, predicting, and acting upon the world. Finally, we discuss the current limitations, aiming to provide useful insights and inspiration for the community.

cs.CV↗

arXiv2026

Automated Synthesis of Facial Mechanisms for Conversational Animatronic Robots

Animatronic faces are a central component of socially interactive robots, enabling rich nonverbal communication through facial articulation. However, state-of-the-art animatronic faces are typically tailored systems: each new facial geometry requires extensive manual mechanical redesign, making large-scale personalization prohibitively slow and costly. In this work, we pursue automated and scalable mechanical face synthesis, aiming to rapidly generate a physically realizable facial mechanism for a wide range of facial geometries. We introduce a parametric, linkage-driven mechanical face template whose topology and actuator layout are explicitly parameterized to support systematic scaling and retargeting across diverse facial morphologies. Building on this template, we propose a hierarchical automatic design algorithm that takes a single 2D portrait as input, reconstructs a target 3D face, and synthesizes a collision-free, manufacturable internal mechanism. The algorithm combines anatomy-guided feasible motion volumes, Action Unit (AU)-derived trajectory-based expressiveness objectives, and a collision-driven outer-loop refinement strategy. Beyond hardware synthesis, we argue that future mechanical faces deployed at scale must engage in bidirectional, multi-turn conversation rather than functioning solely as speaking or listening heads. To this end, we develop a dual-identity conversational facial motion synthesis framework that jointly models speaking and listening behaviors from audio, producing temporally coherent 3D facial motion suitable for physical execution. We validate our system through extensive experiments, including (i) quantitative evaluation of automatic mechanism synthesis across diverse facial geometries, (ii) comparisons against manual mechanical design, (iii) benchmarks on conversational facial motion synthesis and real-time deployment, and (iv) perceptual user studies.

cs.RO↗

arXiv2026

DriveMA: Driving Vision-Language-Action Models with verifiable Meta-Actions

Driving Vision-Language-Action Models (Driving VLAs) aim to use language to improve end-to-end planning, but the language-action gap limits this promise. We propose DriveMA, a Driving VLA framework built on verifiable meta-actions, which summarize future ego motion into compact language-domain intentions and can be constructed from expert trajectories with a trajectory-grounded annotation pipeline and can be verified against generated trajectories through rule-based projection. DriveMA exploits this verifiability with action-centric supervised training and a data-efficient turn-level credit assignment reinforcement learning framework, explicitly aligning high-level decisions with low-level trajectory planning through dense rewards and precise credit assignment. DriveMA sets a new state of the art on the Waymo Open Dataset Vision-based E2E Driving, achieving a Rater Feedback Score of 8.060 with a 2B model and further improving it to 8.079 with a 4B model; it also obtains competitive closed-loop planning performance on NAVSIM. These results show that even a simple meta-action interface can achieve state-of-the-art planning when made verifiable and optimized for language-action alignment. Code, data, and models are available at https://tsinghua-mars-lab.github.io/DriveMA.

cs.CV↗