arXiv subjects

Hang Xu

Publications and source records attributed to Hang Xu.

At least 19 recordsLinked to original sources

arXiv2026

Fast-Slow Evolutionary Occupancy Prediction via Controlled Dynamics

3D semantic occupancy prediction provides dense geometric and semantic scene representations for autonomous driving, where both high accuracy and low response latency are crucial for safe downstream forecasting and planning. Existing methods usually exhibit different accuracy-latency characteristics. Performance-oriented models provide stronger geometric and semantic predictions, while deployment-friendly models provide faster responses. This motivates EvoOcc, a fast-slow evolutionary occupancy prediction framework that jointly exploits their complementary strengths to improve the accuracy-latency balance without changing the upstream architectures. EvoOcc models evolutionary occupancy prediction as a continuous time controlled dynamical system, enabling flexible adaptation to variable slow system delays and irregular fast system arrivals. The framework further decomposes the evolution process into dual state evolution where ego state evolution compensates for the deterministic coordinate shifts and scene state evolution models the genuine geometric and semantic scene changes. Extensive experiments on three different fast-slow system pairs and irregular prediction arrivals show that EvoOcc consistently improves over fast system baselines while maintaining much lower latency than the slow system, indicating a favorable accuracy-latency balance and stable behavior under practical inference situations.

cs.CV↗

arXiv2026

Optimizing synthetic jet placement for control stability in increasing Reynolds number flows based on deep reinforcement learning

This study utilizes reinforcement learning algorithms to develop advanced control strategies for manipulating synthetic jets positioned on a cylinder, aiming to achieve effective flow control. It addresses critical challenges in achieving robust performance across moderate to high Reynolds numbers (Re) and varying jet placement configurations. The results demonstrate that placing synthetic jets near flow separation regions yields optimal control performance. At Re = 500, the multi-objective flow control strategy achieves up to 37.4% drag reduction and 99% suppression of lift oscillations, while completely suppressing vortex shedding. At Re = 1,000, drag reduction improves to 49.1%, with equally effective lift suppression and complete vortex shedding suppression. At Re = 2,000, the strategy achieves a maximum drag reduction of 58.8% and suppresses 90% of lift oscillations, although some residual wake instabilities persist. Additionally, synthetic jets effectively disrupted detached vortices and stabilized the wake, resulting in streamlined flow and suppressed vortex shedding. These findings underscore the pivotal influence of jet placement in optimizing flow control efficacy, while affirming the advanced capability of control strategies to tackle intricate challenges.

physics.flu-dyn↗

arXiv2026

Decompose and Reorganize: Planning with Primitives and Visuomotor Policies Learned from Demonstrations

Successfully automating dexterous, long-horizon bimanual manipulation requires frameworks capable of both high-level reasoning and fine-grained execution. Traditional task and motion planning (TAMP), while excellent at symbolic planning, is often brittle in contact-rich operations. Simultaneously, imitation learning (IL), while effective in manipulation tasks with visual feedback, is limited by its low capability in spatial generalization and multi-stage operation. To reconcile their complementary strengths and limitations, we propose DR-LfD (Decomposed and Reorganized Skills Learned from Demonstrations), a framework that integrates visuomotor policies into a TAMP-gated decision-making system. Based on contact relationships, DR-LfD decomposes human demonstrations into atomic skills, which are reproduced as visuomotor policies or object-centric primitives. The initiation, termination, and constraints of the visuomotor policies are carefully modeled and implemented in a TAMP-compatible form, enabling reorganization of skills learned from different sources. DR-LfD transforms the learning problem from one requiring exponential demonstration data over possible skill sequences to one whose demonstration burden scales with the number of distinct skill types, with limited data for each skill. Real-world and simulation benchmarks demonstrate data-efficient skill composition under unseen setups and physical constraints. On two DexMimicGen tasks, DR-LfD with 100 demonstrations outperforms diffusion-based imitation policies with 1000.

cs.RO↗

arXiv2026

Goal2Pixel: Grounding Goals to Pixels for Vision-Language Navigation

Vision-language models (VLMs) have become a common foundation for vision-and-language navigation in continuous environments (VLN-CE). Yet most VLM-based methods cast navigation as low-level action prediction, an interface that is ambiguous, tied to short-horizon motion primitives, and inefficient due to repeated VLM querying. We propose Goal2Pixel, a pure pixel-based paradigm that reformulates VLN-CE as navigable pixel grounding. Rather than predicting actions, Goal2Pixel uses the image plane as a unified spatial interface between VLM reasoning and robot motion: the model predicts a visible navigable pixel, which is back-projected into a 3D waypoint for forward navigation. Non-forward actions are encoded by auxiliary left/right/bottom regions for turning and stopping. To support long-horizon navigation, we propose ViKeyMem, a visibility-aware keyframe memory, achieving a favorable performance-efficiency trade-off while reducing training cost by over 50%. To adapt pretrained VLMs to navigable pixel grounding, we introduce semantic embeddings and coordinate-aware auxiliary losses. Among methods trained without external data, Goal2Pixel achieves competitive state-of-the-art performance on R2R-CE and RxR-CE. On R2R-CE Val-Unseen, it achieves 54.1% SR and 52.5% SPL with only 7.75 VLM calls per episode. Compared with direct action prediction, Goal2Pixel improves SR by 21.2 percentage points while requiring 6 times fewer VLM calls. Project Page: https://baobao0926.github.io/Goal2Pixel/.

cs.CV↗

arXiv2026

State-augmented deep reinforcement learning for active flow control around an elliptical cylinder

We employ reinforcement learning algorithms to develop control strategies for manipulating synthetic jets on an elliptical cylinder, targeting robust flow control across varying aspect ratios (Ar). Our results show that for high aspect ratios (Ar = 1 and 0.75), the learned strategies effectively mitigate vortex shedding, achieving drag reductions of 13.4% and 20.1%, respectively. As the Ar decreases, more complex wake dynamics challenge flow control. For Ar = 0.5 and 0.25, drag reductions of 26.88% and 30.37% are achieved, though vortex suppression becomes increasingly difficult. For extremely slender cylinders (Ar = 0.1), we enhance control performance by enriching dynamic feature representation and using Kalman filtering for state estimation. Unlike conventional methods, our approach successfully achieves complete vortex shedding suppression, a maximum drag reduction of 32.2%, and eliminates periodic oscillations, stabilizing the flow. These results demonstrate the efficacy of state-enhanced RL in controlling highly slender geometries.

physics.flu-dyn↗

arXiv2026

Toward fully stabilized flow control using deep reinforcement learning

This study enhances the performance of flow control across various synthetic jet configurations by improving deep reinforcement learning techniques. The training results based on the foundational deep reinforcement learning framework indicate that as the Reynolds number increases, the effectiveness of synthetic jet control becomes increasingly sensitive to the position of the jet. When synthetic jets are positioned near the flow separation region, the control strategy consistently exhibits excellent performance. However, when synthetic jets are located farther from the separation region, the flow control performance diminishes, and the consumption of external energy increases. By enhancing dynamic state features and reshaping the reward function, we significantly improve control performance across various Reynolds numbers and synthetic jet positions. With the optimized framework, we achieve significant drag reduction effects ranging from 8% to 34% within the Reynolds number range of 100 to 400. The flow control strategy is capable of simultaneously achieving multiple control objectives, including reducing drag, suppressing lift, eliminating vortex shedding, and decreasing energy consumption. These findings highlight the potential of optimizing deep reinforcement learning frameworks to achieve more adaptive flow control strategies for various flow scenarios.

physics.flu-dyn↗

arXiv2026

FactReview: Evidence-Grounded Peer Review with Execution-Based Claim Verification

AI is accelerating scientific research, but providing timely and trustworthy feedback remains challenging. Such feedback requires evaluating specific claims against verified evidence, helping researchers and autonomous research systems determine which findings can guide subsequent work. Thorough verification is time-consuming, and reviewers under time pressure may overlook or misjudge critical issues. Existing AI reviewers have yet to fill this gap because they often assess claims without adequately verifying the supporting evidence. We introduce FactReview, a framework that verifies claims in papers to provide more trustworthy feedback. It checks claims against the literature and examines derivations, while also executing the paper's code to test empirical claims. Across 300 papers, FactReview ranks best among all evaluated systems on five of seven metrics, achieving 6.8% false support and 79.2% classification accuracy. In a study of 36 papers, reviewers using FactReview detect 9.4 issues per paper compared with 5.6 independently, while spending 74.1% less time. FactReview thus supports more reliable peer review, with the potential to accelerate research iteration. The code is public at https://github.com/DEFENSE-SEU/FactReview.

cs.AI↗

arXiv2026

DK-VLM: Geometry as Position for Spatial Reasoning in Vision-Language Models

Vision-language models still struggle to understand 3D spatial relations across views and update spatial judgments as the observer moves. A common approach fuses 3D reconstruction features into visual tokens, but aligning these features with pretrained semantic representations remains challenging under limited spatial supervision. We propose DK-VLM with Dual-Kernel Attention, which computes attention from both a visual token's input position and its geometric position in the scene. A semantic kernel retains the pretrained model's native attention and positional encoding, while a separate geometric kernel uses estimated 3D points and camera poses to directly modulate attention through point displacements and relative view transformations. Then, a learned gate fuses their outputs. Geometry thus enters attention as position rather than as fused reconstruction features. We further introduce Reference-Frame Composition (RC) supervision to train the model to update its reference frame across successive judgments. It provides stepwise turn and heading targets derived from verified single-step annotations. Among the compared methods, DK-VLM-8B achieves the highest average score across six spatial benchmarks and the highest overall scores on VSI-Bench (74.33) and ReVSI-32 (58.28). RC supervision further improves multi-step spatial reasoning, while the full model preserves general video understanding. Project page: https://sumuru789.github.io/DK-VLM-website/.

cs.CV↗

arXiv2026

Computational compressive imaging reconstruction with a simulated-annealing-based Ising solver

Computational compressive imaging, such as single-pixel imaging and lensless imaging, is a promising imaging technique, enabling the reconstruction of objects from under-sampled measurements through compressed sensing algorithms or deep learning methods. However, the demand for electronic computational resources grows rapidly when recovering high-resolution and multi-dimensional images and training neural networks with numerous parameters, which has become a bottleneck for the widespread adoption of this technique. Here, we propose a physics-driven reconstruction framework that formulates imaging inverse problems as Ising models and directly recovers target objects through the self-evolution of non-von Neumann Ising machines toward the ground state of the Hamiltonian. We employ a simulated-annealing-based Ising solver to demonstrate this proof-of-concept by reconstructing objects in both single-pixel imaging and a lensless diffuser camera at sampling rates ranging from 1% to 25%. By further incorporating a foreground-sparsity constraint and a smoothness constraint, the reconstruction quality of our method is comparable to or even better than that of mainstream algorithms. This approach has the potential to substantially reduce the electronic computational burden of inverse reconstruction, paving the way for real-time, low-power computational imaging.

physics.optics↗

arXiv2026

DynThinker: Unifying Static 3D and Dynamic 4D Spatial Reasoning

Achieving general spatial intelligence requires a unified understanding of both static 3D and dynamic 4D. However, we find that existing models struggle to excel at both: 3D post-training can weaken dynamic understanding, while 4D-specialized models often lack strong static 3D reasoning. Our analysis reveals that this spatial--dynamic interference is highly non-uniform across parameter groups, with the balance between static and dynamic capabilities particularly sensitive to changes in late-layer MLPs. To address this interference, we propose DynThinker, a unified framework for jointly strengthening static and dynamic spatial reasoning. Decoupled Exponential Moving Average (D-EMA) applies configurable group-wise averaging to constrain drift in interference-sensitive pretrained parameters while preserving flexibility for capability enhancement. Spatial-Dynamic Fusion (SDF) complements D-EMA by selectively integrating spatial and temporal priors from a dynamic geometry encoder into intermediate VLM representations under semantic guidance. Across ten metrics spanning nine static 3D and dynamic 4D benchmarks, DynThinker achieves the highest average score among all evaluated models. Notably, DynThinker achieves 56.0 on ReVSI, 67.2 on DSR-Bench, and 51.2 and 40.1 under the sample-wise and group-wise evaluation protocols of DSI-Bench, respectively, setting new state-of-the-art results among the compared open-source models across all four evaluations within a unified model.

cs.CV↗

arXiv2026

REEL: Learning to Retrieve, Evaluate, and Evolve Visual Memory for Any Long-Horizon Multi-Shot Video Generation

Memory-based long-video generation aims to combine user control with long-range visual consistency. We organize this process into three functional components: a planner, an adapter, and a generator. Representative multi-shot systems couple memory to generator-specific interfaces or use predefined agent workflows, rather than independently training a memory policy for cross-shot objectives. We introduce REEL, a general-purpose visual-memory planner. Through a unified tool interface, REEL learns to retrieve references, create missing visual evidence, and update persistent memory. Backend-specific adapters translate its evidence plans into supported conditioning inputs, allowing the same policy to guide different black-box video generators. To train REEL, we construct two high-quality datasets, REEL-SFT-4k and REEL-RL-1k, covering diverse interaction patterns and prompt types. Training proceeds in three stages: supervised fine-tuning, single-shot Group Relative Policy Optimization (GRPO), and multi-shot GRPO. Multi-shot GRPO carries policy-generated memory across consecutive shots, so later outcomes guide earlier reference selection and memory updates. REEL-Bench tests identity preservation and intended state changes under text-only requests and timed reference-image uploads. On JoyAI-Echo~1.5 and MiniMax-H3, REEL improves cross-shot consistency on ST-Bench by 15.1\% and 20.7\%, and Core-100 on our proposed REEL-Bench by 2.41 and 8.32 points, respectively, over the no-memory baseline.

cs.CV↗

arXiv2026

CompoWorld: Compositional Environment Scaling for General Agents

Automatically generated environments provide a scalable source of interaction data for training general agents. However, existing approaches mainly generate tasks within a single environment, while real-world workflows require agents to connect information and actions across multiple services. We introduce Compositional Environment Scaling (\textbf{CompoWorld}), which expands the task space by composing a finite library of reusable services. Coding agents turn tool specifications into verified services with typed states and shared interfaces, while a world model handles tools that cannot be reliably implemented. A random-walk procedure connects services through dependency graphs, enabling the generation and verification of tasks that require information to flow across services. Verified trajectories support supervised fine-tuning (SFT), while our Completion-Focused Rubric Reward guides reinforcement learning (RL) toward full task completion by emphasizing criteria with lower pass rates within each rollout group. We construct 448 services exposing 10,130 tools and use 3K SFT trajectories and 1K RL tasks to train Qwen3.6-35B-A3B. Experimental results show that CompoWorld improves on its backbone by 9.17 points on average across eight benchmarks. On AutomationBench, it surpasses frontier models such as Claude Opus 4.6 and leads all compared agent-specialized 35B-A3B models.

cs.AI↗

arXiv2026

EWAM: Emergent Depth-Wise Specialization in a Unified Embodied Model -- From Semantic Understanding through Visual Foresight to Action

Vision-language-action (VLA) policies emphasize semantic understanding, whereas world-action models (WAMs) learn predictive representations of environment dynamics. Systems that expose a policy to both sources often still concentrate action computation on a single expert. We present EWAM, an action-centric unified embodied model whose asymmetric joint attention lets action tokens read semantic, current-visual, predicted-future, and action information at every layer while the perceptual experts retain their distinct roles. Without layer-wise supervision, EWAM develops an emergent depth-wise specialization: action queries attend mainly to vision-language features in shallow layers, to predicted future frames in intermediate layers, and to action tokens themselves in deep layers. This handoff replicates across tasks and is stable across denoising steps. Checkpoint tracking and causal interventions show that it is learned and that action generation depends on it. EWAM is pretrained in two separate regimes, one on cross-embodiment robot trajectories and one on human egocentric video. In simulation and real-robot experiments, it surpasses existing VLA, WAM, and hybrid baselines. Human egocentric data improve both cross-embodiment transfer and real-robot robustness, and subtask-phase supervision improves long-horizon completion. Together, these results suggest that unified embodied learning can induce an ordered internal progression from semantic understanding, through visual foresight, to action formation.

cs.RO↗

arXiv2026

Skill2Env: Capability-Oriented Environment Synthesis from Skills for General Agents

Executable environments are critical for post-training agents on tasks that require tool use and multi-step interaction, but constructing executable tasks together with their environments remains difficult to scale. Skills provide reusable domain knowledge, operational procedures, and tool-use instructions, but a substantial gap remains between the information contained in a skill and a concrete, challenging task with a complete executable environment. To address this gap, we introduce Skill2Env, a capability-oriented framework that starts from a skill and uses agent capability demands to guide task and environment synthesis. Skill2Env represents these demands through reusable difficulty patterns and instantiates them into task blueprints that specify objectives, challenges, environment facts, information boundaries, and acceptance criteria. These blueprints guide the joint construction of task instructions, execution substrates, workspaces, and rubric-based evaluators around source skills. We further propose Iterative Task Hardening, which uses solver execution evidence to identify insufficiently challenging task designs, strengthen or extend their difficulty-pattern instantiations, and revise the corresponding blueprints and environments. Using 1.5K high-scoring trajectories generated from Skill2Env environments for supervised fine-tuning, we observe consistent improvements across a broad range of agent benchmarks, demonstrating the effectiveness of capability-oriented environment synthesis for agent post-training.

cs.AI↗

arXiv2026

VA-Judger: Reward Modeling from Human Preference Feedback for Joint Video-Audio Generation

Using reinforcement learning to post-train joint video-audio generation models requires a reward signal. Existing methods construct this reward by combining metrics for individual quality dimensions, including audio quality, visual fidelity, and synchronization. However, these metrics evaluate perceptual dimensions separately and fail to capture the overall semantic and temporal coherence among the text prompt, video, and audio that shapes human preferences. Optimizing models against these metrics encourages reward hacking, generating video-audio content that achieves high scores on these metrics yet appears incoherent or unfaithful to human viewers. To address this problem, we first construct a large-scale human-preference dataset VAPref-10K for joint video-audio generation, comprising 9K prompts and 10.3K fine-grained paired comparisons from generation models. We also introduce the VA-Judger-Bench benchmark with both in-domain and out-of-domain model comparisons to evaluate whether reward models truly align with human preferences. We further propose VA-Judger, a chain-of-thought omni-reward model for joint video-audio generation. In particular, VA-Judger first learns from pairs with clear quality gaps to establish structured output and coarse preference discrimination, then distills reliable preference explanations for harder near-quality comparisons via rejection sampling verified against human annotations, and finally performs dimension-wise reinforcement learning that decomposes human feedback into individual quality dimensions for denser reward signals than a single binary preference label. Experiments show that VA-Judger outperforms metric baselines in predicting human preferences on both in-domain and out-of-domain evaluations. Using its human-aligned rewards for post-training audio-video generation model also yields significant improvements in generation quality.

cs.CV↗

arXiv2026

Non-asymptotic Analysis of Expected Reconstruction Risk for Trigonometric Polynomial Models

We investigate the expected reconstruction risk of trigonometric polynomial models under different sampling schemes. Through numerical experiments, we observe that when the sampling nodes $\{t_l\}_{l=1}^m$ are i.i.d. random variables uniformly distributed over $[0,1)$, the associated structured random matrix $\pmb{A} \in \mathbb{C}^{m \times N}$ with $A_{l,k} = e^{2π\mathrm{i} kt_l}, k \in Γ= \{-q, \dots, q\}, N = 2q+1$ frequently becomes nearly singular or severely ill-conditioned. As a consequence, the expected reconstruction risk exhibits divergent behavior. In contrast, when the sampling nodes $t_l$ are either equidistant points or small random perturbations of an equidistant grid, the expected reconstruction risk undergoes a sharp phase transition at the interpolation threshold $m=N$. To better understand the underlying mechanisms behind these different phenomena, we characterize the expected reconstruction risk through the spectral quantity $\sum_{i=1}^{r} \frac{1}{σ_i^2(\pmb{A})}$, where $σ_i(\pmb{A})$ denotes the singular values of the sampling matrix. Based on this spectral representation, we theoretically prove that the expected reconstruction risk diverges under uniformly distributed random sampling. Furthermore, we derive an explicit formula for the expected reconstruction risk in the equidistant sampling case and establish upper and lower bounds for the expected reconstruction risk under jittered sampling.

cs.IT↗

arXiv2026

Double Descent for Random Fourier Series Models

We investigate the least squares linear regression problem with random partial Discrete Fourier Transform (DFT) matrices, providing a rigorous analysis of the model's generalization error. By leveraging tools from random matrix theory, we derive exact non-asymptotic bounds for the risk of the Moore-Penrose estimator, which hold for finite-dimensional problems and reveal the precise dependence on key parameters such as the sample size, dimension, and noise variance. Then we obtain a characterization of the double descent phenomenon in the linear regression context, demonstrating how the risk evolves when the number of parameters $p$ and the number of samples $n$ tend to infinity, with $p/n$ fixed. The analysis relies on applications of the Stieltjes transform for random Fourier matrices, enabling a precise description of the spectral properties of these matrices and their impact on regression performance. To validate our theoretical findings, we present several numerical examples that illustrate the double descent curves. These simulations align closely with our derived bounds, confirming their predictive power in both under-parameterized and over-parameterized regimes.

math.ST↗

arXiv2026

PACT: From Credit Assignment to Critic Alignment

Reinforcement learning has become a central component of large language model (LLM) post-training, yet token-level credit lacks a generally accepted mathematical definition, leaving its relationship to commonly used training signals unclear. We formulate three regularity conditions, namely Completeness, Prefix Consistency, and Neutrality, and prove that they uniquely determine token-level credit. This characterization provides a unified basis for explaining phenomena across existing algorithms and guides the development of an improved actor-critic training procedure. Through this lens, an ideal teacher in On-Policy Distillation (OPD) acts as an implicit critic, yielding an expected policy gradient proportional to that induced by token-level credit. Response-level REINFORCE Leave-One-Out (RLOO) signals match the expected policy-gradient contribution of token-level credit despite their coarser granularity. We further establish approximate credit sparsity under bounded outcome rewards and show how intermediate critic errors in Generalized Advantage Estimation (GAE) can become comparable to the underlying credit. These motivate Policy Aligned Critic Training (PACT), which adopts an Actor-then-Critic update order to apply importance sampling correction to critic training and better align the critic with the updated policy. In agentic mathematical reasoning, PACT achieves 72.87% average accuracy across four benchmarks, outperforming GRPO and PPO by 8.80 and 13.16 percentage points, respectively. On SWE-bench Verified, PACT achieves a pass rate of 67.4%, outperforming PPO, GRPO, and SAO by 2.4, 2.0, and 3.8 percentage points, respectively.

cs.LG↗