arXiv subjects

Hang Zhao

Publications and source records attributed to Hang Zhao.

At least 73 records · Page 4Linked to original sources

arXiv2026

Ultralight Scalar Dark Matter with Off-Diagonal Flavor Couplings

Ultralight dark matter can behave as a coherent background field and induce time-dependent modifications of Standard Model parameters. We study a scenario in which a real ultralight scalar $ϕ$ couples off-diagonally to down-type quarks, linking ultralight dark sectors to flavor physics. Working within an effective field theory, we diagonalize the quark mass matrix in a coherent $ϕ$ background and derive analytic expressions for oscillatory shifts in down-type quark masses and CKM parameters. These effects lead to signatures in both the classical regime, where $ϕ$ acts as a background field, and the quantum (particle) regime, where it contributes through on-shell production or off-shell mediation. Using precision flavor measurements, nuclear $β$ decays, atomic clocks, pulsar timing, and meson observables, we derive constraints on the flavor-violating couplings $λ_{ij}$ for $m_ϕ\sim 10^{-24}$--$10^{-12}\,\mathrm{eV}$, highlighting the complementarity of time-domain and flavor probes of ultralight dark sectors.

hep-ph↗

arXiv2026

DAP: A Discrete-token Autoregressive Planner for Autonomous Driving

Gaining sustainable performance improvement with scaling data and model budget remains a pivotal yet unresolved challenge in autonomous driving. While autoregressive models exhibited promising data-scaling efficiency in planning tasks, predicting ego trajectories alone suffers sparse supervision and weakly constrains how scene evolution should shape ego motion. Therefore, we introduce DAP, a discrete-token autoregressive planner that jointly forecasts BEV semantics and ego trajectories, thereby enforcing comprehensive representation learning and allowing predicted dynamics to directly condition ego motion. In addition, we incorporate a reinforcement-learning-based fine-tuning, which preserves supervised behavior cloning priors while injecting reward-guided improvements. Despite a compact 160M parameter budget, DAP achieves state-of-the-art performance on open-loop metrics and delivers competitive closed-loop results on the NAVSIM benchmark. Overall, the fully discrete-token autoregressive formulation operating on both rasterized BEV and ego actions provides a compact yet scalable planning paradigm for autonomous driving.

cs.AI↗

arXiv2026

Intrinsic Entropy of Context Length Scaling in LLMs

Long Context Language Models have drawn great attention in the past few years. There has been work discussing the impact of long context on Language Model performance: some find that long irrelevant context could harm performance, while some experimentally summarize loss reduction by relevant long context as Scaling Laws. This calls for a more thorough understanding of how long context impacts Language Modeling. In this work, we (1) propose to use `Intrinsic Entropy' for explaining the impact of context length on language modeling; and (2) conduct experiments on natural language and synthetic data, validating our proposed theoretical assumptions and deductions. Our theoretical framework can provide practical insights such as establishing that training dataset size dictates an optimal context length and bounds context length scaling for certain cases. We hope our work may inspire new long context Language Models, as well as future work studying the physics of Language Models.

cs.LG↗

arXiv2026

A Particle-in-Cell Simulation Framework for Thomson Scattering Analysis in Inertial Confinement Fusion

In inertial confinement fusion (ICF), Thomson scattering (TS) is a widely used diagnostic technique for probing plasma conditions. We present a first-principles numerical approach to obtaining scattered light signals of ion acoustic features with high resolution in angle and frequency space using particle-in-cell simulations under typical ICF conditions. Our method demonstrates good agreement with existing theories for thermal collective TS. In the super-thermal collective regime, the results align with theory when the driven plasma modes are well-matched in wave vectors to the probe and collecting beams. Moreover, we also find that TS signals can remain significant even under imperfect wave-vector matching-a result that contradicts the conventional expectation that the TS spectrum strictly follows the plasma density spectrum. We attribute this discrepancy to a beating wave mechanism arising from the interaction between the probe beam and driven plasma density modulations. Our work thus provides a practical framework for interpreting TS signals from driven ion modes, a common yet complex feature in ICF plasmas.

physics.plasm-ph↗

arXiv2026

Communication-Efficient Multi-Modal Edge Inference via Uncertainty-Aware Distributed Learning

Semantic communication is emerging as a key enabler for distributed edge intelligence due to its capability to convey task-relevant meaning. However, achieving communication-efficient training and robust inference over wireless links remains challenging. This challenge is further exacerbated for multi-modal edge inference (MMEI) by two factors: 1) prohibitive communication overhead for distributed learning over bandwidth-limited wireless links, due to the \emph{multi-modal} nature of the system; and 2) limited robustness under varying channels and noisy multi-modal inputs. In this paper, we propose a three-stage communication-aware distributed learning framework to improve training and inference efficiency while maintaining robustness over wireless channels. In Stage~I, devices perform local multi-modal self-supervised learning to obtain shared and modality-specific encoders without device--server exchange, thereby reducing the communication cost. In Stage~II, distributed fine-tuning with centralized evidential fusion calibrates per-modality uncertainty and reliably aggregates features distorted by noise or channel fading. In Stage~III, an uncertainty-guided feedback mechanism selectively requests additional features for uncertain samples, optimizing the communication--accuracy tradeoff in the distributed setting. Experiments on RGB--depth indoor scene classification show that the proposed framework attains higher accuracy with far fewer training communication rounds and remains robust to modality degradation or channel variation, outperforming existing self-supervised and fully supervised baselines.

cs.LG↗

arXiv2026

Deep Whole-body Parkour

Current approaches to humanoid control generally fall into two paradigms: perceptive locomotion, which handles terrain well but is limited to pedal gaits, and general motion tracking, which reproduces complex skills but ignores environmental capabilities. This work unites these paradigms to achieve perceptive general motion control. We present a framework where exteroceptive sensing is integrated into whole-body motion tracking, permitting a humanoid to perform highly dynamic, non-locomotion tasks on uneven terrain. By training a single policy to perform multiple distinct motions across varied terrestrial features, we demonstrate the non-trivial benefit of integrating perception into the control loop. Our results show that this framework enables robust, highly dynamic multi-contact motions, such as vaulting and dive-rolling, on unstructured terrain, significantly expanding the robot's traversability beyond simple walking or running. https://project-instinct.github.io/deep-whole-body-parkour

cs.RO↗

arXiv2025

Embodied Intelligence for Flexible Manufacturing: A Survey

Driven by breakthroughs in next-generation artificial intelligence, embodied intelligence is rapidly advancing into industrial manufacturing. In flexible manufacturing, industrial embodied intelligence faces three core challenges: accurate process modeling and monitoring under limited perception, dynamic balancing between flexible adaptation and high-precision control, and the integration of general-purpose skills with specialized industrial operations. Accordingly, this survey reviews existing work from three viewpoints: Industrial Eye, Industrial Hand, and Industrial Brain. At the perception level (Industrial Eye), multimodal data fusion and real-time modeling in complex dynamic settings are examined. At the control level (Industrial Hand), flexible, adaptive, and precise manipulation for complex manufacturing processes is analyzed. At the decision level (Industrial Brain), intelligent optimization methods for process planning and line scheduling are summarized. By considering multi-level collaboration and interdisciplinary integration, this work reveals the key technological pathways of embodied intelligence for closed-loop optimization of perception-decision-execution in manufacturing systems. A three-stage evolution model for the development of embodied intelligence in flexible manufacturing scenarios, comprising cognition enhancement, skill transition, and system evolution, is proposed, and future development trends are examined, to offer both a theoretical framework and practical guidance for the interdisciplinary advancement of industrial embodied intelligence in the context of flexible manufacturing.

cs.RO↗

arXiv2025

FASTer: Toward Efficient Autoregressive Vision Language Action Modeling via Neural Action Tokenization

Autoregressive vision-language-action (VLA) models have recently demonstrated strong capabilities in robotic manipulation. However, their core process of action tokenization often involves a trade-off between reconstruction fidelity and inference efficiency. We introduce FASTer, a unified framework for efficient and generalizable robot learning that integrates a learnable tokenizer with an autoregressive policy built upon it. FASTerVQ encodes action chunks as single-channel images, capturing global spatio-temporal dependencies while maintaining a high compression ratio. FASTerVLA builds on this tokenizer with block-wise autoregressive decoding and a lightweight action expert, achieving both faster inference and higher task performance. Extensive experiments across simulated and real-world benchmarks show that FASTerVQ delivers superior reconstruction quality, high token utilization, and strong cross-task and cross-embodiment generalization, while FASTerVLA further improves overall capability, surpassing previous state-of-the-art VLA models in both inference speed and task performance.

cs.CV↗

arXiv2025

Rectifying Soft-Label Entangled Bias in Long-Tailed Dataset Distillation

Dataset distillation compresses large-scale datasets into compact, highly informative synthetic data, significantly reducing storage and training costs. However, existing research primarily focuses on balanced datasets and struggles to perform under real-world long-tailed distributions. In this work, we emphasize the critical role of soft labels in long-tailed dataset distillation and uncover the underlying mechanisms contributing to performance degradation. Specifically, we derive an imbalance-aware generalization bound for model trained on distilled dataset. We then identify two primary sources of soft-label bias, which originate from the distillation model and the distilled images, through systematic perturbation of the data imbalance levels. To address this, we propose ADSA, an Adaptive Soft-label Alignment module that calibrates the entangled biases. This lightweight module integrates seamlessly into existing distillation pipelines and consistently improves performance. On ImageNet-1k-LT with EDC and IPC=50, ADSA improves tail-class accuracy by up to 11.8% and raises overall accuracy to 41.4%. Extensive experiments demonstrate that ADSA provides a robust and generalizable solution under limited label budgets and across a range of distillation techniques. Code is available at: https://github.com/j-cyoung/ADSA_DD.git.

cs.CV↗

arXiv2025

On the relative Morrison-Kawamata cone conjecture

We relate the Morrison-Kawamata cone conjecture for Calabi-Yau fiber spaces to the existence of Shokurov polytopes. For K3 fibrations, the existence of (weak) fundamental domains for movable cones is established. The relationship between the relative cone conjecture and the cone conjecture for its geometric or generic fibers is studied.

math.AG↗

arXiv2025

Janus-Pro-R1: Advancing Collaborative Visual Comprehension and Generation via Reinforcement Learning

Recent endeavors in Multimodal Large Language Models (MLLMs) aim to unify visual comprehension and generation. However, these two capabilities remain largely independent, as if they are two separate functions encapsulated within the same model. Consequently, visual comprehension does not enhance visual generation, and the reasoning mechanisms of LLMs have not been fully integrated to revolutionize image generation. In this paper, we propose to enable the collaborative co-evolution of visual comprehension and generation, advancing image generation into an iterative introspective process. We introduce a two-stage training approach: supervised fine-tuning teaches the MLLM with the foundational ability to generate genuine CoT for visual generation, while reinforcement learning activates its full potential via an exploration-exploitation trade-off. Ultimately, we unlock the Aha moment in visual generation, advancing MLLMs from text-to-image tasks to unified image generation. Extensive experiments demonstrate that our model not only excels in text-to-image generation and image editing, but also functions as a superior image semantic evaluator with enhanced visual comprehension capabilities. Project Page: https://janus-pro-r1.github.io.

cs.CV↗

arXiv2025

DepthVLA: Enhancing Vision-Language-Action Models with Depth-Aware Spatial Reasoning

Vision-Language-Action (VLA) models have recently shown impressive generalization and language-guided manipulation capabilities. However, their performance degrades on tasks requiring precise spatial reasoning due to limited spatial reasoning inherited from Vision-Language Models (VLMs). Existing VLAs rely on extensive action-data pretraining to ground VLMs in 3D space, which reduces training efficiency and is still insufficient for accurate spatial understanding. In this work, we present DepthVLA, a simple yet effective VLA architecture that explicitly incorporates spatial awareness through a pretrained depth prediction module. DepthVLA adopts a mixture-of-transformers design that unifies a VLM, a depth transformer, and an action expert with fully shared attentions, forming an end-to-end model with enhanced spatial reasoning. Extensive evaluations in both real-world and simulated environments show that DepthVLA outperforms state-of-the-art approaches, achieving 78.5% vs. 65.0% progress in real-world tasks, 94.9% vs. 93.6% in the LIBERO simulator, and 74.8% vs. 58.8% in the Simpler simulator. Our code will be made publicly available.

cs.CV↗

arXiv2025

Learning Personalized Driving Styles via Reinforcement Learning from Human Feedback

Generating human-like and adaptive trajectories is essential for autonomous driving in dynamic environments. While generative models have shown promise in synthesizing feasible trajectories, they often fail to capture the nuanced variability of personalized driving styles due to dataset biases and distributional shifts. To address this, we introduce TrajHF, a human feedback-driven finetuning framework for generative trajectory models, designed to align motion planning with diverse driving styles. TrajHF incorporates multi-conditional denoiser and reinforcement learning with human feedback to refine multi-modal trajectory generation beyond conventional imitation learning. This enables better alignment with human driving preferences while maintaining safety and feasibility constraints. TrajHF achieves performance comparable to the state-of-the-art on NavSim benchmark. TrajHF sets a new paradigm for personalized and adaptable trajectory generation in autonomous driving.

cs.RO↗

arXiv2025

Discrete Diffusion for Reflective Vision-Language-Action Models in Autonomous Driving

End-to-End (E2E) solutions have emerged as a mainstream approach for autonomous driving systems, with Vision-Language-Action (VLA) models representing a new paradigm that leverages pre-trained multimodal knowledge from Vision-Language Models (VLMs) to interpret and interact with complex real-world environments. However, these methods remain constrained by the limitations of imitation learning, which struggles to inherently encode physical rules during training. Existing approaches often rely on complex rule-based post-refinement, employ reinforcement learning that remains largely limited to simulation, or utilize diffusion guidance that requires computationally expensive gradient calculations. To address these challenges, we introduce ReflectDrive, a novel learning-based framework that integrates a reflection mechanism for safe trajectory generation via discrete diffusion. We first discretize the two-dimensional driving space to construct an action codebook, enabling the use of pre-trained Diffusion Language Models for planning tasks through fine-tuning. Central to our approach is a safety-aware reflection mechanism that performs iterative self-correction without gradient computation. Our method begins with goal-conditioned trajectory generation to model multi-modal driving behaviors. Based on this, we apply local search methods to identify unsafe tokens and determine feasible solutions, which then serve as safe anchors for inpainting-based regeneration. Evaluated on the NAVSIM benchmark, ReflectDrive demonstrates significant advantages in safety-critical trajectory generation, offering a scalable and reliable solution for autonomous driving systems.

cs.RO↗

arXiv2025

SAMP: Spatial Anchor-based Motion Policy for Collision-Aware Robotic Manipulators

Neural-based motion planning methods have achieved remarkable progress for robotic manipulators, yet a fundamental challenge lies in simultaneously accounting for both the robot's physical shape and the surrounding environment when generating safe and feasible motions. Moreover, existing approaches often rely on simplified robot models or focus primarily on obstacle representation, which can lead to incomplete collision detection and degraded performance in cluttered scenes. To address these limitations, we propose spatial anchor-based motion policy (SAMP), a unified framework that simultaneously encodes the environment and the manipulator using signed distance field (SDF) anchored on a shared spatial grid. SAMP incorporates a dedicated robot SDF network that captures the manipulator's precise geometry, enabling collision-aware reasoning beyond coarse link approximations. These representations are fused on spatial anchors and used to train a neural motion policy that generates smooth, collision-free trajectories in the proposed efficient feature alignment strategy. Experiments conducted in both simulated and real-world environments consistently show that SAMP outperforms existing methods, delivering an 11% increase in success rate and a 7% reduction in collision rate. These results highlight the benefits of jointly modelling robot and environment geometry, demonstrating its practical value in challenging real-world environments.

cs.RO↗

arXiv2025

OccVLA: Vision-Language-Action Model with Implicit 3D Occupancy Supervision

Multimodal large language models (MLLMs) have shown strong vision-language reasoning abilities but still lack robust 3D spatial understanding, which is critical for autonomous driving. This limitation stems from two key challenges: (1) the difficulty of constructing accessible yet effective 3D representations without expensive manual annotations, and (2) the loss of fine-grained spatial details in VLMs due to the absence of large-scale 3D vision-language pretraining. To address these challenges, we propose OccVLA, a novel framework that integrates 3D occupancy representations into a unified multimodal reasoning process. Unlike prior approaches that rely on explicit 3D inputs, OccVLA treats dense 3D occupancy as both a predictive output and a supervisory signal, enabling the model to learn fine-grained spatial structures directly from 2D visual inputs. The occupancy predictions are regarded as implicit reasoning processes and can be skipped during inference without performance degradation, thereby adding no extra computational overhead. OccVLA achieves state-of-the-art results on the nuScenes benchmark for trajectory planning and demonstrates superior performance on 3D visual question-answering tasks, offering a scalable, interpretable, and fully vision-based solution for autonomous driving.

cs.AI↗

arXiv2025

Deliberate Planning of 3D Bin Packing on Packing Configuration Trees

Online 3D Bin Packing Problem (3D-BPP) has widespread applications in industrial automation. Existing methods usually solve the problem with limited resolution of spatial discretization, and/or cannot deal with complex practical constraints well. We propose to enhance the practical applicability of online 3D-BPP via learning on a novel hierarchical representation, packing configuration tree (PCT). PCT is a full-fledged description of the state and action space of bin packing which can support packing policy learning based on deep reinforcement learning (DRL). The size of the packing action space is proportional to the number of leaf nodes, making the DRL model easy to train and well-performing even with continuous solution space. We further discover the potential of PCT as tree-based planners in deliberately solving packing problems of industrial significance, including large-scale packing and different variations of BPP setting. A recursive packing method is proposed to decompose large-scale packing into smaller sub-trees while a spatial ensemble mechanism integrates local solutions into global. For different BPP variations with additional decision variables, such as lookahead, buffering, and offline packing, we propose a unified planning framework enabling out-of-the-box problem solving. Extensive evaluations demonstrate that our method outperforms existing online BPP baselines and is versatile in incorporating various practical constraints. The planning process excels across large-scale problems and diverse problem variations. We develop a real-world packing robot for industrial warehousing, with careful designs accounting for constrained placement and transportation stability. Our packing robot operates reliably and efficiently on unprotected pallets at 10 seconds per box. It achieves averagely 19 boxes per pallet with 57.4% space utilization for relatively large-size boxes.

cs.RO↗

arXiv2025

DiffDecompose: Layer-Wise Decomposition of Alpha-Composited Images via Diffusion Transformers

Diffusion models have recently motivated great success in many generation tasks like object removal. Nevertheless, existing image decomposition methods struggle to disentangle semi-transparent or transparent layer occlusions due to mask prior dependencies, static object assumptions, and the lack of datasets. In this paper, we delve into a novel task: Layer-Wise Decomposition of Alpha-Composited Images, aiming to recover constituent layers from single overlapped images under the condition of semi-transparent/transparent alpha layer non-linear occlusion. To address challenges in layer ambiguity, generalization, and data scarcity, we first introduce AlphaBlend, the first large-scale and high-quality dataset for transparent and semi-transparent layer decomposition, supporting six real-world subtasks (e.g., translucent flare removal, semi-transparent cell decomposition, glassware decomposition). Building on this dataset, we present DiffDecompose, a diffusion Transformer-based framework that learns the posterior over possible layer decompositions conditioned on the input image, semantic prompts, and blending type. Rather than regressing alpha mattes directly, DiffDecompose performs In-Context Decomposition, enabling the model to predict one or multiple layers without per-layer supervision, and introduces Layer Position Encoding Cloning to maintain pixel-level correspondence across layers. Extensive experiments on the proposed AlphaBlend dataset and public LOGO dataset verify the effectiveness of DiffDecompose. The code and dataset will be available upon paper acceptance. Our code will be available at: https://github.com/Wangzt1121/DiffDecompose.

cs.CV↗