Searcharxiv⌕ Search

arXiv subjects

Qiang Zhang

Publications and source records attributed to Qiang Zhang.

At least 37 records · Page 2Linked to original sources
arXiv2026

SOLO: Stable Omni-terrain Long-Horizon Perceptive Humanoid Locomotion

Humans traverse complex terrain over long distances without losing balance, whereas perceptive humanoid policies become fragile as perception and control errors accumulate. We present SOLO, a unified framework addressing two compounding causes of this long-horizon fragility: dense terrain reconstruction smooths action-critical details, and pointwise imitation lacks temporal credit assignment. Its Query Reconstructor (QR) uses Fourier-encoded cell queries to retrieve spatially specific evidence from depth-proprioception tokens, preserving sharp terrain boundaries. Trajectory-Aware MSE (TA-MSE) Distillation adds next-state teacher-student disagreement to the PPO reward, enabling Generalized Advantage Estimation to propagate future disagreement penalties to preceding actions. In simulation, QR reduces height-map L1 error by factors of 3.3-4.0, while TA-MSE surpasses PPO and MSE+PPO in curriculum progression. On stress-test terrains, SOLO achieves 97.5% mean traversal success and 96% stepping-stone success, versus 75.0-75.6% and 0-3% for dense-reconstructor variants. Deployed zero-shot with only a chest-mounted depth camera and proprioception, SOLO completes a continuous 1.5-km outdoor route and an indoor mixed-terrain course. Project page: https://sunpihai-up.github.io/solo/

cs.RO↗
arXiv2026

SciAtlas: A Computable Atlas of Science for Knowledge-Grounded AI Research

Artificial intelligence is rapidly entering the core workflows of scientific research. Yet reliable scientific reasoning requires access to accumulated scientific knowledge with sufficient breadth, depth, and standardization. Current AI scientists typically assemble scientific knowledge through workflow- and discipline-specific pipelines, which provide incomplete coverage, leave relations implicit, and make knowledge acquisition pathways fragmented. Here we present SciAtlas, a shared, machine-actionable cross-disciplinary scholarly knowledge infrastructure that integrates evidential, conceptual, disciplinary, expertise, and normative layers under a shared schema. SciAtlas further achieves a unified neuro-symbolic retrieval mechanism that grounds heterogeneous research objects, propagates relevance across the scholarly topology, and projects the resulting relevance field into the context required by each scientific workflow. Across three representative workflows, SciAtlas broadens trajectory reconstruction by recovering overlooked research branches, deepens opportunity discovery by uncovering underexplored bottlenecks and cross-domain insights, and strengthens innovation assessment by integrating evidence, expertise, and evaluation signals. Across three representative workflows, SciAtlas broadens trajectory reconstruction by recovering overlooked stages and branches, deepens opportunity discovery by uncovering underexplored bottlenecks and cross-domain connections, and standardizes innovation assessment by integrating evidence, expertise and evaluation signals. Extensive evaluations validate the foundational capabilities underpinning it as reusable knowledge infrastructure for knowledge-intensive scientific research.

cs.AI↗
arXiv2026

BRIDLE: Generalized Self-supervised Learning with Quantization

Self-supervised learning has been a powerful approach for learning meaningful representations from unlabeled data across various domains, reducing the reliance on large labeled datasets. Inspired by BERT's success in capturing deep bidirectional contexts in natural language processing, similar frameworks have been adapted to other modalities such as audio, with models like BEATs extending the bidirectional training paradigm to audio signals using vector quantization (VQ). However, these frameworks face challenges, notably their dependence on a single codebook for quantization, which may not capture the complex, multifaceted nature of signals. In addition, inefficiencies in codebook utilization lead to underutilized code vectors. To address these limitations, we introduce BRIDLE (Bidirectional Residual Quantization Interleaved Discrete Learning Encoder), a self-supervised encoder pretraining framework that incorporates residual quantization (RQ) into the bidirectional training process, and is generalized for pretraining with audio, image, and video. Using multiple hierarchical codebooks, RQ enables fine-grained discretization in the latent space, enhancing representation quality. BRIDLE involves an interleaved training procedure between the encoder and tokenizer. We evaluate BRIDLE on audio understanding tasks using classification benchmarks, achieving state-of-the-art results, and demonstrate competitive performance on image classification and video classification tasks, showing consistent improvements over traditional VQ methods in downstream performance.

cs.LG↗
arXiv2026

Contrastive Representation-Guided Genetic Minority Oversampling for Imbalanced Time-Series Classification

Real-world time-series classification tasks often exhibit class imbalance, which can be extremely severe in some applications. To avoid training biased classifiers on imbalanced data, sampling is one of the most popular data pre-processing techniques because of its classifier-agnostic nature. However, due to the complex temporal dependencies in original time-series data and the scarcity of minority-class samples, existing sampling methods, including interpolation-based oversampling methods and deep learning-based generative models, usually suffer from limited generalization and poor diversity when generating new time-series samples. This paper proposes a Frequency-domain representation-guided Multi-tree Genetic Programming-based oversampling approach (FreMGP) to imbalanced time-series classification, where each individual represents a set of synthetic samples for the minority class. A frequency-domain class-discriminative representation module based on contrastive learning is also developed, guiding the evolutionary search toward high-quality synthetic time-series samples. Experiments on imbalanced time-series datasets demonstrate that FreMGP outperforms existing oversampling methods and consistently improves the performance of different classifiers, including both general machine learning and deep learning models.

cs.LG↗
arXiv2026

SkillNet: Create, Evaluate, and Connect AI Skills

Current AI agents can flexibly invoke tools and execute complex tasks, yet their long-term advancement is hindered by the lack of systematic accumulation and transfer of skills. Without a unified mechanism for skill consolidation, agents frequently ``reinvent the wheel'', rediscovering solutions in isolated contexts without leveraging prior strategies. To address this challenge, we introduce SkillNet, an open infrastructure for creating, evaluating, and organizing AI skills at scale. SkillNet structures skills within a unified ontology that supports creating skills from heterogeneous sources, establishing rich relational connections, and performing multi-dimensional evaluation across Safety, Completeness, Executability, Maintainability, and Cost-awareness. Our infrastructure integrates a repository of over 600,000 skills, an interactive platform, and a versatile Python toolkit. Experiments on ALFWorld, WebShop, and ScienceWorld show 40% higher average rewards and 30% fewer execution steps across multiple backbone models. Furthermore, SkillNet-Gym benchmarks skill retrieval, utilization, and composition, while SkillNet-Fabric enables task-specific skill routing through lightweight Wikis. By formalizing skills as evolving, composable assets, SkillNet provides a robust foundation for agents to move from transient experience to durable mastery.

cs.AI↗
arXiv2026

Scale-invariant Optimal Sampling for Rare-events Data with Sparse Models

Subsampling is effective in tackling computational challenges for massive data with rare events. Overly aggressive subsampling may adversely affect estimation efficiency, and optimal subsampling is essential to mitigate the information loss. However, existing optimal subsampling probabilities depend on data scales, and some scaling transformations may result in inefficient subsamples. This problem is more significant when there are inactive features, because their influence on the subsampling probabilities can be arbitrarily magnified by inappropriate scaling transformations. We tackle this challenge and introduce a scale-invariant optimal subsampling function in the context of sparse models, where inactive features are commonly assumed. Instead of focusing on estimating model parameters, we define an optimal subsampling function to minimize the prediction error, using adaptive lasso to outline the estimation procedure and study its theoretical guarantee. We first introduce the adaptive lasso estimator for rare-events data and establish its oracle properties, thereby validating the use of subsampling. Then we derive a scale-invariant optimal subsampling function that minimizes the prediction error of the inverse probability weighted (IPW) adaptive lasso. Finally, we present an estimator based on the maximum sampled conditional likelihood (MSCL) to further improve the estimation efficiency. We conduct numerical experiments using both simulated and real-world data sets to demonstrate the performance of the proposed methods.

stat.ML↗
arXiv2026

MINT-Bench: A Comprehensive Multilingual Benchmark for Instruction-Following Text-to-Speech

Instruction-following text-to-speech (TTS) has emerged as an important capability for controllable and expressive speech generation, yet its evaluation remains underdeveloped due to limited benchmark coverage, weak diagnostic granularity, and insufficient multilingual support. We present \textbf{MINT-Bench}, a comprehensive multilingual benchmark for instruction-following TTS. MINT-Bench is built upon a hierarchical multi-axis taxonomy, a scalable multi-stage data construction pipeline, and a hierarchical hybrid evaluation protocol that jointly assesses content consistency, instruction following, and perceptual quality. Experiments across ten languages show that current systems remain far from solved: frontier commercial systems lead overall, while leading open-source models become highly competitive and can even outperform commercial counterparts in localized settings such as Chinese. The benchmark further reveals that harder compositional and paralinguistic controls remain major bottlenecks for current systems. We release MINT-Bench together with the data construction and evaluation toolkit to support future research on controllable, multilingual, and diagnostically grounded TTS evaluation. The leaderboard and demo are available at https://aslp-lab.github.io/MINT-Bench-Demo/

eess.AS↗
arXiv2026

RoboStriker: Latent-Space Strategic Games for Autonomous Humanoid Boxing

Achieving human-level competitive intelligence and physical agility in humanoid robots remains a profound challenge, particularly in contact-rich and highly dynamic tasks such as boxing. While Multi-Agent Reinforcement Learning offers a principled framework for strategic interaction, its direct application to unstructured raw motor spaces inevitably leads to joint-level physical collapse, preventing the emergence of any viable combat tactics. To resolve this fundamental conflict between strategic exploration and physical feasibility, we formulate the humanoid combat task as a novel two-player latent-space zero-sum Markov game. Under standard regularity and approximate best-response assumptions, we show that the latent formulation induces an equivalent game over the decoder-reachable action manifold, providing an approximate-Nash interpretation of the resulting self-play dynamics. To instantiate this theoretical formulation, we propose RoboStriker, a hierarchical framework that decouples high-level reasoning from low-level execution. It first distills the tracking expertise of predefined boxing motions into a topologically bounded latent manifold. This structured latent foundation subsequently drives multi-agent co-evolution via Latent-Space Neural Fictitious Self-Play. Extensive experimental results demonstrate that gaming within this structured latent space substantially outperforms direct exploration. By constraining strategic exploration through a pretrained motion decoder, RoboStriker substantially reduces the catastrophic balance failures observed in raw action-space methods and achieves superior tactical performance in both competitive win rates and striking efficiency. Finally, we successfully deploy and validate our learned combat policies on real-world humanoid robots. Our code and video and supplementary materials are available at RoboStriker.

cs.RO↗
arXiv2026

HPSO: Particle Swarm Optimization with Hypergraph-Based Topology

Particle swarm optimization (PSO) has been widely applied to solve complex optimization problems from real-world applications due to its efficient exploration of large solution spaces and the ability to converge towards optimal solutions without requiring gradient information. Common swarm topologies in standard PSO and its variants, e.g., Ring and Star, can be regarded as graphs, where each edge connects only two particles. Such topology structures allow direct interactions only between connected particle pairs, and thus often fail to directly capture the higher-order social relationships that are necessary for navigating complex search landscapes. Therefore, this article proposes a novel PSO variant termed Hypergraph-assisted Particle Swarm Optimization (HPSO). In HPSO, the topology of the particles in a swarm is modeled by a hypergraph, in which hyperedges are used to connect multiple particles. This allows multiple particles within a hyperedge to interact directly. Furthermore, an adaptive hypergraph updating strategy is designed to periodically reconstruct the topology based on cumulative average particle displacement, thereby maintaining swarm diversity throughout the evolutionary process. In the experiments, the effectiveness of HPSO is verified on the IEEE CEC'17 benchmark suite, and the results demonstrate that HPSO achieves promising performance across various types of functions. Furthermore, the ablation experiment demonstrates that HPSO has excellent search capabilities.

cs.NE↗
arXiv2026

When Teachers Mislead: Spurious-Signal-Aware On-Policy Distillation

On-Policy distillation (OPD) transfers teacher capabilities by supervising student-sampled trajectories with dense token-level teacher signals. Recent selective OPD methods improve this process by prioritizing signals that are confident, informative, or learnable. However, the assumptions overlook a fundamental failure mode of language models: their token-level judgments can be driven by input-agnostic language priors, formatting conventions, or stereotyped reasoning templates rather than task-specific evidence. We refer to such optimization-relevant but weakly input-grounded supervision as spurious signals in OPD, which may produce large gradients while contributing little task-improving direction. To mitigate this issue, we propose SA-OPD, a Spurious-Signal-Aware On-Policy Distillation framework that identifies and filters misleading token-level supervision based on input-groundedness and optimization impact. SA-OPD introduces a lightweight input-groundedness proxy estimating whether a token-level distillation signal truly depends on the input. It then filters only tokens that simultaneously exhibit low input-groundedness and extreme distillation divergence, thereby removing high-impact spurious updates and achieving fine-grained OPD optimization. Extensive experiments on both large language model (LLM) and vision-language model (VLM) settings demonstrate that SA-OPD consistently outperforms Vanilla OPD and competitive selective methods. These results establish input-groundedness as a key dimension for OPD supervision selection and offer a simple, effective strategy for mitigating spurious updates.

cs.AI↗
arXiv2026

Local magnetic order in vacancy-disrupted spin ice Ho2TiO5

We investigate how local magnetic correlations evolve when the classical pyrochlore spin-ice Ho2Ti2O7 is transformed into the partially disordered stuffed compound Ho2TiO5. Neutron scattering measurements were analyzed using real-space magnetic pair distribution function, reciprocal-space reverse Monte Carlo, and half-polarized neutron powder diffraction methods to connect the average crystal structure with local magnetic correlations. Both compounds retain long-range $Fd-3m symmetry, but in Ho2TiO5 this average structure distorts locally through Ho-O, Ti-O and O-O bond-length disorder associated with partial Ho/Ti occupancy. Despite this disorder, half-polarized neutron powder diffraction shows that the Ho moments retain local <111> rangle Ising anisotropy and form spin-in/spin-out configurations on the tetrahedral network. In Ho2Ti2O7, real- and reciprocal-space analyses reveal a nearly ideal two-in/two-out spin-ice state at 0.3K, with 95% of tetrahedra satisfying the ice rule, followed by progressive thermal disordering on warming. In Ho2TiO5, most tetrahedra are magnetically incomplete because some tetrahedral vertices are occupied by nonmagnetic Ti rather than Ho; nevertheless, the dominant incomplete configurations are 2-in/1-out and 1-in/2-out, which are locally compatible with the ice rule if the missing Ho spin is restored. The single-ion <111> Ising anisotropy is therefore retained throughout, while the collective ice ordering is strongly disrupted: Ho2TiO5 is a vacancy-disrupted spin ice in which a local ice-rule tendency persists on a topologically incomplete magnetic network.

cond-mat.str-el↗
arXiv2026

Mamba Policy: Towards Efficient 3D Diffusion Policy with Hybrid Selective State Models

Diffusion models have been widely employed in the field of 3D manipulation due to their efficient capability to learn distributions, allowing for precise prediction of action trajectories. However, diffusion models typically rely on large parameter UNet backbones as policy networks, which can be challenging to deploy on resource-constrained devices. Recently, the Mamba model has emerged as a promising solution for efficient modeling, offering low computational complexity and strong performance in sequence modeling. In this work, we propose the Mamba Policy, a lighter but stronger policy that reduces the parameter count by over 80% compared to the original policy network while achieving superior performance. Specifically, we introduce the XMamba Block, which effectively integrates input information with conditional features and leverages a combination of Mamba and Attention mechanisms for deep feature extraction. Extensive experiments demonstrate that the Mamba Policy excels on the Adroit, Dexart, and MetaWorld datasets, requiring significantly fewer computational resources. Additionally, we highlight the Mamba Policy's enhanced robustness in long-horizon scenarios compared to baseline methods and explore the performance of various Mamba variants within the Mamba Policy framework. Real-world experiments are also conducted to further validate its effectiveness. Our open-source project page can be found at https://sagecao1125.github.io/mamba_policy/.

cs.RO↗
arXiv2026

DPL: Depth-only Perceptive Humanoid Locomotion via Realistic Depth Synthesis and Cross-Attention Terrain Reconstruction

Recent advancements in legged robot perceptive locomotion have shown promising progress. However, terrain-aware humanoid locomotion remains largely constrained to two paradigms: depth image-based end-to-end learning and elevation map-based methods. The former suffers from limited training efficiency and a significant sim-to-real gap in depth perception, while the latter depends heavily on multiple vision sensors and localization systems, resulting in latency and reduced robustness. To overcome these challenges, we propose a novel framework that tightly integrates three key components: (1) Terrain-Aware Locomotion Policy with a Blind Backbone, which leverages pre-trained elevation map-based perception to guide reinforcement learning with minimal visual input; (2) Multi-Modality Cross-Attention Transformer, which reconstructs structured terrain representations from noisy depth images; (3) Realistic Depth Images Synthetic Method, which employs self-occlusion-aware ray casting and noise-aware modeling to synthesize realistic depth observations, achieving over 30\% reduction in terrain reconstruction error. This combination enables efficient policy training with limited data and hardware resources, while preserving critical terrain features essential for generalization. We validate our framework on a full-sized humanoid robot, demonstrating agile and adaptive locomotion across diverse and challenging terrains.

cs.RO↗
arXiv2026

Non-relativistic spin splitting in a triangular metal-excess magnet Fe$_{1+δ}$Sb

Non-relativistic spin-splitting (NRSS) antiferromagnets have recently emerged as an important class of magnetic materials that combine compensated magnetism with momentum-dependent spin splitting, offering new opportunities for spintronic applications. Here, we investigate a NiAs-type Fe$_{1+δ}$Sb series ($δ= 0.17$-0.30) using neutron diffraction, pair distribution function, magnetometry and density functional theory calculations. Neutron diffraction establishes that Fe$_{1+δ}$Sb adopts a $120^\circ$ coplanar compensated magnetic order with a non-zero propagation vector $\mathbf{k}=(1/3,\,1/3,\,0)$. Increasing interstitial Fe suppresses the ordered magnetic moment while inducing local symmetry lowering, as revealed by pair distribution function refinements. Density functional theory predicts momentum-dependent spin splitting, dominated by an out-of-plane spin polarization with an odd-parity f-wave-like symmetry, establishing the material as a non-collinear NRSS antiferromagnet. Motivated by the structural similarities between Fe$_{1+δ}$Sb and a known altermagnet CrSb, we further investigate their solid solution and find that Cr substitution at intermediate concentrations gives rise to a ferromagnetic component and a cluster spin-glass behavior. These results establish Fe$_{1+δ}$Sb as a new platform for non-collinear NRSS antiferromagnetism and demonstrate metal interstitial and substitution as effective parameters for tuning the magnetic order and properties.

cond-mat.mtrl-sci↗
arXiv2026

SciToolAgent-Evo: An Ontology-Aware Self-Evolving Agent for Open-World Scientific Tool Acquisition

Large language model (LLM) agents have been increasingly adopted in scientific research for organizing and invoking specialized computational tools. However, their reliance on predefined tool spaces with static semantics limits their applicability to open-world scientific workflows, where tool requirements, capabilities, and boundaries evolve dynamically. To this end, we propose SciToolAgent-Evo, an ontology-aware self-evolving agent for open-world scientific tool acquisition. Driven by an evolving memory of skills, experiences, and an ontologized tool graph, it distills generalizable knowledge from contrastive trajectories during accumulation, whereas during inference, it formulates active requests and utilizes a LinUCB-based bandit gate to dynamically balance exploration and exploitation. Once a novel tool is acquired, its scientific ontology is completed online for seamless integration into the known graph. Moreover, we introduce OpenSciToolBench, a benchmark containing 900 realistic tasks across four difficulty levels. Extensive evaluations show that SciToolAgent-Evo achieves state-of-the-art performance, validating its robustness and generalization.

cs.AI↗
arXiv2026

RecoWorld: Building Simulated Environments for Agentic Recommender Systems

We present RecoWorld, a blueprint for building simulated environments tailored to agentic recommender systems. Such environments give agents a proper training space where they can learn from errors without impacting real users. RecoWorld distinguishes itself with a dual-view architecture: a simulated user and an agentic recommender engage in multi-turn interactions aimed at maximizing user retention. The user simulator reviews recommended items, updates its mindset, and when sensing potential user disengagement, generates reflective instructions. The agentic recommender adapts its recommendations by incorporating these user instructions and reasoning traces, creating a dynamic feedback loop that actively engages users. This process leverages the exceptional reasoning capabilities of modern LLMs. We explore diverse content representations within the simulator, including text-based, multimodal, and semantic ID modeling, and discuss how multi-turn RL enables the recommender to refine its strategies through iterative interactions. RecoWorld also supports multi-agent simulations, allowing creators to simulate the responses of targeted user populations. It marks an important first step toward recommender systems where users and agents collaboratively shape personalized information streams. We envision new interaction paradigms where "user instructs, recommender responds," jointly optimizing user retention and engagement.

cs.IR↗
arXiv2026

Commutator relators of one-relator groups do not force Hopficity, residual finiteness, or automaticity

Let $G=F/\langle\langle r\rangle\rangle$ be a one-relator group with the relator $r\in [F,F]$ or $r=[u,v] ~(u,v\in F)$, where $F$ is a finitely generated free group. Baumslag asked whether $G$ is Hopfian, residually finite or automatic. In the case of $r\in[F,F]$, a negative answer to the residual finiteness and automaticity has already been obtained by a result of Olshanskii. In this note, we construct a family of one-relator groups $$G_m=\left\langle a,t\ \middle|\ [t,a[a,t]^{-m}]\right\rangle,$$ whose relators are commutators, each of which has a Baumslag-Solitar subgroup as a retract. These groups provide negative answers to these three questions in both cases.

math.GR↗
arXiv2026

Code-in-the-Loop Forensics: Agentic Tool Use for Image Forgery Detection

Existing image forgery detection (IFD) methods either exploit low-level, semantics-agnostic artifacts or rely on multimodal large language models (MLLMs) with high-level semantic knowledge. Although naturally complementary, these two information streams are highly heterogeneous in both paradigm and reasoning, making it difficult for existing methods to unify them or effectively model their cross-level interactions. To address this gap, we propose ForenAgent, a multi-round interactive IFD framework that enables MLLMs to autonomously generate, execute, and iteratively refine Python-based low-level tools around the detection objective, thereby achieving more flexible and interpretable forgery analysis. ForenAgent follows a two-stage training pipeline combining Cold Start and Reinforcement Fine-Tuning to enhance its tool interaction capability and reasoning adaptability progressively. Inspired by human reasoning, we design a dynamic reasoning loop comprising global perception, local focusing, iterative probing, and holistic adjudication, and instantiate it as both a data-sampling strategy and a task-aligned process reward. For systematic training and evaluation, we construct FABench, a heterogeneous, high-quality agent-forensics dataset comprising 100k images and approximately 200k agent-interaction question-answer pairs. Experiments show that ForenAgent exhibits emergent tool-use competence and reflective reasoning on challenging IFD tasks when assisted by low-level tools, charting a promising route toward general-purpose IFD. The code will be released after the review process is completed.

cs.AI↗