Searcharxiv⌕ Search

arXiv subjects

Jian Zhang

Publications and source records attributed to Jian Zhang.

At least 19 recordsLinked to original sources
arXiv2026

Mapping Text to Multiplex Graph: Prompt Compression as Lévy Walk-Guided Graph Pruning

Existing prompt compression methods treat text as flat token sequences, failing to capture the distributed nature of important information, which is often spread across multiple locations and connected through both local syntactic dependencies and global semantic relations. Such relational structure is naturally represented as a graph, where tokens or sentences become nodes and their dependencies become edges. To this end, we propose RAGP, which formulates prompt compression as Redundancy-Aware Graph Pruning on a multiplex graph that jointly models fine-grained attention-based dependencies and coarse-grained semantic relations. To efficiently identify non-redundant nodes in this heterogeneous structure (dense local subgraphs and sparse global connections), we employ Levy walks whose heavy-tailed step distribution naturally balances local exploitation with global exploration. Experiments on LongBench show that RAGP achieves an average score of 49.3 under a 4x compression ratio, outperforming existing LLM-based compression methods, such as LongLLMLingua, which attains 48.8 at a 3x compression ratio. Besides, RAGP also surpasses state-of-the-art vision-based text compression paradigms on multiple tasks.

cs.CL↗
arXiv2026

Bench2Dex: Benchmarking Visuo-Tactile Bimanual Dexterous Manipulation Across Dexterous Hands

Tactile sensing provides contact information that can be difficult to infer from vision alone, but tactile hardware for dexterous hands has not converged to a common design. Dexterous hands differ in finger structure, contact surfaces, and sensor layouts, while simulated tactile signals still differ from measurements produced by physical sensors. These factors make it difficult to study visuo-tactile manipulation across diverse dexterous hands within a consistent experimental setting. We present Bench2Dex, a simulation benchmark for visuo-tactile bimanual manipulation across 12 dexterous hands. We adapt existing robot models with a shared simulated tactile interface that converts local contact geometry into image-like tactile observations. The interface provides a consistent observation format across different hand morphologies without attempting to reproduce the output of a specific physical tactile sensor. Bench2Dex includes 26 bimanual manipulation tasks that involve tool use, articulated-object interaction, and multi-stage manipulation, together with about 1.3K human-teleoperated demonstrations. The benchmark provides synchronized visual, tactile, proprioceptive, action, and object-state observations, together with executable task metrics. For robustness, we group seven perturbation types into invariance axis, where the correct action does not change, and equivariance axis, where the correct action changes together with the perturbation. We evaluate ACT, Diffusion Policy, pi0.5, and GR00T N1.5 on Bench2Dex and report their performance and failure modes. Bench2Dex is meant as a platform for studying visuo-tactile learning across dexterous hands. It does not assume that simulated tactile observations can replace real tactile sensing; it offers a shared setting for algorithm development while tactile hardware and simulation models are still evolving.

cs.RO↗
arXiv2026

Nonparametric Correlation Estimator via Solving Cubic Equations and its Application to Brain Functional Connectivity Analysis

In this paper, we propose a novel nonparametric estimator for the correlation coefficient that is based on solving a cubic equation. This approach allows for the estimation of time-varying correlation coefficients in a nonparametric framework, providing flexibility in capturing complex relationships between variables. Furthermore, we adopt the local linear smoothing technique to correct the boundary effects, which are common in nonparametric estimation. We establish the theoretical properties of the proposed estimator, including consistency and asymptotic normality, and demonstrate its performance through simulation studies. Additionally, we apply our method to analyse dynamic functional connectivity in brain networks under six frequency bands, highlighting its potential for uncovering insights into neural interactions and cognitive processes.

stat.ME↗
arXiv2026

NS-VLA: Towards Neuro-Symbolic Vision-Language-Action Models

Vision-Language-Action (VLA) models are formulated to ground instructions in visual context and generate action sequences for robotic manipulation. Despite recent progress, VLA models still face structure-blind backbones, backbone-bound generalization, and flat single-objective optimization. To address these challenges, we propose a novel Neuro-Symbolic Vision-Language-Action (NS-VLA) framework. It introduces a Neuro-Symbolic Encoder for plan-constrained primitive inference, a Neuro-Symbolic Solver that conditions a backbone-agnostic policy on the active primitive, and Hierarchical Joint Policy Optimization with reward-granularity matching. Experiments on robotic manipulation benchmarks demonstrate that NS-VLA outperforms previous methods in both one-shot training and data-perturbed settings, while simultaneously exhibiting superior zero-shot generalizability and expanded exploration space. Our code is publicly available.

cs.RO↗
arXiv2026

Representations of Super Yangians with Gelfand-Tsetlin bases

The evaluation homomorphism from the super Yangian $\mathrm Y(\mathfrak{gl}_{m|n})$ to the universal enveloping algebra $\mathrm U(\mathfrak{gl}_{m|n})$ allows one to regard the $\mathfrak{gl}_{m|n}$-modules as $\mathrm Y(\mathfrak{gl}_{m|n})$-modules. In this paper, we establish necessary and sufficient conditions for simple tensor products of covariant evaluation modules to be tame. We also provide an explicit construction of Gelfand-Tsetlin bases for tensor products of skew modules.

math.RT↗
arXiv2026

RST: certifying and constructing prescribed information in variational autoencoders

Posterior-collapse diagnostics can show that a VAE uses its latent representation, but they do not determine whether a specified information view crosses a representation/readout interface fixed before training. Reconstruction-Student-Teacher (RST) makes this stronger requirement explicit: Reconstruction supplies the VAE objective, the Student is a fixed witness, and the Teacher is a frozen information specification. We derive a teacher-relative certificate showing that a positive margin guarantees transmission of the declared information through the prescribed interface, while every input-independent representation lies at or below the boundary. A centered regular-simplex witness turns this certificate into an explicit construction: a minimum-dimensional closed-form teacher code, its complete affine solution fiber, witness-visible and witness-null routing, a margin-energy path, function-space departure from the centered input-independent point, preservation cylinders, and orthogonal multi-view composition. Experiments on five datasets test boundary crossing, stronger KL pressure, teacher counterfactuals, null routing, escape, preservation, cross-seed reuse, and cross-architecture reuse. On CIFAR-100, auxiliary learned readers remain natively decodable but fail under no-refit transfer, whereas the same fixed RST witness directly reads independently trained ConvVAE and ResVAE encoders. Affine adapters recover transferred auxiliary readers, localizing much of the failure to interface-coordinate mismatch rather than absence of information. These results support prescribed alignment as distinct from ordinary decodability.

cs.LG↗
arXiv2026

Cartesian closedness of the category of real-valued sets, II

Let $[0,1]_*$ be the unit interval $[0,1]$ equipped with a left-continuous t-norm $*$. We prove that $[0,1]_*\text{-}\mathbf{Set}$ is cartesian closed if and only if $*$ is the minimum t-norm. This extends the classification for continuous t-norms established in the first part of this work to the whole left-continuous setting.

math.CT↗
arXiv2026

DualDiff3D: Dual Structure-Appearance Diffusion Priors for Reliability-Enhanced 3D Gaussian Splatting

While 3D Gaussian Splatting (3DGS) has revolutionized 3D reconstruction and novel-view synthesis, scenarios with limited input views often lead to poor reconstruction quality and artifacts in rendered novel views. Recent efforts attempt to utilize powerful diffusion priors, yet they typically process rendered and reference views concatenated along an additional dimension in a single network. These methods overlook an inherent nature that different views should maintain appearance similarity but differ in structure due to view shifts, leading to blur caused by conflicts between the two properties. In this paper, we propose DualDiff, a novel pipeline that leverages dual diffusion priors with a Structure-Appearance Attention (SAA) module to introduce reference guidance for refining low-quality novel views rendered from flawed 3D representations. Specifically, we retain one diffusion branch to focus on extracting structural information from the low-quality novel views, while introducing another branch to ensure appearance consistency with reference views. Furthermore, we present a 3D reconstruction framework named DualDiff3D, which integrates a reliability-enhanced Render-Refine-Optimize (RRO) loop to progressively and robustly incorporate the refined novel views, yielding more accurate 3DGS. Extensive experiments demonstrate that our approach outperforms state-of-the-art methods even in the inference-only setting, with further performance gains achievable through training. Our code and pre-trained weights are available at https://github.com/Akaneqwq/DualDiff3D.

cs.CV↗
arXiv2026

LAFR: Efficient Diffusion-based Blind Face Restoration via Latent Codebook Alignment Adapter

Blind face restoration from low-quality images is a challenging task that requires not only high-fidelity image reconstruction, but also preservation of facial identity. Although diffusion models like Stable Diffusion have shown promise in generating high-quality images, their VAE modules are typically trained on broad natural-image data dominated by HQ content; severely degraded LQ inputs therefore yield latents that fall in low-density regions of the diffusion prior, weakening the effectiveness of LQ conditions during the denoising process. Existing approaches often tackle this issue by retraining the VAE encoder, which is computationally expensive and memory intensive. To address this limitation efficiently, we propose LAFR, a codebook-based latent space adapter that aligns LQ latents to the in-distribution region the diffusion prior was trained to denoise, enabling sampling from a better matched latent condition without altering the original VAE. To further improve identity and structural consistency relative to OSEDiff-style baselines, we introduce a multilevel restoration loss combining constraints from semantic identity embeddings and facial structural priors. Furthermore, by leveraging the inherent structural regularity of facial images, we show that lightweight fine-tuning of a diffusion prior on just 0.9% of FFHQ can achieve competitive results while reducing training time by 70%. We also give a short analysis of why a codebook correction closes a mode-dependent latent gap that no global normalisation or affine map can. In summary, LAFR is a data and compute efficient one-step face-restoration method that improves perceptual quality, FID, landmark accuracy, and identity/structure consistency over OSEDiff-style baselines, without claiming uniform state of the art; it reaches this operating point while remaining competitive with far more expensive pipelines.

cs.CV↗
arXiv2026

Beyond the Stability-Exploration Dilemma: Environmental Regularization for LLM Policy Optimization

Policy optimization (PO) for Large Language Models faces a stability--exploration trade-off, currently mediated by an action-side Policy-KL regularizer. This puts practitioners in a double bind: keeping Policy-KL constrains response behavior and consumes the action-side exploration budget, while dropping it leaves the optimization without an explicit drift control. We argue for an alternative that breaks the dilemma by moving regularization to the input side. As training progresses, the distribution over training queries induced by the current policy drifts unchecked from its pre-RL reference distribution. Concretely, Environment-Regularized Policy Optimization (ERPO) introduces a Query-KL (QKL) term that bounds this query distribution shift, together with a dataset-static reference-derived per-query weight that biases each per-query update toward queries typical under the reference. The QKL gradient flows strictly through the query likelihood; the response score function used by policy-gradient estimators does not appear in the QKL term, so QKL exerts no direct gradient pressure on the response distribution---exploration is preserved. ERPO plugs into GRPO/PPO/REINFORCE-style pipelines without additional forward passes. On six mathematical reasoning benchmarks, ERPO replaces the standard Policy-KL regularizer while achieving effective control over query distribution drift, delivering stronger accuracy and substantially more stable behavior under high-temperature decoding and long-horizon training. Our source code are available at https://github.com/AlibabaResearch/ERPO

cs.CL↗
arXiv2026

A fast improved quasi-physical dynamic algorithm for efficient wireless coverage in convex polygonal regions

Deploying wireless nodes to maximize coverage area within a given region is an important challenge in wireless sensor networks, UAV path planning, base station placement and other industrial fields. This practical problem can be mathematically equivalent to an optimal circle covering problem. Although theoretical optimal configurations exist for simple cases in mathematics, the NP-hard nature of this problem makes it computationally prohibitive for complex polygons with numerous nodes. Existing approaches are usually designed for regular domains, while those applicable to irregular polygons often suffer from poor initialization, excessive coverage overlap and failure to constrain nodes within the boundary, leading to low coverage efficiency and long runtime. To address these issues, we propose an improved quasi-physical dynamic algorithm (IQPD) for wireless node deployment in arbitrary convex polygons. Our contributions are threefold: (1) proposing a structure-preserving initialization that maps a hexagonal close packing pattern into the target polygon via scaling and affine transformation, ensuring near-optimal initial node distribution; (2) constructing a refined virtual force model by incorporating friction and a radius-expansion optimization mechanism to reduce coverage area overlap; (3) developing a boundary encircling strategy leveraging normal and tangential gradients to reposition nodes deployed outside boundaries after initial optimization. Extensive experimental results demonstrate that our method consistently outperforms other new metaheuristic algorithms across diverse convex polygon shapes, including randomly generated data and real-world scenarios. Our method achieves the highest coverage rate and node utilization rate among all compared algorithms, greatly improving wireless coverage efficiency.

cs.CG↗
arXiv2026

CAS: Conformalized Agentic Search via Adaptive Retrieval and Policy Weighting

Search Agents face a severe reliability crisis during reinforcement learning (RL) fine-tuning. Heuristic Top-K retrieval often causes critical evidence loss or noise inclusion, while over-confidence induced by progressive RL leads to hallucinated answers and redundant searches. To build highly reliable agents, we introduce Conformal Prediction (CP) and propose Conformalized Agentic Search (CAS). This framework establishes reliability guarantees on both the retrieval and training sides: on the retrieval side, an Adaptive Prediction Set (APS), a specific CP realization, translates statistical coverage into dynamic document truncation to construct prediction sets that are adaptive in size; on the training side, Adaptive Conformal Inference (ACI), a dynamic CP algorithm, dynamically constructs prediction sets with controllable coverage to quantify answer confidence, which is then used to penalize low-confidence trajectories within the Group Relative Policy Optimization (GRPO) objective, ensuring the model learns only from reliable ones. Experiments across single-hop and multi-hop QA datasets demonstrate that our framework significantly improves reasoning accuracy while drastically reducing redundant tool invocations, establishing a highly reliable and efficient agent paradigm. Our code is available at https://github.com/S1llyBird/CAS.

cs.AI↗
arXiv2026

Making Collaborative Signals Count: Graph-Aware Large Language Models for Sequential Recommendation

Large language models (LLMs) have been widely adopted as backbones for recommender systems. However, their language-centric pretraining makes it difficult to capture collaborative signals implicit in user-item interactions, which are crucial for personalized recommendation. Existing methods either inject collaborative representations produced by external recommenders or model only intra-sequence dependencies, limiting their ability to exploit global collaborative patterns. To address this limitation, we propose GALLM, a graph-aware LLM framework for sequential recommendation. GALLM constructs a collaborative graph over text tokens and item tokens, and models three types of relations: Text--Text relations for preserving semantic dependencies, Item--Text relations for aligning item tokens with their textual descriptions, and Item--Item relations derived from global item co-occurrence patterns. These relations are transformed into lightweight learnable attention biases and incorporated into the LLM attention mechanism, enabling collaborative-aware token interactions without introducing an additional graph encoder. Experiments on four real-world benchmarks show that GALLM achieves the best performance among the compared baselines, improving over the strongest baseline by 9.76\% on average in HR@5.

cs.IR↗
arXiv2026

CompoSkill: Compositional Skill Chain Attacks from Individually Scanner-Passing LLM Agent Skills

Autonomous AI agents tackling Long Horizon Tasks depend on marketplace skills that are certified one at a time: a scanner returns a safety verdict for each skill and declares the ecosystem safe if every package passes. We show that this assumption fails under skill composition. A skill may pass the per-skill scanner individually yet participate in a risky composition when an agent connects its outputs, capabilities, or side effects with those of other scanner-passing skills. This makes skill composition risk a path level property rather than a node level property, explaining why existing skill scanners that inspect individual packages achieve limited interception. To study this threat, we present CompoSkill, a framework that constructs skill composition attacks through a dual attacker system. The white-box attacker knows the victim's installed skill pool and directly injects explicit skill-id sequences; the black-box attacker knows only a role profile, downloads the top marketplace skills for that scenario, builds a Skill Composition Graph, and searches for high risk chains whose implicit lures never name skill identifiers. We further construct CompoSkill-Bench, a benchmark of 1,140 records built from long-horizon professional workflows across five threats and six scenarios on OpenClaw and Nanobot. CompoSkill achieves risk Chain Formation Rates (CFR) up to 83.3% in the white box setting and 80.6% in the black box setting, while existing skill scanners block only a limited fraction of the risky compositions. Finally, we observe a bridge-bonus-then-hop-decay pattern: a bridge skill can increase attack success, but Attack Success Rate (ASR) decreases once additional hops make the risk chain longer than three skills. These results expose a systematic gap in single skill certification for autonomous AI agents.

cs.CR↗
arXiv2026

Self-Knowledge Retrieval Augmented Generation Framework for Patent Matching

Patent retrieval and matching based on large language models (LLMs) play a vital role in intellectual property protection. However, due to the complex structure of patent documents, dense technical terminology, and multi-modal information, traditional methods struggle to accurately identify subtle differences between patents. Existing LLM-based patent matching approaches typically rely on domain-specific pretrained or instruction tuning, which often entail high manual labeling costs and catastrophic forgetting. While retrieval-augmented generation (RAG) methods introduce external knowledge they fail to fully leverage LLM's capability to automatically parse patents and mine deep semantic relationships. To address these limitations, this paper proposes a self-knowledge RAG framework that guides LLMs to autonomously extract key technical entities and construct hierarchical ontological structures from patent matching queries, thereby enabling query expansion and precise retrieval. The method integrates the FAISS retrieval with a generative matching mechanism, leveraging self-knowledge to enhance the model's understanding of patent innovations and significantly improve retrieval and matching accuracy. Experimental results demonstrate the outstanding performance of the proposed method on real-world patent datasets, validating its effectiveness and application potential.

cs.IR↗
arXiv2026

TEAMMix: Taxonomy Enrichment Augmentation and Minority-augmented Mixing Strategy for LLM-enhanced Weak-Supervised Hierarchical Text Classification

Hierarchical Text Classification (HTC), as a critical text mining task, faces challenges such as complex label hierarchies and class imbalance. Existing methods based on large language models (LLMs) struggle to be efficiently applied to this task due to issues like lengthy prompts and loss of label structural information. To address these limitations, this paper proposes a weakly supervised HTC framework enhanced by LLM-based data augmentation. The framework first enriches the label hierarchy semantically through keyword generation and corpus mining, thereby enhancing the model's understanding of labels. Subsequently, it guides the LLM to generate pseudo-samples to mitigate the long-tail problem, and employs a Gaussian mixture model for confidence-based resampling to optimize the quality of generated data. Experimental results demonstrate that the proposed method effectively improves the reliability of LLM-generated pseudo-labels and significantly enhances classification performance on fine-grained and imbalanced datasets.

cs.CL↗
arXiv2026

CodecArena: Codec Quality Assessment via Visual Reinforcement Learning

Video coding is advancing into the low and ultra-low bitrate regime, driven by end-to-end codecs that replace the hand-crafted pipeline with jointly optimized neural networks and generative codecs that exploit the priors of video generation models. Yet the dominant metrics, LPIPS and DISTS, measure feature and texture similarity rather than content fidelity: a reconstruction that hallucinates a wrong face or blurs text into convincing strokes can still score well, even when a human rejects it instantly. To address this, we propose CodecArena, the first vision-language framework for video coding quality assessment, casting codec evaluation as source-conditioned comparative reasoning between a reference and its reconstructions. We optimize CodecArena with Facet-GRPO, a visual reinforcement learning scheme that aligns pairwise codec preferences while grounding the verdict in five fidelity facets: identity, objects, text, texture, and temporal consistency. Its facet-anchored reward uses automatically derived facet directions as weak anchors, rather than human per-facet labels, to prevent any single sub-score from dominating the holistic preference and to yield interpretable fine-grained quality judgments. To support training and evaluation in this underexplored regime, we construct two complementary resources: CodecArena-1K, a fully automatic preference dataset of 1,500 comparison groups built from traditional, neural, and generative codec reconstructions with fused vision-language and objective supervision; and CodecArena-Bench, a human-ranked benchmark with source-disjoint videos for fair out-of-domain evaluation. Extensive experiments demonstrate that CodecArena achieves state-of-the-art agreement with human judgments on source-disjoint content across diverse codecs and bitrates, surpassing perceptual metrics and prior vision-language evaluators.

cs.CV↗