Searcharxiv⌕ Search

arXiv subjects

Yan Zhang

Publications and source records attributed to Yan Zhang.

At least 91 records · Page 5Linked to original sources
arXiv2026

Unveil: Unified Visual-Textual Integration and Distillation for Multi-modal Document Retrieval

Document retrieval in real-world scenarios faces significant challenges due to diverse document formats and modalities. Traditional text-based approaches rely on tailored parsing techniques that disregard layout information and are prone to errors, while recent parsing-free visual methods often struggle to capture fine-grained textual semantics in text-rich scenarios. To address these limitations, we propose \textbf{Unveil}, a novel visual-textual embedding framework that effectively integrates textual and visual features for robust document representation. Through knowledge distillation, we transfer the semantic understanding capabilities from the visual-textual embedding model to a purely visual model, enabling efficient parsing-free retrieval while preserving semantic fidelity. Experimental results demonstrate that our visual-textual embedding method surpasses existing approaches, while knowledge distillation successfully bridges the performance gap between visual-textual and visual-only methods, improving both retrieval accuracy and efficiency.

cs.CL↗
arXiv2026

Learn2Decompose: Learning Problem Decomposition for Efficient Sequential Multi-object Manipulation Planning

We present an efficient task and motion replanning approach for sequential multi-object manipulation in dynamic environments. Conventional Task And Motion Planning (TAMP) solvers experience an exponential increase in planning time as the planning horizon and number of objects grow, limiting their applicability in real-world scenarios. To address this, we propose learning problem decompositions from demonstrations to accelerate TAMP solvers. Our approach consists of three key components: goal decomposition learning, computational distance learning, and object reduction. Goal decomposition identifies the necessary sequences of states that the system must pass through before reaching the final goal, treating them as subgoal sequences. Computational distance learning predicts the computational complexity between two states, enabling the system to identify the temporally closest subgoal from a disturbed state. Object reduction minimizes the set of active objects considered during replanning, further improving efficiency. We evaluate our approach on three benchmarks, demonstrating its effectiveness in improving replanning efficiency for sequential multi-object manipulation tasks in dynamic environments.

cs.RO↗
arXiv2026

ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Effective information searching is essential for enhancing the reasoning and generation capabilities of large language models (LLMs). Recent research has explored using reinforcement learning (RL) to improve LLMs' search capabilities by interacting with live search engines in real-world environments. While these approaches show promising results, they face two major challenges: (1) Uncontrolled Document Quality: The quality of documents returned by search engines is often unpredictable, introducing noise and instability into the training process. (2) Prohibitively High API Costs: RL training requires frequent rollouts, potentially involving hundreds of thousands of search requests, which incur substantial API expenses and severely constrain scalability. To address these challenges, we introduce ZeroSearch, a novel RL framework that incentivizes the capabilities of LLMs to use a real search engine with simulated searches during training. Our approach begins with lightweight supervised fine-tuning to transform the LLM into a retrieval module capable of generating both useful and noisy documents in response to a query. During RL training, we employ a curriculum-based rollout strategy that incrementally degrades the quality of generated documents, progressively eliciting the model's reasoning ability by exposing it to increasingly challenging retrieval scenarios. Extensive experiments demonstrate that ZeroSearch effectively incentivizes the search capabilities of LLMs using a 3B LLM as the retrieval module. Remarkably, a 7B retrieval module achieves comparable performance to the real search engine, while a 14B retrieval module even surpasses it. Furthermore, it generalizes well across both base and instruction-tuned models of various parameter sizes and is compatible with a wide range of RL algorithms.

cs.CL↗
arXiv2026

AdaSwitch: Adaptive Switching between Small and Large Agents for Effective Cloud-Local Collaborative Learning

Recent advancements in large language models (LLMs) have been remarkable. Users face a choice between using cloud-based LLMs for generation quality and deploying local-based LLMs for lower computational cost. The former option is typically costly and inefficient, while the latter usually fails to deliver satisfactory performance for reasoning steps requiring deliberate thought processes. In this work, we propose a novel LLM utilization paradigm that facilitates the collaborative operation of large cloud-based LLMs and smaller local-deployed LLMs. Our framework comprises two primary modules: the local agent instantiated with a relatively smaller LLM, handling less complex reasoning steps, and the cloud agent equipped with a larger LLM, managing more intricate reasoning steps. This collaborative processing is enabled through an adaptive mechanism where the local agent introspectively identifies errors and proactively seeks assistance from the cloud agent, thereby effectively integrating the strengths of both locally-deployed and cloud-based LLMs, resulting in significant enhancements in task completion performance and efficiency. We evaluate AdaSwitch across 7 benchmarks, ranging from mathematical reasoning and complex question answering, using various types of LLMs to instantiate the local and cloud agents. The empirical results show that AdaSwitch effectively improves the performance of the local agent, and sometimes achieves competitive results compared to the cloud agent while utilizing much less computational overhead.

cs.CL↗
arXiv2026

DecoupleSearch: Decouple Planning and Search via Hierarchical Reward Modeling

Retrieval-Augmented Generation (RAG) systems have emerged as a pivotal methodology for enhancing Large Language Models (LLMs) through the dynamic integration of external knowledge. To further improve RAG's flexibility, Agentic RAG introduces autonomous agents into the workflow. However, Agentic RAG faces several challenges: (1) the success of each step depends on both high-quality planning and accurate search, (2) the lack of supervision for intermediate reasoning steps, and (3) the exponentially large candidate space for planning and searching. To address these challenges, we propose DecoupleSearch, a novel framework that decouples planning and search processes using dual value models, enabling independent optimization of plan reasoning and search grounding. Our approach constructs a reasoning tree, where each node represents planning and search steps. We leverage Monte Carlo Tree Search to assess the quality of each step. During inference, Hierarchical Beam Search iteratively refines planning and search candidates with dual value models. Extensive experiments across policy models of varying parameter sizes demonstrate the effectiveness of our method.

cs.IR↗
arXiv2026

Setting the Stage: Text-Driven Scene-Consistent Image Generation

We focus on the foundational task of Scene Staging: given a reference scene image and a text condition specifying an actor category to be generated in the scene and its spatial relation to the scene, the goal is to synthesize an output image that preserves the same scene identity as the reference image while correctly generating the actor according to the spatial relation described in the text. Existing methods struggle with this task, largely due to the scarcity of high-quality paired data and unconstrained generation objectives. To overcome the data bottleneck, we propose a novel data construction pipeline that combines real-world photographs, entity removal, and image-to-video diffusion models to generate training pairs with diverse scenes, viewpoints and correct entity-scene relationships. Furthermore, we introduce a novel correspondence-guided attention loss that leverages cross-view cues to enforce spatial alignment with the reference scene. Experiments on our scene-consistent benchmark show that our approach achieves better scene alignment and text-image alignment than state-of-the-art baselines, according to both automatic metrics and human preference studies. Our method generates images with diverse viewpoints and compositions while faithfully following the textual instructions and preserving the reference scene identity.

cs.CV↗
arXiv2026

Modality-Aware Identity Construction and Counterfactual Structure Learning for ID-Free Multimodal Recommendation

Multimodal recommendation has attracted extensive attention by leveraging heterogeneous modality information to alleviate data sparsity and improve recommendation accuracy. Existing methods have attempted to replace ID embeddings with multimodal features and have achieved promising preliminary results. However, these methods still exhibit the following two limitations: (1) the reconstructed ID representations remain relatively static and fail to fully exploit multimodal semantics; and (2) the graph learning process is insufficient in mining latent long-tail semantic relations and is easily affected by popularity bias. To address these issues, we propose a novel method named Modality-Aware Identity Construction and Counterfactual Structure Learning for ID-free Multimodal Recommendation (MAIL). Specifically, we design a modality-aware identity construction module that dynamically modulates positional encodings with multimodal semantics to construct content-aware ID-free identity representations. Then, we propose a counterfactual structure learning paradigm that mines low-exposure semantic neighbors via popularity penalization and alleviates popularity bias. Extensive experiments are conducted on five public Amazon datasets. Experimental results show that MAIL achieves average improvements of 7.81% in Recall@10 and 12.81% in NDCG@10 compared with the baseline models. Our code is available at https://github.com/HubuKG/MAIL.

cs.IR↗
arXiv2026

VoxScene: Anchor-Conditioned Voxel Diffusion for Indoor Scene Arrangement

We present VoxScene, a novel anchor-conditioned voxel diffusion framework tailored for 3D scene synthesis. Current data-driven layout generation techniques typically rely on bounding proxies or implicit representations, which overlook volumetric structures. This geometric blindness inevitably leads to severe physical collisions and structural entanglement, particularly in densely populated environments. To overcome these limitations, we shift the paradigm to an explicit, object-centric voxel representation. Our pipeline sequentially synthesizes discrete volumetric occupancies conditioned on prior anchors and local context. By exploiting the mutually exclusive nature of discrete voxels, our approach eliminates spatial ambiguities and guarantees collision-free arrangements, even in highly complex environments. Furthermore, the synthesized high-fidelity voxel grids serve as discriminative geometric queries for downstream asset retrieval. Extensive experiments demonstrate the universality of our method, achieving state-of-the-art physical plausibility and unlocking shape diversity compared to existing layout planners.

cs.GR↗
arXiv2026

Learn where to Click from Yourself: On-Policy Self-Distillation for GUI Grounding

Graphical User Interface (GUI) grounding maps natural language instructions to the visual coordinates of target elements and serves as a core capability for autonomous GUI agents. Recent reinforcement learning methods (e.g., GRPO) have achieved strong performance, but they rely on expensive multiple rollouts and suffer from sparse signals on hard samples. These limitations make on-policy self-distillation (OPSD), which provides dense token-level supervision from a single rollout, a promising alternative. However, its applicability to GUI grounding remains unexplored. In this paper, we present GUI-SD, the first OPSD framework tailored for GUI grounding. First, it constructs a visually enriched privileged context for the teacher using a target bounding box and a Gaussian soft mask, providing informative guidance without leaking exact coordinates. Second, it employs entropy-guided distillation, which adaptively weights tokens based on digit significance and teacher confidence, concentrating optimization on the most impactful and reliable positions. Extensive experiments on six representative GUI grounding benchmarks show that GUI-SD consistently outperforms GRPO-based methods and naive OPSD in both accuracy and training efficiency. Code and training data are available at https://zhangyan-ucas.github.io/GUI-SD/.

cs.AI↗
arXiv2026

Light baryonium states with exotic quantum numbers

The existence of baryonium-bound or resonant states composed of a baryon and an antibaryon has long been postulated as a natural extension of conventional hadron spectroscopy. In the present work, we conduct a systematic investigation of the mass spectrum and internal configurations of light baryonium candidates exhibiting exotic quantum numbers that are inaccessible within the framework of the traditional quark model. Employing the method of QCD sum rules, we analyze nucleon-antinucleon and light hyperon-anti-hyperon systems with quantum numbers $J^{PC}=0^{--}$ and $0^{+-}$, which are quantum number combinations prohibited for conventional mesonic states. Our analysis reveals the potential existence of two $0^{--}$ $Λ$-$\barΛ$ baryonium states with masses $(2.90\pm0.09)$ GeV and $(3.36\pm0.09)$ GeV, respectively, as well as two $0^{+-}$ $Λ$-$\barΛ$ states with masses $(2.91\pm0.07)$ GeV and $(3.29\pm0.07)$ GeV, respectively. In addition, corresponding nucleon-antinucleon partner states are identified at $(2.69\pm0.07)$ GeV, $(3.07\pm0.08)$ GeV, $(2.86\pm0.07)$ GeV, and $(3.22\pm0.07)$ GeV, respectively. Furthermore, analogous $Ξ$-$\barΞ$ configurations are predicted with masses of $(3.10\pm0.09)$ GeV, $(3.54\pm0.07)$ GeV, $(3.08\pm0.08)$ GeV, and $(3.45\pm0.08)$ GeV, respectively. The possible decay modes of the light exotic baryonium states are analyzed, which are hopefully measurable in BESIII, BELLEII, and LHCb experiments.

hep-ph↗
arXiv2026

Quantum state preparation and transfer based on the bound state in the doublon continuum

Bound states in the continuum (BICs) have attracted intense interest, yet their many-particle counterparts remain largely unexplored in waveguide quantum electrodynamics. We identify and characterize a bound state embedded in the doublon continuum (BIDC) that emerges when four atoms couple to a coupled-resonator waveguide with strong on-site interaction. Exploiting this interaction-enabled BIDC, we show that (i) a distant, four-atom entangled state can be prepared with high fidelity, and (ii) quantum entangled states can be coherently transferred between spatially separated nodes. Our results establish a scalable mechanism for multi-particle state generation and routing in waveguide platforms, opening a route to interaction-protected quantum communication with many-particle BICs.

quant-ph↗
arXiv2026

Spectrum of $J^{PC} = 0^{\pm\pm}$ Gluonic Hidden-Charm Tetraquark States

We investigate gluonic hidden-charm tetraquark states composed of two valence quarks, two valence antiquarks and an explicit valence gluon. In the color configuration $[\bar{3}_c]_{c q}\otimes[8_c]_{G}\otimes[3_c]_{\bar{c}\bar{q}}$, a complete set of eight interpolating currents is constructed for states with quantum numbers $^{PC}=0^{++}$, $0^{-+},$ $0^{--}$, and $0^{+-}$. The corresponding mass spectra are systematically analysed within the QCD sum rule framework, including nonperturbative condensate contributions up to dimension eight. Our numerical analysis indicates the possible existence of six gluonic hidden-charm tetraquark states exhibiting stable behaviour in the adopted Borel windows. By replacing the charm quark with the bottom quark, masses for the corresponding hidden-bottom partners are also estimated. Possible production mechanisms and dominant decay channels are discussed, providing phenomenological guidance for experimental searches. These predicted states may be accessible at current and forthcoming facilities, including Belle II, PANDA, SuperB and LHCb, and thus offer an opportunity to probe explicit gluonic degrees of freedom in multiquark systems and deepen our understanding of nonperturbative QCD.

hep-ph↗
arXiv2026

X-NegoBox: An Explainable Privacy-Budget Negotiation Framework for Secure Peer-to-Peer Energy Data Exchange

The decentralization of modern energy systems is transforming consumers into prosumers who continuously exchange data with aggregators, peers, and market operators. While such data is essential for peer-to-peer trading, demand response, and distributed forecasting, it can reveal sensitive household patterns and introduce privacy risks. Existing data sharing mechanisms rely on fixed policies or predefined differential privacy budgets, limiting their ability to adapt to variations in reliability, data sensitivity, and request purpose. As a result, prosumers rarely receive explanations for why a request is accepted, rejected, or modified, reducing trust and participation. To address these limitations, we propose X-NegoBox, an explainable negotiation framework for adaptive privacy budgeting and transparent decision making. Each prosumer data is managed locally within a private DataBox, where raw data remain confined. Incoming requests are processed by an Autonomous Privacy Budget Negotiation Protocol (APBNP), which determines an appropriate privacy budget based on trust, feature sensitivity, declared purpose, historical behavior, and risk-aware pricing. When needed, APBNP generates privacy-preserving counter-offers, such as reduced resolution or duration. An Explainable Agreement Layer (X-Contract) produces human- and machine-readable justifications for each decision. After agreement, requester code executes locally in a sandbox, and only sanitized outputs are shared. Experiments on realistic energy market settings show reduced privacy leakage, higher acceptance rates, and improved interpretability.

cs.CR↗
arXiv2026

How Far Are Video Models from True Multimodal Reasoning?

Despite remarkable progress toward general-purpose video models, a critical question remains unanswered: how far are these models from achieving true multimodal reasoning? Existing benchmarks fail to address this question rigorously, as they remain constrained by straightforward task designs and fragmented evaluation metrics that neglect complex multimodal reasoning. To bridge this gap, we introduce CLVG-Bench, an evaluation framework designed to probe video models' zero-shot reasoning capabilities via Context Learning in Video Generation. CLVG-Bench comprises more than 1,000 high-quality, manually annotated metadata across 6 categories and 47 subcategories, covering complex scenarios including physical simulation, logical reasoning, and interactive contexts. To enable rigorous and scalable assessment, we further propose an Adaptive Video Evaluator (AVE) that aligns with human expert perception using minimal annotations, delivering interpretable textual feedback across diverse video context tasks. Extensive experiments reveal a striking answer to our central question: while state-of-the-art (SOTA) video models, such as Seedance 2.0, demonstrate competence on certain understanding and reasoning subtasks, they fall substantially short with logically grounded and interactive generation tasks (achieving success rates <25% and ~0%, respectively), exposing multimodal reasoning and physical grounding as critical bottlenecks. By systematically quantifying these limitations, the proposed method provides actionable feedbacks and a clear roadmap toward truly robust, general-purpose video models. CLVG-Bench and code are released here.

cs.CV↗
arXiv2026

Q-DeepSight: Incentivizing Thinking with Images for Image Quality Assessment and Refinement

Image Quality Assessment (IQA) models are increasingly deployed as perceptual critics to guide generative models and image restoration. This role demands not only accurate scores but also actionable, localized feedback. However, current MLLM-based methods adopt a single-look, language-only paradigm, which departs from human evidence-seeking judgment and yields weakly grounded rationales, limiting their reliability for in-the-loop refinement. We propose Q-DeepSight, a think-with-image framework that emulates this human-like process. It performs interleaved Multimodal Chain-of-Thought (iMCoT) with tool-augmented evidence acquisition (e.g., crop-and-zoom) to explicitly determine where quality degrades and why. To train these long iMCoT trajectories via reinforcement learning, we introduce two techniques: Perceptual Curriculum Reward (PCR) to mitigate reward sparsity and Evidence Gradient Filtering (EGF) to improve credit assignment for visually-grounded reasoning. Q-DeepSight achieves state-of-the-art performance across diverse benchmarks, including natural, restored, and AI-generated content. Furthermore, we demonstrate its practical value with Perceptual-in-Generation (PiG), a training-free framework where Q-DeepSight's diagnoses guide iterative image enhancement, effectively closing the loop between assessment and refinement.

cs.CV↗
arXiv2026

CPU Optimization of a Monocular 3D Biomechanics Pipeline for Low-Resource Deployment

Markerless 3D movement analysis from monocular video enables accessible biomechanical assessment in clinical and sports settings. However, most research-grade pipelines rely on GPU acceleration, limiting deployment on consumer-grade hardware and in low-resource environments. In this work, we optimize a monocular 3D biomechanics pipeline derived from the MonocularBiomechanics framework for efficient CPU-only execution. Through profiling-driven system optimization, including model initialization restructuring, elimination of disk I/O serialization, and improved CPU parallelization. Experiments on a consumer workstation (AMD Ryzen 7 9700X CPU) show a 2.47x increase in processing throughput and a 59.6\% reduction in total runtime, with initialization latency reduced by 4.6x. Despite these changes, biomechanical outputs remain highly consistent with the baseline implementation (mean joint-angle deviation 0.35$^\circ$, $r=0.998$). These results demonstrate that research-grade vision-based biomechanics pipelines can be deployed on commodity CPU hardware for scalable movement assessment.

cs.CV↗
arXiv2026

Impact of leaky dynamics on predictive path integration accuracy in recurrent neural networks

Experimental evidence indicates that intrinsic temporal dynamics operating across multiple time scales are closely associated with the emergence of periodic spatial activity of increasing complexity. However, how information encoded in grid-like firing patterns for path integration is processed across these intrinsic time scales remains unclear. To address this question, we introduce adaptive time scales through a leak term in recurrent neural networks (RNNs), forming leaky RNNs discretized from the continuous attractors of firing rate models. Our results demonstrate that leaky RNNs substantially enhance the emergence of well-defined and highly regular hexagonal firing patterns. Compared with vanilla RNNs lacking a leak term, the trained leaky RNNs produce more accurate position estimates while generating reliable grid-cell-like representations. Furthermore, under identical noise conditions, leaky RNNs consistently exhibit more stable dynamics and better-defined grid structures. The learned dynamics also give rise to stable torus attractors with a clear central hole, supporting robust and regular grid-like activity. Overall, the dynamic leak acts as a low-pass filtering mechanism that protects recurrent neural circuitry from noise, stabilizes network dynamics, and improves path-integration accuracy in recurrent neural networks.

cs.NE↗
arXiv2026

Role of chloride concentration in modulating seizure transitions in excitatory and inhibitory networks

Experimental evidence indicates that intracellular chloride concentration regulates the excitation and inhibition (EI) balance, yet the mechanisms by which activity-dependent chloride dynamics drive seizure evolution and stage transitions remain unclear. We present a conductance-based neuronal network in which EI balance emerges from chloride homeostasis via channel-mediated influx and transporter-mediated extrusion. We show that the fraction of inhibitory synaptic conductance contributing to channel-mediated influx acts as a control parameter that organizes seizure dynamics into distinct stages,pre-ictal, ictal-tonic, and ictal-clonic,distinguished by characteristic amplitude and frequency signatures. Decreasing this fraction shortens ictal activity and suppresses seizure initiation, whereas high fraction promotes the emergence of ictal-tonic and ictal-clonic stages and spiral-wave dynamics, rendering seizure dynamics largely insensitive to inhibition. At intermediate values, seizures bypass the ictal-tonic stage and emerge directly as the icta,clonic stage. Moreover, joint variation of fractions with synaptic strengths reveals that recurrent excitation expands the tonic-clonic seizure, while recurrent inhibition prolongs pre-ictal states and suppresses ictal-clonic activity.

q-bio.NC↗