Searcharxiv⌕ Search

arXiv subjects

Jing Zhang

Publications and source records attributed to Jing Zhang.

At least 181 records · Page 10Linked to original sources
arXiv2026

Text Before Vision: Staged Knowledge Injection Matters for Agentic RLVR in Ultra-High-Resolution Remote Sensing Understanding

Multimodal reasoning for ultra-high-resolution (UHR) remote sensing (RS) is usually bottlenecked by visual evidence acquisition: the model necessitates localizing tiny task-relevant regions in massive pixel spaces. While Agentic Reinforcement Learning with Verifiable Rewards (RLVR) using zoom-in tools offers a path forward, we find that standard reinforcement learning struggles to navigate these vast visual spaces without structured domain priors. In this paper, we investigate the interplay between post-training paradigms: comparing Cold-start Supervised Fine-Tuning (SFT), RLVR, and Agentic RLVR on the UHR RS benchmark.Our controlled studies yield a counter-intuitive finding: high-quality Earth-science text-only QA is a primary driver of UHR visual reasoning gains. Despite lacking images, domain-specific text injects the concepts, mechanistic explanations, and decision rules necessary to guide visual evidence retrieval.Based on this, we propose a staged knowledge injection recipe: (1) cold-starting with scalable, knowledge-graph-verified Earth-science text QA to instill reasoning structures;and (2) "pre-warming" on the same hard UHR image-text examples during SFT to stabilize and amplify subsequent tool-based RL. This approach achieves a 60.40% Pass@1 on XLRS-Bench, significantly outperforming larger general purpose models (e.g., GPT-5.2, Gemini 3.0 Pro, Intern-S1) and establishing a new state-of-the-art.

cs.AI↗
arXiv2026

Experimental study of matter-wave four-wave mixing in $^{39}$K Bose-Einstein condensates with tunable interaction

We experimentally investigate four-wave mixing (FWM) of matter waves in two geometric configurations in $^{39}$K Bose-Einstein condensates with the atomic interaction tuned via Feshbach resonances. For one configuration with the single-spin component, the FWM yield increases with a larger scattering length. For the two-spin component configuration, we specifically investigate FWM in both the droplet and gas parameter regimes. We find that the FWM yield reaches its maximum near the critical parameter region between the gas and droplet phases. Our research can help to optimize the FWM yield for matter-wave amplification and entangled atom pair generation, making it conducive to applications in quantum information processing and precision measurement.

cond-mat.quant-gas↗
arXiv2026

Efficient-SAM2: Accelerating SAM2 with Object-Aware Visual Encoding and Memory Retrieval

Segment Anything Model 2 (SAM2) shows excellent performance in video object segmentation tasks; however, the heavy computational burden hinders its application in real-time video processing. Although there have been efforts to improve the efficiency of SAM2, most of them focus on retraining a lightweight backbone, with little exploration into post-training acceleration. In this paper, we observe that SAM2 exhibits sparse perception pattern as biological vision, which provides opportunities for eliminating redundant computation and acceleration: i) In mask decoder, the attention primarily focuses on the foreground objects, whereas the image encoder in the earlier stage exhibits a broad attention span, which results in unnecessary computation to background regions. ii) In memory bank, only a small subset of tokens in each frame contribute significantly to memory attention, and the salient regions exhibit temporal consistency, making full-token computation redundant. With these insights, we propose Efficient-SAM2, which promotes SAM2 to adaptively focus on object regions while eliminating task-irrelevant computations, thereby significantly improving inference efficiency. Specifically, for image encoder, we propose object-aware Sparse Window Routing (SWR), a window-level computation allocation mechanism that leverages the consistency and saliency cues from the previous-frame decoder to route background regions into a lightweight shortcut branch. Moreover, for memory attention, we propose object-aware Sparse Memory Retrieval (SMR), which allows only the salient memory tokens in each frame to participate in computation, with the saliency pattern reused from their first recollection. With negligible additional parameters and minimal training overhead, Efficient-SAM2 delivers 1.68x speedup on SAM2.1-L model with only 1.0% accuracy drop on SA-V test set.

cs.CV↗
arXiv2026

REG4Rec: Reasoning-Enhanced Generative Model for Large-Scale Recommendation Systems

Sequential recommendation aims to predict a user's next action in large-scale recommender systems. While traditional methods often suffer from insufficient information interaction, recent generative recommendation models partially address this issue by directly generating item predictions. To better capture user intents, recent studies have introduced a reasoning process into generative recommendation, significantly improving recommendation performance. However, these approaches are constrained by the singularity of item semantic representations, facing challenges such as limited diversity in reasoning pathways and insufficient reliability in the reasoning process. To tackle these issues, we introduce REG4Rec, a reasoning-enhanced generative model that constructs multiple dynamic semantic reasoning paths alongside a self-reflection process, ensuring high-confidence recommendations. Specifically, REG4Rec utilizes an MoE-based parallel quantization codebook (MPQ) to generate multiple unordered semantic tokens for each item, thereby constructing a larger-scale diverse reasoning space. Furthermore, to enhance the reliability of reasoning, we propose a training reasoning enhancement stage, which includes Preference Alignment for Reasoning (PARS) and a Multi-Step Reward Augmentation (MSRA) strategy. PARS uses reward functions tailored for recommendation to enhance reasoning and reflection, while MSRA introduces future multi-step actions to improve overall generalization. During inference, Consistency-Oriented Self-Reflection for Pruning (CORP) is proposed to discard inconsistent reasoning paths, preventing the propagation of erroneous reasoning. Lastly, we develop an efficient offline training strategy for large-scale recommendation. Experiments on real-world datasets and online evaluations show that REG4Rec delivers outstanding performance and substantial practical value.

cs.IR↗
arXiv2026

CAE-AV: Improving Audio-Visual Learning via Cross-modal Interactive Enrichment

Audio-visual learning suffers from modality misalignment caused by off-screen sources and background clutter, and current methods usually amplify irrelevant regions or moments, leading to unstable training and degraded representation quality. To address this challenge, we proposed a novel Caption-aligned and Agreement-guided Enhancement framework (CAE-AV) for audio-visual learning, which used two complementary modules: Cross-modal Agreement-guided Spatio-Temporal Enrichment (CASTE) and Caption-Aligned Saliency-guided Enrichment (CASE) to relieve audio-visual misalignment. CASTE dynamically balances spatial and temporal relations by evaluating frame-level audio-visual agreement, ensuring that key information is captured from both preceding and subsequent frames under misalignment. CASE injects cross-modal semantic guidance into selected spatio-temporal positions, leveraging high-level semantic cues to further alleviate misalignment. In addition, we design lightweight objectives, caption-to-modality InfoNCE, visual-audio consistency, and entropy regularization to guide token selection and strengthen cross-modal semantic alignment. With frozen backbones, CAE-AV achieves state-of-the-art performance on AVE, AVVP, AVS, and AVQA benchmarks, and qualitative analyses further validate its robustness against audio-visual misalignment.

cs.CV↗
arXiv2026

LAB-Det: Language as a Domain-Invariant Bridge for Training-Free One-Shot Domain Generalization in Object Detection

Foundation object detectors such as GLIP and Grounding DINO excel on general-domain data but often degrade in specialized and data-scarce settings like underwater imagery or industrial defects. Typical cross-domain few-shot approaches rely on fine-tuning scarce target data, incurring cost and overfitting risks. We instead ask: Can a frozen detector adapt with only one exemplar per class without training? To answer this, we introduce training-free one-shot domain generalization for object detection, where detectors must adapt to specialized domains with only one annotated exemplar per class and no weight updates. To tackle this task, we propose LAB-Det, which exploits Language As a domain-invariant Bridge. Instead of adapting visual features, we project each exemplar into a descriptive text that conditions and guides a frozen detector. This linguistic conditioning replaces gradient-based adaptation, enabling robust generalization in data-scarce domains. We evaluate on UODD (underwater) and NEU-DET (industrial defects), two widely adopted benchmarks for data-scarce detection, where object boundaries are often ambiguous, and LAB-Det achieves up to 5.4 mAP improvement over state-of-the-art fine-tuned baselines without updating a single parameter. These results establish linguistic adaptation as an efficient and interpretable alternative to fine-tuning in specialized detection settings.

cs.CV↗
arXiv2026

Scaling Agentic Verifier for Competitive Coding

Large language models (LLMs) have demonstrated strong coding capabilities but still struggle to solve competitive programming problems correctly in a single attempt. Execution-based re-ranking offers a promising test-time scaling strategy, yet existing methods are constrained by either difficult test case generation or inefficient random input sampling. To address this limitation, we propose Agentic Verifier, an execution-based agent that actively reasons about program behaviors and searches for highly discriminative test inputs that expose behavioral discrepancies among candidate solutions. Through multi-turn interaction with code execution environments, the verifier iteratively refines the candidate input generator and produces targeted counterexamples rather than blindly sampling inputs. We train the verifier to acquire this discriminative input generation capability via a scalable pipeline combining large-scale data synthesis, rejection fine-tuning, and agentic reinforcement learning. Extensive experiments across five competitive programming benchmarks demonstrate consistent improvements over strong execution-based baselines, achieving up to +10-15% absolute gains in Best@K accuracy. Further analysis reveals clear test-time scaling behavior and highlights the verifier's broader potential beyond reranking.

cs.CL↗
arXiv2026

JOintGS: Joint Optimization of Cameras, Bodies and 3D Gaussians for In-the-Wild Monocular Reconstruction

Reconstructing high-fidelity animatable 3D human avatars from monocular RGB videos remains challenging, particularly in unconstrained in-the-wild scenarios where camera parameters and human poses from off-the-shelf methods (e.g., COLMAP, HMR2.0) are often inaccurate. Splatting (3DGS) advances demonstrate impressive rendering quality and real-time performance, they critically depend on precise camera calibration and pose annotations, limiting their applicability in real-world settings. We present JOintGS, a unified framework that jointly optimizes camera extrinsics, human poses, and 3D Gaussian representations from coarse initialization through a synergistic refinement mechanism. Our key insight is that explicit foreground-background disentanglement enables mutual reinforcement: static background Gaussians anchor camera estimation via multi-view consistency; refined cameras improve human body alignment through accurate temporal correspondence; optimized human poses enhance scene reconstruction by removing dynamic artifacts from static constraints. We further introduce a temporal dynamics module to capture fine-grained pose-dependent deformations and a residual color field to model illumination variations. Extensive experiments on NeuMan and EMDB datasets demonstrate that JOintGS achieves superior reconstruction quality, with 2.1~dB PSNR improvement over state-of-the-art methods on NeuMan dataset, while maintaining real-time rendering. Notably, our method shows significantly enhanced robustness to noisy initialization compared to the baseline.Our source code is available at https://github.com/MiliLab/JOintGS.

cs.CV↗
arXiv2026

Hierarchical Adaptive Eviction for KV Cache Management in Multimodal Language Models

The integration of visual information into Large Language Models (LLMs) has enabled Multimodal LLMs (MLLMs), but the quadratic memory and computational costs of Transformer architectures remain a bottleneck. Existing KV cache eviction strategies fail to address the heterogeneous attention distributions between visual and text tokens, leading to suboptimal efficiency or degraded performance. In this paper, we propose Hierarchical Adaptive Eviction (HAE), a KV cache eviction framework that optimizes text-visual token interaction in MLLMs by implementing Dual-Attention Pruning during pre-filling (leveraging visual token sparsity and attention variance) and a Dynamic Decoding Eviction Strategy (inspired by OS Recycle Bins) during decoding. HAE minimizes KV cache usage across layers, reduces computational overhead via index broadcasting, and theoretically ensures superior information integrity and lower error bounds compared to greedy strategies, enhancing efficiency in both comprehension and generation tasks. Empirically, HAE reduces KV-Cache memory by 41\% with minimal accuracy loss (0.3\% drop) in image understanding tasks and accelerates story generation inference by 1.5x while maintaining output quality on Phi3.5-Vision-Instruct model.

cs.LG↗
arXiv2026

Semantically Guided Dynamic Visual Prototype Refinement for Compositional Zero-Shot Learning

Compositional Zero-Shot Learning (CZSL) seeks to recognize unseen state-object pairs by recombining primitives learned from seen compositions. Despite recent progress with vision-language models (VLMs), two limitations remain: (i) text-driven semantic prototypes are weakly discriminative in the visual feature space; and (ii) unseen pairs are optimized passively, thereby inducing seen bias. To address these limitations, we present Duplex, a framework that couples dual-prototype learning with dynamic local-graph refinement of visual prototypes. For each composition, Duplex maintains a semantic prototype via prompt learning and a visual prototype for unseen pairs constructed by recombining disentangled state and object primitives from seen images. The visual prototypes are updated dynamically through lightweight aggregation on mini-batch local graphs, which incorporates unseen compositions during training without labels. This design introduces fine-grained visual evidence while preserving semantic structure. It enriches class prototypes, better disambiguates semantically similar yet visually distinct pairs, and mitigates seen bias. Experiments on MIT-States, UT-Zappos, and CGQA in closed-world and open-world settings achieve competitive performance and consistent compositional generalization. Our source code is available at https://github.com/ISPZ/Duplex-CZSL.

cs.CV↗
arXiv2026

Community-Level Modeling of Gyral Folding Patterns for Robust and Anatomically Informed Individualized Brain Mapping

Cortical folding exhibits substantial inter-individual variability while preserving stable anatomical landmarks that enable fine-scale characterization of cortical organization. Among these, the three-hinge gyrus (3HG) serves as a key folding primitive, showing consistent topology yet meaningful variations in morphology, connectivity, and function. Existing landmark-based methods typically model each 3HG independently, ignoring that 3HGs form higher-order folding communities that capture mesoscale structure. This simplification weakens anatomical representation and makes one-to-one matching sensitive to positional variability and noise. We propose a spectral graph representation learning framework that models community-level folding units rather than isolated landmarks. Each 3HG is encoded using a dual-profile representation combining surface topology and structural connectivity. Subject-specific spectral clustering identifies coherent folding communities, followed by topological refinement to preserve anatomical continuity. For cross-subject correspondence, we introduce Joint Morphological-Geometric Matching, jointly optimizing geometric and morphometric similarity. Across over 1000 Human Connectome Project subjects, the resulting communities show reduced morphometric variance, stronger modular organization, improved hemispheric consistency, and superior alignment compared with atlas-based and landmark-based or embedding-based baselines. These findings demonstrate that community-level modeling provides a robust and anatomically grounded framework for individualized cortical characterization and reliable cross-subject correspondence.

q-bio.NC↗
arXiv2026

Masked Diffusion Generative Recommendation

Generative recommendation (GR) typically first quantizes continuous item embeddings into multi-level semantic IDs (SIDs), and then generates the next item via autoregressive decoding. Although existing methods are already competitive in terms of recommendation performance, directly inheriting the autoregressive decoding paradigm from language models still suffers from three key limitations: (1) autoregressive decoding struggles to jointly capture global dependencies among the multi-dimensional features associated with different positions of SID; (2) using a unified, fixed decoding path for the same item implicitly assumes that all users attend to item attributes in the same order; (3) autoregressive decoding is inefficient at inference time and struggles to meet real-time requirements. To tackle these challenges, we propose MDGR, a Masked Diffusion Generative Recommendation framework that reshapes the GR pipeline from three perspectives: codebook, training, and inference. (1) We adopt a parallel codebook to provide a structural foundation for diffusion-based GR. (2) During training, we adaptively construct masking supervision signals along both the temporal and sample dimensions. (3) During inference, we develop a warm-up-based two-stage parallel decoding strategy for efficient generation of SIDs. Extensive experiments on multiple public and industrial-scale datasets show that MDGR outperforms ten state-of-the-art baselines by up to 10.78%. Furthermore, by deploying MDGR on a large-scale online advertising platform, we achieve a 1.20% increase in revenue, demonstrating its practical value.

cs.IR↗
arXiv2026

PTQ4ARVG: Post-Training Quantization for AutoRegressive Visual Generation Models

AutoRegressive Visual Generation (ARVG) models retain an architecture compatible with language models, while achieving performance comparable to diffusion-based models. Quantization is commonly employed in neural networks to reduce model size and computational latency. However, applying quantization to ARVG remains largely underexplored, and existing quantization methods fail to generalize effectively to ARVG models. In this paper, we explore this issue and identify three key challenges: (1) severe outliers at channel-wise level, (2) highly dynamic activations at token-wise level, and (3) mismatched distribution information at sample-wise level. To these ends, we propose PTQ4ARVG, a training-free post-training quantization (PTQ) framework consisting of: (1) Gain-Projected Scaling (GPS) mitigates the channel-wise outliers, which expands the quantization loss via a Taylor series to quantify the gain of scaling for activation-weight quantization, and derives the optimal scaling factor through differentiation.(2) Static Token-Wise Quantization (STWQ) leverages the inherent properties of ARVG, fixed token length and position-invariant distribution across samples, to address token-wise variance without incurring dynamic calibration overhead.(3) Distribution-Guided Calibration (DGC) selects samples that contribute most to distributional entropy, eliminating the sample-wise distribution mismatch. Extensive experiments show that PTQ4ARVG can effectively quantize the ARVG family models to 8-bit and 6-bit while maintaining competitive performance. Code is available at http://github.com/BienLuky/PTQ4ARVG .

cs.CV↗
arXiv2026

A Probabilistic Interpretation of the Master Equation Arising from Mean Field Games with Jump Diffusion

In this paper we study the classical solution to the master equation arising from mean-field games (MFGs) driven by jump-diffusion processes. The master equation, a nonlinear partial differential equation on Wasserstein space, characterizes the value function of MFGs and is challenging to analyze directly due to its measure-valued derivatives. We propose a probabilistic interpretation using coupled McKean-Vlasov forward-backward stochastic differential equations (MV-FBSDEs) with jumps. Under suitable Lipschitz and differentiability assumptions on the coefficients, we first establish the well-posedness of the MV-FBSDEs on a small time interval via a contraction mapping argument. We then prove the existence and regularity of the first- and second-order derivatives of the solutions with respect to the spatial and measure variables, relying on careful estimates involving jump terms and measure derivatives. Finally, we show that the decoupling field of the MV-FBSDEs satisfies the master equation in the classical sense, providing both existence and uniqueness of the solution. Our work extends earlier results on diffusion-driven MFGs to the jump-diffusion setting and offers a probabilistic framework for analyzing and numerically solving such kind of master equations.

math.PR↗
arXiv2026

GeoVLMath: Enhancing Geometry Reasoning in Vision-Language Models via Cross-Modal Reward for Auxiliary Line Creation

Auxiliary lines are essential for solving complex geometric problems but remain challenging for large vision-language models (LVLMs). Recent attempts construct auxiliary lines via code-driven rendering, a strategy that relies on accurate and executable code generation to produce visual renderings of the auxiliary lines for subsequent reasoning. However, in complex solid geometry settings, such a strong dependence on precise specifications substantially restricts the robustness of this strategy. Alternatively, we turn to a simpler and more stable solution, representing auxiliary-line constructions as structured textual descriptions. To bridge the gap between textual descriptions and spatial structure, we propose a reinforcement learning framework that enhances diagram-text alignment. The core is a cross-modal reward model that evaluates how well the generated auxiliary-line description matches the ground-truth auxiliary-line diagram. The reward signal drives a GRPO-based RL stage to yield informative auxiliary-line descriptions for the reasoning. To support the training and evaluation, we develop a scalable data pipeline and construct AuxSolidMath, a dataset of 3,018 real-exam geometry problems with paired diagrams and aligned textual fields. Based on this framework, we derive GeoVLMath, an LVLM for solving complex solid geometry.

cs.CV↗
arXiv2026

CARE Transformer: Mobile-Friendly Linear Visual Transformer via Decoupled Dual Interaction

Recently, large efforts have been made to design efficient linear-complexity visual Transformers. However, current linear attention models are generally unsuitable to be deployed in resource-constrained mobile devices, due to suffering from either few efficiency gains or significant accuracy drops. In this paper, we propose a new de\textbf{C}oupled du\textbf{A}l-interactive linea\textbf{R} att\textbf{E}ntion (CARE) mechanism, revealing that features' decoupling and interaction can fully unleash the power of linear attention. We first propose an asymmetrical feature decoupling strategy that asymmetrically decouples the learning process for local inductive bias and long-range dependencies, thereby preserving sufficient local and global information while effectively enhancing the efficiency of models. Then, a dynamic memory unit is employed to maintain critical information along the network pipeline. Moreover, we design a dual interaction module to effectively facilitate interaction between local inductive bias and long-range information as well as among features at different layers. By adopting a decoupled learning way and fully exploiting complementarity across features, our method can achieve both high efficiency and accuracy. Extensive experiments on ImageNet-1K, COCO, and ADE20K datasets demonstrate the effectiveness of our approach, e.g., achieving $78.4/82.1\%$ top-1 accuracy on ImagegNet-1K at the cost of only $0.7/1.9$ GMACs. Codes will be released on \href{https://github.com/zhouyuan888888/CARE-Transformer}{https://github.com/zhouyuan888888/CARE-Transformer}.

cs.CV↗
arXiv2026

Experimental study of magnetically insensitive transitions in ultracold Fermi gas of $^{40}$K

This paper presents an experimental study of microwave single-photon transitions that are magnetic-field-insensitive in degenerate Fermi gases of $^{40}$K. This contrasts with microwave single-photon clock transitions for 0-0 magnetic-field-insensitive states and two-photon clock transitions for non 0-0 magnetic-field-insensitive states in bosonic alkali metal atoms. We show that there are two sets of special transitions between two different hyperfine ground states ($|F$=9/2, $m_{F}$=1/2$\rangle$ $\Leftrightarrow$ $|$7/2, -1/2$\rangle$ and $|$9/2, -1/2$\rangle$ $\Leftrightarrow$ $|$7/2, 1/2$\rangle$), whose microwave single-photon transition frequency is insensitive to low magnetic fields, as the first-order Zeeman shift is almost completely canceled. By using the microwave spectrum and Ramsey interference fringes, we demonstrate the long-time stability of the coherent transition under magnetic field fluctuations. These magnetic-field-insensitive microwave hyperfine transitions in ultracold $^{40}$K Fermi gases offer promising applications in quantum information and precision measurements.

cond-mat.quant-gas↗
arXiv2026

EmoKGEdit: Training-free Affective Injection via Visual Cue Transformation

Existing image emotion editing methods struggle to disentangle emotional cues from latent content representations, often yielding weak emotional expression and distorted visual structures. To bridge this gap, we propose EmoKGEdit, a novel training-free framework for precise and structure-preserving image emotion editing. Specifically, we construct a Multimodal Sentiment Association Knowledge Graph (MSA-KG) to disentangle the intricate relationships among objects, scenes, attributes, visual clues and emotion. MSA-KG explicitly encode the causal chain among object-attribute-emotion, and as external knowledge to support chain of thought reasoning, guiding the multimodal large model to infer plausible emotion-related visual cues and generate coherent instructions. In addition, based on MSA-KG, we design a disentangled structure-emotion editing module that explicitly separates emotional attributes from layout features within the latent space, which ensures that the target emotion is effectively injected while strictly maintaining visual spatial coherence. Extensive experiments demonstrate that EmoKGEdit achieves excellent performance in both emotion fidelity and content preservation, and outperforms the state-of-the-art methods.

cs.CV↗