arXiv subjects

Jian Zhang

Publications and source records attributed to Jian Zhang.

At least 109 records · Page 6Linked to original sources

arXiv2026

SVOM/VT: Real-Time Onboard Data Processing

The SVOM Visible Telescope (VT) is critical for the rapid identification of gamma-ray burst (GRB) optical counterparts, particularly for high-redshift candidates that require immediate infrared spectroscopic follow-up. To address the stringent bandwidth constraints of the VHF downlink while ensuring real-time data availability, we developed the VT Onboard Data Processing Pipeline (VOPP).This paper details the software architecture, algorithms, and hardware implementation of VOPP using an FPGA and a CPU. The pipeline performs essential real-time tasks, including image quality assessment, dark and flat-field correction, and optimized image stacking to mitigate cosmic ray contamination and variable background noise. Furthermore, it generates compact source catalogs and highly compressed 1-bit images to facilitate rapid downlink.In-flight performance analysis confirms the pipeline's robustness, demonstrating the availability of VT VHF data for 78 percent of promptly slewed SVOM GRBs, with 56 percent leading to the identification of optical counterparts, typically within 18 minutes post-trigger.

astro-ph.IM↗

arXiv2026

Quantum Super Littlewood Correspondences

In this paper, we study the Littlewood theory associated with the quantum super immanants and supersymmetric polynomials, including both the super case and the quantum generalization. In the setting of quantum super Schur-Weyl duality between the quantum superalgebra $U_q(\mathfrak{gl}_{m|n})$ and the Iwahori-Hecke algebra $\mathcal{H}_r$ of type A, we explicitly construct basis vectors of the $(U_q(\mathfrak{gl}_{m|n}), \mathcal{H}_r)$-bimodule on the tensor product space $(\mathbb{C}^{m|n})^{\otimes r}$. Using this construction, we interpret the quantum super immanants via weight spaces of covariant tensor representations of $U_q(\mathfrak{gl}_{m|n})$.

math.QA↗

arXiv2026

Making TransactionIsolation Checking Practical

Checking whether database transactions adhere to isolation levels is a crucial yet challenging problem. We present Boomslang, the first general-purpose checking framework capable of verifying configurations that were previously uncheckable. Boomslang advances beyond prior work in three key aspects: (1) it supports arbitrary operation types provided by modern transactional key-value stores, (2) it requires no knowledge of database internals, and (3) it offers a modular, extensible pipeline amenable to customization and optimizations. Boomslang adopts a front-/back-end separation. As the front-end, it parses a database trace into an Abstract Semantic Graph, which is then lowered -- via semantic analysis -- into a low-level intermediate representation (IR). The back-end converts this IR to a set of constraints for SMT solving. This design is enabled by a key abstraction in the IR, called superpositions, which capture the uncertainty and complexity caused by arbitrary operations and missing information. Our experiments show that with just 271--386 lines of code, the core logic of three prior checkers can be reimplemented as Boomslang modules, achieving comparable or superior performance. Using Boomslang, we also identify a new bug in TiDB, audit the metadata layer of the JuiceFS file system, check vendor-specific behavior in MariaDB, support five previously unchecked isolation levels, and confirm a theoretical result on the correctness of strict serializability.

cs.DB↗

arXiv2026

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

The rapid advancement of Large Multimodal Models (LMMs) for 2D images and videos has motivated extending these models to understand 3D scenes, aiming for human-like visual-spatial intelligence. Nevertheless, achieving deep spatial understanding comparable to human capabilities poses significant challenges in model encoding and data acquisition. Existing methods frequently depend on external depth sensors for geometry capture or utilize off-the-shelf algorithms for pre-constructing 3D maps, thereby limiting their scalability, especially with prevalent monocular video inputs and for time-sensitive applications. In this work, we introduce VLM-3R, a unified framework for Vision-Language Models (VLMs) that incorporates 3D Reconstructive instruction tuning. VLM-3R processes monocular video frames by employing a geometry encoder to derive implicit 3D tokens that represent spatial understanding. Leveraging our Spatial-Visual-View Fusion and over 200K curated 3D reconstructive instruction tuning question-answer (QA) pairs, VLM-3R effectively aligns real-world spatial context with language instructions. This enables monocular 3D spatial assistance and embodied reasoning. To facilitate the evaluation of temporal reasoning, we introduce the Vision-Spatial-Temporal Intelligence benchmark, featuring over 138.6K QA pairs across five distinct tasks focused on evolving spatial relationships. Extensive experiments demonstrate that our model, VLM-3R, not only facilitates robust visual-spatial reasoning but also enables the understanding of temporal 3D context changes, excelling in both accuracy and scalability.

cs.CV↗

arXiv2026

SmartPhotoCrafter: Unified Reasoning, Generation and Optimization for Automatic Photographic Image Editing

Traditional photographic image editing typically requires users to possess sufficient aesthetic understanding to provide appropriate instructions for adjusting image quality and camera parameters. However, this paradigm relies on explicit human instruction of aesthetic intent, which is often ambiguous, incomplete, or inaccessible to non-expert users. In this work, we propose SmartPhotoCrafter, an automatic photographic image editing method which formulates image editing as a tightly coupled reasoning-to-generation process. The proposed model first performs image quality comprehension and identifies deficiencies by the Image Critic module, and then the Photographic Artist module realizes targeted edits to enhance image appeal, eliminating the need for explicit human instructions. A multi-stage training pipeline is adopted: (i) Foundation pretraining to establish basic aesthetic understanding and editing capabilities, (ii) Adaptation with reasoning-guided multi-edit supervision to incorporate rich semantic guidance, and (iii) Coordinated reasoning-to generation reinforcement learning to jointly optimize reasoning and generation. During training, SmartPhotoCrafter emphasizes photo-realistic image generation, while supporting both image restoration and retouching tasks with consistent adherence to color- and tone-related semantics. We also construct a stage-specific dataset, which progressively builds reasoning and controllable generation, effective cross-module collaboration, and ultimately high-quality photographic enhancement. Experiments demonstrate that SmartPhotoCrafter outperforms existing generative models on the task of automatic photographic enhancement, achieving photo-realistic results while exhibiting higher tonal sensitivity to retouching instructions. Project page: https://github.com/vivoCameraResearch/SmartPhotoCrafter.

cs.CV↗

arXiv2026

Bulk superconductivity up to 96 K in pressurized nickelate single crystals

Recently, the Ruddlesden-Popper bilayer nickelate $La_3Ni_2O_7$ has emerged as a superconductor with a transition temperature ($T_c$) of approximately 80 K above 14 GPa (Refs. 1-3). Achieving higher $T_c$ in nickelate superconductors, along with the synthesis of reproducible high-quality single crystals without relying on high-oxygen-pressure growth conditions, remains a significant challenge$^{[4-7]}$. Here we report superconductivity up to 96 K under high pressure in bilayer nickelate single crystals synthesized at ambient pressure. Energy-dispersive spectroscopy, single-crystal X-ray diffraction, nuclear quadrupole resonance and scanning transmission electron microscopy evidenced high crystal quality of the flux-grown $La_2SmNi_2O_{7-δ}$ single crystals. $La_2SmNi_2O_7$ exhibits clear bulk superconductivity, including zero resistivity ($T_{c,max}^{onset}$ = 92 K and $T_{c,max}^{zero}$ = 73 K at 21.6 GPa) and the Meissner effect ($T_c$= 60 K at 20.6 GPa). A low-temperature high-pressure structural study indicates that both monoclinic and tetragonal structures can support superconductivity in this bilayer nickelate. Furthermore, we established a correlation between higher $T_c$ under high pressures and larger in-plane lattice distortion under ambient conditions, corroborated by observing even higher $T_c^{onset}$ of 96 K in $La_{1.57}Sm_{1.43}Ni_2O_{7-δ}$. This study overcomes key limitations in growing nickelate superconductor crystals, resolves the crystal structure in the superconducting state and demonstrates an effective pathway towards achieving higher $T_c$.

cond-mat.supr-con↗

arXiv2026

DeepFWI: Identifying Bug-Sensitive Warnings with Multi-Modal Code-Warning Semantics

Static analysis tools have evolved over time to assist in detecting bugs. However, the excessive false warnings can impede developers' productivity and confidence in the tools. Previous research efforts have explored learning-based approaches to identify bug warnings. Nevertheless, their coarse granularity, focusing on either long-term warnings or function-level alerts, is insensitive to individual bugs. Also, they rely on manually crafted features or solely on source code semantics, which is inadequate for effective learning. In this paper, we propose DeepFWI, a learning-based approach that identifies bug-sensitive warnings at a fine-grained granularity. Specifically, we design a novel LSTM-based model that captures multi-modal semantics of source code and warnings from automated static analysis tools (ASATs) and highlights their correlations with cross-attention. To tackle the data scarcity of training and evaluation, we collected a large-scale dataset of 280,273 warnings. We conducted extensive experiments on the dataset to evaluate DeepFWI. The experimental results demonstrate the effectiveness of our approach, with an F1-score 67.06% for confirming true warnings in a finer-grained manner, significantly outperforming all baselines. Additionally, to validate the practicality of DeepFWI from the perspective of developers, we applied DeepFWI to four popular open-source projects. Our approach filtered out the vast majority of warnings, while still successfully surfacing 25 true bug-related warnings that were confirmed through manual analysis.

cs.SE↗

arXiv2026

Dissecting Failure Dynamics in Large Language Model Reasoning

Large Language Models (LLMs) achieve strong performance through extended inference-time deliberation, yet how their reasoning failures arise remains poorly understood. By analyzing model-generated reasoning trajectories, we find that errors are not uniformly distributed but often originate from a small number of early transition points, after which reasoning remains locally coherent but globally incorrect. These transitions coincide with localized spikes in token-level entropy, and alternative continuations from the same intermediate state can still lead to correct solutions. Based on these observations, we introduce GUARD, a targeted inference-time framework that probes and redirects critical transitions using uncertainty signals. Empirical evaluations across multiple benchmarks confirm that interventions guided by these failure dynamics lead to more reliable reasoning outcomes. Our findings highlight the importance of understanding when and how reasoning first deviates, complementing existing approaches that focus on scaling inference-time computation.

cs.AI↗

arXiv2026

A1: A Fully Transparent Open-Source, Adaptive and Efficient Truncated Vision-Language-Action Model

Vision-Language-Action (VLA) models have emerged as a powerful paradigm for open-world robot manipulation, but their practical deployment is often constrained by cost: billion-scale VLM backbones and iterative diffusion/flow-based action heads incur high latency and compute, making real-time control expensive on commodity hardware. We present A1, a fully open-source and transparent VLA framework designed for low-cost, high-throughput inference without sacrificing manipulation success; Our approach leverages pretrained VLMs that provide implicit affordance priors for action generation. We release the full training stack (training code, data/data-processing pipeline, intermediate checkpoints, and evaluation scripts) to enable end-to-end reproducibility. Beyond optimizing the VLM alone, A1 targets the full inference pipeline by introducing a budget-aware adaptive inference scheme that jointly accelerates the backbone and the action head. Specifically, we monitor action consistency across intermediate VLM layers to trigger early termination, and propose Inter-Layer Truncated Flow Matching that warm-starts denoising across layers, enabling accurate actions with substantially fewer effective denoising iterations. Across simulation benchmarks (LIBERO, VLABench) and real robots (Franka, AgiBot), A1 achieves state-of-the-art success rates while significantly reducing inference cost (e.g., up to 72% lower per-episode latency for flow-matching inference and up to 76.6% backbone computation reduction with minor performance degradation). On RoboChallenge, A1 achieves an average success rate of 29.00%, outperforming baselines including pi0(28.33%), X-VLA (21.33%), and RDT-1B (15.00%).

cs.RO↗

arXiv2026

Sharp Exponent of Stable Standing Waves for the Perturbated Hartree Equation

This paper is concerned with the stability of standing waves for the mass-critical Hartree equation with a focusing perturbation by the variational method. The profile decomposition theory is employed to prove the attainability of the cross constrained variational problem, and then the comparison of two cross constrained variational problems is derived. The sharp criteria of blowup, the orbital stability, and strong instability of standing waves without any frequency constraint are obtained. This improves the cross constrained variational argument proposed by Zhang (2005).

math.AP↗

arXiv2026

Interpretable Zero-shot Referring Expression Comprehension with Query-driven Scene Graphs

Zero-shot referring expression comprehension (REC) aims to locate target objects in images given natural language queries without relying on task-specific training data, demanding strong visual understanding capabilities. Existing Vision-Language Models~(VLMs), such as CLIP, commonly address zero-shot REC by directly measuring feature similarities between textual queries and image regions. However, these methods struggle to capture fine-grained visual details and understand complex object relationships. Meanwhile, Large Language Models~(LLMs) excel at high-level semantic reasoning, their inability to directly abstract visual features into textual semantics limits their application in REC tasks. To overcome these limitations, we propose \textbf{SGREC}, an interpretable zero-shot REC method leveraging query-driven scene graphs as structured intermediaries. Specifically, we first employ a VLM to construct a query-driven scene graph that explicitly encodes spatial relationships, descriptive captions, and object interactions relevant to the given query. By leveraging this scene graph, we bridge the gap between low-level image regions and higher-level semantic understanding required by LLMs. Finally, an LLM infers the target object from the structured textual representation provided by the scene graph, responding with detailed explanations for its decisions that ensure interpretability in the inference process. Extensive experiments show that SGREC achieves top-1 accuracy on most zero-shot REC benchmarks, including RefCOCO val (66.78\%), RefCOCO+ testB (53.43\%), and RefCOCOg val (73.28\%), highlighting its strong visual scene understanding.

cs.CV↗

arXiv2026

VQ-Jarvis: Retrieval-Augmented Video Restoration Agent with Sharp Vision and Fast Thought

Video restoration in real-world scenarios is challenged by heterogeneous degradations, where static architectures and fixed inference pipelines often fail to generalize. Recent agent-based approaches offer dynamic decision making, yet existing video restoration agents remain limited by insufficient quality perception and inefficient search strategies. We propose VQ-Jarvis, a retrieval-augmented, all-in-one intelligent video restoration agent with sharper vision and faster thought. VQ-Jarvis is designed to accurately perceive degradations and subtle differences among paired restoration results, while efficiently discovering optimal restoration trajectories. To enable sharp vision, we construct VSR-Compare, the first large-scale video paired enhancement dataset with 20K comparison pairs covering 7 degradation types, 11 enhancement operators, and diverse content domains. Based on this dataset, we train a multiple operator judge model and a degradation perception model to guide agent decisions. To achieve fast thought, we introduce a hierarchical operator scheduling strategy that adapts to video difficulty: for easy cases, optimal restoration trajectories are retrieved in a one-step manner from a retrieval-augmented generation (RAG) library; for harder cases, a step-by-step greedy search is performed to balance efficiency and accuracy. Extensive experiments demonstrate that VQ-Jarvis consistently outperforms existing methods on complex degraded videos.

cs.CV↗

arXiv2026

Super-immanants and Littlewood correspondences

In this paper, we introduce the notion of super-immanants for supermatrices over a supercommutative algebra. Using the super Schur-Weyl duality we show that the super immanants play a significant role in covariant tensor representations of the general linear Lie superalgebra. Among various things, we obtain a supertrace formula for super-immanants, which generalizes Kostant's trace formula to the super setting. Furthermore, we show that the Littlewood correspondences between super-immanants and supersymmetric polynomials establish an isomorphism between their corresponding algebras.

math.RT↗

arXiv2026

Time-Critical Adversarial Influence Blocking Maximization

Adversarial Influence Blocking Maximization (AIBM) aims to select a set of positive seed nodes that propagate synchronously with the known negative seed nodes to counteract their negative influence. Time factor plays a particularly vital role for many AIBM application scenarios. However, the AIBM problem with time constraint remains unexplored. More importantly, existing AIBM studies have not thoroughly investigated the submodularity of the objective function, thereby failing to establish a theoretical approximation guarantee. To address these challenges, firstly, we establish the Time-Critical Adversarial Influence Blocking Maximization (TC-AIBM), which explicitly incorporates time constraint. Then, we provide a theoretical proof of the submodularity of the TC-AIBM objective function under three different tie-breaking rules. Finally, a Bidirectional Influence Sampling (BIS) algorithm is proposed to solve the TC-AIBM problem. Leveraging the monotonicity and submodularity of the objective function, BIS achieves an approximation guarantee of $(1-1/e-ε)(1-ψ)$. Comprehensive experiments on four real-world datasets demonstrate that the proposed BIS algorithm exhibits excellent robustness across various negative seeds, time constraint, and tie-breaking rules, outperforming state-of-the-art baselines. In addition, BIS is up to three orders of magnitude faster than the Greedy algorithm.

cs.SI↗

arXiv2026

PivotRL: High Accuracy Agentic Post-Training at Low Compute Cost

Post-training for long-horizon agentic tasks has a tension between compute efficiency and generalization. While supervised fine-tuning (SFT) is compute efficient, it often suffers from out-of-domain (OOD) degradation. Conversely, end-to-end reinforcement learning (E2E RL) preserves OOD capabilities, but incurs high compute costs due to many turns of on-policy rollout. We introduce PivotRL, a novel framework that operates on existing SFT trajectories to combine the compute efficiency of SFT with the OOD accuracy of E2E RL. PivotRL relies on two key mechanisms: first, it executes local, on-policy rollouts and filters for pivots: informative intermediate turns where sampled actions exhibit high variance in outcomes; second, it utilizes rewards for functional-equivalent actions rather than demanding strict string matching with the SFT data demonstration. We theoretically show that these mechanisms incentivize strong learning signals with high natural gradient norm, while maximally preserving policy probability ordering on actions unrelated to training tasks. In comparison to standard SFT on identical data, we demonstrate that PivotRL achieves +4.17% higher in-domain accuracy on average across four agentic domains, and +10.04% higher OOD accuracy in non-agentic tasks. Notably, on agentic coding tasks, PivotRL achieves competitive accuracy with E2E RL with 4x fewer rollout turns. PivotRL is adopted by NVIDIA's Nemotron-3-Super-120B-A12B, acting as the workhorse in production-scale agentic post-training.

cs.AI↗

arXiv2026

Neuronal Self-Adaptation Enhances Capacity and Robustness of Representation in Spiking Neural Networks

Spiking Neural Networks (SNNs) are promising for energy-efficient, real-time edge computing, yet their performance is often constrained by the limited adaptability of conventional leaky integrate-and-fire (LIF) neurons. Existing LIF models struggle with restricted information capacity and susceptibility to noise, leading to degraded accuracy and compromised robustness. Inspired by the dynamic self-regulation of biological potassium channels, we propose the Potassium-regulated LIF (KvLIF) neuron model. KvLIF introduces an auxiliary conductance state that integrates membrane potential and spiking history to adaptively modulate neuronal excitability and reset dynamics. This design extends the dynamic response range of neurons to varying input intensities and effectively suppresses noise-induced spikes. We extensively evaluate KvLIF on both static image and neuromorphic datasets, demonstrating consistent improvements in classification accuracy and superior robustness compared to existing LIF models. Our work bridges biological plausibility with computational efficiency, offering a neuron model that enhances SNN performance while maintaining suitability for low-power neuromorphic deployment.

cs.LG↗

arXiv2026

Disentangle-then-Align: Non-Iterative Hybrid Multimodal Image Registration via Cross-Scale Feature Disentanglement

Multimodal image registration is a fundamental task and a prerequisite for downstream cross-modal analysis. Despite recent progress in shared feature extraction and multi-scale architectures, two key limitations remain. First, some methods use disentanglement to learn shared features but mainly regularize the shared part, allowing modality-private cues to leak into the shared space. Second, most multi-scale frameworks support only a single transformation type, limiting their applicability when global misalignment and local deformation coexist. To address these issues, we formulate hybrid multimodal registration as jointly learning a stable shared feature space and a unified hybrid transformation. Based on this view, we propose HRNet, a Hybrid Registration Network that couples representation disentanglement with hybrid parameter prediction. A shared backbone with Modality-Specific Batch Normalization (MSBN) extracts multi-scale features, while a Cross-scale Disentanglement and Adaptive Projection (CDAP) module suppresses modality-private cues and projects shared features into a stable subspace for matching. Built on this shared space, a Hybrid Parameter Prediction Module (HPPM) performs non-iterative coarse-to-fine estimation of global rigid parameters and deformation fields, which are fused into a coherent deformation field. Extensive experiments on four multimodal datasets demonstrate state-of-the-art performance on rigid and non-rigid registration tasks. The code is available at the project website.

cs.CV↗

arXiv2026

GenCompositor: Generative Video Compositing with Diffusion Transformer

Video compositing combines live-action footage to create video production, serving as a crucial technique in video creation and film production. Traditional pipelines require intensive labor efforts and expert collaboration, resulting in lengthy production cycles and high manpower costs. To address this issue, we automate this process with generative models, called generative video compositing. This new task strives to adaptively inject identity and motion information of foreground video to the target video in an interactive manner, allowing users to customize the size, motion trajectory, and other attributes of the dynamic elements added in final video. Specifically, we designed a novel Diffusion Transformer (DiT) pipeline based on its intrinsic properties. To maintain consistency of the target video before and after editing, we revised a light-weight DiT-based background preservation branch with masked token injection. As to inherit dynamic elements from other sources, a DiT fusion block is proposed using full self-attention, along with a simple yet effective foreground augmentation for training. Besides, for fusing background and foreground videos with different layouts based on user control, we developed a novel position embedding, named Extended Rotary Position Embedding (ERoPE). Finally, we curated a dataset comprising 61K sets of videos for our new task, called VideoComp. This data includes complete dynamic elements and high-quality target videos. Experiments demonstrate that our method effectively realizes generative video compositing, outperforming existing possible solutions in fidelity and consistency. Project is available at https://gencompositor.github.io/

cs.CV↗