arXiv subjects

Shengjie Zhao

Publications and source records attributed to Shengjie Zhao.

At least 19 recordsLinked to original sources

arXiv2026

Video-IFBench: Evaluating Instruction Following of Multimodal LLMs in Video Understanding Scenarios

Multimodal Large Language Models (MLLMs) have shown strong performance in video understanding. However, their ability to follow instructions in this domain remains under-explored. Real-world video understanding requires models not only to interpret video content correctly, but also to satisfy diverse user-specified constraints. Existing benchmarks focus primarily on task accuracy rather than instruction adherence, leaving this capability insufficiently evaluated. To address this gap, we introduce Video-IFBench, a comprehensive benchmark for evaluating instruction following in video understanding, where models must satisfy diverse user-specified constraints, including those grounded in visual and audio content. We develop an instruction taxonomy with four templates, including single-task, multi-task, selection, and nested instructions, covering 32 task types and 39 manually designed constraint categories spanning both semantic and format requirements. To reduce annotation cost, we build a semi-automatic data construction pipeline that combines MLLMs, programmatic processing, and human verification, resulting in 1.5K samples. We conduct a large-scale evaluation of more than 20 recent MLLMs and show that video instruction following remains challenging for current models, especially for instructions with many constraints, semantic constraints, or complex conditional structures that require selecting the correct branch or path based on video content. We hope our work will facilitate future research on instruction following in video understanding scenarios.

cs.CV↗

arXiv2026

JADE-GS: Joint Allocation of Deblurring Evidence for Event-Assisted 3D Gaussian Splatting

Neural radiance fields and 3D Gaussian Splatting assume that each training image is a sharp and geometrically consistent observation of the scene. Motion blur violates this assumption because a single exposure integrates a continuous range of camera poses. Exposure integration also removes the temporal information needed to recover the corresponding sharp observation. Event cameras preserve this information at microsecond resolution and therefore provide a natural complement to conventional images. Existing event-assisted reconstruction methods predominantly obtain image supervision through analytical inversion of the Event Double Integral. Learned restoration from frames and events offers a second prior. Although weaker when used alone, it fails in different regions and provides complementary evidence. We present JADE-GS, which formulates the combination of these priors as spatial evidence allocation. A lightweight Spatial Prior Router predicts a pixelwise allocation using only the blurry frame and event stream, then fuses the two fixed restorations into an additional supervision target. The router is trained without a sharp reference using consistency with the scene under reconstruction and the measured exposure, and is removed after optimization. Experiments show that JADE-GS achieves leading perceptual quality on both benchmarks, attains the best fidelity on the real benchmark, and remains competitive on the synthetic one. It requires substantially lower training overhead than diffusion-based alternatives and preserves native 3DGS rendering with no generative decoding at inference.

cs.CV↗

arXiv2026

LXD-SLAM: LiDAR+X Dense SLAM with $\sum_{i=0}^{5}C_5^i$ Configurable Sensor Combinations

Simultaneous Localization and Mapping (SLAM) is essential for autonomous systems, yet achieving reliable, globally consistent pose estimation and dense mapping in complex environments remains challenging due to geometric degeneracy and sensor drift. While multi-sensor fusion addresses these issues, existing systems often lack the modularity to adapt to diverse platforms and rely on mathematically inconsistent fusion or suboptimal map representations. To address these limitations, we propose LXD-SLAM (LiDAR+X Dense SLAM), a highly versatile and unified multi-sensor fusion framework. Centered around 3D LiDAR, our system allows for the plug-and-play integration of LiDAR, Camera, IMU, Wheel Encoder, and GNSS, supporting up to 32 distinct sensor combinations. We employ a mathematically unified Iterative Error-Sate Kalman Filter with an adaptive hierarchical prediction strategy and an update step that minimizes point-to-mesh distances and visual reprojection errors. To support this, the environment is modeled using continuous multi-layered Gaussian Process (GP) sub-meshes, which enables efficient ray-to-mesh depth recovery for visual features. For global consistency, we introduce an Extended Scan Context (ESC) descriptor derived from the GP sub-meshes alongside a Bidirectional PnP optimization for robust multi-modal loop closure within a hybrid pose graph. Extensive evaluations on public datasets and real-world experiments demonstrate that LXD-SLAM matches or exceeds state-of-the-art specialized odometry solutions across various configurations while generating high-fidelity, globally consistent dense meshes in real-time. The relevant codes and data will be made available at https://github.com/peterWon/LXD-SLAM upon publication.

cs.RO↗

arXiv2026

Metacognition as Reward: Reinforcing LLM Reasoning via Knowledge and Regulation Signals

Recent RL methods have substantially improved the reasoning abilities of LLMs. Existing reward designs mainly follow two paradigms: (1) Reinforcement learning with verifiable rewards (RLVR) derives outcome signals from executable checks or ground-truth answers, but provides limited guidance for intermediate reasoning behaviors. (2) Rubrics-as-reward (RaR) goes beyond final-answer checking by using natural-language rubrics to assess reasoning quality and task compliance, but often requires instance-specific rubrics and substantial design effort. To address these issues, we introduce Metacognition-as-Reward (MaR), a metacognition-inspired RL framework that guides LLM reasoning through two general process dimensions: i) metacognitive knowledge, which identifies task-relevant information without hand-crafted instance-specific rubrics, and ii) metacognitive regulation, which plans and adjusts the reasoning process to provide reward guidance beyond final-answer outcomes. MaR scaffolds model rollouts into explicit metacognitive components and optimizes them with a trajectory-level reward over task knowledge coverage, regulation fidelity, and final-answer correctness. In this way, MaR extends reward feedback to reasoning trajectories while grounding the reward signals in general metacognitive dimensions. Experiments on 22 benchmarks show that MaR consistently improves model performance, achieving up to a 7.7% gain over the base model and up to an 11.0% gain over vanilla DAPO. Notably, Qwen3.5-9B + MaR narrows the gap to frontier models, surpassing GPT-OSS-120B on overall average and outperforming stronger models on several individual benchmarks. Process-level analysis further shows substantial improvements in reasoning process quality. MaR also generalizes to out-of-domain datasets, where MaR-trained models improve over their corresponding base models on average.

cs.CL↗

arXiv2026

GenCape: Structure-Inductive Generative Modeling for Category-Agnostic Pose Estimation

Category-agnostic pose estimation (CAPE) aims to localize keypoints on query images from arbitrary categories, using only a few annotated support examples for guidance. Recent approaches either treat keypoints as isolated entities or rely on manually defined skeleton priors, which are costly to annotate and inherently inflexible across diverse categories. Such oversimplification limits the model's capacity to capture instance-wise structural cues critical for accurate pixel-level localization. To overcome these limitations, we propose GenCape, a Generative-based framework for CAPE that infers keypoint relationships solely from image-based support inputs, without additional textual descriptions or predefined skeletons. Our framework consists of two principal components: an iterative Structure-aware Variational Autoencoder (i-SVAE) and a Compositional Graph Transfer (CGT) module. The former infers soft, instance-specific adjacency matrices from support features through variational inference, embedded layer-wise into the Graph Transformer Decoder for progressive structural priors refinement. The latter adaptively aggregates multiple latent graphs into a query-aware structure via Bayesian fusion and attention-based reweighting, enhancing resilience to visual uncertainty and support-induced bias. This structure-aware design facilitates effective message propagation among keypoints and promotes semantic alignment across object categories with diverse keypoint topologies. Experimental results on the MP-100 dataset show that our method achieves substantial gains over graph-support baselines under both 1- and 5-shot settings, while maintaining competitive performance against text-support counterparts.

cs.CV↗

arXiv2026

STAR: Semantic-Temporal Adaptive Representation Learning for Few-Shot Action Recognition

Few-shot action recognition (FSAR) requires models to generalize to novel action categories from only a handful of annotated samples. Despite progress with vision-language models, existing approaches still suffer from semantic-temporal misalignment, where static textual prompts fail to capture decisive visual cues that appear sparsely across sequences, and from inadequate modeling of multi-scale temporal dynamics, as short-term discriminative cues and long-range dependencies are often either oversmoothed or fragmented. To address these challenges, we propose Semantic Temporal Adaptive Representation Learning (STAR), a unified framework, consisting of a semantic-alignment component and a temporal-aware component, effectively bridging the semantic and temporal gaps and transferring the sequence modeling capability of Mamba into the FSAR. The semantic alignment module introduces a Temporal Semantic Attention (TSA) mechanism, which performs frame-level cross-modal alignment with textual cues, ensuring fine-grained semantic-temporal consistency. The temporal-aware module incorporates a Semantic Temporal Prototype Refiner (STPR) that integrates semantic-guided Mamba blocks with multi-frequency temporal sampling and bidirectional state-space refinement, yielding semantically aligned prototypes with enhanced discriminative fidelity and temporal consistency. Furthermore, temporally dependent class descriptors derived from large language models (LLMs) provide long-range semantic guidance. Extensive experiments on five FSAR benchmarks demonstrate the consistent superiority of STAR over state-of-the-art methods. For instance, STAR achieves up to 8.1% and 6.7% gains on the SSv2-Full and SSv2-Small datasets under the 1-shot setting, and 7.3% on HMDB51, validating its effectiveness under limited supervision. The code is available at https://github.com/HongliLiu1/STAR-main.

cs.CV↗

arXiv2026

Automated Functional Testing for Malleable Mobile Application Driven from User Intent

Software malleability allows applications to be easily changed, configured, and adapted even after deployment. While prior work has explored configurable systems, adaptive recommender systems, and malleable GUIs, these approaches are often tailored to specific software and lack generalizability. In this work, we envision per-user malleable mobile applications, where end-users can specify requirements that are automatically implemented via LLM-based code generation. However, realizing this vision requires overcoming the key challenge of designing automated test generation that can reliably verify both the presence and correctness of user-specified functionalities. We propose ALADDIN, a user-requirement-driven GUI test generation framework that incrementally navigates the UI, triggers desired functionalities, and constructs LLM-guided oracles to validate correctness. We build a benchmark spanning six popular mobile applications with both correct and faulty user-requested functionalities, demonstrating that ALADDIN effectively validates per-user features and is practical for real-world deployment. Our work highlights the feasibility of shifting mobile app development from a product-manager-driven to an end-user-driven paradigm.

cs.SE↗

arXiv2026

SiMO: Single-Modality-Operable Multimodal Collaborative Perception

Collaborative perception integrates multi-agent perspectives to enhance the sensing range and overcome occlusion issues. While existing multimodal approaches leverage complementary sensors to improve performance, they are highly prone to failure--especially when a key sensor like LiDAR is unavailable. The root cause is that feature fusion leads to semantic mismatches between single-modality features and the downstream modules. This paper addresses this challenge for the first time in the field of collaborative perception, introducing Single-Modality-Operable Multimodal Collaborative Perception (SiMO). By adopting the proposed Length-Adaptive Multi-Modal Fusion (LAMMA), SiMO can adaptively handle remaining modal features during modal failures while maintaining consistency of the semantic space. Additionally, leveraging the innovative "Pretrain-Align-Fuse-RD" training strategy, SiMO addresses the issue of modality competition--generally overlooked by existing methods--ensuring the independence of each individual modality branch. Experiments demonstrate that SiMO effectively aligns multimodal features while simultaneously preserving modality-specific features, enabling it to maintain optimal performance across all individual modalities. The implementation details can be found in https://github.com/dempsey-wen/SiMO.

cs.CV↗

arXiv2026

Unify the Views: View-Consistent Prototype Learning for Few-Shot Segmentation

Few-shot segmentation (FSS) has gained significant attention for its ability to generalize to novel classes with limited supervision, yet remains challenged by structural misalignment and cross-view inconsistency under large appearance or viewpoint variations. This paper tackles these challenges by introducing VINE (View-Informed NEtwork), a unified framework that jointly models structural consistency and foreground discrimination to refine class-specific prototypes. Specifically, VINE introduces a spatial-view graph on backbone features, where the spatial graph captures local geometric topology and the view graph connects features from different perspectives to propagate view-invariant structural semantics. To further alleviate foreground ambiguity, we derive a discriminative prior from the support-query feature discrepancy to capture category-specific contrast, which reweights SAM features by emphasizing salient regions and recalibrates backbone activations for improved structural focus. The foreground-enhanced SAM features and structurally enriched ResNet features are progressively integrated through masked cross-attention, yielding class-consistent prototypes used as adaptive prompts for the SAM decoder to generate accurate masks. Extensive experiments on multiple FSS benchmarks validate the effectiveness and robustness of VINE, particularly under challenging scenarios with viewpoint shifts and complex structures. The code is available at https://github.com/HongliLiu1/VINE-main.

cs.CV↗

arXiv2026

Weakly Supervised Video Anomaly Detection with Anomaly-Connected Components and Intention Reasoning

Weakly supervised video anomaly detection (WS-VAD) involves identifying the temporal intervals that contain anomalous events in untrimmed videos, where only video-level annotations are provided as supervisory signals. However, a key limitation persists in WS-VAD, as dense frame-level annotations are absent, which often leaves existing methods struggling to learn anomaly semantics effectively. To address this issue, we propose a novel framework named LAS-VAD, short for Learning Anomaly Semantics for WS-VAD, which integrates anomaly-connected component mechanism and intention awareness mechanism. The former is designed to assign video frames into distinct semantic groups within a video, and frame segments within the same group are deemed to share identical semantic information. The latter leverages an intention-aware strategy to distinguish between similar normal and abnormal behaviors (e.g., taking items and stealing). To further model the semantic information of anomalies, as anomaly occurrence is accompanied by distinct characteristic attributes (i.e., explosions are characterized by flames and thick smoke), we additionally incorporate anomaly attribute information to guide accurate detection. Extensive experiments on two benchmark datasets, XD-Violence and UCF-Crime, demonstrate that our LAS-VAD outperforms current state-of-the-art methods with remarkable gains.

cs.CV↗

arXiv2026

Balanced Edge Pruning for Graph Anomaly Detection with Noisy Labels

Graph anomaly detection (GAD) is widely applied in many areas, such as financial fraud detection and social spammer detection. Anomalous nodes in the graph not only impact their own communities but also create a ripple effect on neighbors throughout the graph structure. Detecting anomalous nodes in complex graphs has been a challenging task. While existing GAD methods assume all labels are correct, real-world scenarios often involve inaccurate annotations. These noisy labels can severely degrade GAD performance because, with anomalies representing a minority class, even a small number of mislabeled instances can disproportionately interfere with detection models. Cutting edges to mitigate the negative effects of noisy labels is a good option; however, it has both positive and negative influences and also presents an issue of weak supervision. To perform effective GAD with noisy labels, we propose REinforced Graph Anomaly Detector (REGAD) by pruning the edges of candidate nodes potentially with mistaken labels. Moreover, we design the performance feedback based on strategically crafted confident labels to guide the cutting process, ensuring optimal results. Specifically, REGAD contains two novel components. (i) A tailored policy network, which involves two-step actions to remove negative effect propagation step by step. (ii) A policy-in-the-loop mechanism to identify suitable edge removal strategies that control the propagation of noise on the graph and estimate the updated structure to obtain reliable pseudo labels iteratively. Experiments on three real-world datasets demonstrate that REGAD outperforms all baselines under different noisy ratios.

cs.LG↗

arXiv2025

DEPO: Dual-Efficiency Preference Optimization for LLM Agents

Recent advances in large language models (LLMs) have greatly improved their reasoning and decision-making abilities when deployed as agents. Richer reasoning, however, often comes at the cost of longer chain of thought (CoT), hampering interaction efficiency in real-world scenarios. Nevertheless, there still lacks systematic definition of LLM agent efficiency, hindering targeted improvements. To this end, we introduce dual-efficiency, comprising (i) step-level efficiency, which minimizes tokens per step, and (ii) trajectory-level efficiency, which minimizes the number of steps to complete a task. Building on this definition, we propose DEPO, a dual-efficiency preference optimization method that jointly rewards succinct responses and fewer action steps. Experiments on WebShop and BabyAI show that DEPO cuts token usage by up to 60.9% and steps by up to 26.9%, while achieving up to a 29.3% improvement in performance. DEPO also generalizes to three out-of-domain math benchmarks and retains its efficiency gains when trained on only 25% of the data. Our project page is at https://opencausalab.github.io/DEPO.

cs.CL↗

arXiv2025

Uncovering Pretraining Code in LLMs: A Syntax-Aware Attribution Approach

As large language models (LLMs) become increasingly capable, concerns over the unauthorized use of copyrighted and licensed content in their training data have grown, especially in the context of code. Open-source code, often protected by open source licenses (e.g, GPL), poses legal and ethical challenges when used in pretraining. Detecting whether specific code samples were included in LLM training data is thus critical for transparency, accountability, and copyright compliance. We propose SynPrune, a syntax-pruned membership inference attack method tailored for code. Unlike prior MIA approaches that treat code as plain text, SynPrune leverages the structured and rule-governed nature of programming languages. Specifically, it identifies and excludes consequent tokens that are syntactically required and not reflective of authorship, from attribution when computing membership scores. Experimental results show that SynPrune consistently outperforms the state-of-the-arts. Our method is also robust across varying function lengths and syntax categories.

cs.CR↗

arXiv2025

Learning from Rendering: Realistic and Controllable Extreme Rainy Image Synthesis for Autonomous Driving Simulation

Autonomous driving simulators provide an effective and low-cost alternative for evaluating or enhancing visual perception models. However, the reliability of evaluation depends on the diversity and realism of the generated scenes. Extreme weather conditions, particularly extreme rainfalls, are rare and costly to capture in real-world settings. While simulated environments can help address this limitation, existing rainy image synthesizers often suffer from poor controllability over illumination and limited realism, which significantly undermines the effectiveness of the model evaluation. To that end, we propose a learning-from-rendering rainy image synthesizer, which combines the benefits of the realism of rendering-based methods and the controllability of learning-based methods. To validate the effectiveness of our extreme rainy image synthesizer on semantic segmentation task, we require a continuous set of well-labeled extreme rainy images. By integrating the proposed synthesizer with the CARLA driving simulator, we develop CARLARain an extreme rainy street scene simulator which can obtain paired rainy-clean images and labels under complex illumination conditions. Qualitative and quantitative experiments validate that CARLARain can effectively improve the accuracy of semantic segmentation models in extreme rainy scenes, with the models' accuracy (mIoU) improved by 5% - 8% on the synthetic dataset and significantly enhanced in real extreme rainy scenarios under complex illuminations. Our source code and datasets are available at https://github.com/kb824999404/CARLARain/.

cs.CV↗

arXiv2025

Targeted Mining of Time-Interval Related Patterns

Compared to frequent pattern mining, sequential pattern mining emphasizes the temporal aspect and finds broad applications across various fields. However, numerous studies treat temporal events as single time points, neglecting their durations. Time-interval-related pattern (TIRP) mining is introduced to address this issue and has been applied to healthcare analytics, stock prediction, etc. Typically, mining all patterns is not only computationally challenging for accurate forecasting but also resource-intensive in terms of time and memory. Targeting the extraction of time-interval-related patterns based on specific criteria can improve data analysis efficiency and better align with customer preferences. Therefore, this paper proposes a novel algorithm called TaTIRP to discover Targeted Time-Interval Related Patterns. Additionally, we develop multiple pruning strategies to eliminate redundant extension operations, thereby enhancing performance on large-scale datasets. Finally, we conduct experiments on various real-world and synthetic datasets to validate the accuracy and efficiency of the proposed algorithm.

cs.DB↗

arXiv2025

UrbanMind: Towards Urban General Intelligence via Tool-Enhanced Retrieval-Augmented Generation and Multilevel Optimization

Urban general intelligence (UGI) refers to the capacity of AI systems to autonomously perceive, reason, and act within dynamic and complex urban environments. In this paper, we introduce UrbanMind, a tool-enhanced retrieval-augmented generation (RAG) framework designed to facilitate UGI. Central to UrbanMind is a novel architecture based on Continual Retrieval-Augmented MoE-based LLM (C-RAG-LLM), which dynamically incorporates domain-specific knowledge and evolving urban data to support long-term adaptability. The architecture of C-RAG-LLM aligns naturally with a multilevel optimization framework, where different layers are treated as interdependent sub-problems. Each layer has distinct objectives and can be optimized either independently or jointly through a hierarchical learning process. The framework is highly flexible, supporting both end-to-end training and partial layer-wise optimization based on resource or deployment constraints. To remain adaptive under data drift, it is further integrated with an incremental corpus updating mechanism. Evaluations on real-world urban tasks of a variety of complexity verify the effectiveness of the proposed framework. This work presents a promising step toward the realization of general-purpose LLM agents in future urban environments.

cs.LG↗

arXiv2025

ShotBench: Expert-Level Cinematic Understanding in Vision-Language Models

Cinematography, the fundamental visual language of film, is essential for conveying narrative, emotion, and aesthetic quality. While recent Vision-Language Models (VLMs) demonstrate strong general visual understanding, their proficiency in comprehending the nuanced cinematic grammar embedded within individual shots remains largely unexplored and lacks robust evaluation. This critical gap limits both fine-grained visual comprehension and the precision of AI-assisted video generation. To address this, we introduce ShotBench, a comprehensive benchmark specifically designed for cinematic language understanding. It features over 3.5k expert-annotated QA pairs from images and video clips, meticulously curated from over 200 acclaimed (predominantly Oscar-nominated) films and spanning eight key cinematography dimensions. Our evaluation of 24 leading VLMs on ShotBench reveals their substantial limitations: even the top-performing model achieves less than 60% average accuracy, particularly struggling with fine-grained visual cues and complex spatial reasoning. To catalyze advancement in this domain, we construct ShotQA, a large-scale multimodal dataset comprising approximately 70k cinematic QA pairs. Leveraging ShotQA, we develop ShotVL through supervised fine-tuning and Group Relative Policy Optimization. ShotVL significantly outperforms all existing open-source and proprietary models on ShotBench, establishing new state-of-the-art performance. We open-source our models, data, and code to foster rapid progress in this crucial area of AI-driven cinematic understanding and generation.

cs.CV↗

arXiv2025

On the Robustness of Human-Object Interaction Detection against Distribution Shift

Human-Object Interaction (HOI) detection has seen substantial advances in recent years. However, existing works focus on the standard setting with ideal images and natural distribution, far from practical scenarios with inevitable distribution shifts. This hampers the practical applicability of HOI detection. In this work, we investigate this issue by benchmarking, analyzing, and enhancing the robustness of HOI detection models under various distribution shifts. We start by proposing a novel automated approach to create the first robustness evaluation benchmark for HOI detection. Subsequently, we evaluate more than 40 existing HOI detection models on this benchmark, showing their insufficiency, analyzing the features of different frameworks, and discussing how the robustness in HOI is different from other tasks. With the insights from such analyses, we propose to improve the robustness of HOI detection methods through: (1) a cross-domain data augmentation integrated with mixup, and (2) a feature fusion strategy with frozen vision foundation models. Both are simple, plug-and-play, and applicable to various methods. Our experimental results demonstrate that the proposed approach significantly increases the robustness of various methods, with benefits on standard benchmarks, too. The dataset and code will be released.

cs.CV↗