arXiv subjects

Jinlin Wu

Publications and source records attributed to Jinlin Wu.

At least 37 records · Page 2Linked to original sources

arXiv2025

6DAttack: Backdoor Attacks in the 6DoF Pose Estimation

Deep learning advances have enabled accurate six-degree-of-freedom (6DoF) object pose estimation, widely used in robotics, AR/VR, and autonomous systems. However, backdoor attacks pose significant security risks. While most research focuses on 2D vision, 6DoF pose estimation remains largely unexplored. Unlike traditional backdoors that only change classes, 6DoF attacks must control continuous parameters like translation and rotation, rendering 2D methods inapplicable. We propose 6DAttack, a framework using 3D object triggers to induce controlled erroneous poses while maintaining normal behavior. Evaluations on PVNet, DenseFusion, and PoseDiffusion across LINEMOD, YCB-Video, and CO3D show high attack success rates (ASRs) without compromising clean performance. Backdoored models achieve up to 100% clean ADD accuracy and 100% ASR, with triggered samples reaching 97.70% ADD-P. Furthermore, a representative defense remains ineffective. Our findings reveal a serious, underexplored threat to 6DoF pose estimation.

cs.CV↗

arXiv2025

NeuroABench: A Multimodal Evaluation Benchmark for Neurosurgical Anatomy Identification

Multimodal Large Language Models (MLLMs) have shown significant potential in surgical video understanding. With improved zero-shot performance and more effective human-machine interaction, they provide a strong foundation for advancing surgical education and assistance. However, existing research and datasets primarily focus on understanding surgical procedures and workflows, while paying limited attention to the critical role of anatomical comprehension. In clinical practice, surgeons rely heavily on precise anatomical understanding to interpret, review, and learn from surgical videos. To fill this gap, we introduce the Neurosurgical Anatomy Benchmark (NeuroABench), the first multimodal benchmark explicitly created to evaluate anatomical understanding in the neurosurgical domain. NeuroABench consists of 9 hours of annotated neurosurgical videos covering 89 distinct procedures and is developed using a novel multimodal annotation pipeline with multiple review cycles. The benchmark evaluates the identification of 68 clinical anatomical structures, providing a rigorous and standardized framework for assessing model performance. Experiments on over 10 state-of-the-art MLLMs reveal significant limitations, with the best-performing model achieving only 40.87% accuracy in anatomical identification tasks. To further evaluate the benchmark, we extract a subset of the dataset and conduct an informative test with four neurosurgical trainees. The results show that the best-performing student achieves 56% accuracy, with the lowest scores of 28% and an average score of 46.5%. While the best MLLM performs comparably to the lowest-scoring student, it still lags significantly behind the group's average performance. This comparison underscores both the progress of MLLMs in anatomical understanding and the substantial gap that remains in achieving human-level performance.

cs.CV↗

arXiv2025

The Forgotten Shield: Safety Grafting in Parameter-Space for Medical MLLMs

Medical Multimodal Large Language Models (Medical MLLMs) have achieved remarkable progress in specialized medical tasks; however, research into their safety has lagged, posing potential risks for real-world deployment. In this paper, we first establish a multidimensional evaluation framework to systematically benchmark the safety of current SOTA Medical MLLMs. Our empirical analysis reveals pervasive vulnerabilities across both general and medical-specific safety dimensions in existing models, particularly highlighting their fragility against cross-modality jailbreak attacks. Furthermore, we find that the medical fine-tuning process frequently induces catastrophic forgetting of the model's original safety alignment. To address this challenge, we propose a novel "Parameter-Space Intervention" approach for efficient safety re-alignment. This method extracts intrinsic safety knowledge representations from original base models and concurrently injects them into the target model during the construction of medical capabilities. Additionally, we design a fine-grained parameter search algorithm to achieve an optimal trade-off between safety and medical performance. Experimental results demonstrate that our approach significantly bolsters the safety guardrails of Medical MLLMs without relying on additional domain-specific safety data, while minimizing degradation to core medical performance.

cs.LG↗

arXiv2025

A Survey on Personalized Content Synthesis with Diffusion Models

Recent advancements in diffusion models have significantly impacted content creation, leading to the emergence of Personalized Content Synthesis (PCS). By utilizing a small set of user-provided examples featuring the same subject, PCS aims to tailor this subject to specific user-defined prompts. Over the past two years, more than 150 methods have been introduced in this area. However, existing surveys primarily focus on text-to-image generation, with few providing up-to-date summaries on PCS. This paper provides a comprehensive survey of PCS, introducing the general frameworks of PCS research, which can be categorized into test-time fine-tuning (TTF) and pre-trained adaptation (PTA) approaches. We analyze the strengths, limitations, and key techniques of these methodologies. Additionally, we explore specialized tasks within the field, such as object, face, and style personalization, while highlighting their unique challenges and innovations. Despite the promising progress, we also discuss ongoing challenges, including overfitting and the trade-off between subject fidelity and text alignment. Through this detailed overview and analysis, we propose future directions to further the development of PCS.

cs.CV↗

arXiv2025

SA-Person: Text-Based Person Retrieval with Scene-aware Re-ranking

Text-based person retrieval aims to identify a target individual from an image gallery using a natural language description. Existing methods primarily focus on appearance-driven cross-modal retrieval, yet face significant challenges due to the visual complexity of scenes and the inherent ambiguity of textual descriptions. The contextual information, such as landmarks and relational cues, provides complementary cues that can offer valuable complementary insights for retrieval, but remains underexploited in current approaches. Motivated by this limitation, we propose a novel paradigm: scene-aware text-based person retrieval, which explicitly integrates both individual appearance and global scene context to improve retrieval accuracy. To support this, we first introduce ScenePerson-13W, a large-scale benchmark dataset comprising over 100,000 real-world scenes with rich annotations encompassing both pedestrian attributes and scene context. Based on this dataset, we further present SA-Person, a two-stage retrieval framework. In the first stage, SA-Person performs discriminative appearance grounding by aligning textual descriptions with pedestrian-specific regions. In the second stage, it introduces SceneRanker, a training-free, scene-aware re-ranking module that refines retrieval results by jointly reasoning over pedestrian appearance and the global scene context. Extensive experiments on ScenePerson-13W and existing benchmarks demonstrate the effectiveness of our proposed SA-Person. Both the dataset and code will be publicly released to facilitate future research.

cs.CV↗

arXiv2025

How Far Are Surgeons from Surgical World Models? A Pilot Study on Zero-shot Surgical Video Generation with Expert Assessment

Foundation models in video generation are demonstrating remarkable capabilities as potential world models for simulating the physical world. However, their application in high-stakes domains like surgery, which demand deep, specialized causal knowledge rather than general physical rules, remains a critical unexplored gap. To systematically address this challenge, we present SurgVeo, the first expert-curated benchmark for video generation model evaluation in surgery, and the Surgical Plausibility Pyramid (SPP), a novel, four-tiered framework tailored to assess model outputs from basic appearance to complex surgical strategy. On the basis of the SurgVeo benchmark, we task the advanced Veo-3 model with a zero-shot prediction task on surgical clips from laparoscopic and neurosurgical procedures. A panel of four board-certified surgeons evaluates the generated videos according to the SPP. Our results reveal a distinct "plausibility gap": while Veo-3 achieves exceptional Visual Perceptual Plausibility, it fails critically at higher levels of the SPP, including Instrument Operation Plausibility, Environment Feedback Plausibility, and Surgical Intent Plausibility. This work provides the first quantitative evidence of the chasm between visually convincing mimicry and causal understanding in surgical AI. Our findings from SurgVeo and the SPP establish a crucial foundation and roadmap for developing future models capable of navigating the complexities of specialized, real-world healthcare domains.

cs.CV↗

arXiv2025

PRO-VPT: Distribution-Adaptive Visual Prompt Tuning via Prompt Relocation

Visual prompt tuning (VPT), i.e., fine-tuning some lightweight prompt tokens, provides an efficient and effective approach for adapting pre-trained models to various downstream tasks. However, most prior art indiscriminately uses a fixed prompt distribution across different tasks, neglecting the importance of each block varying depending on the task. In this paper, we introduce adaptive distribution optimization (ADO) by tackling two key questions: (1) How to appropriately and formally define ADO, and (2) How to design an adaptive distribution strategy guided by this definition? Through empirical analysis, we first confirm that properly adjusting the distribution significantly improves VPT performance, and further uncover a key insight that a nested relationship exists between ADO and VPT. Based on these findings, we propose a new VPT framework, termed PRO-VPT (iterative Prompt RelOcation-based VPT), which adaptively adjusts the distribution built upon a nested optimization formulation. Specifically, we develop a prompt relocation strategy derived from this formulation, comprising two steps: pruning idle prompts from prompt-saturated blocks, followed by allocating these prompts to the most prompt-needed blocks. By iteratively performing prompt relocation and VPT, our proposal can adaptively learn the optimal prompt distribution in a nested optimization-based manner, thereby unlocking the full potential of VPT. Extensive experiments demonstrate that our proposal significantly outperforms advanced VPT methods, e.g., PRO-VPT surpasses VPT by 1.6 pp and 2.0 pp average accuracy, leading prompt-based methods to state-of-the-art performance on VTAB-1k and FGVC benchmarks. The code is available at https://github.com/ckshang/PRO-VPT.

cs.CV↗

arXiv2025

Bayesian Test-time Adaptation for Object Recognition and Detection with Vision-language Models

Vision-language models (VLMs) such as CLIP and Grounding DINO have achieved remarkable success in object recognition and detection. However, their performance often degrades under real-world distribution shifts. Test-time adaptation (TTA) aims to mitigate this issue by adapting models during inference. Existing methods either rely on computationally expensive backpropagation, which hinders real-time deployment, or focus solely on likelihood adaptation, which overlooks the critical role of the prior. Our prior work, Bayesian Class Adaptation (BCA), addressed these shortcomings for object recognition by introducing a training-free framework that incorporates adaptive priors. Building upon this foundation, we now present Bayesian Class Adaptation plus (BCA+), a unified, training-free framework for TTA for both object recognition and detection. BCA+ introduces a dynamic cache that adaptively stores and updates class embeddings, spatial scales (for detection), and, crucially, adaptive class priors derived from historical predictions. We formulate adaptation as a Bayesian inference problem, where final predictions are generated by fusing the initial VLM output with a cache-based prediction. This cache-based prediction combines a dynamically updated likelihood (measuring feature and scale similarity) and a prior (reflecting the evolving class distribution). This dual-adaptation mechanism, coupled with uncertainty-guided fusion, enables BCA+ to correct both the model's semantic understanding and its contextual confidence. As a training-free method requiring no backpropagation, BCA+ is highly efficient. Extensive experiments demonstrate that BCA+ achieves state-of-the-art performance on both recognition and detection benchmarks.

cs.CV↗

arXiv2025

Towards Realistic Hand-Object Interaction with Gravity-Field Based Diffusion Bridge

Existing reconstruction or hand-object pose estimation methods are capable of producing coarse interaction states. However, due to the complex and diverse geometry of both human hands and objects, these approaches often suffer from interpenetration or leave noticeable gaps in regions that are supposed to be in contact. Moreover, the surface of a real human hand undergoes non-negligible deformations during interaction, which are difficult to capture and represent with previous methods. To tackle these challenges, we formulate hand-object interaction as an attraction-driven process and propose a Gravity-Field Based Diffusion Bridge (GravityDB) to simulate interactions between a deformable hand surface and rigid objects. Our approach effectively resolves the aforementioned issues by generating physically plausible interactions that are free of interpenetration, ensure stable grasping, and capture realistic hand deformations. Furthermore, we incorporate semantic information from textual descriptions to guide the construction of the gravitational field, enabling more semantically meaningful interaction regions. Extensive qualitative and quantitative experiments on multiple datasets demonstrate the effectiveness of our method.

cs.CV↗

arXiv2025

SurgLLM: A Versatile Large Multimodal Model with Spatial Focus and Temporal Awareness for Surgical Video Understanding

Surgical video understanding is crucial for facilitating Computer-Assisted Surgery (CAS) systems. Despite significant progress in existing studies, two major limitations persist, including inadequate visual content perception and insufficient temporal awareness in surgical videos, and hinder the development of versatile CAS solutions. In this work, we propose the SurgLLM framework, an effective large multimodal model tailored for versatile surgical video understanding tasks with enhanced spatial focus and temporal awareness. Specifically, to empower the spatial focus of surgical videos, we first devise Surgical Context-aware Multimodal Pretraining (Surg-Pretrain) for the video encoder of SurgLLM, by performing instrument-centric Masked Video Reconstruction (MV-Recon) and subsequent multimodal alignment. To incorporate surgical temporal knowledge into SurgLLM, we further propose Temporal-aware Multimodal Tuning (TM-Tuning) to enhance temporal reasoning with interleaved multimodal embeddings. Moreover, to accommodate various understanding tasks of surgical videos without conflicts, we devise a Surgical Task Dynamic Ensemble to efficiently triage a query with optimal learnable parameters in our SurgLLM. Extensive experiments performed on diverse surgical video understanding tasks, including captioning, general VQA, and temporal VQA, demonstrate significant improvements over the state-of-the-art approaches, validating the effectiveness of our SurgLLM in versatile surgical video understanding. The source code is available at https://github.com/franciszchen/SurgLLM.

cs.CV↗

arXiv2025

Text-Driven Causal Representation Learning for Source-Free Domain Generalization

Deep learning often struggles when training and test data distributions differ. Traditional domain generalization (DG) tackles this by including data from multiple source domains, which is impractical due to expensive data collection and annotation. Recent vision-language models like CLIP enable source-free domain generalization (SFDG) by using text prompts to simulate visual representations, reducing data demands. However, existing SFDG methods struggle with domain-specific confounders, limiting their generalization capabilities. To address this issue, we propose TDCRL (\textbf{T}ext-\textbf{D}riven \textbf{C}ausal \textbf{R}epresentation \textbf{L}earning), the first method to integrate causal inference into the SFDG setting. TDCRL operates in two steps: first, it employs data augmentation to generate style word vectors, combining them with class information to generate text embeddings to simulate visual representations; second, it trains a causal intervention network with a confounder dictionary to extract domain-invariant features. Grounded in causal learning, our approach offers a clear and effective mechanism to achieve robust, domain-invariant features, ensuring robust generalization. Extensive experiments on PACS, VLCS, OfficeHome, and DomainNet show state-of-the-art performance, proving TDCRL effectiveness in SFDG.

cs.LG↗

arXiv2025

SurgVisAgent: Multimodal Agentic Model for Versatile Surgical Visual Enhancement

Precise surgical interventions are vital to patient safety, and advanced enhancement algorithms have been developed to assist surgeons in decision-making. Despite significant progress, these algorithms are typically designed for single tasks in specific scenarios, limiting their effectiveness in complex real-world situations. To address this limitation, we propose SurgVisAgent, an end-to-end intelligent surgical vision agent built on multimodal large language models (MLLMs). SurgVisAgent dynamically identifies distortion categories and severity levels in endoscopic images, enabling it to perform a variety of enhancement tasks such as low-light enhancement, overexposure correction, motion blur elimination, and smoke removal. Specifically, to achieve superior surgical scenario understanding, we design a prior model that provides domain-specific knowledge. Additionally, through in-context few-shot learning and chain-of-thought (CoT) reasoning, SurgVisAgent delivers customized image enhancements tailored to a wide range of distortion types and severity levels, thereby addressing the diverse requirements of surgeons. Furthermore, we construct a comprehensive benchmark simulating real-world surgical distortions, on which extensive experiments demonstrate that SurgVisAgent surpasses traditional single-task models, highlighting its potential as a unified solution for surgical assistance.

cs.CV↗

arXiv2025

Endo-4DGX: Robust Endoscopic Scene Reconstruction and Illumination Correction with Gaussian Splatting

Accurate reconstruction of soft tissue is crucial for advancing automation in image-guided robotic surgery. The recent 3D Gaussian Splatting (3DGS) techniques and their variants, 4DGS, achieve high-quality renderings of dynamic surgical scenes in real-time. However, 3D-GS-based methods still struggle in scenarios with varying illumination, such as low light and over-exposure. Training 3D-GS in such extreme light conditions leads to severe optimization problems and devastating rendering quality. To address these challenges, we present Endo-4DGX, a novel reconstruction method with illumination-adaptive Gaussian Splatting designed specifically for endoscopic scenes with uneven lighting. By incorporating illumination embeddings, our method effectively models view-dependent brightness variations. We introduce a region-aware enhancement module to model the sub-area lightness at the Gaussian level and a spatial-aware adjustment module to learn the view-consistent brightness adjustment. With the illumination adaptive design, Endo-4DGX achieves superior rendering performance under both low-light and over-exposure conditions while maintaining geometric accuracy. Additionally, we employ an exposure control loss to restore the appearance from adverse exposure to the normal level for illumination-adaptive optimization. Experimental results demonstrate that Endo-4DGX significantly outperforms combinations of state-of-the-art reconstruction and restoration methods in challenging lighting environments, underscoring its potential to advance robot-assisted surgical applications. Our code is available at https://github.com/lastbasket/Endo-4DGX.

cs.CV↗

arXiv2025

PCaM: A Progressive Focus Attention-Based Information Fusion Method for Improving Vision Transformer Domain Adaptation

Unsupervised Domain Adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Recent UDA methods based on Vision Transformers (ViTs) have achieved strong performance through attention-based feature alignment. However, we identify a key limitation: foreground object mismatch, where the discrepancy in foreground object size and spatial distribution across domains weakens attention consistency and hampers effective domain alignment. To address this issue, we propose the Progressive Focus Cross-Attention Mechanism (PCaM), which progressively filters out background information during cross-attention, allowing the model to focus on and fuse discriminative foreground semantics across domains. We further introduce an attentional guidance loss that explicitly directs attention toward task-relevant regions, enhancing cross-domain attention consistency. PCaM is lightweight, architecture-agnostic, and easy to integrate into existing ViT-based UDA pipelines. Extensive experiments on Office-Home, DomainNet, VisDA-2017, and remote sensing datasets demonstrate that PCaM significantly improves adaptation performance and achieves new state-of-the-art results, validating the effectiveness of attention-guided foreground fusion for domain adaptation.

cs.LG↗

arXiv2025

What Makes a Scene ? Scene Graph-based Evaluation and Feedback for Controllable Generation

While text-to-image generation has been extensively studied, generating images from scene graphs remains relatively underexplored, primarily due to challenges in accurately modeling spatial relationships and object interactions. To fill this gap, we introduce Scene-Bench, a comprehensive benchmark designed to evaluate and enhance the factual consistency in generating natural scenes. Scene-Bench comprises MegaSG, a large-scale dataset of one million images annotated with scene graphs, facilitating the training and fair comparison of models across diverse and complex scenes. Additionally, we propose SGScore, a novel evaluation metric that leverages chain-of-thought reasoning capabilities of multimodal large language models (LLMs) to assess both object presence and relationship accuracy, offering a more effective measure of factual consistency than traditional metrics like FID and CLIPScore. Building upon this evaluation framework, we develop a scene graph feedback pipeline that iteratively refines generated images by identifying and correcting discrepancies between the scene graph and the image. Extensive experiments demonstrate that Scene-Bench provides a more comprehensive and effective evaluation framework compared to existing benchmarks, particularly for complex scene generation. Furthermore, our feedback strategy significantly enhances the factual consistency of image generation models, advancing the field of controllable image generation.

cs.CV↗

arXiv2025

Compile Scene Graphs with Reinforcement Learning

Next-token prediction is the fundamental principle for training large language models (LLMs), and reinforcement learning (RL) further enhances their reasoning performance. As an effective way to model language, image, video, and other modalities, the use of LLMs for end-to-end extraction of structured visual representations, such as scene graphs, remains underexplored. It requires the model to accurately produce a set of objects and relationship triplets, rather than generating text token by token. To achieve this, we introduce R1-SGG, a multimodal LLM (M-LLM) initially trained via supervised fine-tuning (SFT) on the scene graph dataset and subsequently refined using reinforcement learning to enhance its ability to generate scene graphs in an end-to-end manner. The SFT follows a conventional prompt-response paradigm, while RL requires the design of effective reward signals. We design a set of graph-centric rewards, including three recall-based variants -- Hard Recall, Hard Recall+Relax, and Soft Recall -- which evaluate semantic and spatial alignment between predictions and ground truth at the object and relation levels. A format consistency reward further ensures that outputs follow the expected structural schema. Extensive experiments on the VG150 and PSG benchmarks show that R1-SGG substantially reduces failure rates and achieves strong performance in Recall and mean Recall, surpassing traditional SGG models and existing multimodal language models. Our code is available at https://github.com/gpt4vision/R1-SGG

cs.CV↗

arXiv2025

From Data to Modeling: Fully Open-vocabulary Scene Graph Generation

We present OvSGTR, a novel transformer-based framework for fully open-vocabulary scene graph generation that overcomes the limitations of traditional closed-set models. Conventional methods restrict both object and relationship recognition to a fixed vocabulary, hindering their applicability to real-world scenarios where novel concepts frequently emerge. In contrast, our approach jointly predicts objects (nodes) and their inter-relationships (edges) beyond predefined categories. OvSGTR leverages a DETR-like architecture featuring a frozen image backbone and text encoder to extract high-quality visual and semantic features, which are then fused via a transformer decoder for end-to-end scene graph prediction. To enrich the model's understanding of complex visual relations, we propose a relation-aware pre-training strategy that synthesizes scene graph annotations in a weakly supervised manner. Specifically, we investigate three pipelines--scene parser-based, LLM-based, and multimodal LLM-based--to generate transferable supervision signals with minimal manual annotation. Furthermore, we address the common issue of catastrophic forgetting in open-vocabulary settings by incorporating a visual-concept retention mechanism coupled with a knowledge distillation strategy, ensuring that the model retains rich semantic cues during fine-tuning. Extensive experiments on the VG150 benchmark demonstrate that OvSGTR achieves state-of-the-art performance across multiple settings, including closed-set, open-vocabulary object detection-based, relation-based, and fully open-vocabulary scenarios. Our results highlight the promise of large-scale relation-aware pre-training and transformer architectures for advancing scene graph generation towards more generalized and reliable visual understanding.

cs.CV↗

arXiv2025

Surgical-LVLM: Learning to Adapt Large Vision-Language Model for Grounded Visual Question Answering in Robotic Surgery

Recent advancements in Surgical Visual Question Answering (Surgical-VQA) and related region grounding have shown great promise for robotic and medical applications, addressing the critical need for automated methods in personalized surgical mentorship. However, existing models primarily provide simple structured answers and struggle with complex scenarios due to their limited capability in recognizing long-range dependencies and aligning multimodal information. In this paper, we introduce Surgical-LVLM, a novel personalized large vision-language model tailored for complex surgical scenarios. Leveraging the pre-trained large vision-language model and specialized Visual Perception LoRA (VP-LoRA) blocks, our model excels in understanding complex visual-language tasks within surgical contexts. In addressing the visual grounding task, we propose the Token-Interaction (TIT) module, which strengthens the interaction between the grounding module and the language responses of the Large Visual Language Model (LVLM) after projecting them into the latent space. We demonstrate the effectiveness of Surgical-LVLM on several benchmarks, including EndoVis-17-VQLA, EndoVis-18-VQLA, and a newly introduced EndoVis Conversations dataset, which sets new performance standards. Our work contributes to advancing the field of automated surgical mentorship by providing a context-aware solution.

cs.CV↗