arXiv subjects

Zhu Zhuo

Publications and source records attributed to Zhu Zhuo.

12 recordsLinked to original sources

arXiv2026

SurgRAW: Multi-Agent Workflow with Chain of Thought Reasoning for Robotic Surgical Video Analysis

Robotic-assisted surgery (RAS) is central to modern surgery, driving the need for intelligent systems with accurate scene understanding. Most existing surgical AI methods rely on isolated, task-specific models, leading to fragmented pipelines with limited interpretability and no unified understanding of RAS scene. Vision-Language Models (VLMs) offer strong zero-shot reasoning, but struggle with hallucinations, domain gaps and weak task-interdependency modeling. To address the lack of unified data for RAS scene understanding, we introduce SurgCoTBench, the first reasoning-focused benchmark in RAS, covering 14256 QA pairs with frame-level annotations across five major surgical tasks. Building on SurgCoTBench, we propose SurgRAW, a clinically aligned Chain-of-Thought (CoT) driven agentic workflow for zero-shot multi-task reasoning in surgery. SurgRAW employs a hierarchical reasoning workflow where an orchestrator divides surgical scene understanding into two reasoning streams and directs specialized agents to generate task-level reasoning, while higher-level agents capture workflow interdependencies or ground output clinically. Specifically, we propose a panel discussion mechanism to ensure task-specific agents collaborate synergistically and leverage on task interdependencies. Similarly, we incorporate a retrieval-augmented generation module to enrich agents with surgical knowledge and alleviate domain gaps in general VLMs. We design task-specific CoT prompts grounded in surgical domain to ensure clinically aligned reasoning, reduce hallucinations and enhance interpretability. Extensive experiments show that SurgRAW surpasses mainstream VLMs and agentic systems and outperforms a supervised model by 14.61% accuracy. Dataset and code is available at https://github.com/jinlab-imvr/SurgRAW.git .

cs.AI↗

arXiv2026

CockpitHAT: Dependency-Graph-Driven Hierarchical Attribution for Embodied Multi-Agent Cockpits

LLM multi-agent systems suffer from Correctness Collapse, where high task-level accuracy conceals severe process-level failures. This is especially hazardous in safety-critical embodied settings such as automotive cockpits, where lexically correct utterances may trigger dangerous physical operations. Existing attribution methods rely on text traces alone, missing dependency structure, multi-channel evidence, and safety-aware evaluation. We introduce CockpitHAT, a hierarchical attribution framework that replaces positional windows with dependency-distance thresholds from interaction DAGs, integrates multi-channel evidence via an embodied adapter, and applies a safety-uplift to high-risk failures during confidence-weighted analyst consensus. We further release CockpitBench, a benchmark of 212 annotated failure traces spanning dialogue, vehicle-state, environmental, and memory channels, each labeled with ISO 26262 ASIL severity via three-expert consensus. On the public Who&When benchmark, CockpitHAT achieves agent-level / step-exact accuracies of 77.9% / 37.8% on the Hand-Crafted split and 86.5% / 46.0% on the Algorithm-Generated split, surpassing the text-only SOTA ECHO by up to 17.6 / 16.7 points. On CockpitBench, it attains 78.3% agent-level and 38.2% step-exact accuracy. These results establish dependency-aware, multi-channel, risk-calibrated attribution as an effective paradigm for reliable failure diagnosis in real-world embodied LLM multi-agent systems.

cs.AI↗

arXiv2026

SurgSLOT: Segment Anything in Surgical Videos via Semantic Long-term Tracking

Surgical scene understanding demands temporally consistent tracking of instruments and tissues. For clinical use, such tracking should generalize to new centers and procedure types, yet retraining for each of them is costly and not scalable. Interactive video object segmentation offers a way toward this generalization: the target is specified at inference by a first-frame visual prompt, so a model can generalize to unseen categories and new scenarios without retraining. However, training such a generalizable model demands spatio-temporal masklet annotations at a scale and procedural diversity that existing surgical benchmarks lack. We fill this gap with iSurg, the largest surgical segmentation benchmark to our knowledge, spanning six procedure types with over 170k frames, 410k object masks, and 2.4k masklets, including an in-house clinical dataset of four 30-minute videos. Yet tracking over such long videos remains challenging: the target needs to be re-identified among visually similar objects after long absences, while long-term memory has to judge whether each stored frame genuinely depicts the target, both demanding a stable object-level semantic identity. To this end, we propose SurgSLOT, a surgical segmentation generalist that segments any prompted target through two coupled modules built on this semantic identity: Temporal Semantic Learning learns it for re-identification, and Semantic-driven Long-term Memory reuses it to select reliable memory frames, suppressing identity drift over long procedures. On the SAM2 and SAM3 backbones, SurgSLOT reaches 81.0 and 82.8 Macro Average J&F under cross-dataset evaluation, surpassing their fine-tuned counterparts by 5.1 and 5.3 points and transferring zero-shot to an unseen procedure type and unseen object categories, with the SAM2 version running in real time at 68 FPS.

cs.CV↗

arXiv2026

Surg$Σ$: A Spectrum of Large-Scale Multimodal Data and Foundation Models for Surgical Intelligence

Surgical intelligence has the potential to improve the safety and consistency of surgical care, yet most existing surgical AI frameworks remain task-specific and struggle to generalize across procedures and institutions. Although multimodal foundation models, particularly multimodal large language models, have demonstrated strong cross-task capabilities across various medical domains, their advancement in surgery remains constrained by the lack of large-scale, systematically curated multimodal data. To address this challenge, we introduce Surg$Σ$, a spectrum of large-scale multimodal data and foundation models for surgical intelligence. At the core of this framework lies Surg$Σ$-DB, a large-scale multimodal data foundation designed to support diverse surgical tasks. Surg$Σ$-DB consolidates heterogeneous surgical data sources (including open-source datasets, curated in-house clinical collections and web-source data) into a unified schema, aiming to improve label consistency and data standardization across heterogeneous datasets. Surg$Σ$-DB spans 6 clinical specialties and diverse surgical types, providing rich image- and video-level annotations across 18 practical surgical tasks covering understanding, reasoning, planning, and generation, at an unprecedented scale (over 5.98M conversations). Beyond conventional multimodal conversations, Surg$Σ$-DB incorporates hierarchical reasoning annotations, providing richer semantic cues to support deeper contextual understanding in complex surgical scenarios. We further provide empirical evidence through recently developed surgical foundation models built upon Surg$Σ$-DB, illustrating the practical benefits of large-scale multimodal annotations, unified semantic design, and structured reasoning annotations for improving cross-task generalization and interpretability.

cs.AI↗

arXiv2026

Surg-R1: A Hierarchical Reasoning Foundation Model for Scalable and Interpretable Surgical Decision Support with Multi-Center Clinical Validation

Surgical scene understanding demands not only accurate predictions but also interpretable reasoning that surgeons can verify against clinical expertise. However, existing surgical vision-language models generate predictions without reasoning chains, and general-purpose reasoning models fail on compositional surgical tasks without domain-specific knowledge. We present Surg-R1, a surgical Vision-Language Model that addresses this gap through hierarchical reasoning trained via a four-stage pipeline. Our approach introduces three key contributions: (1) a three-level reasoning hierarchy decomposing surgical interpretation into perceptual grounding, relational understanding, and contextual reasoning; (2) the largest surgical chain-of-thought dataset with 320,000 reasoning pairs; and (3) a four-stage training pipeline progressing from supervised fine-tuning to group relative policy optimization and iterative self-improvement. Evaluation on SurgBench, comprising six public benchmarks and six multi-center external validation datasets from five institutions, demonstrates that Surg-R1 achieves the highest Arena Score (64.9%) on public benchmarks versus Gemini 3.0 Pro (46.1%) and GPT-5.1 (37.9%), outperforming both proprietary reasoning models and specialized surgical VLMs on the majority of tasks spanning instrument localization, triplet recognition, phase recognition, action recognition, and critical view of safety assessment, with a 15.2 percentage point improvement over the strongest surgical baseline on external validation.

cs.CV↗

arXiv2026

SurgFed: Language-guided Multi-Task Federated Learning for Surgical Video Understanding

Surgical scene Multi-Task Federated Learning (MTFL) is essential for robot-assisted minimally invasive surgery (RAS) but remains underexplored in surgical video understanding due to two key challenges: (1) Tissue Diversity: Local models struggle to adapt to site-specific tissue features, limiting their effectiveness in heterogeneous clinical environments and leading to poor local predictions. (2) Task Diversity: Server-side aggregation, relying solely on gradient-based clustering, often produces suboptimal or incorrect parameter updates due to inter-site task heterogeneity, resulting in inaccurate localization. In light of these two issues, we propose SurgFed, a multi-task federated learning framework, enabling federated learning for surgical scene segmentation and depth estimation across diverse surgical types. SurgFed is powered by two appealing designs, i.e., Language-guided Channel Selection (LCS) and Language-guided Hyper Aggregation (LHA), to address the challenge of fully exploration on corss-site and cross-task. Technically, the LCS is first designed a lightweight personalized channel selection network that enhances site-specific adaptation using pre-defined text inputs, which optimally the local model learn the specific embeddings. We further introduce the LHA that employs a layer-wise cross-attention mechanism with pre-defined text inputs to model task interactions across sites and guide a hypernetwork for personalized parameter updates. Extensive empirical evidence shows that SurgFed yields improvements over the state-of-the-art methods in five public datasets across four surgical types. The code is available at https://anonymous.4open.science/r/SurgFed-070E/.

cs.CV↗

arXiv2026

SurGo-R1: Benchmarking and Modeling Contextual Reasoning for Operative Zone in Surgical Video

Minimally invasive surgery has dramatically improved patient operative outcomes, yet identifying safe operative zones remains challenging in critical phases, requiring surgeons to integrate visual cues, procedural phase, and anatomical context under high cognitive load. Existing AI systems offer binary safety verification or static detection, ignoring the phase-dependent nature of intraoperative reasoning. We introduce ResGo, a benchmark of laparoscopic frames annotated with Go Zone bounding boxes and clinician-authored rationales covering phase, exposure quality reasoning, next action and risk reminder. We introduce evaluation metrics that treat correct grounding under incorrect phase as failures, revealing that most vision-language models cannot handle such tasks and perform poorly. We then present SurGo-R1, a model optimized via RLHF with a multi-turn phase-then-go architecture where the model first identifies the surgical phase, then generates reasoning and Go Zone coordinates conditioned on that context. On unseen procedures, SurGo-R1 achieves 76.6% phase accuracy, 32.7 mIoU, and 54.8% hardcore accuracy, a 6.6$\times$ improvement over the mainstream generalist VLMs. Code, model and benchmark will be available at https://github.com/jinlab-imvr/SurGo-R1

cs.CV↗

arXiv2025

CARES: Collaborative Agentic Reasoning for Error Detection in Surgery

Robotic-assisted surgery (RAS) introduces complex challenges that current surgical error detection methods struggle to address effectively due to limited training data and methodological constraints. Therefore, we construct MERP (Multi-class Error in Robotic Prostatectomy), a comprehensive dataset for error detection in robotic prostatectomy with frame-level annotations featuring six clinically aligned error categories. In addition, we propose CARES (Collaborative Agentic Reasoning for Error Detection in Surgery), a novel zero-shot clinically-informed and risk-stratified agentic reasoning architecture for multi-class surgical error detection. CARES implements adaptive generation of medically informed, error-specific Chain-of-Thought (CoT) prompts across multiple expertise levels. The framework employs risk-aware routing to assign error task to expertise-matched reasoning pathways based on complexity and clinical impact. Subsequently, each pathway decomposes surgical error analysis into three specialized agents with temporal, spatial, and procedural analysis. Each agent analyzes using dynamically selected prompts tailored to the assigned expertise level and error type, generating detailed and transparent reasoning traces. By incorporating clinically informed reasoning from established surgical assessment guidelines, CARES enables zero-shot surgical error detection without prior training. Evaluation demonstrates superior performance with 54.3 mF1 on RARP and 52.0 mF1 on MERP datasets, outperforming existing zero-shot approaches by up to 14% while remaining competitive with trained models. Ablation studies demonstrate the effectiveness of our method. The dataset and code will be publicly available.

cs.MA↗

arXiv2025

SurgVLM: A Large Vision-Language Model and Systematic Evaluation Benchmark for Surgical Intelligence

Foundation models have achieved transformative success across biomedical domains by enabling holistic understanding of multimodal data. However, their application in surgery remains underexplored. Surgical intelligence presents unique challenges - requiring surgical visual perception, temporal analysis, and reasoning. Existing general-purpose vision-language models fail to address these needs due to insufficient domain-specific supervision and the lack of a large-scale high-quality surgical database. To bridge this gap, we propose SurgVLM, one of the first large vision-language foundation models for surgical intelligence, where this single universal model can tackle versatile surgical tasks. To enable this, we construct a large-scale multimodal surgical database, SurgVLM-DB, comprising over 1.81 million frames with 7.79 million conversations, spanning more than 16 surgical types and 18 anatomical structures. We unify and reorganize 23 public datasets across 10 surgical tasks, followed by standardizing labels and doing hierarchical vision-language alignment to facilitate comprehensive coverage of gradually finer-grained surgical tasks, from visual perception, temporal analysis, to high-level reasoning. Building upon this comprehensive dataset, we propose SurgVLM, which is built upon Qwen2.5-VL, and undergoes instruction tuning to 10+ surgical tasks. We further construct a surgical multimodal benchmark, SurgVLM-Bench, for method evaluation. SurgVLM-Bench consists of 6 popular and widely-used datasets in surgical domain, covering several crucial downstream tasks. Based on SurgVLM-Bench, we evaluate the performance of our SurgVLM (3 SurgVLM variants: SurgVLM-7B, SurgVLM-32B, and SurgVLM-72B), and conduct comprehensive comparisons with 14 mainstream commercial VLMs (e.g., GPT-4o, Gemini 2.0 Flash, Qwen2.5-Max).

cs.CV↗

arXiv2023

Joint Generative-Contrastive Representation Learning for Anomalous Sound Detection

In this paper, we propose a joint generative and contrastive representation learning method (GeCo) for anomalous sound detection (ASD). GeCo exploits a Predictive AutoEncoder (PAE) equipped with self-attention as a generative model to perform frame-level prediction. The output of the PAE together with original normal samples, are used for supervised contrastive representative learning in a multi-task framework. Besides cross-entropy loss between classes, contrastive loss is used to separate PAE output and original samples within each class. GeCo aims to better capture context information among frames, thanks to the self-attention mechanism for PAE model. Furthermore, GeCo combines generative and contrastive learning from which we aim to yield more effective and informative representations, compared to existing methods. Extensive experiments have been conducted on the DCASE2020 Task2 development dataset, showing that GeCo outperforms state-of-the-art generative and discriminative methods.

eess.AS↗

arXiv2020

Transfer Learning for Context-Aware Spoken Language Understanding

Spoken language understanding (SLU) is a key component of task-oriented dialogue systems. SLU parses natural language user utterances into semantic frames. Previous work has shown that incorporating context information significantly improves SLU performance for multi-turn dialogues. However, collecting a large-scale human-labeled multi-turn dialogue corpus for the target domains is complex and costly. To reduce dependency on the collection and annotation effort, we propose a Context Encoding Language Transformer (CELT) model facilitating exploiting various context information for SLU. We explore different transfer learning approaches to reduce dependency on data collection and annotation. In addition to unsupervised pre-training using large-scale general purpose unlabeled corpora, such as Wikipedia, we explore unsupervised and supervised adaptive training approaches for transfer learning to benefit from other in-domain and out-of-domain dialogue corpora. Experimental results demonstrate that the proposed model with the proposed transfer learning approaches achieves significant improvement on the SLU performance over state-of-the-art models on two large-scale single-turn dialogue benchmarks and one large-scale multi-turn dialogue benchmark.

cs.CL↗

arXiv2019

BERT for Joint Intent Classification and Slot Filling

Intent classification and slot filling are two essential tasks for natural language understanding. They often suffer from small-scale human-labeled training data, resulting in poor generalization capability, especially for rare words. Recently a new language representation model, BERT (Bidirectional Encoder Representations from Transformers), facilitates pre-training deep bidirectional representations on large-scale unlabeled corpora, and has created state-of-the-art models for a wide variety of natural language processing tasks after simple fine-tuning. However, there has not been much effort on exploring BERT for natural language understanding. In this work, we propose a joint intent classification and slot filling model based on BERT. Experimental results demonstrate that our proposed model achieves significant improvement on intent classification accuracy, slot filling F1, and sentence-level semantic frame accuracy on several public benchmark datasets, compared to the attention-based recurrent neural network models and slot-gated models.

cs.CL↗