arXiv subjects

Long Bai

Publications and source records attributed to Long Bai.

At least 37 records · Page 2Linked to original sources

arXiv2026

Towards Knowledgeable Deep Research: Framework and Benchmark

Deep Research (DR) requires LLM agents to autonomously perform multi-step information seeking, processing, and reasoning to generate comprehensive reports. In contrast to existing studies that mainly focus on unstructured web content, a more challenging DR task should additionally utilize structured knowledge to provide a solid data foundation, facilitate quantitative computation, and lead to in-depth analyses. In this paper, we refer to this novel task as Knowledgeable Deep Research (KDR), which requires DR agents to generate reports with both structured and unstructured knowledge. Furthermore, we propose the Hybrid Knowledge Analysis framework (HKA), a multi-agent architecture that reasons over both kinds of knowledge and integrates the texts, figures, and tables into coherent multimodal reports. The key design is the Structured Knowledge Analyzer, which utilizes both coding and vision-language models to produce figures, tables, and corresponding insights. To support systematic evaluation, we construct KDR-Bench, which covers 9 domains, includes 41 expert-level questions, and incorporates a large number of structured knowledge resources (e.g., 1,252 tables). We further annotate the main conclusions and key points for each question and propose three categories of evaluation metrics including general-purpose, knowledge-centric, and vision-enhanced ones. Experimental results demonstrate that HKA consistently outperforms most existing DR agents on general-purpose and knowledge-centric metrics, and even surpasses the Gemini DR agent on vision-enhanced metrics, highlighting its effectiveness in deep, structure-aware knowledge analysis. Finally, we hope this work can serve as a new foundation for structured knowledge analysis in DR agents and facilitate future multimodal DR studies.

cs.AI↗

arXiv2026

TR2M: Transferring Monocular Relative Depth to Metric Depth with Language Descriptions and Dual-Level Scale-Oriented Contrast

This work presents a generalizable framework to transfer relative depth to metric depth. Current monocular depth estimation methods are mainly divided into metric depth estimation (MMDE) and relative depth estimation (MRDE). MMDEs estimate depth in metric scale but are often limited to a specific domain. MRDEs generalize well across different domains, but with uncertain scales which hinders downstream applications. To this end, we aim to build up a framework to solve scale uncertainty and transfer relative depth to metric depth. Previous methods used language as input and estimated two factors for conducting rescaling. Our approach, TR2M, utilizes both text description and image as inputs and estimates two rescale maps to transfer relative depth to metric depth at pixel level. Features from two modalities are fused with a cross-modality attention module to better capture scale information. A strategy is designed to construct and filter confident pseudo metric depth for more comprehensive supervision. We also develop scale-oriented contrastive learning to utilize depth distribution as guidance to enforce the model learning about intrinsic knowledge aligning with the scale distribution. TR2M only exploits a small number of trainable parameters to train on datasets in various domains and experiments not only demonstrate TR2M's great performance in seen datasets but also reveal superior zero-shot capabilities on five unseen datasets. We show the huge potential in pixel-wise transferring relative depth to metric depth with language assistance. (Code is available at: https://github.com/BeileiCui/TR2M)

cs.CV↗

arXiv2026

Leveling3D: Leveling Up 3D Reconstruction with Feed-Forward 3D Gaussian Splatting and Geometry-Aware Generation

Feed-forward 3D reconstruction has revolutionized 3D vision, providing a powerful baseline for downstream tasks such as novel-view synthesis with 3D Gaussian Splatting. Previous works explore fixing the corrupted rendering results with a diffusion model. However, they lack geometric concern and fail at filling the missing area on the extrapolated view. In this work, we introduce Leveling3D, a novel pipeline that integrates feed-forward 3D reconstruction with geometrical-consistent generation to enable holistic simultaneous reconstruction and generation. We propose a geometry-aware leveling adapter, a lightweight technique that aligns internal knowledge in the diffusion model with the geometry prior from the feed-forward model. The leveling adapter enables generation on the artifact area of the extrapolated novel views caused by underconstrained regions of the 3D representation. Specifically, to learn a more diverse distributed generation, we introduce the palette filtering strategy for training, and a test-time masking refinement to prevent messy boundaries along the fixing regions. More importantly, the enhanced extrapolated novel views from Leveling3D could be used as the inputs for feed-forward 3DGS, leveling up the 3D reconstruction. We achieve SOTA performance on public datasets, including tasks such as novel-view synthesis and depth estimation.

cs.CV↗

arXiv2026

TMR-VLA:Vision-Language-Action Model for Magnetic Motion Control of Tri-leg Silicone-based Soft Robot

In-vivo environments, magnetically actuated soft robots offer advantages such as wireless operation and precise control, showing promising potential for painless detection and therapeutic procedures. We developed a trileg magnetically driven soft robot (TMR) whose multi-legged design enables more flexible gaits and diverse motion patterns. For the silicone made of reconfigurable soft robots, its navigation ability can be separated into sequential motions, namely squatting, rotation, lifting a leg, walking and so on. Its motion and behavior depend on its bending shapes. To bridge motion type description and specific low-level voltage control, we introduced TMR-VLA, an end-to-end multi-modal system for a trileg magnetic soft robot capable of performing hybrid motion types, which is promising for developing a navigation ability by adapting its shape to language-constrained motion types. The TMR-VLA deploys embodied endoluminal localization ability from EndoVLA, and fuses sequential frames and natural language commands as input. Low-level voltage output is generated based on the current observation state and specific motion type description. The result shows the TMR-VLA can predict how the voltage applied to TMR will change the dynamics of a silicon-made soft robot. The TMR-VLA reached a 74% average success rate.

cs.RO↗

arXiv2026

Geometry OR Tracker: Universal Geometric Operating Room Tracking

In operating rooms (OR), world-scale multi-view 3D tracking supports downstream applications such as surgeon behavior recognition, where physically meaningful quantities such as distances and motion statistics must be measured in meters. However, real clinical deployments rarely satisfy the geometric prerequisites for stable multi-view fusion and tracking: camera calibration and RGB-D registration are always unreliable, leading to cross-view geometric inconsistency that produces "ghosting" during fusion and degrades 3D trajectories in a shared OR coordinate frame. To address this, we introduce Geometry OR Tracker, a two-stage pipeline that first rectifies imprecise calibration into a scaleconsistent and geometrically consistent camera setup with a single global scale via a Multi-view Metric Geometry Rectification module, and then performs Occlusion-Robust 3D Point Tracking directly in the unified OR world frame. On the MM-OR benchmark, improved geometric consistency translates into tracking gains: our rectification front-end reduces cross-view depth disagreement by more than 30$\times$ compared to raw calibration. Ablation studies further demonstrate the relationship between calibration quality and tracking accuracy, showing that improved geometric consistency yields stronger world-frame tracking.

cs.CV↗

arXiv2026

EndoDDC: Learning Sparse to Dense Reconstruction for Endoscopic Robotic Navigation via Diffusion Depth Completion

Accurate depth estimation plays a critical role in the navigation of endoscopic surgical robots, forming the foundation for 3D reconstruction and safe instrument guidance. Fine-tuning pretrained models heavily relies on endoscopic surgical datasets with precise depth annotations. While existing self-supervised depth estimation techniques eliminate the need for accurate depth annotations, their performance degrades in environments with weak textures and variable lighting, leading to sparse reconstruction with invalid depth estimation. Depth completion using sparse depth maps can mitigate these issues and improve accuracy. Despite the advances in depth completion techniques in general fields, their application in endoscopy remains limited. To overcome these limitations, we propose EndoDDC, an endoscopy depth completion method that integrates images, sparse depth information with depth gradient features, and optimizes depth maps through a diffusion model, addressing the issues of weak texture and light reflection in endoscopic environments. Extensive experiments on two publicly available endoscopy datasets show that our approach outperforms state-of-the-art models in both depth accuracy and robustness. This demonstrates the potential of our method to reduce visual errors in complex endoscopic environments. Our code will be released at https://github.com/yinheng-lin/EndoDDC.

cs.CV↗

arXiv2026

GeoLanG: Geometry-Aware Language-Guided Grasping with Unified RGB-D Multimodal Learning

Language-guided grasping has emerged as a promising paradigm for enabling robots to identify and manipulate target objects through natural language instructions, yet it remains highly challenging in cluttered or occluded scenes. Existing methods often rely on multi-stage pipelines that separate object perception and grasping, which leads to limited cross-modal fusion, redundant computation, and poor generalization in cluttered, occluded, or low-texture scenes. To address these limitations, we propose GeoLanG, an end-to-end multi-task framework built upon the CLIP architecture that unifies visual and linguistic inputs into a shared representation space for robust semantic alignment and improved generalization. To enhance target discrimination under occlusion and low-texture conditions, we explore a more effective use of depth information through the Depth-guided Geometric Module (DGGM), which converts depth into explicit geometric priors and injects them into the attention mechanism without additional computational overhead. In addition, we propose Adaptive Dense Channel Integration, which adaptively balances the contributions of multi-layer features to produce more discriminative and generalizable visual representations. Extensive experiments on the OCID-VLG dataset, as well as in both simulation and real-world hardware, demonstrate that GeoLanG enables precise and robust language-guided grasping in complex, cluttered environments, paving the way toward more reliable multimodal robotic manipulation in real-world human-centric settings.

cs.RO↗

arXiv2026

SurgVidLM: Towards Multi-grained Surgical Video Understanding with Large Language Model

Surgical scene understanding is critical for surgical training and robotic decision-making in robot-assisted surgery. Recent advances in Multimodal Large Language Models (MLLMs) have demonstrated great potential for advancing scene perception in the medical domain, facilitating surgeons to understand surgical scenes and procedures. However, these methods are primarily oriented towards image-based analysis or global video understanding, overlooking the fine-grained video reasoning that is crucial for analyzing specific processes and capturing detailed task execution within a surgical procedure. To bridge this gap, we propose SurgVidLM, the first video language model designed to address both full and fine-grained surgical video comprehension. To train our SurgVidLM, we construct the SVU-31K that is a large-scale dataset with over 31K video-instruction pairs, enabling both holistic understanding and detailed analysis of surgical procedures. Building on this resource, SurgVidLM incorporates a two-stage StageFocus mechanism: the first stage extracts global procedural context, while the second stage performs high-frequency local analysis guided by temporal cues. We also develop the Multi-frequency Fusion Attention to effectively integrate low- and high-frequency visual tokens, ensuring the preservation of critical task-specific details. Experimental results demonstrate that SurgVidLM significantly outperforms state-of-the-art Vid-LLMs of comparable parameter scale in both full and fine-grained video understanding tasks, showcasing its superior capability in capturing the context of complex robot-assisted surgeries. Our code and dataset will be publicly accessible soon.

cs.CV↗

arXiv2026

Comparative validation of surgical phase recognition, instrument keypoint estimation, and instrument instance segmentation in endoscopy: Results of the PhaKIR 2024 challenge

Reliable recognition and localization of surgical instruments in endoscopic video recordings are foundational for a wide range of applications in computer- and robot-assisted minimally invasive surgery (RAMIS), including surgical training, skill assessment, and autonomous assistance. However, robust performance under real-world conditions remains a significant challenge. Incorporating surgical context - such as the current procedural phase - has emerged as a promising strategy to improve robustness and interpretability. To address these challenges, we organized the Surgical Procedure Phase, Keypoint, and Instrument Recognition (PhaKIR) sub-challenge as part of the Endoscopic Vision (EndoVis) challenge at MICCAI 2024. We introduced a novel, multi-center dataset comprising thirteen full-length laparoscopic cholecystectomy videos collected from three distinct medical institutions, with unified annotations for three interrelated tasks: surgical phase recognition, instrument keypoint estimation, and instrument instance segmentation. Unlike existing datasets, ours enables joint investigation of instrument localization and procedural context within the same data while supporting the integration of temporal information across entire procedures. We report results and findings in accordance with the BIAS guidelines for biomedical image analysis challenges. The PhaKIR sub-challenge advances the field by providing a unique benchmark for developing temporally aware, context-driven methods in RAMIS and offers a high-quality resource to support future research in surgical scene understanding.

cs.CV↗

arXiv2026

Where It Moves, It Matters: Referring Surgical Instrument Segmentation via Motion

Enabling intuitive, language-driven interaction with surgical scenes is a critical step toward intelligent operating rooms and autonomous surgical robotic assistance. However, the task of referring segmentation, localizing surgical instruments based on natural language descriptions, remains underexplored in surgical videos, with existing approaches struggling to generalize due to reliance on static visual cues and predefined instrument names. In this work, we introduce SurgRef, a novel motion-guided framework that grounds free-form language expressions in instrument motion, capturing how tools move and interact across time, rather than what they look like. This allows models to understand and segment instruments even under occlusion, ambiguity, or unfamiliar terminology. To train and evaluate SurgRef, we present Ref-IMotion, a diverse, multi-institutional video dataset with dense spatiotemporal masks and rich motion-centric expressions. SurgRef achieves state-of-the-art accuracy and generalization across surgical procedures, setting a new benchmark for robust, language-driven surgical video segmentation.

cs.CV↗

arXiv2026

Does DINOv3 Set a New Medical Vision Standard? Benchmarking 2D and 3D Classification, Segmentation, and Registration

The advent of large-scale vision foundation models, pre-trained on diverse natural images, has marked a paradigm shift in computer vision. However, how the frontier vision foundation models' efficacies transfer to specialised domains such as medical imaging remains an open question. This report investigates whether DINOv3, a state-of-the-art self-supervised vision transformer (ViT) pre-trained on natural images, can directly serve as a powerful, unified encoder for medical vision tasks without domain-specific fine-tuning. To answer this, we benchmark DINOv3 across common medical vision tasks, including 2D and 3D classification, segmentation, and registration on a wide range of medical imaging modalities. We systematically analyse its scalability by varying model sizes and input image resolutions. Our findings reveal that DINOv3 shows impressive performance and establishes a formidable new baseline. Remarkably, it can even outperform medical-specific foundation models like BiomedCLIP and CT-Net on several tasks, despite being trained solely on natural images. However, we identify clear limitations: The model's features degrade in scenarios requiring deep domain specialisation, such as in whole-slide images (WSIs), electron microscopy (EM), and positron emission tomography (PET). Furthermore, we observe that DINOv3 does not consistently follow the scaling law in the medical domain. Its performance does not reliably increase with larger models or finer feature resolutions, showing diverse scaling behaviours across tasks. Overall, our work establishes DINOv3 as a strong baseline, whose powerful visual features can serve as a robust prior for multiple medical tasks. This opens promising future directions, such as leveraging its features to enforce multiview consistency in 3D reconstruction.

cs.CV↗

arXiv2026

Temporal Knowledge Graph Question Answering: A Survey

Knowledge Base Question Answering (KBQA) has been a long-standing field to answer questions based on knowledge bases. Recently, the evolving dynamics of knowledge have attracted a growing interest in Temporal Knowledge Graph Question Answering (TKGQA), an emerging task to answer temporal questions. However, this field grapples with ambiguities in defining temporal questions and lacks a systematic categorization of existing methods for TKGQA. In response, this paper provides a thorough survey from two perspectives: the taxonomy of temporal questions and the methodological categorization for TKGQA. Specifically, we first establish a detailed taxonomy of temporal questions engaged in prior studies. Subsequently, we provide a comprehensive review of TKGQA techniques of two categories: semantic parsing-based and TKG embedding-based. Building on this review, the paper outlines potential research directions aimed at advancing the field of TKGQA. This work aims to serve as a comprehensive reference for TKGQA and to stimulate further research.

cs.CL↗

arXiv2025

More than Segmentation: Benchmarking SAM 3 for Segmentation, 3D Perception, and Reconstruction in Robotic Surgery

The recent SAM 3 and SAM 3D have introduced significant advancements over the predecessor, SAM 2, particularly with the integration of language-based segmentation and enhanced 3D perception capabilities. SAM 3 supports zero-shot segmentation across a wide range of prompts, including point, bounding box, and language-based prompts, allowing for more flexible and intuitive interactions with the model. In this empirical evaluation, we assess the performance of SAM 3 in robot-assisted surgery, benchmarking its zero-shot segmentation with point and bounding box prompts and exploring its effectiveness in dynamic video tracking, alongside its newly introduced language prompt segmentation. While language prompts show potential, their performance in the surgical domain is currently suboptimal, highlighting the need for further domain-specific training. Additionally, we investigate SAM 3D's depth reconstruction abilities, demonstrating its capacity to process surgical scene data and reconstruct 3D anatomical structures from 2D images. Through comprehensive testing on the MICCAI EndoVis 2017 and EndoVis 2018 benchmarks, SAM 3 shows clear improvements over SAM and SAM 2 in both image and video segmentation under spatial prompts, while the zero-shot evaluations of SAM 3D on SCARED, StereoMIS, and EndoNeRF indicate strong monocular depth estimation and realistic 3D instrument reconstruction, yet also reveal remaining limitations in complex, highly dynamic surgical scenes.

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

EndoIR: Degradation-Agnostic All-in-One Endoscopic Image Restoration via Noise-Aware Routing Diffusion

Endoscopic images often suffer from diverse and co-occurring degradations such as low lighting, smoke, and bleeding, which obscure critical clinical details. Existing restoration methods are typically task-specific and often require prior knowledge of the degradation type, limiting their robustness in real-world clinical use. We propose EndoIR, an all-in-one, degradation-agnostic diffusion-based framework that restores multiple degradation types using a single model. EndoIR introduces a Dual-Domain Prompter that extracts joint spatial-frequency features, coupled with an adaptive embedding that encodes both shared and task-specific cues as conditioning for denoising. To mitigate feature confusion in conventional concatenation-based conditioning, we design a Dual-Stream Diffusion architecture that processes clean and degraded inputs separately, with a Rectified Fusion Block integrating them in a structured, degradation-aware manner. Furthermore, Noise-Aware Routing Block improves efficiency by dynamically selecting only noise-relevant features during denoising. Experiments on SegSTRONG-C and CEC datasets demonstrate that EndoIR achieves state-of-the-art performance across multiple degradation scenarios while using fewer parameters than strong baselines, and downstream segmentation experiments confirm its clinical utility.

eess.IV↗

arXiv2025

Recognizing Surgical Phases Anywhere: Few-Shot Test-time Adaptation and Task-graph Guided Refinement

The complexity and diversity of surgical workflows, driven by heterogeneous operating room settings, institutional protocols, and anatomical variability, present a significant challenge in developing generalizable models for cross-institutional and cross-procedural surgical understanding. While recent surgical foundation models pretrained on large-scale vision-language data offer promising transferability, their zero-shot performance remains constrained by domain shifts, limiting their utility in unseen surgical environments. To address this, we introduce Surgical Phase Anywhere (SPA), a lightweight framework for versatile surgical workflow understanding that adapts foundation models to institutional settings with minimal annotation. SPA leverages few-shot spatial adaptation to align multi-modal embeddings with institution-specific surgical scenes and phases. It also ensures temporal consistency through diffusion modeling, which encodes task-graph priors derived from institutional procedure protocols. Finally, SPA employs dynamic test-time adaptation, exploiting the mutual agreement between multi-modal phase prediction streams to adapt the model to a given test video in a self-supervised manner, enhancing the reliability under test-time distribution shifts. SPA is a lightweight adaptation framework, allowing hospitals to rapidly customize phase recognition models by defining phases in natural language text, annotating a few images with the phase labels, and providing a task graph defining phase transitions. The experimental results show that the SPA framework achieves state-of-the-art performance in few-shot surgical phase recognition across multiple institutions and procedures, even outperforming full-shot models with 32-shot labeled data. Code is available at https://github.com/CAMMA-public/SPA

cs.CV↗

arXiv2025

Geo-RepNet: Geometry-Aware Representation Learning for Surgical Phase Recognition in Endoscopic Submucosal Dissection

Surgical phase recognition plays a critical role in developing intelligent assistance systems for minimally invasive procedures such as Endoscopic Submucosal Dissection (ESD). However, the high visual similarity across different phases and the lack of structural cues in RGB images pose significant challenges. Depth information offers valuable geometric cues that can complement appearance features by providing insights into spatial relationships and anatomical structures. In this paper, we pioneer the use of depth information for surgical phase recognition and propose Geo-RepNet, a geometry-aware convolutional framework that integrates RGB image and depth information to enhance recognition performance in complex surgical scenes. Built upon a re-parameterizable RepVGG backbone, Geo-RepNet incorporates the Depth-Guided Geometric Prior Generation (DGPG) module that extracts geometry priors from raw depth maps, and the Geometry-Enhanced Multi-scale Attention (GEMA) to inject spatial guidance through geometry-aware cross-attention and efficient multi-scale aggregation. To evaluate the effectiveness of our approach, we construct a nine-phase ESD dataset with dense frame-level annotations from real-world ESD videos. Extensive experiments on the proposed dataset demonstrate that Geo-RepNet achieves state-of-the-art performance while maintaining robustness and high computational efficiency under complex and low-texture surgical environments.

cs.CV↗

arXiv2025

SurgTPGS: Semantic 3D Surgical Scene Understanding with Text Promptable Gaussian Splatting

In contemporary surgical research and practice, accurately comprehending 3D surgical scenes with text-promptable capabilities is particularly crucial for surgical planning and real-time intra-operative guidance, where precisely identifying and interacting with surgical tools and anatomical structures is paramount. However, existing works focus on surgical vision-language model (VLM), 3D reconstruction, and segmentation separately, lacking support for real-time text-promptable 3D queries. In this paper, we present SurgTPGS, a novel text-promptable Gaussian Splatting method to fill this gap. We introduce a 3D semantics feature learning strategy incorporating the Segment Anything model and state-of-the-art vision-language models. We extract the segmented language features for 3D surgical scene reconstruction, enabling a more in-depth understanding of the complex surgical environment. We also propose semantic-aware deformation tracking to capture the seamless deformation of semantic features, providing a more precise reconstruction for both texture and semantic features. Furthermore, we present semantic region-aware optimization, which utilizes regional-based semantic information to supervise the training, particularly promoting the reconstruction quality and semantic smoothness. We conduct comprehensive experiments on two real-world surgical datasets to demonstrate the superiority of SurgTPGS over state-of-the-art methods, highlighting its potential to revolutionize surgical practices. SurgTPGS paves the way for developing next-generation intelligent surgical systems by enhancing surgical precision and safety. Our code is available at: https://github.com/lastbasket/SurgTPGS.

eess.IV↗