paperlist.ai

AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

arXiv

SkyNative: A Native Multimodal Architecture for Remote Sensing Vision-Language Understanding

Xiao Yang, Ronghao Fu, Zhiwen Lin, Zhuoran Duan, Lang Sun, Jiaqi Liu, Jiashun Zhu, Jiasen Hu, Xu Na, Bo Yang

Remote sensing vision-language models (RS-VLMs) commonly employ a pretrained vision encoder and a projection module to map image features into the token space of a large language model. Although effective, this modular RS-VLMs separates visual representation from language reasoning, potentially limiting the direct involvement of fine-grained visual evidence in complex spatial inference. This challenge is particularly relevant to remote sensing imagery, which often covers broad geographic areas and contains multi-scale objects, dense target distributions, and intricate spatial layouts. In this paper, we propose SkyNative, the first study to explore a native multimodal architecture for remote sensing vision-language tasks. SkyNative converts remote sensing images into visual tokens through a lightweight patch embedding module and places them together with text tokens in a shared autoregressive sequence, allowing textual tokens to directly access the preceding visual context. To accommodate the heterogeneous characteristics of the two modalities, we further adopt a modality-aware decoupling mechanism that applies modality-specific projections, normalization, and feed-forward transformations while processing both modalities through shared causal self-attention. Extensive experiments demonstrate SkyNative's strong capabilities in dense small-object perception, large-format contextual understanding, complex reasoning, and robustness, with scores of 68.93%, 47.40%, and 63.43% on HRRSD, RSHR reasoning, and OmniEarth, respectively. These results suggest that the native VLM architecture explored in SkyNative represents a promising approach to RS vision-language modeling.

arXiv

A Mixture Autoregressive Image Generative Model on Quadtree Regions for Gaussian Noise Removal via Variational Bayes and Gradient Methods

Shota Saito, Yuta Nakahara, Kohei Horinouchi, Naoki Ichijo, Manabu Kobayashi, Toshiyasu Matsushima

This paper addresses the problem of image denoising for grayscale images. We propose a probabilistic image generative model that combines a quadtree region-partitioning model with a mixture autoregressive model, and propose a framework that reduces MAP (maximum a posteriori)-estimation-based denoising to the maximization of a variational lower bound. To maximize this lower bound, we develop an algorithm that alternately applies variational Bayes and gradient methods. We particularly demonstrate that the gradient-based update rule can be computed analytically without numerical computation or approximation. We carried out some experiments to verify that the proposed algorithm actually removes image noise and to identify directions for future improvement.

arXiv

Tumor-aware augmentation with task-guided attention analysis improves rectal cancer segmentation from magnetic resonance images

Aneesh Rangnekar, Joao Miranda, Natally Horvat, Stephanie Chahwan, Samir Alrayess, Aditya Apte, Aditi Iyer, Eve LoCastro, Revathi Ravella, Marc J Gollub, Iva Petkovska, Jesse Joshua Smith, Paul Romesser, Julio Garcia-Aguilar, Harini Veeraraghavan, Joseph O Deasy

Although self-supervised pretraining is expected to learn broadly transferable representations, its effectiveness across imaging modalities substantially different from the pretraining domain, and on complex tumor-segmentation tasks, remains understudied. Evaluating CT-pretrained transformers on MRI rectal cancer segmentation, we identified two interacting failure modes in CT-to-MRI transfer: (a) inefficient token usage caused by zero-padding to match pretrained input dimensions, and (b) ineffective feature adaptation. We investigated these vulnerabilities using two primary CT-pretrained hierarchical shifted-window transformer backbones, SMIT and Swin UNETR, together with VoCo as a large-scale-pretrained supporting benchmark; these models differ in pretraining objectives and datasets. Mechanistic analysis leveraged an attention dilution index (ADI), an entropy-based metric quantifying attention diverted toward uninformative padding tokens, and centered kernel alignment (CKA) to measure feature reuse during MRI adaptation. ADI increased with zero-padding, while high feature reuse did not necessarily translate to improved downstream accuracy. To mitigate these issues, we introduced two interventions: a tumor-aware augmentation strategy to expand tumor appearance heterogeneity coverage, and an anisotropic cropping strategy to restore token efficiency. Fine-tuning with these strategies on identical rectal MRI datasets yielded detection rates of 91.1% (225/247) and 88.7% (219/247) for the primary SMIT and Swin UNETR backbones, with the supporting VoCo benchmark reaching 90.3% (223/247), demonstrating significantly improved robustness under CT-to-MRI transfer. This study is among the first to examine when pretrained transformers fail to transfer across imaging modalities and demonstrates how targeted mitigation strategies can systematically overcome cross-modality transfer limitations.

arXiv

AnimateAnyMesh++: A Flexible Feed-Forward Framework for High-Fidelity Text-Driven Mesh Animation

Zijie Wu, Chaohui Yu, Fan Wang, Xiang Bai

Recent advances in 4D content generation have attracted increasing attention, yet creating high-quality animated 3D models remains challenging due to the complexity of modeling spatio-temporal distributions and the scarcity of 4D training data. We present AnimateAnyMesh++, a feed-forward framework for text-driven animation of arbitrary 3D meshes with substantial upgrades in data, architecture, and generative capability. First, we expand the DyMesh-XL dataset by mining dynamic content from Objaverse-XL, increasing the number of unique identities from 60K to 300K and substantially broadening category and motion diversity. Second, we redesign DyMeshVAE-Flex with power-law topology-aware attention and vertex-normal enhanced features, which significantly improves trajectory reconstruction, local geometry preservation, and mitigates trajectory-sticking artifacts. Third, we introduce architectural changes to both DyMeshVAE-Flex and the rectified-flow (RF) generator to support variable-length sequence training and generation, enabling longer animations while preserving reconstruction fidelity. Extensive experiments demonstrate that AnimateAnyMesh++ generates semantically accurate and temporally coherent mesh animations within seconds, surpassing prior approaches in quality and efficiency. The enlarged DyMesh-XL, the upgraded DyMeshVAE-Flex, and variable-length RF together deliver consistent gains across benchmarks and in-the-wild meshes. We will release code, models, and the expanded DyMesh-XL upon acceptance of this manuscript to facilitate research in 4D content creation.

arXiv

Bridging Restoration and Generation in One-step Diffusion for Real-World Image Super-Resolution

Shyang-En Weng, Yi-Cheng Liao, Yu-Syuan Xu, Chia-Hung Yuan, Wei-Chen Chiu, Ching-Chun Huang

Pretrained diffusion models have revolutionized real-world image super-resolution (Real-ISR), but their iterative sampling is computationally prohibitive, driving efforts to distill it into a single step. General one-step methods fine-tune the generative prior into a deterministic mapping, restoring efficiency but discarding its stochastic nature. Conversely, recent attempts re-engage generation by shifting the timestep or injecting random noise, adjusting either the position or the state while the other stays fixed. Because only one side is controlled, the two align at isolated preset timesteps but drift apart once steered, leaving generation unstable. To address this, we present one-step diffusion via Inversion and Degradation-aware Sampling for Real-ISR (IDaS-SR), a one-step framework that bridges deterministic restoration and stochastic generation. At its core, Manifold Anchoring grounds the low-quality latent on the pretrained trajectory through two operations jointly estimated by the Manifold Inversion Noise Estimator (MINE): positioning declares where the latent lies and how it deviates from the clean state, while inversion aligns the latent to the declared position. Upon the anchor, CHARIOT reintroduces controlled stochasticity by jointly rescheduling the trajectory and interpolating the noise, enabling a single scalar to smoothly navigate the fidelity-realism trade-off. Extensive experiments demonstrate that IDaS-SR effectively unleashes the generative prior, achieving state-of-the-art performance under explicit control in a single inference step.

arXiv

VAGNet: Vision-based Accident Anticipation with Global Features

Vipooshan Vipulananthan, Charith D. Chitraranjan

Traffic accidents are a leading cause of fatalities and injuries across the globe. Therefore, the ability to anticipate hazardous situations in advance is essential. Automated accident anticipation enables timely intervention through driver alerts and collision avoidance maneuvers, forming a key component of advanced driver assistance systems. In autonomous driving, such predictive capabilities support proactive safety behaviors, such as initiating defensive driving and human takeover when required. Using dash-cam video as input offers a cost-effective solution, but it is challenging due to the complexity of real-world driving scenes. Accident anticipation systems need to operate in real-time. However, current methods involve extracting features from each detected object, which is computationally intensive. We propose VAGNet, a deep neural network that learns to predict accidents from dash-cam video using global features of traffic scenes without requiring explicit object-level features. The network consists of transformer and graph modules, and we use the vision foundation model VideoMAE-V2 for global feature extraction. Experiments on four benchmark datasets (DAD, DoTA, DADA, and Nexar) show that our method anticipates accidents with higher average precision while being computationally more efficient compared to existing methods. It also achieves higher mean time-to-accident scores in most cases, while being competitive in others.

arXiv

SurgTEMP: Temporal-Aware Surgical Video Question Answering with Text-guided Visual Memory for Laparoscopic Cholecystectomy

Shi Li, Vinkle Srivastav, Nicolas Chanel, Saurav Sharma, Nabani Banik, Lorenzo Arboit, Kun Yuan, Pietro Mascagni, Nicolas Padoy

Surgical procedures are inherently complex and risky, requiring extensive expertise and constant focus to navigate evolving intraoperative scenes. Computer-assisted systems such as surgical visual question answering (VQA) offer promises for education and intraoperative support. Current surgical VQA research largely focuses on static frame analysis, overlooking rich temporal semantics. Surgical video question answering is further challenged by low visual contrast, its highly knowledge-driven nature, diverse analytical needs spanning scattered temporal windows, and the hierarchy from basic perception to high-level intraoperative assessment. To address these challenges, we propose SurgTEMP, a multimodal LLM framework featuring (i) a query-guided token selection module that builds hierarchical visual memory (spatial and temporal memory banks) and (ii) a Surgical Competency Progression (SCP) training scheme. Together, they enable effective modeling of variable-length surgical videos while preserving procedure-relevant cues and temporal coherence, and better support diverse downstream assessment tasks. To support model development, we introduce CholeVidQA-32K, a surgical video question answering dataset comprising 32K open-ended QA pairs and 3,855 video segments (approximately 128 h total) from laparoscopic cholecystectomy. The dataset is organized into a three-level hierarchy -- Perception, Assessment, and Reasoning -- spanning 11 tasks from instrument/action/anatomy perception to Critical View of Safety (CVS), intraoperative difficulty, skill proficiency, and adverse event assessment. In comprehensive evaluations against state-of-the-art open-source multimodal and video LLMs (fine-tuned and zero-shot), SurgTEMP achieves substantial performance improvements, advancing the state of video-based surgical VQA. The project page is available at: https://camma-public.github.io/SurgTEMP/

arXiv

ZOTTA: Test-Time Adaptation with Gradient-Free Zeroth-Order Optimization

Ronghao Zhang, Shuaicheng Niu, Qi Deng, Yanjie Dong, Jian Chen, Runhao Zeng

Test-time adaptation (TTA) aims to improve model robustness under distribution shifts by adapting to unlabeled test data, but most existing methods rely on backpropagation (BP), which is computationally costly and incompatible with non-differentiable models such as quantized models, limiting practical deployment on numerous edge devices. Recent BP-free approaches alleviate overhead but remain either architecture-specific or limited in optimization capacity to handle high-dimensional models. We propose ZOTTA, a fully BP-free TTA framework that performs efficient adaptation using only forward passes via Zeroth-Order Optimization (ZOO). While ZOO is theoretically appealing, naive application leads to slow convergence under high-dimensional parameter spaces and unstable optimization due to the lack of labels. ZOTTA overcomes these challenges through 1) Distribution-Robust Layer Selection, which automatically identifies and freezes layers that already extract distribution-invariant features, updating only domain-sensitive layers to reduce the optimization dimensionality and accelerate convergence; 2) Spatial Feature Aggregation Alignment, which stabilizes ZOO by aligning globally aggregated spatial features between source and target to reduce gradient variance. Together, these components enable architecture-agnostic and stable BP-free adaptation. Extensive experiments on ImageNet-C/R/Sketch/A show that ZOTTA outperforms or matches BP-based methods, e.g., it reduces memory usage by 84% and improves accuracy by 3.9% over SAR on ImageNet-C. Code:https://github.com/Zhang-Ronghao/zotta.

arXiv

ShotVerse: Advancing Cinematic Camera Control for Text-Driven Multi-Shot Video Creation

Songlin Yang, Zhe Wang, Xuyi Yang, Songchun Zhang, Xianghao Kong, Taiyi Wu, Xiaotong Zhao, Ran Zhang, Alan Zhao, Anyi Rao

Text-driven video generation has democratized film creation, but camera control in cinematic multi-shot scenarios remains a significant block. Implicit textual prompts lack precision, while explicit trajectory conditioning imposes prohibitive manual overhead and often triggers execution failures in current models. To overcome this bottleneck, we propose a data-centric paradigm shift, positing that aligned (Caption, Trajectory, Video) triplets form an inherent joint distribution that can connect automated plotting and precise execution. Guided by this insight, we present ShotVerse, a ``Plan-then-Control'' framework that decouples generation into two collaborative agents: a VLM (Vision-Language Model)-based Planner that leverages spatial priors to obtain cinematic, globally aligned trajectories from text, and a Controller that renders these trajectories into multi-shot video content via a camera adapter. Central to our approach is the construction of a data foundation: we design an automated multi-shot camera calibration pipeline aligns disjoint single-shot trajectories into a unified global coordinate system. This facilitates the curation of ShotVerse-Bench, a high-fidelity cinematic dataset with a three-track evaluation protocol that serves as the bedrock for our framework. Extensive experiments demonstrate that ShotVerse effectively bridges the gap between unreliable textual control and labor-intensive manual plotting, achieving superior cinematic aesthetics and generating multi-shot videos that are both camera-accurate and cross-shot consistent.

arXiv

PRISM: Streaming Human Motion Generation with Per-Joint Latent Decomposition

Zeyu Ling, Qing Shuai, Teng Zhang, Shiyang Li, Bo Han, Changqing Zou

Text-to-motion generation has advanced with larger corpora and stronger generators, yet many models still rely on holistic frame- or clip-level latents that entangle trajectory, orientation, and articulation. This entanglement obscures body topology and forces the generator to recover kinematic structure implicitly. We present \name, a SMPL motion generation framework that factorizes motion into continuous kinematic-unit latents. A causal Motion VAE maps motion to a time-by-kinematic-unit latent manifold, and a Kinematic-Unit Flow Transformer performs text-conditioned flow matching in this structured space. Because each latent coordinate remains tied to a physical body unit, \name can use kinematic-tree rotary position encoding and kinematic-adaptive flow scheduling. We further train the generator with per-token timesteps over clean-context/noisy-target masks, enabling frame-conditioned continuation and autoregressive segment chaining within one model. Experiments first validate the representation: the kinematic-unit VAE achieves lower geometry, rotation, and feature errors than existing motion tokenizers, showing that the latent space preserves articulated structure rather than merely compressing frames. With a 1.4B-parameter generator trained only on publicly available academic motion--text data, \name outperforms all evaluated academic-data text-to-motion baselines and remains competitive with systems trained on much larger non-public motion corpora. Without task-specific retraining, the same formulation also improves prefix-conditioned generation, BABEL sequential rollout, and narrative motion composition. These results indicate that kinematic-unit latent factorization provides an effective generation substrate for controllable SMPL motion synthesis. Code will be released at https://github.com/ZeyuLing/PRISM.

arXiv

Data-Centric Benchmark for Label Noise Estimation and Ranking in Remote Sensing Binary Building Segmentation

Keiller Nogueira, Codrut-Andrei Diaconu, Dávid Kerekes, Jakob Gawlikowski, Cédric Léonard, Nassim Ait Ali Braham, June Moh Goo, Zichao Zeng, Zhipeng Liu, Pallavi Jain, Andrea Nascetti, Ronny Hänsch

High-quality pixel-level annotations are essential for the semantic segmentation of remote sensing imagery. However, such labels are expensive to obtain and often affected by noise due to the labor-intensive and time-consuming nature of pixel-wise annotation, which makes it challenging for human annotators to label every pixel accurately. Annotation errors can significantly degrade the performance and robustness of modern segmentation models, motivating the need for reliable mechanisms to identify and quantify noisy training samples. This paper introduces a novel data-centric benchmark, together with a new, publicly available binary building segmentation dataset. This specific task serves as a representative and practically relevant testbed that enables controlled experimentation with different annotation perturbations. Furthermore, we also introduce two techniques for identifying, quantifying, and ranking training samples according to their level of label noise in remote sensing semantic segmentation. Such proposed methods leverage complementary strategies based on model uncertainty, prediction consistency, and representation analysis, and consistently outperform established baselines across a range of experimental settings. The outcomes of this work are publicly available at https://github.com/keillernogueira/label_noise_segmentation.

arXiv

Ordinal Diffusion Models for Color Fundus Images

Gustav Schmidt, Philipp Berens, Sarah Müller

Generative image models such as diffusion models can improve performance on clinically relevant tasks by offering deep learning models supplementary training data. However, most conditional diffusion models treat disease stages as independent classes, ignoring the continuous nature of disease progression. This mismatch is problematic in medical imaging because continuous pathological processes are typically only observed through coarse, discrete but ordered labels as in ophthalmology for diabetic retinopathy (DR). We propose an ordinal latent diffusion model for generating color fundus images that explicitly incorporates the ordered structure of DR severity into the generation process. Instead of categorical conditioning, we used a scalar disease representation, enabling a smooth transition between adjacent stages. We evaluated our approach using visual realism metrics and classification-based clinical consistency analysis on the EyePACS dataset. Compared to a standard conditional diffusion model, our model reduced the Fréchet inception distance for four of the five DR stages and increased the quadratic weighted $κ$ from 0.79 to 0.87. Furthermore, interpolation experiments showed that the model captured a continuous spectrum of disease progression learned from ordered, coarse class labels. Code available at https://github.com/berenslab/OrdinalDiffusionModels.

arXiv

PEAfowl: Perception-Enhanced Multi-View Vision-Language-Action for Bimanual Manipulation

Qingyu Fan, Zhaoxiang Li, Jinrui Hu, Yi Lu, WANG CHEN, Qiu Shen, Xiao-Xiao Long, Yinghao Cai, Tao Lu, Shuo Wang, Xun Cao

Bimanual manipulation in cluttered scenes requires policies that remain stable under occlusions, viewpoint changes and scene variations. Existing vision-language-action models often lack such robustness because (i) multi-view features are fused via view-agnostic token concatenation, yielding limited cross-view spatial representations, and (ii) language is injected as global conditioning, resulting in coarse instruction grounding. In this paper, we introduce PEAfowl, a perception-enhanced multi-view VLA policy for bimanual manipulation. For spatial perception, PEAfowl predicts per-token depth distributions, performs differentiable 3D lifting, and aggregates local cross-view neighbors to form geometrically grounded, cross-view aligned representations. For language utilization, we propose to replace global conditioning with a Perceiver-style text-aware readout over frozen CLIP visual features, enabling iterative evidence accumulation. To better exploit commodity RGB-D sensing despite noisy and incomplete depth, PEAfowl's depth-distribution lifting naturally supports training-only depth distillation, where a pretrained depth teacher supervises the depth-distribution head to inject refined geometric priors without adding inference overhead. On RoboTwin 2.0 under domain-randomized setting, PEAfowl improves the strongest baseline by 23.0 pp in success rate, and physical experiments further demonstrate improved performance on the evaluated real-robot tasks. Project website: https://peafowlvla.github.io/.

arXiv

HOT-POT: Optimal Transport for Sparse Stereo Matching

Antonin Clerc, Michael Quellmalz, Moritz Piening, Philipp Flotho, Gregor Kornhardt, Gabriele Steidl

Stereo vision between images faces a range of challenges, including occlusions, motion, and camera distortions, across applications in autonomous driving, robotics, and face analysis. Due to parameter sensitivity, further complications arise for stereo matching with sparse features, such as facial landmarks. To overcome this ill-posedness and enable unsupervised sparse matching, we consider line constraints of the camera geometry from an optimal transport (OT) viewpoint. Formulating camera-projected points as (half)lines, we propose the use of the classical epipolar distance as well as a 3D ray distance to quantify matching quality. Employing these distances as a cost function of a (partial) OT problem, we arrive at efficiently solvable assignment problems. Moreover, we extend our approach to unsupervised object matching by formulating it as a hierarchical OT problem. The resulting algorithms allow for efficient feature and object matching, as demonstrated in our numerical experiments. Here, we focus on applications in facial analysis, where we aim to match distinct landmarking conventions.

arXiv

Multi-Context Fusion Transformer for Pedestrian Crossing Intention Prediction in Urban Environments

Yuanzhe Li, Hang Zhong, Steffen Müller

Pedestrian crossing intention prediction is essential for autonomous vehicles to improve pedestrian safety and reduce traffic accidents. However, accurate pedestrian intention prediction in urban environments remains challenging due to the multitude of factors affecting pedestrian behavior. In this paper, we propose a multi-context fusion Transformer (MFT) that leverages diverse numerical contextual attributes across four key dimensions, encompassing pedestrian behavior context, environmental context, pedestrian localization context and vehicle motion context, to enable accurate pedestrian intention prediction. MFT employs a progressive fusion strategy, where mutual intra-context attention enables reciprocal interactions within each context, thereby facilitating feature sequence fusion and yielding a context token as a context-specific representation. This is followed by mutual cross-context attention, which integrates features across contexts with a global CLS token serving as a compact multi-context representation. Finally, guided intra-context attention refines context tokens within each context through directed interactions, while guided cross-context attention strengthens the global CLS token to promote multi-context fusion via guided information propagation, yielding deeper and more efficient integration. Experimental results validate the superiority of MFT over state-of-the-art methods, achieving accuracy rates of 73%, 93%, and 90% on the JAADbeh, JAADall, and PIE datasets, respectively. Extensive ablation studies are further conducted to investigate the effectiveness of the network architecture and contribution of different input context. Our code is open-source: https://github.com/ZhongHang0307/Multi-Context-Fusion-Transformer.

arXiv

DiffSwap++: 3D Latent-Controlled Diffusion for Identity-Preserving Face Swapping

Weston Bondurant, Arkaprava Sinha, Hieu Le, Srijan Das, Stephanie Schuckers

Diffusion-based approaches have recently achieved strong results in face swapping, offering improved visual quality over traditional GAN-based methods. However, even state-of-the-art models often suffer from fine-grained artifacts and poor identity preservation, particularly under challenging poses and expressions. A key limitation of existing approaches is their failure to meaningfully leverage 3D facial structure, which is crucial for disentangling identity from pose and expression. In this work, we propose DiffSwap++, a novel diffusion-based face-swapping pipeline that incorporates 3D facial latent features during training. By guiding the generation process with 3D-aware representations, our method enhances geometric consistency and improves the disentanglement of facial identity from appearance attributes. We further design a diffusion architecture that conditions the denoising process on both identity embeddings and facial landmarks, enabling high-fidelity and identity-preserving face swaps. Extensive experiments on CelebA, FFHQ, and CelebV-Text demonstrate that DiffSwap++ outperforms prior methods in preserving source identity while maintaining target pose and expression. Additionally, we introduce a biometric-style evaluation and conduct a user study to further validate the realism and effectiveness of our approach. Code will be made publicly available at https://github.com/WestonBond/DiffSwapPP

arXiv

Environmental Injection Attacks against GUI Agents in Realistic Dynamic Environments

Yitong Zhang, Ximo Li, Liyi Cai, Jia Li

Graphical User Interface (GUI) agents are increasingly deployed to interact with online web services, yet their exposure to open-world content renders them vulnerable to Environmental Injection Attacks (EIAs). In these attacks, an attacker can inject crafted triggers into website to manipulate the behavior of GUI agents used by other users. In this paper, we find that most existing EIA studies fall short of realism. In particular, they fail to capture the dynamic nature of real-world web content, often assuming that a trigger's on-screen position and surrounding visual context remain largely consistent between training and testing. To better reflect practice, we introduce a realistic dynamic-environment threat model in which the attacker is a regular user and the trigger is embedded within a dynamically changing environment. Under this threat model, existing approaches largely fail, suggesting that their effectiveness in exposing GUI agent vulnerabilities has been substantially overestimated. To expose the hidden vulnerabilities of existing GUI agents effectively, we propose Chameleon, an attack framework with two key novelties designed for dynamic environments. (1) To synthesize more realistic training data, we introduce LLM-Driven Environment Simulation, which automatically generates diverse, high-fidelity webpage simulations that mimic the variability of real-world dynamic environments. (2) To optimize the trigger more effectively, we introduce Attention Black Hole, which converts attention weights into explicit supervisory signals. This mechanism encourages the agent to remain insensitive to irrelevant surrounding content, thereby improving robustness in dynamic environments. We evaluate Chameleon on six realistic websites and four representative LVLM-powered GUI agents, where it significantly outperforms existing methods.

arXiv

LanGuSTE: Language-Guided Coarse-to-Fine Patch Selection for Efficient Whole Slide Image Analysis

Yonghan Shin, Gangsu Kim, Won-Ki Jeong

Whole slide images (WSIs) in computational pathology pose a major computational challenge due to their gigapixel scale, often requiring tens to hundreds of thousands of high-resolution patches to be processed per slide. In conventional WSI pipelines, exhaustive high-resolution patch processing makes preprocessing far more time-consuming than downstream model training. Existing patch selection methods suffer from a fundamental paradox: all patches must still be extracted and encoded at least during training, and sometimes during both training and inference, before irrelevant ones can be discarded. To address this, we propose LanGuSTE, an efficient patch selection framework that integrates pathology-domain vision-language models (VLMs) and knowledge derived from large language models (LLMs) through two key modules: Cross- Scale Visual Prompt Tuning (CS-VPT) and coarse-to-fine patch selection. CS-VPT aligns low-resolution patches with their spatially corresponding high-resolution patches through contrastive learning, transferring fine-grained diagnostic semantics into low-resolution representations. The patch selection module then leverages VLM representations and LLM-generated pathology-specific descriptions to identify informative regions in a coarse-to-fine manner, encoding only the corresponding high-resolution patches to reduce preprocessing time. Extensive experiments demonstrate that LanGuSTE reduces overall WSI processing time to approximately 3x while achieving diagnostic performance comparable to or better than exhaustive patch processing and recent state-of-the-art patch-selection methods.

arXiv

RobustGS: Unified Boosting of Feedforward 3D Gaussian Splatting under Low-Quality Conditions

Anran Wu, Long Peng, Xin Di, Xueyuan Dai, Chen Wu, Yang Wang, Xueyang Fu, Yang Cao, Zheng-Jun Zha

Feedforward 3D Gaussian Splatting (3DGS) overcomes the limitations of optimization-based 3DGS by enabling fast and high-quality reconstruction without the need for per-scene optimization. However, existing feedforward approaches typically assume that input multi-view images are clean and high-quality. In real-world scenarios, images are often captured under challenging conditions such as noise, low light, or rain, resulting in inaccurate geometry and degraded 3D reconstruction. To address these challenges, we propose a general and efficient multi-view feature enhancement module, RobustGS, which substantially improves the robustness of feedforward 3DGS methods under various adverse imaging conditions, enabling high-quality 3D reconstruction. The RobustGS module can be seamlessly integrated into existing pretrained pipelines in a plug-and-play manner to enhance reconstruction robustness. Specifically, we introduce a novel component, Generalized Degradation Learner, designed to extract generic representations and distributions of multiple degradations from multi-view inputs, thereby enhancing degradation-awareness and improving the overall quality of 3D reconstruction. In addition, we propose a novel semantic-aware state-space model. It first leverages the extracted degradation representations to enhance corrupted inputs in the feature space. Then, it employs a semantic-aware strategy to aggregate semantically similar information across different views, enabling the extraction of fine-grained cross-view correspondences and further improving the quality of 3D representations. Extensive experiments demonstrate that our approach, when integrated into existing methods in a plug-and-play manner, consistently achieves state-of-the-art reconstruction quality across various types of degradations.

arXiv

StereoDiff: Stereo-Diffusion Synergy for Video Depth Estimation

Haodong LI, Chen Wang, Jiahui Lei, Kostas Daniilidis, Lingjie Liu

Recent video depth estimation methods achieve great performance by following the paradigm of image depth estimation, i.e., typically fine-tuning pre-trained video diffusion models with massive data. However, we argue that video depth estimation is not a naive extension of image depth estimation. The temporal consistency requirements for dynamic and static regions in videos are fundamentally different. Consistent video depth in static regions, typically backgrounds, can be more effectively achieved via stereo matching across all frames, which provides much stronger global 3D cues. While the consistency for dynamic regions still should be learned from large-scale video depth data to ensure smooth transitions, due to the violation of triangulation constraints. Based on these insights, we introduce StereoDiff, a two-stage video depth estimator that synergizes stereo matching for mainly the static areas with video depth diffusion for maintaining consistent depth transitions in dynamic areas. We mathematically demonstrate how stereo matching and video depth diffusion offer complementary strengths through frequency domain analysis, highlighting the effectiveness of their synergy in capturing the advantages of both. Experimental results on zero-shot, real-world, dynamic video depth benchmarks, both indoor and outdoor, demonstrate StereoDiff's SoTA performance, showcasing its superior consistency and accuracy in video depth estimation.

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.