arXivDaily arXiv每日学术速递 周一至周五更新
全部学科分类 1771
专题追踪
2512.07155 2026-03-25 cs.CV

CHIMERA: Adaptive Cache Injection and Semantic Anchor Prompting for Zero-shot Image Morphing with Morphing-oriented Metrics

Dahyeon Kye, Jeahun Sung, Minkyu Jeon, Jihyong Oh

Comments Please visit our project page at https://cmlab-korea.github.io/CHIMERA/

详情
英文摘要

Recent diffusion-based image morphing methods typically interpolate inverted latents and reuse limited conditioning signals, which often yields unstable intermediates for heterogeneous endpoint pairs. In particular, (i) feature reuse is usually partial or non-adaptive, leading to abrupt structural changes or over-smoothing, and (ii) text conditions are commonly obtained independently per endpoint and then interpolated, which can introduce incompatible semantics. We present CHIMERA, a novel zero-shot diffusion morphing framework that addresses both issues via inversion-guided denoising with complementary feature reuse and text conditioning. ACI caches a broader set of multi-scale diffusion features beyond Key--Value-only reuse during DDIM inversion, and re-injects them with layer- and timestep-aware scheduling to stabilize denoising and enable gradual fusion. Semantic Anchor Prompting (SAP) uses a vision-language model to generate a shared anchor-prompt and anchor-conditioned endpoint prompts, and injects the anchor into cross-attention to improve intermediate semantic coherence. Finally, we propose Global-Local Consistency Score (GLCS), a morphing-oriented metric that jointly captures global domain harmonization and local transition smoothness. Extensive experiments and user study show that CHIMERA produces smoother and more semantically consistent morphs than prior methods, while remaining efficient and applicable across diverse diffusion backbones without retraining. Code and the project page will be released.

2512.06796 2026-03-25 cs.RO

db-LaCAM: Fast and Scalable Multi-Robot Kinodynamic Motion Planning with Discontinuity-Bounded Search and Lightweight MAPF

Akmaral Moldagalieva, Keisuke Okumura, Amanda Prorok, Wolfgang Hönig

详情
英文摘要

State-of-the-art multi-robot kinodynamic motion planners struggle to handle more than a few robots due to high computational burden, which limits their scalability and results in slow planning time. In this work, we combine the scalability and speed of modern multi-agent path finding (MAPF) algorithms with the dynamic-awareness of kinodynamic planners to address these limitations. To this end, we propose discontinuity-Bounded LaCAM (db-LaCAM), a planner that utilizes a precomputed set of motion primitives that respect robot dynamics to generate horizon-length motion sequences, while allowing a user-defined discontinuity between successive motions. The planner db-LaCAM is resolution-complete with respect to motion primitives and supports arbitrary robot dynamics. Extensive experiments demonstrate that db-LaCAM scales efficiently to scenarios with up to 50 robots, achieving up to ten times faster runtime compared to state-of-the-art planners, while maintaining comparable solution quality. The approach is validated in both 2D and 3D environments with dynamics such as the unicycle and 3D double integrator. We demonstrate the safe execution of trajectories planned with db-LaCAM in two distinct physical experiments involving teams of flying robots and car-with-trailer robots.

2512.06737 2026-03-25 cs.LG cs.AI cs.CL cs.CV cs.NE

Arc Gradient Descent: A Geometrically Motivated Gradient Descent-based Optimiser with Phase-Aware, User-Controlled Step Dynamics (proof-of-concept)

Nikhil Verma, Joonas Linnosmaa, Leonardo Espinosa-Leal, Napat Vajragupta

Comments 90 pages, 6 appendices, proof-of-concept

详情
英文摘要

The paper presents the formulation, implementation, and evaluation of the ArcGD optimiser. The evaluation is conducted initially on a non-convex benchmark function and subsequently on a real-world ML dataset. The initial comparative study using the Adam optimiser is conducted on a stochastic variant of the highly non-convex and notoriously challenging Rosenbrock function, renowned for its narrow, curved valley, across dimensions ranging from 2D to 1000D and an extreme case of 50,000D. Two configurations were evaluated to eliminate learning-rate bias: (i) both using ArcGD's effective learning rate and (ii) both using Adam's default learning rate. ArcGD consistently outperformed Adam under the first setting and, although slower under the second, achieved superior final solutions in most cases. In the second evaluation, ArcGD is evaluated against state-of-the-art optimizers (Adam, AdamW, Lion, SGD) on the CIFAR-10 image classification dataset across 8 diverse MLP architectures ranging from 1 to 5 hidden layers. ArcGD achieved the highest average test accuracy (50.7%) at 20,000 iterations, outperforming AdamW (46.6%), Adam (46.8%), SGD (49.6%), and Lion (43.4%), winning or tying on 6 of 8 architectures. Notably, while Adam and AdamW showed strong early convergence at 5,000 iterations, but regressed with extended training, whereas ArcGD continued improving, demonstrating generalization and resistance to overfitting without requiring early stopping tuning. Strong performance on geometric stress tests and standard deep-learning benchmarks indicates broad applicability, highlighting the need for further exploration. Moreover, it is also shown that both a limiting variant of ArcGD and a momentum augmented ArcGD, recover sign-based momentum updates, revealing a clear conceptual link between ArcGD's phase structure and the core mechanism of the Lion Optimiser.

2512.04165 2026-03-25 cs.LG stat.ML

Mitigating the Curse of Detail: Scaling Arguments for Feature Learning and Sample Complexity

Noa Rubin, Orit Davidovich, Zohar Ringel

详情
英文摘要

Two pressing topics in the theory of deep learning are the interpretation of feature learning (FL) mechanisms and the determination of implicit bias of networks in the rich regime. Current theories of rich FL often appear in the form of high-dimensional non-linear equations, which require computationally intensive numerical solutions. Given the many details that go into defining a deep learning problem, this analytical complexity is a significant and often unavoidable challenge. Here, we propose a powerful heuristic route for predicting the data and width scales at which various patterns of FL emerge. This form of scale analysis is considerably simpler than such exact theories and reproduces the scaling exponents of various known results. In addition, we make novel predictions on complex toy architectures, such as three-layer non-linear networks and attention heads, thus extending the scope of first-principle theories of deep learning.

2512.03405 2026-03-25 cs.CV

ViDiC: Video Difference Captioning

Jiangtao Wu, Shihao Li, Zhaozhou Bian, Jialu Chen, Runzhe Wen, An Ping, Yiwen He, Jiakai Wang, Yuanxing Zhang, Jiaheng Liu

详情
英文摘要

Understanding visual differences between dynamic scenes requires the comparative perception of compositional, spatial, and temporal changes--a capability that remains underexplored in existing vision-language systems. While prior work on Image Difference Captioning (IDC) has enabled models to describe semantic changes between static images, these approaches fail to capture motion continuity, event evolution, or editing consistency over time. We introduce the ViDiC (Video Difference Captioning) task and its corresponding ViDiC-1K dataset, designed to evaluate the ability of Multimodal Large Language Models (MLLMs) to provide fine-grained descriptions of similarities and differences between video pairs. ViDiC-1K comprises 1,000 curated video pairs annotated with over 4,000 comparative checklist items, covering seven categories: subject, style, background, cinematography, motion, location, and playback techniques. To ensure reliable evaluation, we propose a dual-checklist framework that measures the accuracy of similarity and difference separately, based on the LLM-as-a-Judge protocol. Experiments on nineteen representative multimodal models reveal a significant performance gap in their comparative description and difference perception abilities. We hope ViDiC-1K can be a challenging benchmark that lays a solid foundation for advancing video understanding, edit awareness, and comparative reasoning in multimodal intelligence.

2512.03044 2026-03-25 cs.RO

Video2Act: A Dual-System Video Diffusion Policy with Robotic Spatio-Motional Modeling

Yueru Jia, Jiaming Liu, Shengbang Liu, Rui Zhou, Wanhe Yu, Yuyang Yan, Xiaowei Chi, Yandong Guo, Boxin Shi, Shanghang Zhang

详情
英文摘要

Robust perception and dynamics modeling are fundamental to real-world robotic policy learning. Recent methods employ video diffusion models (VDMs) to enhance robotic policies, improving their understanding and modeling of the physical world. However, existing approaches overlook the coherent and physically consistent motion representations inherently encoded across frames in VDMs. To this end, we propose Video2Act, a framework that efficiently guides robotic action learning by explicitly integrating spatial and motion-aware representations. Building on the inherent representations of VDMs, we extract foreground boundaries and inter-frame motion variations while filtering out background noise and task-irrelevant biases. These refined representations are then used as additional conditioning inputs to a diffusion transformer (DiT) action head, enabling it to reason about what to manipulate and how to move. To mitigate inference inefficiency, we propose an asynchronous dual-system design, where the VDM functions as the slow System 2 and the DiT head as the fast System 1, working collaboratively to generate adaptive actions. By providing motion-aware conditions to System 1, Video2Act maintains stable manipulation even with low-frequency updates from the VDM. For evaluation, Video2Act surpasses previous state-of-the-art VLA methods by 7.7% in simulation and 21.7% in real-world tasks in terms of average success rate, further exhibiting strong generalization capabilities.

2512.02982 2026-03-25 cs.CV cs.RO

U4D: Uncertainty-Aware 4D World Modeling from LiDAR Sequences

Xiang Xu, Alan Liang, Youquan Liu, Linfeng Li, Lingdong Kong, Ziwei Liu, Qingshan Liu

Comments CVPR 2026; 20 pages, 7 figures, 11 tables; Code at https://github.com/worldbench/U4D

详情
英文摘要

Modeling dynamic 3D environments from LiDAR sequences is central to building reliable 4D worlds for autonomous driving and embodied AI. Existing generative frameworks, however, often treat all spatial regions uniformly, overlooking the varying uncertainty across real-world scenes. This uniform generation leads to artifacts in complex or ambiguous regions, limiting realism and temporal stability. In this work, we present U4D, an uncertainty-aware framework for 4D LiDAR world modeling. Our approach first estimates spatial uncertainty maps from a pretrained segmentation model to localize semantically challenging regions. It then performs generation in a "hard-to-easy" manner through two sequential stages: (1) uncertainty-region modeling, which reconstructs high-entropy regions with fine geometric fidelity, and (2) uncertainty-conditioned completion, which synthesizes the remaining areas under learned structural priors. To further ensure temporal coherence, U4D incorporates a mixture of spatio-temporal (MoST) block that adaptively fuses spatial and temporal representations during diffusion. Extensive experiments show that U4D produces geometrically faithful and temporally consistent LiDAR sequences, advancing the reliability of 4D world modeling for autonomous perception and simulation.

2512.02505 2026-03-25 cs.CV

GeoDiT: A Diffusion-based Vision-Language Model for Geospatial Understanding

Jiaqi Liu, Ronghao Fu, Haoran Liu, Lang Sun, Bo Yang

详情
英文摘要

Autoregressive models are structurally misaligned with the inherently parallel nature of geospatial understanding, forcing a rigid sequential narrative onto scenes and fundamentally hindering the generation of structured and coherent outputs. We challenge this paradigm by reframing geospatial generation as a parallel refinement process, enabling a holistic, coarse-to-fine synthesis that resolves all semantic elements simultaneously. To operationalize this, we introduce GeoDiT, the first diffusion-based vision-language model tailored for the geospatial domain. Extensive experiments demonstrate that GeoDiT establishes a new state-of-the-art on benchmarks requiring structured, object-centric outputs. It achieves significant gains in image captioning, visual grounding, and multi-object detection, precisely the tasks where autoregressive models falter. Our work validates that aligning the generative process with the data's intrinsic structure is key to unlocking superior performance in complex geospatial analysis.

2512.02487 2026-03-25 cs.CV cs.AI

Masking Matters: Unlocking the Spatial Reasoning Capabilities of LLMs for 3D Scene-Language Understanding

Yerim Jeon, Miso Lee, WonJun Moon, Jae-Pil Heo

Comments Accepted to CVPR 2026. GitHub Page: https://github.com/Jyerim/3D-SLIM

详情
英文摘要

Recent advances in 3D scene-language understanding have leveraged Large Language Models (LLMs) for 3D reasoning by transferring their general reasoning ability to 3D multi-modal contexts. However, existing methods typically adopt standard decoders from language modeling, which rely on a causal attention mask. This design introduces two fundamental conflicts in 3D scene understanding: sequential bias among order-agnostic 3D objects and restricted object-instruction attention, hindering task-specific reasoning. To overcome these limitations, we propose 3D Spatial Language Instruction Mask (3D-SLIM), an effective masking strategy that replaces the causal mask with an adaptive attention mask tailored to the spatial structure of 3D scenes. Our 3D-SLIM introduces two key components: a Geometry-adaptive Mask that constrains attention based on spatial density rather than token order, and an Instruction-aware Mask that enables object tokens to directly access instruction context. This design allows the model to process objects based on their spatial relationships while being guided by the user's task. 3D-SLIM is simple, requires no architectural modifications, and adds no extra parameters, yet it yields substantial performance improvements across diverse 3D scene-language tasks. Extensive experiments across multiple benchmarks and LLM baselines validate its effectiveness and underscore the critical role of decoder design in 3D multi-modal reasoning.

2512.02448 2026-03-25 cs.CV cs.RO

nuScenes Revisited: Progress and Challenges in Autonomous Driving

Whye Kit Fong, Venice Erin Liong, Kok Seang Tan, Holger Caesar

Comments 18 pages, 17 figures

详情
英文摘要

Autonomous Vehicles (AV) and Advanced Driver Assistance Systems (ADAS) have been revolutionized by Deep Learning. As a data-driven approach, Deep Learning relies on vast amounts of driving data, typically labeled in great detail. As a result, datasets, alongside hardware and algorithms, are foundational building blocks for the development of AVs. In this work we revisit one of the most widely used autonomous driving datasets: the nuScenes dataset. nuScenes exemplifies key trends in AV development, being the first dataset to include radar data, to feature diverse urban driving scenes from two continents, and to be collected using a fully autonomous vehicle operating on public roads, while also promoting multi-modal sensor fusion, standardized benchmarks, and a broad range of tasks including perception, localization & mapping, prediction and planning. We provide an unprecedented look into the creation of nuScenes, as well as its extensions nuImages and Panoptic nuScenes, summarizing many technical details that have hitherto not been revealed in academic publications. Furthermore, we trace how the influence of nuScenes impacted a large number of other datasets that were released later and how it defined numerous standards that are used by the community to this day. Finally, we present an overview of both official and unofficial tasks using the nuScenes dataset and review major methodological developments, thereby offering a comprehensive survey of the autonomous driving literature, with a particular focus on nuScenes.

2512.01248 2026-03-25 cs.CV

TRivia: Self-supervised Fine-tuning of Vision-Language Models for Table Recognition

Junyuan Zhang, Bin Wang, Qintong Zhang, Fan Wu, Zichen Wen, Jialin Lu, Junjie Shan, Ziqi Zhao, Shuya Yang, Ziling Wang, Ziyang Miao, Huaping Zhong, Yuhang Zang, Xiaoyi Dong, Ka-Ho Chow, Conghui He

Comments Accepted by CVPR 2026

详情
英文摘要

Table recognition (TR) aims to transform table images into semi-structured representations such as HTML or Markdown. As a core component of document parsing, TR has long relied on supervised learning, with recent efforts dominated by fine-tuning vision-language models (VLMs) using labeled data. While VLMs have brought TR to the next level, pushing performance further demands large-scale labeled data that is costly to obtain. Consequently, although proprietary models have continuously pushed the performance boundary, open-source models, often trained with limited resources and, in practice, the only viable option for many due to privacy regulations, still lag far behind. To bridge this gap, we introduce TRivia, a self-supervised fine-tuning method that enables pretrained VLMs to learn TR directly from unlabeled table images in the wild. Built upon Group Relative Policy Optimization, TRivia automatically identifies unlabeled samples that most effectively facilitate learning and eliminates the need for human annotations through a question-answering-based reward mechanism. An attention-guided module generates diverse questions for each table image, and the ability to interpret the recognition results and answer them correctly provides feedback to optimize the TR model. This closed-loop process allows the TR model to autonomously learn to recognize, structure, and reason over tables without labeled data. Leveraging this pipeline, we present TRivia-3B, an open-sourced, compact, and state-of-the-art TR model that surpasses existing systems (e.g., Gemini 2.5 Pro, MinerU2.5) on three popular benchmarks. Model and code are released at: https://github.com/HKU-TASR/TRivia

2511.22815 2026-03-25 cs.CV

Captain Safari: A World Engine with Pose-Aligned 3D Memory

Yu-Cheng Chou, Xingrui Wang, Yitong Li, Jiahao Wang, Hanting Liu, Cihang Xie, Alan Yuille, Junfei Xiao

详情
英文摘要

World engines aim to synthesize long, 3D-consistent videos that support interactive exploration of a scene under user-controlled camera motion. However, existing systems struggle under aggressive 6-DoF trajectories and complex outdoor layouts: they lose long-range geometric coherence, deviate from the target path, or collapse into overly conservative motion. To this end, we introduce Captain Safari, a pose-conditioned world engine that generates videos by retrieving from a persistent world memory. Given a camera path, our method maintains a dynamic local memory and uses a retriever to fetch pose-aligned world tokens, which then condition video generation along the trajectory. This design enables the model to maintain stable 3D structure while accurately executing challenging camera maneuvers. To evaluate this setting, we curate OpenSafari, a new in-the-wild FPV dataset containing high-dynamic drone videos with verified camera trajectories, constructed through a multi-stage geometric and kinematic validation pipeline. Across video quality, 3D consistency, and trajectory following, Captain Safari substantially outperforms state-of-the-art camera-controlled generators. It reduces MEt3R from 0.3703 to 0.3690, improves AUC@30 from 0.181 to 0.200, and yields substantially lower FVD than all camera-controlled baselines. More importantly, in a 50-participant, 5-way human study where annotators select the best result among five anonymized models, 67.6% of preferences favor our method across all axes. Our results demonstrate that pose-conditioned world memory is a powerful mechanism for long-horizon, controllable video generation and provide OpenSafari as a challenging new benchmark for future world-engine research.

2511.22076 2026-03-25 cs.AI

Hybrid Stackelberg Game and Diffusion-based Auction for Two-tier Agentic AI Task Offloading in Internet of Agents

Yue Zhong, Yongju Tong, Jiawen Kang, Minghui Dai, Hong-Ning Dai, Zhou Su, Dusit Niyato

Comments Revisions are needed

详情
英文摘要

The Internet of Agents (IoA) is rapidly gaining prominence as a foundational architecture for interconnected intelligent systems, designed to facilitate seamless discovery, communication, and collaborative reasoning among a vast network of Artificial Intelligence (AI) agents. Powered by Large Language and Vision-Language Models, IoA enables the development of interactive, rational agents capable of complex cooperation, moving far beyond traditional isolated models. IoA involves physical entities, i.e., Wireless Agents (WAs) with limited onboard resources, which need to offload their compute-intensive agentic AI services to nearby servers. Such servers can be Mobile Agents (MAs), e.g., vehicle agents, or Fixed Agents (FAs), e.g., end-side units agents. Given their fixed geographical locations and stable connectivity, FAs can serve as reliable communication gateways and task aggregation points. This stability allows them to effectively coordinate with and offload to an Aerial Agent (AA) tier, which has an advantage not affordable for highly mobile MAs with dynamic connectivity limitations. As such, we propose a two-tier optimization approach. The first tier employs a multi-leader multi-follower Stackelberg game. In the game, MAs and FAs act as the leaders who set resource prices. WAs are the followers to determine task offloading ratios. However, when FAs become overloaded, they can further offload tasks to available aerial resources. Therefore, the second tier introduces a Double Dutch Auction model where overloaded FAs act as the buyers to request resources, and AAs serve as the sellers for resource provision. We then develop a diffusion-based Deep Reinforcement Learning algorithm to solve the model. Numerical results demonstrate the superiority of our proposed scheme in facilitating task offloading.

2511.21732 2026-03-25 cs.CL cs.AI

HUMORCHAIN: Theory-Guided Multi-Stage Reasoning for Interpretable Multimodal Humor Generation

Jiajun Zhang, Shijia Luo, Ruikang Zhang, Qi Su

详情
英文摘要

Humor, as both a creative human activity and a social binding mechanism, has long posed a major challenge for AI generation. Although producing humor requires complex cognitive reasoning and social understanding, theories of humor suggest that it follows learnable patterns and structures, making it theoretically possible for generative models to acquire them implicitly. In recent years, multimodal humor has become a prevalent form of online communication, especially among Gen Z, highlighting the need for AI systems capable of integrating visual understanding with humorous language generation. However, existing data-driven approaches lack explicit modeling or theoretical grounding of humor, often producing literal descriptions that fail to capture its underlying cognitive mechanisms, resulting in the generated image descriptions that are fluent but lack genuine humor or cognitive depth. To address this limitation, we propose HUMORCHAIN (HUmor-guided Multi-step Orchestrated Reasoning Chain for Image Captioning), a theory-guided multi-stage reasoning framework. It integrates visual semantic parsing, humor- and psychology-based reasoning, and a fine-tuned discriminator for humor evaluation, forming an interpretable and controllable cognitive reasoning chain. To the best of our knowledge, this is the first work to explicitly embed cognitive structures from humor theories into multimodal humor generation, enabling a structured reasoning process from visual understanding to humor creation. Experiments on Meme-Image-No-Text, Oogiri-GO, and OxfordTVG-HIC datasets show that HUMORCHAIN outperforms state-of-the-art baselines in human humor preference, Elo/BT scores, and semantic diversity, demonstrating that theory-driven structured reasoning enables large language models to generate humor aligned with human perception.

2511.20996 2026-03-25 cs.CV

From Inpainting to Layer Decomposition: Repurposing Generative Inpainting Models for Image Layer Decomposition

Jingxi Chen, Yixiao Zhang, Xiaoye Qian, Zongxia Li, Cornelia Fermuller, Caren Chen, Yiannis Aloimonos

Comments Accepted by CVPR 2026

详情
英文摘要

Images can be viewed as layered compositions, foreground objects over background, with potential occlusions. This layered representation enables independent editing of elements, offering greater flexibility for content creation. Despite the progress in large generative models, decomposing a single image into layers remains challenging due to limited methods and data. We observe a strong connection between layer decomposition and in/outpainting tasks, and propose adapting a diffusion-based inpainting model for layer decomposition using lightweight finetuning. To further preserve detail in the latent space, we introduce a novel multi-modal context fusion module with linear attention complexity. Our model is trained purely on a synthetic dataset constructed from open-source assets and achieves superior performance in object removal and occlusion recovery, unlocking new possibilities in downstream editing and creative applications.

2511.20565 2026-03-25 cs.CV

DINO-Tok: Adapting DINO for Visual Tokenizers

Mingkai Jia, Mingxiao Li, Zhijian Shu, Anlin Zheng, Liaoyuan Fan, Jiaxin Guo, Tianxing Shi, Dongyue Lu, Zeming Li, Xiaoyang Guo, Xiaojuan Qi, Xiao-Xiao Long, Qian Zhang, Ping Tan, Wei Yin

详情
英文摘要

Recent advances in visual generation have emphasized the importance of Latent Generative Models (LGMs), which critically depend on effective visual tokenizers to bridge pixels and semantic representations. However, tokenizers constructed on pre-trained vision foundation models (VFMs) often struggle to balance semantic richness and reconstruction fidelity in high-dimensional latent spaces. In this paper, we introduce DINO-Tok, a visual tokenizer built upon a frozen DINO encoder that supports both continuous autoencoding (DINO-Tok-AE) and discrete vector-quantization (DINO-Tok-VQ). By unifying hierarchical representations from both shallow fine-grained features and deep global semantics into an information-complete latent space, DINO-Tok preserves texture details while maintaining \textit{semantic consistency} for generation. We further investigate VQ in frozen semantic feature spaces of high dimensionality, where information dilution and codebook collapse frequently arise. To address this issue, we propose Dominant-Subspace Quantization (DSQ), which leverages a global PCA analysis to select principal components while suppressing noisy dimensions, thereby stabilizing codebook optimization and improving reconstruction and generation quality. On ImageNet 256x256, DINO-Tok achieves strong reconstruction performance, achieving 0.28 rFID for continuous autoencoding and 1.10 rFID for discrete VQ, as well as strong few-step generation performance 1.82 gFID for diffusion and 2.44 gFID for autoregressive generation. These results demonstrate that pre-trained VFMs such as DINO can be directly adapted into high-fidelity, semantically aligned visual tokenizers for next-generation latent generative models. Code will be publicly available at https://github.com/MKJia/DINO-Tok.

2511.20515 2026-03-25 cs.CV

HalDec-Bench: Benchmarking Hallucination Detector in Image Captioning

Kuniaki Saito, Risa Shinoda, Shohei Tanaka, Tosho Hirasawa, Fumio Okura, Yoshitaka Ushiku

Comments Previously this version appeared as arXiv:2603.15253 which was submitted as a new work by accident

详情
英文摘要

Hallucination detection in captions (HalDec) assesses a vision-language model's ability to correctly align image content with text by identifying errors in captions that misrepresent the image. Beyond evaluation, effective hallucination detection is also essential for curating high-quality image-caption pairs used to train VLMs. However, the generalizability of VLMs as hallucination detectors across different captioning models and hallucination types remains unclear due to the lack of a comprehensive benchmark. In this work, we introduce HalDec-Bench, a benchmark designed to evaluate hallucination detectors in a principled and interpretable manner. HalDec-Bench contains captions generated by diverse VLMs together with human annotations indicating the presence of hallucinations, detailed hallucination-type categories, and segment-level labels. The benchmark provides tasks with a wide range of difficulty levels and reveals performance differences across models that are not visible in existing multimodal reasoning or alignment benchmarks. Our analysis further uncovers two key findings. First, detectors tend to recognize sentences appearing at the beginning of a response as correct, regardless of their actual correctness. Second, our experiments suggest that dataset noise can be substantially reduced by using strong VLMs as filters while employing recent VLMs as caption generators. Our project page is available at https://dahlian00.github.io/HalDec-Bench-Page/.

2511.20008 2026-03-25 cs.CV cs.AI

Pedestrian Crossing Intention Prediction Using Multimodal Fusion Network

Yuanzhe Li, Steffen Müller

Comments 29th IAVSD International Symposium on Dynamics of Vehicles on Roads and Tracks (IAVSD 2025)

详情
英文摘要

Pedestrian crossing intention prediction is essential for the deployment of autonomous vehicles (AVs) in urban environments. Ideal prediction provides AVs with critical environmental cues, thereby reducing the risk of pedestrian-related collisions. However, the prediction task is challenging due to the diverse nature of pedestrian behavior and its dependence on multiple contextual factors. This paper proposes a multimodal fusion network that leverages seven modality features from both visual and motion branches, aiming to effectively extract and integrate complementary cues across different modalities. Specifically, motion and visual features are extracted from the raw inputs using multiple Transformer-based extraction modules. Depth-guided attention module leverages depth information to guide attention towards salient regions in another modality through comprehensive spatial feature interactions. To account for the varying importance of different modalities and frames, modality attention and temporal attention are designed to selectively emphasize informative modalities and effectively capture temporal dependencies. Extensive experiments on the JAAD dataset validate the effectiveness of the proposed network, achieving superior performance compared to the baseline methods.

2511.17181 2026-03-25 cs.CV cs.LG cs.SD

Investigating self-supervised representations for audio-visual deepfake detection

Dragos-Alexandru Boldisor, Stefan Smeu, Dan Oneata, Elisabeta Oneata

Comments Accepted to the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026

详情
英文摘要

Self-supervised representations excel at many vision and speech tasks, but their potential for audio-visual deepfake detection remains underexplored. Unlike prior work that uses these features in isolation or buried within complex architectures, we systematically evaluate them across modalities (audio, video, multimodal) and domains (lip movements, generic visual content). We assess three key dimensions: detection effectiveness, interpretability of encoded information, and cross-modal complementarity. We find that most self-supervised features capture deepfake-relevant information, and that this information is complementary. Moreover, models primarily attend to semantically meaningful regions rather than spurious artifacts (such as the leading silence). Among the investigated features, audio-informed representations generalize best and achieve state-of-the-art results. However, generalization to realistic in-the-wild data remains challenging. Our analysis indicates this gap stems from intrinsic dataset difficulty rather than from features latching onto superficial patterns. Project webpage: https://bit-ml.github.io/ssr-dfd.

2511.16105 2026-03-25 cs.LG

Data-Efficient and Robust Trajectory Generation through Pathlet Dictionary Learning

Yuanbo Tang, Yan Tang, Zixuan Zhang, Zihui Zhao, Yang Li

详情
英文摘要

Trajectory generation has recently drawn growing interest in privacy-preserving urban mobility studies and location-based service applications. Although many studies have used deep learning or generative AI methods to model trajectories and have achieved promising results, the robustness and interpretability of such models are largely unexplored. This limits the application of trajectory generation algorithms on noisy real-world data and their trustworthiness in downstream tasks. To address this issue, we exploit the regular structure in urban trajectories and propose a deep generative model based on the pathlet representation, which encode trajectories with binary vectors associated with a learned dictionary of trajectory segments. Specifically, we introduce a probabilistic graphical model to describe the trajectory generation process, which includes a Variational Autoencoder (VAE) component and a linear decoder component. During training, the model can simultaneously learn the latent embedding of pathlet representations and the pathlet dictionary that captures mobility patterns in the trajectory dataset. The conditional version of our model can also be used to generate customized trajectories based on temporal and spatial constraints. Our model can effectively learn data distribution even using noisy data, achieving relative improvements of $35.4\%$ and $26.3\%$ over strong baselines on two real-world trajectory datasets. Moreover, the generated trajectories can be conveniently utilized for multiple downstream tasks, including trajectory prediction and data denoising. Lastly, the framework design offers a significant efficiency advantage, saving $64.8\%$ of the time and $56.5\%$ of GPU memory compared to previous approaches.

2511.14440 2026-03-25 cs.CV

Learning to See Through a Baby's Eyes: Early Visual Diets Enable Robust Visual Intelligence in Humans and Machines

Yusen Cai, Qing Lin, Bhargava Satya Nunna, Mengmi Zhang

详情
英文摘要

Newborns perceive the world with low-acuity, color-degraded, and temporally continuous vision, which gradually sharpens as infants develop. To explore the ecological advantages of such staged "visual diets", we train self-supervised learning (SSL) models on object-centric videos under constraints that simulate infant vision: grayscale-to-color (C), blur-to-sharp (A), and preserved temporal continuity (T)-collectively termed CATDiet. For evaluation, we establish a comprehensive benchmark across ten datasets, covering clean and corrupted image recognition, texture-shape cue conflict tests, silhouette recognition, depth-order classification, and the visual cliff paradigm. All CATDiet variants demonstrate enhanced robustness in object recognition, despite being trained solely on object-centric videos. Remarkably, models also exhibit biologically aligned developmental patterns, including neural plasticity changes mirroring synaptic density in macaque V1 and behaviors resembling infants' visual cliff responses. Building on these insights, CombDiet initializes SSL with CATDiet before standard training while preserving temporal continuity. Trained on object-centric or head-mounted infant videos, CombDiet outperforms standard SSL on both in-domain and out-of-domain object recognition and depth perception. Together, these results suggest that the developmental progression of early infant visual experience offers a powerful reverse-engineering framework for understanding the emergence of robust visual intelligence in machines. All code, data, and models are available at Github.

2511.12449 2026-03-25 cs.CV cs.AI cs.IR cs.LG

MOON2.0: Dynamic Modality-balanced Multimodal Representation Learning for E-commerce Product Understanding

Zhanheng Nie, Chenghan Fu, Daoze Zhang, Junxian Wu, Wanxian Guan, Pengjie Wang, Jian Xu, Bo Zheng

Comments 11 pages, 7 figures

详情
英文摘要

Recent Multimodal Large Language Models (MLLMs) have significantly advanced e-commerce product understanding. However, they still face three challenges: (i) the modality imbalance induced by modality mixed training; (ii) underutilization of the intrinsic alignment relationships among visual and textual information within a product; and (iii) limited handling of noise in e-commerce multimodal data. To address these, we propose MOON2.0, a dynamic modality-balanced MultimOdal representation learning framework for e-commerce prOduct uNderstanding. It comprises: (1) a Modality-driven Mixture-of-Experts (MoE) that adaptively processes input samples by their modality composition, enabling Multimodal Joint Learning to mitigate the modality imbalance; (2) a Dual-level Alignment method to better leverage semantic alignment properties inside individual products; and (3) an MLLM-based Image-text Co-augmentation strategy that integrates textual enrichment with visual expansion, coupled with Dynamic Sample Filtering to improve training data quality. We further release MBE2.0, a co-augmented Multimodal representation Benchmark for E-commerce representation learning and evaluation at https://huggingface.co/datasets/ZHNie/MBE2.0. Experiments show that MOON2.0 delivers state-of-the-art zero-shot performance on MBE2.0 and multiple public datasets. Furthermore, attention-based heatmap visualization provides qualitative evidence of improved multimodal alignment of MOON2.0.

2511.09211 2026-03-25 cs.LG

Parameter-Free Clustering via Self-Supervised Consensus Maximization (Extended Version)

Lijun Zhang, Suyuan Liu, Siwei Wang, Shengju Yu, Xueling Zhu, Miaomiao Li, Xinwang Liu

Comments Accept by AAAI 2026

详情
英文摘要

Clustering is a fundamental task in unsupervised learning, but most existing methods heavily rely on hyperparameters such as the number of clusters or other sensitive settings, limiting their applicability in real-world scenarios. To address this long-standing challenge, we propose a novel and fully parameter-free clustering framework via Self-supervised Consensus Maximization, named SCMax. Our framework performs hierarchical agglomerative clustering and cluster evaluation in a single, integrated process. At each step of agglomeration, it creates a new, structure-aware data representation through a self-supervised learning task guided by the current clustering structure. We then introduce a nearest neighbor consensus score, which measures the agreement between the nearest neighbor-based merge decisions suggested by the original representation and the self-supervised one. The moment at which consensus maximization occurs can serve as a criterion for determining the optimal number of clusters. Extensive experiments on multiple datasets demonstrate that the proposed framework outperforms existing clustering approaches designed for scenarios with an unknown number of clusters.

2511.07808 2026-03-25 cs.CV

DI3CL: Contrastive Learning With Dynamic Instances and Contour Consistency for SAR Land-Cover Classification Foundation Model

Zhongle Ren, Hui Ding, Kai Wang, Biao Hou, Xingyu Luo, Weibin Li, Licheng Jiao

Comments 16 pages, 7 figures;Accepted for publication in IEEE Transactions on Image Processing (TIP)

详情
英文摘要

Although significant advances have been achieved in SAR land-cover classification, recent methods remain predominantly focused on supervised learning, which relies heavily on extensive labeled datasets. This dependency not only limits scalability and generalization but also restricts adaptability to diverse application scenarios. In this paper, a general-purpose foundation model for SAR land-cover classification is developed, serving as a robust cornerstone to accelerate the development and deployment of various downstream models. Specifically, a Dynamic Instance and Contour Consistency Contrastive Learning (DI3CL) pre-training framework is presented, which incorporates a Dynamic Instance (DI) module and a Contour Consistency (CC) module. DI module enhances global contextual awareness by enforcing local consistency across different views of the same region. CC module leverages shallow feature maps to guide the model to focus on the geometric contours of SAR land-cover objects, thereby improving structural discrimination. Additionally, to enhance robustness and generalization during pre-training, a large-scale and diverse dataset named SARSense, comprising 460,532 SAR images, is constructed to enable the model to capture comprehensive and representative features. To evaluate the generalization capability of our foundation model, we conducted extensive experiments across a variety of SAR land-cover classification tasks, including SAR land-cover mapping, water body detection, and road extraction. The results consistently demonstrate that the proposed DI3CL outperforms existing methods. Our code and pre-trained weights are publicly available at: https://github.com/SARpre-train/DI3CL.

2511.07719 2026-03-25 cs.AI cs.CV

Operational machine learning for remote spectroscopic detection of CH$_{4}$ point sources

Vít Růžička, Gonzalo Mateo-García, Itziar Irakulis-Loitxate, Juan Emmanuel Johnson, Manuel Montesino San Martín, Anna Allen, Alma Raunak, Carol Castaneda, Luis Guanter, David R. Thompson

Comments 20 pages, 14 figures, 10 tables. In review

详情
英文摘要

Mitigating anthropogenic methane sources is one of the most cost-effective levers to slow down global warming. While satellite-based imaging spectrometers, such as EMIT, PRISMA, and EnMAP, can detect these point sources, current methane retrieval methods based on matched filters produce a high number of false detections requiring manual verification. To address this challenge, we deployed a ML system for detecting methane emissions within the Methane Alert and Response System (MARS) of UNEP's IMEO. This represents the first operational deployment of automated methane point-source detection using spaceborne imaging spectrometers, providing regular global coverage and scalability to future constellations with even higher data volumes. This task required several technical advances. First, we created one of the largest and most diverse and global ML ready datasets to date of annotated methane plumes from three imaging spectrometer missions, and quantitatively compared different deep learning model configurations. Second, we extended prior evaluation methodologies from small, tiled datasets to full granules that are more representative of operational use. This revealed that deep learning models still produce a large number of false detections, a problem we addressed with model ensembling, which reduced false detections by over 74%. During 11 months of operational deployment, our system processed more than 25,000 hyperspectral products faciliting the verification of 2,851 distinct methane leaks, which resulted in 834 stakeholder notifications. We further demonstrate the model's utility in verifying mitigation success through case studies in Libya, Argentina, Oman, and Azerbaijan. Our work represents a critical step towards a global AI-assisted methane leak detection system, which is required to process the dramatically higher data volumes expected from current and future imaging spectrometers.

2511.06901 2026-03-25 cs.CV

Classification of Microplastic Particles in Water using Polarized Light Scattering and Machine Learning Methods

Leonard Saur, Marc von Pawlowski, Ulrich Gengenbach, Ingo Sieber, Hossein Shirali, Lorenz Wührl, Xiangyu Weng, Rainer Kiko, Christian Pylatiuk

Comments 22 pages, 9 figures

详情
英文摘要

The detection and classification of microplastics in water remain a significant challenge due to their diverse properties and the limitations of traditional optical methods. Standard spectroscopic techniques often suffer from the strong infrared absorption of water, while many emerging optical approaches rely on transmission geometries that require sample transparency. This study presents a systematic classification framework utilizing 120 degree backscattering reflection polarimetry and deep learning to identify common polymers (HDPE, LDPE, and PP) directly in water. This backscattering-based approach is specifically designed to analyze opaque, irregularly shaped particles that lack distinguishable surface features under standard illumination. To ensure high-fidelity data, we introduce a feedback review loop to identify and remove outliers, which significantly stabilizes model training and improves generalization. This framework is validated on a dataset of 600 individually imaged microplastic fragments spanning three polymer types. Our results evaluate the distinct contributions of the Angle of Linear Polarization and the Degree of Linear Polarization to the classification process. By implementing a late fusion architecture to combine these signals, we achieve an average test accuracy of 83 percent. Finally, a systematic feature hierarchy analysis reveals that the convolutional neural network relies on internal polarization textures associated with the particle's microstructure, rather than on macro-contours, with classification accuracy declining by over 40 percent when internal structure is removed. This demonstrates that the system extracts polarization-dependent internal structural information that is inaccessible to conventional intensity-only imaging methods.

2511.05876 2026-03-25 cs.CV cs.LG

MoEGCL: Mixture of Ego-Graphs Contrastive Representation Learning for Multi-View Clustering

Jian Zhu, Xin Zou, Jun Sun, Cheng Luo, Lei Liu, Lingfang Zeng, Ning Zhang, Bian Wu, Chang Tang, Lirong Dai

详情
英文摘要

In recent years, the advancement of Graph Neural Networks (GNNs) has significantly propelled progress in Multi-View Clustering (MVC). However, existing methods face the problem of coarse-grained graph fusion. Specifically, current approaches typically generate a separate graph structure for each view and then perform weighted fusion of graph structures at the view level, which is a relatively rough strategy. To address this limitation, we present a novel Mixture of Ego-Graphs Contrastive Representation Learning (MoEGCL). It mainly consists of two modules. In particular, we propose an innovative Mixture of Ego-Graphs Fusion (MoEGF), which constructs ego graphs and utilizes a Mixture-of-Experts network to implement fine-grained fusion of ego graphs at the sample level, rather than the conventional view-level fusion. Additionally, we present the Ego Graph Contrastive Learning (EGCL) module to align the fused representation with the view-specific representation. The EGCL module enhances the representation similarity of samples from the same cluster, not merely from the same sample, further boosting fine-grained graph representation. Extensive experiments demonstrate that MoEGCL achieves state-of-the-art results in deep multi-view clustering tasks. The source code is publicly available at https://github.com/HackerHyper/MoEGCL.

2511.03334 2026-03-25 cs.CV

UniAVGen: Unified Audio and Video Generation with Asymmetric Cross-Modal Interactions

Guozhen Zhang, Zixiang Zhou, Teng Hu, Ziqiao Peng, Youliang Zhang, Yi Chen, Yuan Zhou, Qinglin Lu, Limin Wang

Comments CVPR 2026

详情
英文摘要

Due to the lack of effective cross-modal modeling, existing open-source audio-video generation methods often exhibit compromised lip synchronization and insufficient semantic consistency. To mitigate these drawbacks, we propose UniAVGen, a unified framework for joint audio and video generation. UniAVGen is anchored in a dual-branch joint synthesis architecture, incorporating two parallel Diffusion Transformers (DiTs) to build a cohesive cross-modal latent space. At its heart lies an Asymmetric Cross-Modal Interaction mechanism, which enables bidirectional, temporally aligned cross-attention, thus ensuring precise spatiotemporal synchronization and semantic consistency. Furthermore, this cross-modal interaction is augmented by a Face-Aware Modulation module, which dynamically prioritizes salient regions in the interaction process. To enhance generative fidelity during inference, we additionally introduce Modality-Aware Classifier-Free Guidance, a novel strategy that explicitly amplifies cross-modal correlation signals. Notably, UniAVGen's robust joint synthesis design enables seamless unification of pivotal audio-video tasks within a single model, such as joint audio-video generation and continuation, video-to-audio dubbing, and audio-driven video synthesis. Comprehensive experiments validate that, with far fewer training samples (1.3M vs. 30.1M), UniAVGen delivers overall advantages in audio-video synchronization, timbre consistency, and emotion consistency.

2510.26865 2026-03-25 cs.CV cs.AI

Do Vision-Language Models Measure Up? Benchmarking Visual Measurement Reading with MeasureBench

Fenfen Lin, Yesheng Liu, Haiyu Xu, Chen Yue, Zheqi He, Mingxuan Zhao, Miguel Hu Chen, Jiakang Liu, JG Yao, Xi Yang

Comments Project page: https://flageval-baai.github.io/MeasureBenchPage/

详情
英文摘要

Reading measurement instruments is effortless for humans and requires relatively little domain expertise, yet it remains surprisingly challenging for current vision-language models (VLMs) as we find in preliminary evaluation. In this work, we introduce MeasureBench, a benchmark on visual measurement reading covering both real-world and synthesized images of various types of measurements, along with an extensible pipeline for data synthesis. Our pipeline procedurally generates a specified type of gauge with controllable visual appearance, enabling scalable variation in key details such as pointers, scales, fonts, lighting, and clutter. Evaluation on popular proprietary and open-weight VLMs shows that even the strongest frontier VLMs struggle with measurement reading in general. We have also conducted preliminary experiments with reinforcement finetuning (RFT) over synthetic data, and find a significant improvement on both in-domain synthetic subset and real-world images. Our analysis highlights a fundamental limitation of current VLMs in fine-grained spatial grounding. We hope this resource and our code releases can help future advances on visually grounded numeracy and precise spatial perception of VLMs, bridging the gap between recognizing numbers and measuring the world.

2510.21356 2026-03-25 cs.CV cs.AI

Gaze-VLM:Bridging Gaze and VLMs through Attention Regularization for Egocentric Understanding

Anupam Pani, Yanchao Yang

详情
英文摘要

Eye gaze offers valuable cues about attention, short-term intent, and future actions, making it a powerful signal for modeling egocentric behavior. In this work, we propose a gaze-regularized framework that enhances VLMs for two key egocentric understanding tasks: fine-grained future event prediction and current activity understanding. Unlike prior approaches that rely solely on visual inputs or use gaze as an auxiliary input signal , our method uses gaze only during training. We introduce a gaze-regularized attention mechanism that aligns model focus with human visual gaze. This design is flexible and modular, allowing it to generalize across multiple VLM architectures that utilize attention. Experimental results show that our approach improves semantic prediction scores by up to 11 for future event prediction and around 7 for current activity understanding, compared to the corresponding baseline models trained without gaze regularization. These results highlight the value of gaze-guided training in improving the accuracy and robustness of egocentric VLMs. Overall, this work establishes a foundation for using human gaze to enhance the predictive capabilities of VLMs in real-world scenarios like assistive robots and human-machine collaboration. Code and additional information is available at: https://github.com/anupampani/Gaze-VLM