Peer Revenue Fully funded

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science Computer Vision

cs.CV Watch Computer Vision

Friday 3 April

Computer Vision · Cross-listed from cs.HC

Can LLMs Reason About Attention? Towards Zero-Shot Analysis of Multimodal Classroom Behavior

Nolan Platt, Sehrish Nizamani, Alp Tural et al. (+5 more)

Understanding student engagement usually requires time-consuming manual observation or invasive recording that raises privacy concerns. We present a privacy-preserving pipeline that analyzes classroom videos to extract insights about student attention, without storing any identifiable footage. Our system runs on a single GPU, using OpenPose for skeletal extraction and Gaze-LLE for visual attention estimation. Original video frames are deleted immediately after pose extraction, thus only geometric coordinates (stored as JSON) are retained, ensuring compliance with FERPA. The extracted pose and gaze data is processed by QwQ-32B-Reasoning, which performs zero-shot analysis of student behavior across lecture segments. Instructors access results through a web dashboard featuring attention heatmaps and behavioral summaries. Our preliminary findings suggest that LLMs may show promise for multimodal behavior understanding, although they still struggle with spatial reasoning about classroom layouts. We discuss these limitations and outline directions for improving LLM spatial comprehension in educational analytics contexts.
Read the full abstract

All authors Nolan Platt, Sehrish Nizamani, Alp Tural, Elif Tural, Saad Nizamani, Andrew Katz, Yoonje Lee, Nada Basit

Computer Vision

Banana100: Breaking NR-IQA Metrics by 100 Iterative Image Replications with Nano Banana Pro

Kenan Tang, Praveen Arunshankar, Andong Hua et al. (+2 more)

The multi-step, iterative image editing capabilities of multi-modal agentic systems have transformed digital content creation. Although latest image editing models faithfully follow instructions and generate high-quality images in single-turn edits, we identify a critical weakness in multi-turn editing, which is the iterative degradation of image quality. As images are repeatedly edited, minor artifacts accumulate, rapidly leading to a severe accumulation of visible noise and a failure to follow simple editing instructions. To systematically study these failures, we introduce Banana100, a comprehensive dataset of 28,000 degraded images generated through 100 iterative editing steps, including diverse textures and image content. Alarmingly, image quality evaluators fail to detect the degradation. Among 21 popular no-reference image quality assessment (NR-IQA) metrics, none of them consistently assign lower scores to heavily degraded images than to clean ones. The dual failures of generators and evaluators may threaten the stability of future model training and the safety of deployed agentic systems, if the low-quality synthetic data generated by multi-turn edits escape quality filters. We release the full code and data to facilitate the development of more robust models, helping to mitigate the fragility of multi-modal agentic systems.
Read the full abstract

All authors Kenan Tang, Praveen Arunshankar, Andong Hua, Anthony Yang, Yao Qin

Computer Vision

ViBA: Implicit Bundle Adjustment with Geometric and Temporal Consistency for Robust Visual Matching

Xiaoji Niu, Yuqing Wang, Yan Wang et al. (+2 more)

Most existing image keypoint detection and description methods rely on datasets with accurate pose and depth annotations, limiting scalability and generalization, and often degrading navigation and localization performance. We propose ViBA, a sustainable learning framework that integrates geometric optimization with feature learning for continuous online training on unconstrained video streams. Embedded in a standard visual odometry pipeline, it consists of an implicitly differentiable geometric residual framework: (i) an initial tracking network for inter-frame correspondences, (ii) depth-based outlier filtering, and (iii) differentiable global bundle adjustment that jointly refines camera poses and feature positions by minimizing reprojection errors. By combining geometric consistency from BA with long-term temporal consistency across frames, ViBA enforces stable and accurate feature representations. We evaluate ViBA on EuRoC and UMA datasets. Compared with state-of-the-art methods such as SuperPoint+SuperGlue, ALIKED, and LightGlue, ViBA reduces mean absolute translation error (ATE) by 12-18% and absolute rotation error (ARE) by 5-10% across sequences, while maintaining real-time inference speeds (FPS 36-91). When evaluated on unseen sequences, it retains over 90% localization accuracy, demonstrating robust generalization. These results show that ViBA supports continuous online learning with geometric and temporal consistency, consistently improving navigation and localization in real-world scenarios.
Read the full abstract

All authors Xiaoji Niu, Yuqing Wang, Yan Wang, Hailiang Tang, Tisheng Zhang

Computer Vision · Cross-listed from eess.IV

NeuralLVC: Neural Lossless Video Compression via Masked Diffusion with Temporal Conditioning

Tiberio Uricchio and Marco Bertini

While neural lossless image compression has advanced significantly with learned entropy models, lossless video compression remains largely unexplored in the neural setting. We present NeuralLVC, a neural lossless video codec that combines masked diffusion with an I/P-frame architecture for exploiting temporal redundancy. Our I-frame model compresses individual frames using bijective linear tokenization that guarantees exact pixel reconstruction. The P-frame model compresses temporal differences between consecutive frames, conditioned on the previous decoded frame via a lightweight reference embedding that adds only 1.3% trainable parameters. Group-wise decoding enables controllable speed-compression trade-offs. Our codec is lossless in the input domain: for video, it reconstructs YUV420 planes exactly; for image evaluation, RGB channels are reconstructed exactly. Experiments on 9 Xiph CIF sequences and on 24 HD sequences at 720p and 1080p (Xiph, UVG, and the modern BVI-AOM benchmark) show that NeuralLVC outperforms H.264 and H.265 lossless by a significant margin at every resolution tested. We verify exact reconstruction through end-to-end encode-decode testing with arithmetic coding. These results suggest that masked diffusion with temporal conditioning is a promising direction for neural lossless video compression.
Read the full abstract

Computer Vision

YOLOv11 Demystified: A Practical Guide to High-Performance Object Detection

Nikhileswara Rao Sulake

YOLOv11 is the latest iteration in the You Only Look Once (YOLO) series of real-time object detectors, introducing novel architectural modules to improve feature extraction and small-object detection. In this paper, we present a detailed analysis of YOLOv11, including its backbone, neck, and head components. The model key innovations, the C3K2 blocks, Spatial Pyramid Pooling - Fast (SPPF), and C2PSA (Cross Stage Partial with Spatial Attention) modules enhance spatial feature processing while preserving speed. We compare YOLOv11 performance to prior YOLO versions on standard benchmarks, highlighting improvements in mean Average Precision (mAP) and inference speed. Our results demonstrate that YOLOv11 achieves superior accuracy without sacrificing real-time capabilities, making it well-suited for applications in autonomous driving, surveillance, and video analytics.This work formalizes YOLOv11 in a research context, providing a clear reference for future studies.
Read the full abstract

Computer Vision

Mixture-of-Experts in Remote Sensing: A Survey

Yongchuan Cui, Peng Liu and Lajiao Chen

Remote sensing data analysis and interpretation present unique challenges due to the diversity in sensor modalities and spatiotemporal dynamics of Earth observation data. Mixture-of-Experts (MoE) model has emerged as a powerful paradigm that addresses these challenges by dynamically routing inputs to specialized experts designed for different aspects of a task. However, despite rapid progress, the community still lacks a comprehensive review of MoE for remote sensing. This survey provides the first systematic overview of MoE applications in remote sensing, covering fundamental principles, architectural designs, and key applications across a variety of remote sensing tasks. The survey also outlines future trends to inspire further research and innovation in applying MoE to remote sensing.
Read the full abstract

Computer Vision

Learning Additively Compositional Latent Actions for Embodied AI

Hangxing Wei, Xiaoyu Chen, Chuheng Zhang et al. (+5 more)

Latent action learning infers pseudo-action labels from visual transitions, providing an approach to leverage internet-scale video for embodied AI. However, most methods learn latent actions without structural priors that encode the additive, compositional structure of physical motion. As a result, latents often entangle irrelevant scene details or information about future observations with true state changes and miscalibrate motion magnitude. We introduce Additively Compositional Latent Action Model (AC-LAM), which enforces scene-wise additive composition structure over short horizons on the latent action space. These AC constraints encourage simple algebraic structure in the latent action space~(identity, inverse, cycle consistency) and suppress information that does not compose additively. Empirically, AC-LAM learns more structured, motion-specific, and displacement-calibrated latent actions and provides stronger supervision for downstream policy learning, outperforming state-of-the-art LAMs across simulated and real-world tabletop tasks.
Read the full abstract

All authors Hangxing Wei, Xiaoyu Chen, Chuheng Zhang, Tim Pearce, Jianyu Chen, Alex Lamb, Li Zhao, Jiang Bian

Computer Vision

Hierarchical Awareness Adapters with Hybrid Pyramid Feature Fusion for Dense Depth Prediction

Wuqi Su, Huilun Song, Chen Zhao et al. (+1 more)

Monocular depth estimation from a single RGB image remains a fundamental challenge in computer vision due to inherent scale ambiguity and the absence of explicit geometric cues. Existing approaches typically rely on increasingly complex network architectures to regress depth maps, which escalates training costs and computational overhead without fully exploiting inter-pixel spatial dependencies. We propose a multilevel perceptual conditional random field (CRF) model built upon the Swin Transformer backbone that addresses these limitations through three synergistic innovations: (1) an adaptive hybrid pyramid feature fusion (HPF) strategy that captures both short-range and long-range dependencies by combining multi-scale spatial pyramid pooling with biaxial feature aggregation, enabling effective integration of global and local contextual information; (2) a hierarchical awareness adapter (HA) that enriches cross-level feature interactions within the encoder through lightweight broadcast modules with learnable dimensional scaling, reducing computational complexity while enhancing representational capacity; and (3) a fully-connected CRF decoder with dynamic scaling attention that models fine-grained pixel-level spatial relationships, incorporating a bias learning unit to prevent extreme-value collapse and ensure stable training. Extensive experiments on NYU Depth v2, KITTI, and MatterPort3D datasets demonstrate that our method achieves state-of-the-art performance, reducing Abs Rel to 0.088 ($-$7.4%) and RMSE to 0.316 ($-$5.4%) on NYU Depth v2, while attaining near-perfect threshold accuracy ($\delta < 1.25^3 \approx 99.8\%$) on KITTI with only 194M parameters and 21ms inference time.
Read the full abstract

All authors Wuqi Su, Huilun Song, Chen Zhao, Chi Xu

Computer Vision

Significance and Stability Analysis of Genotype-Environment Interaction using GxEStat

Meng'en Qin, Zhe Li, Hui Huang et al. (+1 more)

Genotype-environment (GxE) interactions can influence the performance of genotypes across diverse environments, limiting the reliability of genotype evaluation and selection in breeding programs. In-depth analysis of GxE interactions is therefore essential for understanding how genetic advantages or defects are expressed under varying environmental conditions and for identifying superior and stable genotypes. This study presents an integrated computational framework for GxE analysis that combines significance and stability evaluation within a unified analytical workflow. The framework incorporates the mixed effect modeling to quantify the significance of environment, genotype, and GxE effects, together with multiple stability analysis approaches for characterizing genotype adaptability, environmental representativeness, and performance consistency across environments. To support reproducible statistical analysis, we develop GxEStat, an interactive R platform that automates model construction, parameter estimation, statistical inference, and graphical visualization. GxEStat substantially improves analytical efficiency, reproducibility, and accessibility for multi-environment trial analysis. Applications to real breeding datasets demonstrate the effectiveness of the proposed framework for practical breeding research. Codes are available at https://github.com/mason-ching/GxEStat.
Read the full abstract

All authors Meng'en Qin, Zhe Li, Hui Huang, Xihong Liu

Computer Vision

Bridging the Dimensionality Gap: A Taxonomy and Survey of 2D Vision Model Adaptation for 3D Analysis

Akshat Pandya and Bhavuk Jain

The remarkable success of Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) in 2D vision has spurred significant research in extending these architectures to the complex domain of 3D analysis. Yet, a core challenge arises from a fundamental dichotomy between the regular, dense grids of 2D images and the irregular, sparse nature of 3D data such as point clouds and meshes. This survey provides a comprehensive review and a unified taxonomy of adaptation strategies that bridge this gap, classifying them into three families: (1) Data-centric methods that project 3D data into 2D formats to leverage off-the-shelf 2D models, (2) Architecture-centric methods that design intrinsic 3D networks, and (3) Hybrid methods, which synergistically combine the two modeling paradigms to benefit from both rich visual priors of large 2D datasets and explicit geometric reasoning of 3D models. Through this framework, we qualitatively analyze the fundamental trade-offs between these families concerning computational complexity, reliance on large-scale pre-training, and the preservation of geometric inductive biases. We discuss key open challenges and outline promising future research directions, including the development of 3D foundation models, advancements in self-supervised learning (SSL) for geometric data, and the deeper integration of multi-modal signals.
Read the full abstract

Computer Vision

CoME-VL: Scaling Complementary Multi-Encoder Vision-Language Learning

Ankan Deria, Komal Kumar, Xilin He et al. (+4 more)

Recent vision-language models (VLMs) typically rely on a single vision encoder trained with contrastive image-text objectives, such as CLIP-style pretraining. While contrastive encoders are effective for cross-modal alignment and retrieval, self-supervised visual encoders often capture richer dense semantics and exhibit stronger robustness on recognition and understanding tasks. In this work, we investigate how to scale the fusion of these complementary visual representations for vision-language modeling. We propose CoME-VL: Complementary Multi-Encoder Vision-Language, a modular fusion framework that integrates a contrastively trained vision encoder with a self-supervised DINO encoder. Our approach performs representation-level fusion by (i) entropy-guided multi-layer aggregation with orthogonality-constrained projections to reduce redundancy, and (ii) RoPE-enhanced cross-attention to align heterogeneous token grids and produce compact fused visual tokens. The fused tokens can be injected into a decoder-only LLM with minimal changes to standard VLM pipelines. Extensive experiments across diverse vision-language benchmarks demonstrate that CoME-VL consistently outperforms single-encoder baselines. In particular, we observe an average improvement of 4.9% on visual understanding tasks and 5.4% on grounding tasks. Our method achieves state-of-the-art performance on RefCOCO for detection while improving over the baseline by a large margin. Finally, we conduct ablation studies on layer merging, non-redundant feature mixing, and fusion capacity to evaluate how complementary contrastive and self-supervised signals affect VLM performance.
Read the full abstract

All authors Ankan Deria, Komal Kumar, Xilin He, Imran Razzak, Hisham Cholakkal, Fahad Shahbaz Khan, Salman Khan

Computer Vision

VOSR: A Vision-Only Generative Model for Image Super-Resolution

Rongyuan Wu, Lingchen Sun, Zhengqiang Zhang et al. (+4 more)

Most of the recent generative image super-resolution (SR) methods rely on adapting large text-to-image (T2I) diffusion models pretrained on web-scale text-image data. While effective, this paradigm starts from a generic T2I generator, despite that SR is fundamentally a low-resolution (LR) input-conditioned image restoration task. In this work, we investigate whether an SR model trained purely on visual data can rival T2I-based ones. To this end, we propose VOSR, a Vision-Only generative framework for SR. We first extract semantically rich and spatially grounded features from the LR input using a pretrained vision encoder as visual semantic guidance. We then revisit classifier-free guidance for training generative models and show that the standard unconditional branch is ill-suited to restoration models trained from scratch. We therefore replace it with a restoration-oriented guidance strategy that preserves weak LR anchors. Built upon these designs, we first train a multi-step VOSR model from scratch and then distill it into a one-step model for efficient inference. VOSR requires less than one-tenth of the training cost of representative T2I-based SR methods, yet in both multi-step and one-step settings, it achieves competitive or even better perceptual quality and efficiency, while producing more faithful structures with fewer hallucinations on both synthetic and real-world benchmarks. Our results, for the first time, show that high-quality generative SR can be achieved without multimodal pretraining. The code and models can be found at https://github.com/cswry/VOSR.
Read the full abstract

All authors Rongyuan Wu, Lingchen Sun, Zhengqiang Zhang, Xiangtao Kong, Jixin Zhao, Shihao Wang, Lei Zhang

Computer Vision · Cross-listed from eess.IV

HyperCT: Low-Rank Hypernet for Unified Chest CT Analysis

Fengbei Liu, Sunwoo Kwak, Hao Phung et al. (+6 more)

Non-contrast chest CTs offer a rich opportunity for both conventional pulmonary and opportunistic extra-pulmonary screening. While Multi-Task Learning (MTL) can unify these diverse tasks, standard hard-parameter sharing approaches are often suboptimal for modeling distinct pathologies. We propose HyperCT, a framework that dynamically adapts a Vision Transformer backbone via a Hypernetwork. To ensure computational efficiency, we integrate Low-Rank Adaptation (LoRA), allowing the model to regress task-specific low-rank weight updates rather than full parameters. Validated on a large-scale dataset of radiological and cardiological tasks, \method{} outperforms various strong baselines, offering a unified, parameter-efficient solution for holistic patient assessment. Our code is available at https://github.com/lfb-1/HyperCT.
Read the full abstract

All authors Fengbei Liu, Sunwoo Kwak, Hao Phung, Nusrat Binta Nizam, Ilan Richter, Nir Uriel, Hadar Averbuch-Elor, Daborah Estrin, Mert R. Sabuncu

Computer Vision

ProtoFlow: Mitigating Forgetting in Class-Incremental Remote Sensing Segmentation via Low-Curvature Prototype Flow

Jiekai Wu, Rong Fu, Chuangqi Li et al. (+9 more)

Remote sensing segmentation in real deployment is inherently continual: new semantic categories emerge, and acquisition conditions shift across seasons, cities, and sensors. Despite recent progress, many incremental approaches still treat training steps as isolated updates, which leaves representation drift and forgetting insufficiently controlled. We present ProtoFlow, a time-aware prototype dynamics framework that models class prototypes as trajectories and learns their evolution with an explicit temporal vector field. By jointly enforcing low-curvature motion and inter-class separation, ProtoFlow stabilizes prototype geometry throughout incremental learning. Experiments on standard class- and domain-incremental remote sensing benchmarks show consistent gains over strong baselines, including up to 1.5-2.0 points improvement in mIoUall, together with reduced forgetting. These results suggest that explicitly modeling temporal prototype evolution is a practical and interpretable strategy for robust continual remote sensing segmentation. Open-source code:https://github.com/dudududke/protoflow.
Read the full abstract

All authors Jiekai Wu, Rong Fu, Chuangqi Li, Zijian Zhang, Guangxin Wu, Hao Zhang, Shiyin Lin, Yang Li, Dongxu Zhang, Amir H. Gandomi, Simon Fong, Pengbin Feng

Computer Vision

PR3DICTR: A modular AI framework for medical 3D image-based detection and outcome prediction

Daniel C. MacRae, Luuk van der Hoek, Robert van der Wal et al. (+5 more)

Three-dimensional medical image data and computer-aided decision making, particularly using deep learning, are becoming increasingly important in the medical field. To aid in these developments we introduce PR3DICTR: Platform for Research in 3D Image Classification and sTandardised tRaining. Built using community-standard distributions (PyTorch and MONAI), PR3DICTR provides an open-access, flexible and convenient framework for prediction model development, with an explicit focus on classification using three-dimensional medical image data. By combining modular design principles and standardization, it aims to alleviate developmental burden whilst retaining adjustability. It provides users with a wealth of pre-established functionality, for instance in model architecture design options, hyper-parameter solutions and training methodologies, but still gives users the opportunity and freedom to “plug in” their own solutions or modules. PR3DICTR can be applied to any binary or event-based three-dimensional classification task and can work with as little as two lines of code.
Read the full abstract

All authors Daniel C. MacRae, Luuk van der Hoek, Robert van der Wal, Suzanne P.M. de Vette, Hendrike Neh, Baoqiang Ma, Peter M.A. van Ooijen, Lisanne V. van Dijk

Computer Vision

The Eleventh NTIRE 2026 Efficient Super-Resolution Challenge Report

Bin Ren, Hang Guo, Yan Shu et al. (+60 more)

This paper reviews the NTIRE 2026 challenge on efficient single-image super-resolution with a focus on the proposed solutions and results. The aim of this challenge is to devise a network that reduces one or several aspects, such as runtime, parameters, and FLOPs, while maintaining PSNR of around 26.90 dB on the DIV2K_LSDIR_valid dataset, and 26.99 dB on the DIV2K_LSDIR_test dataset. The challenge had 95 registered participants, and 15 teams made valid submissions. They gauge the state-of-the-art results for efficient single-image super-resolution.
Read the full abstract

All authors Bin Ren, Hang Guo, Yan Shu, Jiaqi Ma, Ziteng Cui, Shuhong Liu, Guofeng Mei, Lei Sun, Zongwei Wu, Fahad Shahbaz Khan, Salman Khan, Radu Timofte, Yawei Li, Hongyuan Yu, Pufan Xu, Chen Wu, Long Peng, Jiaojiao Yi, Siyang Yi, Yuning Cui, Jingyuan Xia, Xing Mou, Keji He, Jinlin Wu, Zongang Gao, Sen Yang, Rui Zheng, Fengguo Li, Yecheng Lei, Wenkai Min, Jie Liu, Keye Cao, Shubham Sharma, Manish Prasad, Haobo Li, Matin Fazel, Abdelhak Bentaleb, Rui Chen, Shurui Shi, Zitao Dai, Qingliang Liu, Yang Cheng, Jing Hu, Xuan Zhang, Rui Ding, Tingyi Zhang, Hui Deng, Mengyang Wang, Fulin Liu, Jing Wei, Qian Wang, Hongying Liu, Mingyang Li, Guanglu Dong, Zheng Yang, Chao Ren, Hongbo Fang, Lingxuan Li, Lin Si, Pan Gao, Moncef Gabbouj, Watchara Ruangsang, Supavadee Aramvith

Computer Vision · Cross-listed from cs.RO

The Compression Gap: Why Discrete Tokenization Limits Vision-Language-Action Model Scaling

Takuya Shiba

Scaling Vision-Language-Action (VLA) models by upgrading the vision encoder is expected to improve downstream manipulation performance–as it does in vision-language modeling. We show that this expectation fails when actions are represented as discrete tokens, and explain why through an information-theoretic principle we call the Compression Gap: in any visuomotor pipeline, scaling behavior is governed by the location of the tightest information bottleneck. When actions are continuous (e.g., Diffusion Policy), the vision encoder is the binding constraint, and upgrading it directly improves performance. When actions are discretized through a fixed-capacity codebook (e.g., OAT), the codebook becomes the binding constraint, and encoder improvements cannot propagate past it–regardless of how rich the upstream representation is. We validate this principle on the LIBERO benchmark with three lines of evidence: a factorial experiment showing that encoder upgrades improve Diffusion Policy by over 21 percentage points while OAT gains are substantially attenuated across model scales; an encoder quality gradient across four encoders confirming that Diffusion Policy tracks encoder quality monotonically while OAT remains flat; and a codebook size experiment demonstrating that relaxing codebook capacity partially recovers encoder sensitivity, providing causal evidence for the bottleneck hypothesis. Our findings reveal that scaling in Physical AI requires identifying where information bottlenecks lie in the pipeline, rather than uniformly increasing model or data size.
Read the full abstract

Computer Vision · Cross-listed from cs.RO

SpatialVAM:Spatial-Aware Multi-View Video Diffusion as a Data-Efficient Robot Policy

Peiyan Li, Yixiang Chen, Yuan Xu et al. (+13 more)

Robotic manipulation requires understanding both the 3D spatial structure of the environment and its temporal evolution, yet most existing policies neglect one or both aspects. They often rely on 2D visual observations or backbones pretrained on static image–text pairs, which leads to high data requirements and limited comprehension of environment dynamics. To address this, we introduce SpatialVAM, the first 3D Video Action Model that simultaneously predict spatial-aware multi-view heatmap videos and RGB videos. Our key insight is that this design naturally injects 3D information into video foundation models while aligning the representation format between video pretraining and action finetuning. Extensive experiments demonstrate that SpatialVAM enables data-efficient, robust, generalizable, and interpretable manipulation. With only ten demonstration trajectories and no additional pretraining, SpatialVAM handles challenging long-horizon and contact-rich tasks, generalizes to out-of-distribution settings, and predicts realistic future videos. Evaluations on Meta-World (22%$\uparrow$), RoboCasa (15%$\uparrow$) and real-world robotic platforms (16%$\uparrow$) show that SpatialVAM consistently outperforms other video action models, vision language action models and 3D-based policies, establishing a new state-of-the-art in data-efficient multi-task manipulation.
Read the full abstract

All authors Peiyan Li, Yixiang Chen, Yuan Xu, Jiabing Yang, Xiangnan Wu, Jun Guo, Nan Sun, Long Qian, Xinghang Li, Xin Xiao, Jing Liu, Nianfeng Liu, Tao Kong, Yan Huang, Liang Wang, Tieniu Tan

Computer Vision · Cross-listed from cs.LG

Understanding the Role of Hallucination in Reinforcement Post-Training of Multimodal Reasoning Models

Gengwei Zhang, Jie Peng, Zhen Tan et al. (+6 more)

The recent success of reinforcement learning (RL) in large reasoning models has inspired the growing adoption of RL for post-training Multimodal Large Language Models (MLLMs) to enhance their visual reasoning capabilities. Although many studies have reported improved performance, it remains unclear whether RL training truly enables models to learn from visual information. In this work, we propose the Hallucination-as-Cue Framework, an analytical framework designed to investigate the effects of RL-based post-training on multimodal reasoning models from the perspective of model hallucination. Specifically, we introduce hallucination-inductive, modality-specific corruptions that remove or replace essential information required to derive correct answers, thereby forcing the model to reason by hallucination. By applying these corruptions during both training and evaluation, our framework provides a unique perspective for diagnosing RL training dynamics and understanding the intrinsic properties of datasets. Through extensive experiments and analyses across multiple multimodal reasoning benchmarks, we reveal that the role of model hallucination for RL-training is more significant than previously recognized. For instance, we find that RL post-training under purely hallucination-inductive settings can still significantly improve models' reasoning performance, and in some cases even outperform standard training. These findings challenge prevailing assumptions about MLLM reasoning training and motivate the development of more modality-aware RL-based training designs.
Read the full abstract

All authors Gengwei Zhang, Jie Peng, Zhen Tan, Mufan Qiu, Hossein Nourkhiz Mahjoub, Vaishnav Tadiparthi, Kwonjoon Lee, Yanyong Zhang, Tianlong Chen

Computer Vision

SFFNet: Synergistic Feature Fusion Network With Dual-Domain Edge Enhancement for UAV Image Object Detection

Wenfeng Zhang, Jun Ni, Yue Meng et al. (+4 more)

Object detection in unmanned aerial vehicle (UAV) images remains a highly challenging task, primarily caused by the complexity of background noise and the imbalance of target scales. Traditional methods easily struggle to effectively separate objects from intricate backgrounds and fail to fully leverage the rich multi-scale information contained within images. To address these issues, we have developed a synergistic feature fusion network (SFFNet) with dual-domain edge enhancement specifically tailored for object detection in UAV images. Firstly, the multi-scale dynamic dual-domain coupling (MDDC) module is designed. This component introduces a dual-driven edge extraction architecture that operates in both the frequency and spatial domains, enabling effective decoupling of multi-scale object edges from background noise. Secondly, to further enhance the representation capability of the model's neck in terms of both geometric and semantic information, a synergistic feature pyramid network (SFPN) is proposed. SFPN leverages linear deformable convolutions to adaptively capture irregular object shapes and establishes long-range contextual associations around targets through the designed wide-area perception module (WPM). Moreover, to adapt to the various applications or resource-constrained scenarios, six detectors of different scales (N/S/M/B/L/X) are designed. Experiments on two challenging aerial datasets (VisDrone and UAVDT) demonstrate the outstanding performance of SFFNet-X, achieving 36.8 AP and 20.6 AP, respectively. The lightweight models (N/S) also maintain a balance between detection accuracy and parameter efficiency. The code will be available at https://github.com/CQNU-ZhangLab/SFFNet.
Read the full abstract

All authors Wenfeng Zhang, Jun Ni, Yue Meng, Xiaodong Pei, Wei Hu, Qibing Qin, Lei Huang

Computer Vision

EffiMiniVLM: A Compact Dual-Encoder Regression Framework

Yin-Loon Khor, Yi-Jie Wong and Yan Chai Hum

Predicting product quality from multimodal item information is critical in cold-start scenarios, where user interaction history is unavailable and predictions must rely on images and textual metadata. However, existing vision-language models typically depend on large architectures and/or extensive external datasets, resulting in high computational cost. To address this, we propose EffiMiniVLM, a compact dual-encoder vision-language regression framework that integrates an EfficientNet-B0 image encoder and a MiniLM-based text encoder with a lightweight regression head. To improve training sample efficiency, we introduce a weighted Huber loss that leverages rating counts to emphasize more reliable samples, yielding consistent performance gains. Trained using only 20% of the Amazon Reviews 2023 dataset, the proposed model contains 27.7M parameters and requires 6.8 GFLOPs, yet achieves a CES score of 0.40 with the lowest resource cost in the benchmark. Despite its small size, it remains competitive with significantly larger models, achieving comparable performance while being approximately 4x to 8x more resource-efficient than other top-5 methods and being the only approach that does not use external datasets. Further analysis shows that scaling the data to 40% alone allows our model to overtake other methods, which use larger models and datasets, highlighting strong scalability despite the model's compact design.
Read the full abstract

Computer Vision

CAMEO: A Conditional and Quality-Aware Multi-Agent Image Editing Orchestrator

Yuhan Pu, Hao Zheng, Ziqian Mo et al. (+5 more)

Conditional image editing aims to modify a source image according to textual prompts and optional reference guidance. Such editing is crucial in scenarios requiring strict structural control (i.e., anomaly insertion in driving scenes and complex human pose transformation). Despite recent advances in large-scale editing models (i.e., Seedream, Nano Banana, etc), most approaches rely on single-step generation. This paradigm often lacks explicit quality control, may introduce excessive deviation from the original image, and frequently produces structural artifacts or environment-inconsistent modifications, typically requiring manual prompt tuning to achieve acceptable results. We propose CAMEO, a structured multi-agent framework that reformulates conditional editing as a quality-aware, feedback-driven process rather than a one-shot generation task. CAMEO decomposes editing into coordinated stages of planning, structured prompting, hypothesis generation, and adaptive reference grounding, where external guidance is invoked only when task complexity requires it. To overcome the lack of intrinsic quality control in existing methods, evaluation is embedded directly within the editing loop. Intermediate results are iteratively refined through structured feedback, forming a closed-loop process that progressively corrects structural and contextual inconsistencies. We evaluate CAMEO on anomaly insertion and human pose switching tasks. Across multiple strong editing backbones and independent evaluation models, CAMEO consistently achieves 20% more win rate on average compared to multiple state-of-the-art models, demonstrating improved robustness, controllability, and structural reliability in conditional image editing.
Read the full abstract

All authors Yuhan Pu, Hao Zheng, Ziqian Mo, Zirui Pang, Hill Zhang, Tianyi Fan, Shuhong Wu, Jiaheng Wei

Computer Vision

SD-FSMIS: Adapting Stable Diffusion for Few-Shot Medical Image Segmentation

Meihua Li, Yang Zhang, Weizhao He et al. (+2 more)

Few-Shot Medical Image Segmentation (FSMIS) aims to segment novel object classes in medical images using only minimal annotated examples, addressing the critical challenges of data scarcity and domain shifts prevalent in medical imaging. While Diffusion Models (DM) excel in visual tasks, their potential for FSMIS remains largely unexplored. We propose that the rich visual priors learned by large-scale DMs offer a powerful foundation for a more robust and data-efficient segmentation approach. In this paper, we introduce SD-FSMIS, a novel framework designed to effectively adapt the powerful pre-trained Stable Diffusion (SD) model for the FSMIS task. Our approach repurposes its conditional generative architecture by introducing two key components: a Support-Query Interaction (SQI) and a Visual-to-Textual Condition Translator (VTCT). Specifically, SQI provides a straightforward yet powerful means of adapting SD to the FSMIS paradigm. The VTCT module translates visual cues from the support set into an implicit textual embedding that guides the diffusion model, enabling precise conditioning of the generation process. Extensive experiments demonstrate that SD-FSMIS achieves competitive results compared to state-of-the-art methods in standard settings. Surprisingly, it also demonstrated excellent generalization ability in more challenging cross-domain scenarios. These findings highlight the immense potential of adapting large-scale generative models to advance data-efficient and robust medical image segmentation.
Read the full abstract

All authors Meihua Li, Yang Zhang, Weizhao He, Hu Qu, Yisong Li

Computer Vision

SCC-Loc: A Unified Semantic Cascade Consensus Framework for UAV Thermal Geo-Localization

Xiaoran Zhang, Yu Liu, Jinyu Liang et al. (+3 more)

Cross-modal Thermal Geo-localization (TG) provides a robust, all-weather solution for Unmanned Aerial Vehicles (UAVs) in Global Navigation Satellite System (GNSS)-denied environments. However, profound thermal-visible modality gaps introduce severe feature ambiguity, systematically corrupting conventional coarse-to-fine registration. To dismantle this bottleneck, we propose SCC-Loc, a unified Semantic-Cascade-Consensus localization framework. By sharing a single DINOv2 backbone across global retrieval and MINIMA$_{\text{RoMa}}$ matching, it minimizes memory footprint and achieves zero-shot, highly accurate absolute position estimation. Specifically, we tackle modality ambiguity by introducing three cohesive components. First, we design the Semantic-Guided Viewport Alignment (SGVA) module to adaptively optimize satellite crop regions, effectively correcting initial spatial deviations. Second, we develop the Cascaded Spatial-Adaptive Texture-Structure Filtering (C-SATSF) mechanism to explicitly enforce geometric consistency, thereby eradicating dense cross-modal outliers. Finally, we propose the Consensus-Driven Reliability-Aware Position Selection (CD-RAPS) strategy to derive the optimal solution through a synergy of physically constrained pose optimization. To address data scarcity, we construct Thermal-UAV, a comprehensive dataset providing 11,890 diverse thermal queries referenced against a large-scale satellite ortho-photo and corresponding spatially aligned Digital Surface Model (DSM). Extensive experiments demonstrate that SCC-Loc establishes a new state-of-the-art, suppressing the mean localization error to 9.37 m and providing a 7.6-fold accuracy improvement within a strict 5-m threshold over the strongest baseline. Code and dataset are available at https://github.com/FloralHercules/SCC-Loc.
Read the full abstract

All authors Xiaoran Zhang, Yu Liu, Jinyu Liang, Kangqiushi Li, Zhiwei Huang, Huaxin Xiao

Computer Vision

Salt: Self-Consistent Distribution Matching with Cache-Aware Training for Fast Video Generation

Xingtong Ge, Yi Zhang, Yushi Huang et al. (+6 more)

Distilling video generation models to extremely low inference budgets (e.g., 2–4 NFEs) is crucial for real-time deployment, yet remains challenging. Trajectory-style consistency distillation often becomes conservative under complex video dynamics, yielding an over-smoothed appearance and weak motion. Distribution matching distillation (DMD) can recover sharp, mode-seeking samples, but its local training signals do not explicitly regularize how denoising updates compose across timesteps, making composed rollouts prone to drift. To overcome this challenge, we propose Self-Consistent Distribution Matching Distillation (SC-DMD), which explicitly regularizes the endpoint-consistent composition of consecutive denoising updates. For real-time autoregressive video generation, we further treat the KV cache as a quality parameterized condition and propose Cache-Distribution-Aware training. This training scheme applies SC-DMD over multi-step rollouts and introduces a cache-conditioned feature alignment objective that steers low-quality outputs toward high-quality references. Across extensive experiments on both non-autoregressive backbones (e.g., Wan~2.1) and autoregressive real-time paradigms (e.g., Self Forcing), our method, dubbed Salt, consistently improves low-NFE video generation quality while remaining compatible with diverse KV-cache memory mechanisms. Project page: https://xingtongge.github.io/Salt
Read the full abstract

All authors Xingtong Ge, Yi Zhang, Yushi Huang, Dailan He, Xiahong Wang, Bingqi Ma, Guanglu Song, Yu Liu, Jun Zhang

Computer Vision

Revealing Physical-World Semantic Vulnerabilities: Universal Adversarial Patch for Infrared Vision-Language Models

Chengyin Hu, Yuxian Dong, Yikun Guo et al. (+8 more)

Infrared vision-language models (IR-VLMs) are becoming important for semantic perception in low-visibility environments, yet their robustness to physical semantic attacks remains underexplored. Existing adversarial patch methods are mainly designed for red-green-blue (RGB) images or closed-set infrared detectors and do not directly address open-ended IR-VLM tasks, where one deployable artifact can affect classification, captioning, and visual question answering (VQA) simultaneously. We propose Universal Curved-Grid Patch, abbreviated UCGP, a universal physical adversarial patch framework tailored to IR-VLMs. UCGP represents the patch as a deployable low-frequency curved grid and optimizes it with a representation-driven objective over subspace departure, topology disruption, and local appearance regularization. Meta Differential Evolution (MetaDE) searches for patch parameters with two physical robustness augmentations: Expectation over Transformation (EOT) capture sampling for imaging variations and thin-plate spline (TPS) patch-deformation modeling for non-rigid local shape changes. Rather than manipulating labels or prompts, UCGP disrupts the clean-category manifold in visual representation space, which later appears as degraded cross-modal outputs. Experiments show that a single shared patch degrades classification, captioning, and VQA across diverse IR-VLM architectures while retaining measurable cross-model transfer, cross-dataset generalization, cross-category extensibility, and real-scene physical effectiveness under the evaluated conditions. These results reveal a robustness blind spot in current infrared multimodal systems. Code and reproducibility assets are available at https://github.com/dyx6663/UCGP.
Read the full abstract

All authors Chengyin Hu, Yuxian Dong, Yikun Guo, Xiang Chen, Qike Zhang, Junqi Wu, Jiahuan Long, Jiujiang Guo, Yiwei Wei, Tingsong Jiang, Wen Yao

Computer Vision

Suppression Is Not Forgetting: Residual Recoverability in Visual Concept Unlearning for VLMs

Zhangyun Tan, Zeliang Zhang, Jiani Liu et al. (+4 more)

Vision-language models (VLMs) may need to forget visual concepts after deployment because of privacy, copyright, licensing, safety, or policy changes. Conventional machine unlearning modifies model parameters, which may be costly or inaccessible for API-only models. Prompt-based suppression offers a training-free alternative, but does it make a concept inaccessible or merely change the model's answer? We investigate this question in off-the-shelf VLMs. Our visually grounded, multi-probe evaluation first verifies that a model recognizes each concept from the image, then tests its recoverability through multiple-choice, short-answer, and indirect queries. Across objects, scenes, and identities, prompt suppression reduces short-answer recall for some concepts while leaving multiple-choice and indirect performance largely unchanged. Explicitly listing the concepts to suppress often increases short-answer recall, suggesting that the list itself cues the answer. Beyond prompting, decoding constraints, representation editing, and parameter updates can suppress particular responses while the same concept remains detectable through other queries. A model may stop naming a visual concept yet still identify or use it when queried differently.
Read the full abstract

All authors Zhangyun Tan, Zeliang Zhang, Jiani Liu, Susan Liang, Yolo Y. Tang, Lisha Chen, Chenliang Xu

Computer Vision · Cross-listed from eess.IV

ARIQA-3DS: A Stereoscopic Image Quality Assessment Dataset for Realistic Augmented Reality

Aymen Sekhri, Seyed Ali Amirshahi and Mohamed-Chaker Larabi

As Augmented Reality (AR) technologies advance towards immersive consumer adoption, the need for rigorous Quality of Experience (QoE) assessment becomes critical. However, existing datasets often lack ecological validity, relying on monocular viewing or simplified backgrounds that fail to capture the complex perceptual interplay, termed visual confusion, between real and virtual layers. To address this gap, we present ARIQA-3DS, the first large stereoscopic AR Image Quality Assessment dataset. Comprising 1,200 AR viewports, the dataset fuses high-resolution stereoscopic omnidirectional captures of real-world scenes with diverse augmented foregrounds under controlled transparency and degradation conditions. We conducted a comprehensive subjective study with 36 participants using a video see-through head-mounted display, collecting both quality ratings and simulator-sickness indicators. Our analysis reveals that perceived quality is primarily driven by foreground degradations and modulated by transparency levels, while oculomotor and disorientation symptoms show a progressive but manageable increase during viewing. ARIQA-3DS will be publicly released to serve as a comprehensive benchmark for developing next-generation AR quality assessment models.
Read the full abstract

Computer Vision

A Data-Centric Vision Transformer Baseline for SAR Sea Ice Classification

David Mike-Ewewie, Panhapiseth Lim and Priyanka Kumar

Accurate and automated sea ice classification is important for climate monitoring and maritime safety in the Arctic. While Synthetic Aperture Radar (SAR) is the operational standard because of its all-weather capability, it remains challenging to distinguish morphologically similar ice classes under severe class imbalance. Rather than claiming a fully validated multimodal system, this paper establishes a trustworthy SAR only baseline that future fusion work can build upon. Using the AI4Arctic/ASIP Sea Ice Dataset (v2), which contains 461 Sentinel-1 scenes matched with expert ice charts, we combine full-resolution Sentinel-1 Extra Wide inputs, leakage-aware stratified patch splitting, SIGRID-3 stage-of-development labels, and training-set normalization to evaluate Vision Transformer baselines. We compare ViT-Base models trained with cross entropy and weighted cross-entropy against a ViT-Large model trained with focal loss. Among the tested configurations, ViT-Large with focal loss achieves 69.6% held-out accuracy, 68.8% weighted F1, and 83.9% precision on the minority Multi-Year Ice class. These results show that focal-loss training offers a more useful precision-recall trade-off than weighted cross-entropy for rare ice classes and establishes a cleaner baseline for future multimodal fusion with optical, thermal, or meteorological data.
Read the full abstract

Computer Vision

MI-Pruner: Crossmodal Mutual Information-guided Token Pruner for Efficient MLLMs

Jiameng Li, Aleksei Tiulpin and Matthew B. Blaschko

For multimodal large language models (MLLMs), visual information is relatively sparse compared with text. As a result, research on visual pruning emerges for efficient inference. Current approaches typically measure token importance based on the attention scores in the visual encoder or in the LLM decoder, then select visual tokens with high attention scores while pruning others. In this paper, we pursue a different and more surgical approach. Instead of relying on mechanism-specific signals, we directly compute Mutual Information (MI) between visual and textual features themselves, prior to their interaction. This allows us to explicitly measure crossmodal dependency at the feature levels. Our MI-Pruner is simple, efficient and non-intrusive, requiring no access to internal attention maps or architectural modifications. Experimental results demonstrate that our approach outperforms previous attention-based pruning methods with minimal latency.
Read the full abstract