Peer Revenue Past citations are no guarantee of future returns

Papers

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

Computer Science Computer Vision

cs.CV Watch Computer Vision (sign in to use)

Tuesday 25 November

Computer Vision

RefTr: Recurrent Refinement of Confluent Trajectories for 3D Vascular Tree Centerlines

Tubular tree structures such as blood vessels and lung airways are central to many clinical tasks, including diagnosis, treatment planning, and surgical navigation. Accurate centerline extraction with correct topology is essential, as missing small branches can lead to incomplete assessments or overlooked abnormalities. We propose RefTr, a 3D image-to-graph framework that generates vascular centerlines via recurrent refinement of confluent trajectories. RefTr adopts a Transformer-based Producer-Refiner architecture in which the Producer predicts candidate trajectories and a shared Refiner iteratively refines them toward the target branches. The confluent trajectory representation enables whole-branch refinement while explicitly enforcing valid topology. This recurrent scheme improves precision and reduces decoder parameters by 2.4x compared to the state-of-the-art. We further introduce an efficient non-maximum suppression algorithm for spatial tree graphs to merge duplicate branches and extend evaluation metrics to be radius-aware for robust comparison. Experiments on multiple public datasets demonstrate stronger overall performance, faster inference, and substantially fewer parameters, highlighting the effectiveness of RefTr for 3D vascular tree analysis.
Read the full abstract

All authors Roman Naeem, David Hagerman, Jennifer Alvén, Fredrik Kahl

Computer Vision

Training-Free Diffusion Priors for Text-to-Image Generation via Optimization-based Visual Inversion

Diffusion models have established the state-of-the-art in text-to-image generation, but their performance often relies on a diffusion prior network to translate text embeddings into the visual manifold for easier decoding. These priors are computationally expensive and require extensive training on massive datasets. In this work, we challenge the necessity of a trained prior at all by employing Optimization-based Visual Inversion (OVI), a training-free and zero-shot alternative, to replace the need for a prior. OVI initializes a latent visual representation from random pseudo-tokens and iteratively optimizes it to maximize the cosine similarity with the input textual prompt embedding. We further propose two novel constraints, a Mahalanobis-based and a Nearest-Neighbor loss, to regularize the OVI optimization process toward the distribution of realistic images. Our experiments, conducted on Kandinsky 2.2, show that OVI can serve as an alternative to traditional priors. More importantly, our analysis reveals a critical flaw in current evaluation benchmarks like T2I-CompBench++, where simply using the text embedding as a prior achieves surprisingly high scores, despite lower perceptual quality. Our constrained OVI methods improve visual fidelity over this baseline, with the Nearest-Neighbor approach proving particularly effective. It achieves quantitative scores comparable to or higher than the state-of-the-art data-efficient prior, underscoring the potential of optimization-based strategies as viable, training-free alternatives to traditional priors. The code will be publicly available upon acceptance.
Read the full abstract

Computer Vision

SPHINX: A Synthetic Environment for Visual Perception and Reasoning

We present Sphinx, a synthetic environment for visual perception and reasoning that targets core cognitive primitives. Sphinx procedurally generates puzzles using motifs, tiles, charts, icons, and geometric primitives, each paired with verifiable ground-truth solutions, enabling both precise evaluation and large-scale dataset construction. The benchmark covers 25 task types spanning symmetry detection, geometric transformations, spatial reasoning, chart interpretation, and sequence prediction. Evaluating recent large vision-language models (LVLMs) shows that even state-of-the-art GPT-5 attains only 51.1% accuracy, well below human performance. Finally, we demonstrate that reinforcement learning with verifiable rewards (RLVR) substantially improves model accuracy on these tasks and yields gains on external visual reasoning benchmarks, highlighting its promise for advancing multimodal reasoning.
Read the full abstract

All authors Md Tanvirul Alam, Saksham Aggarwal, Justin Yang Chae, Nidhi Rastogi

Computer Vision

Layer-Aware Video Composition via Split-then-Merge

We present Split-then-Merge (StM), a novel framework designed to enhance control in generative video composition and address its data scarcity problem. Unlike conventional methods relying on annotated datasets or handcrafted rules, StM splits a large corpus of unlabeled videos into dynamic foreground and background layers, then self-composes them to learn how dynamic subjects interact with diverse scenes. This process enables the model to learn the complex compositional dynamics required for realistic video generation. StM introduces a novel transformation-aware training pipeline that utilizes a multi-layer fusion and augmentation to achieve affordance-aware composition, alongside an identity-preservation loss that maintains foreground fidelity during blending. Experiments show StM outperforms SoTA methods in both quantitative benchmarks and in humans/VLM-based qualitative evaluations. More details are available at our project page: https://split-then-merge.github.io
Read the full abstract

All authors Ozgur Kara, Yujia Chen, Ming-Hsuan Yang, James M. Rehg, Wen-Sheng Chu, Du Tran

Computer Vision

$\Delta$-NeRF: Incremental Refinement of Neural Radiance Fields through Residual Control and Knowledge Transfer

Neural Radiance Fields (NeRFs) have demonstrated remarkable capabilities in 3D reconstruction and novel view synthesis. However, most existing NeRF frameworks require complete retraining when new views are introduced incrementally, limiting their applicability in domains where data arrives sequentially. This limitation is particularly problematic in satellite-based terrain analysis, where regions are repeatedly observed over time. Incremental refinement of NeRFs remains underexplored, and naive approaches suffer from catastrophic forgetting when past data is unavailable. We propose $\Delta$-NeRF, a unique modular residual framework for incremental NeRF refinement. $\Delta$-NeRF introduces several novel techniques including: (1) a residual controller that injects per-layer corrections into a frozen base NeRF, enabling refinement without access to past data; (2) an uncertainty-aware gating mechanism that prevents overcorrection by adaptively combining base and refined predictions; and (3) a view selection strategy that reduces training data by up to 47% while maintaining performance. Additionally, we employ knowledge distillation to compress the enhanced model into a compact student network (20% of original size). Experiments on satellite imagery demonstrate that $\Delta$-NeRF achieves performance comparable to joint training while reducing training time by 30-42%. $\Delta$-NeRF consistently outperforms existing baselines, achieving an improvement of up to 43.5% in PSNR over naive fine-tuning and surpassing joint training on some metrics.
Read the full abstract

All authors Kriti Ghosh, Devjyoti Chakraborty, Lakshmish Ramaswamy, Suchendra M. Bhandarkar, In Kee Kim, Nancy O'Hare, Deepak Mishra

Computer Vision

Intriguing Properties of Dynamic Sampling Networks

Dynamic sampling mechanisms in deep learning architectures have demonstrated utility across many computer vision models, though the theoretical analysis of these structures has not yet been unified. In this paper we connect the various dynamic sampling methods by developing and analyzing a novel operator which generalizes existing methods, which we term "warping". Warping provides a minimal implementation of dynamic sampling which is amenable to analysis, and can be used to reconstruct existing architectures including deformable convolutions, active convolutional units, and spatial transformer networks. Using our formalism, we provide statistical analysis of the operator by modeling the inputs as both IID variables and homogeneous random fields. Extending this analysis, we discover a unique asymmetry between the forward and backward pass of the model training. We demonstrate that these mechanisms represent an entirely different class of orthogonal operators to the traditional translationally invariant operators defined by convolutions. With a combination of theoretical analysis and empirical investigation, we find the conditions necessary to ensure stable training of dynamic sampling networks. In addition, statistical analysis of discretization effects are studied. Finally, we introduce a novel loss landscape visualization which utilizes gradient update information directly, to better understand learning behavior.
Read the full abstract

Computer Vision

Revisiting KRISP: A Lightweight Reproduction and Analysis of Knowledge-Enhanced Vision-Language Models

Facebook AI Research introduced KRISP [4], which integrates structured external knowledge into pipelines for vision-language reasoning. Despite its effectiveness, the original model has been developed for industrial-scale training, is computationally demanding, and is tightly connected to a large backbone. In this work, we reexamine KRISP from a different angle and offer a lightweight reproduction with significantly fewer parameters. Even though our replicated model performs about 75 % of the original, the replication process uncovers a number of design flaws, real-world pitfalls, and implicit problems that were not fully covered in the original paper. We offer insights into the scalability and efficacy of knowledge-enhanced VQA architectures under resource constraints through systematic ablation studies, which include a proof-of-concept on synthetic VQA data and evaluation on the DAQUAR dataset. Our model, configured with a low parameter setup and constrained by the external Knowledge graph domain, prevents AI hallucinations and generates outputs solely within that domain. Minimal parameters allow us to function on edge devices like smartphones and AR-VR, further improving offline visual reasoning.
Read the full abstract

Computer Vision · Cross-listed from eess.IV

Adversarial Multi-Task Learning for Liver Tumor Segmentation, Dynamic Enhancement Regression, and Classification

Liver tumor segmentation, dynamic enhancement regression, and classification are critical for clinical assessment and diagnosis. However, no prior work has attempted to achieve these tasks simultaneously in an end-to-end framework, primarily due to the lack of an effective framework that captures inter-task relevance for mutual improvement and the absence of a mechanism to extract dynamic MRI information effectively. To address these challenges, we propose the Multi-Task Interaction adversarial learning Network (MTI-Net), a novel integrated framework designed to tackle these tasks simultaneously. MTI-Net incorporates Multi-domain Information Entropy Fusion (MdIEF), which utilizes entropy-aware, high-frequency spectral information to effectively integrate features from both frequency and spectral domains, enhancing the extraction and utilization of dynamic MRI data. The network also introduces a task interaction module that establishes higher-order consistency between segmentation and regression, thus fostering inter-task synergy and improving overall performance. Additionally, we designed a novel task-driven discriminator (TDD) to capture internal high-order relationships between tasks. For dynamic MRI information extraction, we employ a shallow Transformer network to perform positional encoding, which captures the relationships within dynamic MRI sequences. In experiments on a dataset of 238 subjects, MTI-Net demonstrates high performance across multiple tasks, indicating its strong potential for assisting in the clinical assessment of liver tumors. The code is available at: https://github.com/xiaojiao929/MTI-Net.
Read the full abstract

All authors Xiaojiao Xiao, Qinmin Vivian Hu, Tae Hyun Kim, Guanghui Wang

Computer Vision

LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling

Large multimodal models (LMMs) have shown great potential for video reasoning with textual Chain-of-Thought. However, they remain vulnerable to hallucinations, especially when processing long-form videos where evidence is sparse and temporally dispersed. Inspired by how humans comprehend long videos - by first skimming globally and then examining relevant clips for details - we introduce LongVT, an end-to-end agentic framework that enables "Thinking with Long Videos" via interleaved Multimodal Chain-of-Tool-Thought. Specifically, we exploit LMMs' inherent temporal grounding ability as a native video cropping tool to zoom in on a specific video clip and resample finer-grained video frames. This global-to-local reasoning loop continues until answers are grounded in retrieved visual evidence. Given the scarcity of fine-grained question-answering (QA) data for the long video reasoning task, we curate and will release a data suite named VideoSIAH to facilitate both training and evaluation. Specifically, our training dataset consists of 247.9K samples for tool-integrated cold-start supervised fine-tuning, 1.6K samples for agentic reinforcement learning, and 15.4K samples for agentic reinforcement fine-tuning, respectively. Our evaluation benchmark consists of 1,280 QA pairs that are carefully curated through a semi-automatic data pipeline with human-in-the-loop validation. With a meticulously designed three-stage training strategy and extensive empirical validation, LongVT consistently outperforms existing strong baselines across four challenging long-video understanding and reasoning benchmarks. Our codes, data, and model checkpoints are publicly available at https://github.com/EvolvingLMMs-Lab/LongVT .
Read the full abstract

All authors Zuhao Yang, Sudong Wang, Kaichen Zhang, Keming Wu, Sicong Leng, Yifan Zhang, Bo Li, Chengwei Qin, Shijian Lu, Xingxuan Li, Lidong Bing

Computer Vision

One Patch is All You Need: Joint Surface Material Reconstruction and Classification from Minimal Visual Cues

Understanding material surfaces from sparse visual cues is critical for applications in robotics, simulation, and material perception. However, most existing methods rely on dense or full-scene observations, limiting their effectiveness in constrained or partial view environment. To address this challenge, we introduce SMARC, a unified model for Surface MAterial Reconstruction and Classification from minimal visual input. By giving only a single 10% contiguous patch of the image, SMARC recognizes and reconstructs the full RGB surface while simultaneously classifying the material category. Our architecture combines a Partial Convolutional U-Net with a classification head, enabling both spatial inpainting and semantic understanding under extreme observation sparsity. We compared SMARC against five models including convolutional autoencoders [17], Vision Transformer (ViT) [13], Masked Autoencoder (MAE) [5], Swin Transformer [9], and DETR [2] using Touch and Go dataset [16] of real-world surface textures. SMARC achieves state-of-the-art results with a PSNR of 17.55 dB and a material classification accuracy of 85.10%. Our findings highlight the advantages of partial convolution in spatial reasoning under missing data and establish a strong foundation for minimal-vision surface understanding.
Read the full abstract

All authors Sindhuja Penchala, Gavin Money, Gabriel Marques, Samuel Wood, Jessica Kirschman, Travis Atkison, Shahram Rahimi, Noorbakhsh Amiri Golilarz

Computer Vision · Cross-listed from cs.LG

CHiQPM: Calibrated Hierarchical Interpretable Image Classification

Globally interpretable models are a promising approach for trustworthy AI in safety-critical domains. Alongside global explanations, detailed local explanations are a crucial complement to effectively support human experts during inference. This work proposes the Calibrated Hierarchical QPM (CHiQPM) which offers uniquely comprehensive global and local interpretability, paving the way for human-AI complementarity. CHiQPM achieves superior global interpretability by contrastively explaining the majority of classes and offers novel hierarchical explanations that are more similar to how humans reason and can be traversed to offer a built-in interpretable Conformal prediction (CP) method. Our comprehensive evaluation shows that CHiQPM achieves state-of-the-art accuracy as a point predictor, maintaining 99% accuracy of non-interpretable models. This demonstrates a substantial improvement, where interpretability is incorporated without sacrificing overall accuracy. Furthermore, its calibrated set prediction is competitively efficient to other CP methods, while providing interpretable predictions of coherent sets along its hierarchical explanation.
Read the full abstract

All authors Thomas Norrenbrock, Timo Kaiser, Sovan Biswas, Neslihan Kose, Ramesh Manuvinakurike, Bodo Rosenhahn

Computer Vision

Text-Guided Semantic Image Encoder

Image encoders, a fundamental component of vision-language models (VLMs), are typically pretrained independently before being aligned with a language model. This standard paradigm results in encoders that process images agnostically, without regard to the specific downstream task or text query. To address this limitation, we propose the Text-Guided Semantic Image Encoder (TIE), which generates image representations conditioned on the input text query. VLMs equipped with TIE outperform their conventional counterparts by +1.5 and +1.3 points on average across nine image-to-text benchmarks at the 1B and 3B scales, respectively, with gains reaching up to 6 points on tasks such as DocVQA and InfoVQA. Moreover, TIE-based VLMs attain superior performance while utilizing only half as many image tiles (tokens), resulting in notably improved inference efficiency. TIE also generalizes well with generic queries, indicating that text-conditioned training effectively optimizes the encoder to capture key visual features. Qualitative analysis confirms that TIE consistently attends to query-relevant regions, enhancing both interpretability and query-specific grounding.
Read the full abstract

All authors Raghuveer Thirukovalluru, Xiaochuang Han, Bhuwan Dhingra, Emily Dinan, Maha Elbayad

Computer Vision

CANVAS: A Benchmark for Vision-Language Models on Tool-Based User Interface Design

User interface (UI) design is an iterative process in which designers progressively refine their work with design software such as Figma or Sketch. Recent advances in vision language models (VLMs) with tool invocation suggest these models can operate design software to edit a UI design through iteration. Understanding and enhancing this capacity is important, as it highlights VLMs' potential to collaborate with designers within conventional software. However, as no existing benchmark evaluates tool-based design performance, the capacity remains unknown. To address this, we introduce CANVAS, a benchmark for VLMs on tool-based user interface design. Our benchmark contains 598 tool-based design tasks paired with ground-truth references sampled from 3.3K mobile UI designs across 30 function-based categories (e.g., onboarding, messaging). In each task, a VLM updates the design step-by-step through context-based tool invocations (e.g., create a rectangle as a button background), linked to design software. Specifically, CANVAS incorporates two task types: (i) design replication evaluates the ability to reproduce a whole UI screen; (ii) design modification evaluates the ability to modify a specific part of an existing screen. Results suggest that leading models exhibit more strategic tool invocations, improving design quality. Furthermore, we identify common error patterns models exhibit, guiding future work in enhancing tool-based design capabilities.
Read the full abstract

All authors Daeheon Jeong, Seoyeon Byun, Kihoon Son, Dae Hyun Kim, Juho Kim

Computer Vision · Cross-listed from q-bio.QM

Automated Histopathologic Assessment of Hirschsprung Disease Using a Multi-Stage Vision Transformer Framework

Hirschsprung Disease is characterized by the absence of ganglion cells in the myenteric plexus. Therefore, the correct identification of ganglion cells is crucial for diagnosing Hirschsprung disease. We introduce a three-stage analysis framework that mimics the pathologist's diagnostic approach. The framework, based on a Vision Transformer model (ViT-B/16), sequentially segments the muscularis propria, segments the myenteric plexus, and detects ganglion cells within anatomically valid regions. 30 whole-slide images of colon tissue were used, each containing manual annotations of muscularis, plexus, and ganglion cells. A 5-fold cross-validation scheme was applied to each stage, along with resolution-specific tiling strategies and tailored postprocessing to ensure anatomical consistency. The proposed method achieved a Dice coefficient of 89.9% and a Plexus Inclusion Rate of 100% for muscularis segmentation. Plexus segmentation reached a recall of 94.8%, a precision of 84.2% and a Ganglia Inclusion Rate of 99.7%. For ganglion cells annotated with high certainty, the model achieved 62.1% precision and 89.1% recall. When considering all annotated ganglion cells, regardless of certainty level, the overall precision was 67.0%. These results indicate that ViT-based models are effective at leveraging global tissue context and capturing cellular morphology at small scales, even within complex histological tissue structures. This multi-stage methodology has great potential to support digital pathology workflows by reducing inter-observer variability and assisting in the evaluation of Hirschsprung disease. The clinical impact will be evaluated in future work with larger multi-center datasets and additional expert annotations.
Read the full abstract

All authors Youssef Megahed, Saleh Abou-Alwan, Anthony Fuller, Dina El Demellawy, Steven Hawken, Adrian D. C. Chan

Computer Vision · Cross-listed from cs.MM

Prompt-Aware Adaptive Elastic Weight Consolidation for Continual Learning in Medical Vision-Language Models

Medical AI systems face catastrophic forgetting when deployed in clinical settings, where models must learn new imaging protocols while retaining prior diagnostic capabilities. This challenge is particularly acute for medical vision-language models that must preserve complex cross-modal alignments between medical images and clinical terminology across diverse imaging modalities. We introduce Prompt- Aware Adaptive Elastic Weight Consolidation (PA-EWC), a novel continual learning approach that addresses catastrophic forgetting through prompt-guided parameter specialization. Our method systematically categorizes model parameters based on their functional roles in processing visual-descriptive, spatial-guided, and medical-semantic information, enabling targeted protection of critical knowledge while allowing adaptation to new clinical requirements. PA-EWC incorporates adaptive Fisher Information computation with gradient stability analysis and develops weighted complexity metrics based on medical terminology density. We evaluate our approach across five medical imaging datasets (Kvasir-SEG, ISIC 2018, CheXlocalize, BUSI, CAMUS) representing diverse modalities including endoscopy, dermoscopy, radiography, and ultrasound. Experimental results demonstrate that PA-EWC reduces catastrophic forgetting by up to 17.58% compared to baseline methods, with performance improvements of 4.30% on chest X-ray pathology localization and 6.06% on polyp segmentation.
Read the full abstract

Computer Vision

DinoLizer: Separating VAE and Diffusion Artifacts in Generative Inpainting Localization

We introduce DinoLizer, a DINOv2-based localizer of manipulated areas in generative inpainting. The model is trained to focus on semantically altered regions by treating reconstructed areas outside the inpainted mask as a separate class, which yields significant improvements w.r.t. the conven- tional approach. We train the model with LORA on the Query and Value of the transformer blocks and simply add 1 linear layer on top of the backbone to predict manipulations on a 14 x 14 patch resolution. Because DINOv2 only accepts fixed- sized images, we use a sliding window approach to aggregate the predictions on larger images. Empirical results show that DinoLizer outperforms state-of-the-art methods on our proposed dataset and SOTA inpainting datasets. Furthermore, it is very robust to JPEG (double) compression. On average, DinoLizer achieves a 20% higher Intersection over Union score compared to the second best model. The code is publicly available here: https://github.com/anonyme610/dinolizer.
Read the full abstract

All authors Minh Thong Doi, Vincent Itier, Jan Butora, Jérémie Boulanger, Patrick Bas

Computer Vision

Foundry: Distilling 3D Foundation Models for the Edge

Foundation models pre-trained with self-supervised learning (SSL) on large-scale datasets have become powerful general-purpose feature extractors. However, their immense size and computational cost make them prohibitive for deployment on edge devices such as robots and AR/VR headsets. Existing compression techniques like standard knowledge distillation create efficient 'specialist' models but sacrifice the crucial, downstream-agnostic generality that makes foundation models so valuable. In this paper, we introduce Foundation Model Distillation (FMD), a new paradigm for compressing large SSL models into compact, efficient, and faithful proxies that retain their general-purpose representational power. We present Foundry, the first implementation of FMD for 3D point clouds. Our approach, Foundry, trains a student to learn a compressed set of SuperTokens that reconstruct the teacher's token-level representations, capturing a compact basis of its latent space. A single distilled model maintains strong transferability across diverse downstream tasks-classification, part segmentation, and few-shot scenarios-approaching full foundation-model performance while using significantly fewer tokens and FLOPs, making such models more practical for deployment on resourceconstrained hardware.
Read the full abstract

All authors Guillaume Letellier, Siddharth Srivastava, Frédéric Jurie, Gaurav Sharma

Computer Vision

DeeAD: Dynamic Early Exit of Vision-Language Action for Efficient Autonomous Driving

Vision-Language Action (VLA) models unify perception, reasoning, and trajectory generation for autonomous driving, but suffer from significant inference latency due to deep transformer stacks. We present DeeAD, a training-free, action-guided early-exit framework that accelerates VLA planning by evaluating the physical feasibility of intermediate trajectories. Instead of relying on confidence scores, DeeAD terminates inference when predicted trajectories align with lightweight planning priors (e.g., Navigation or Low-precision Planning) within a tolerable deviation (<2m). To improve efficiency, we introduce a multi-hop controller that adaptively skips redundant layers based on the change rate of scores. DeeAD integrates into existing VLA models, such as ORION, without requiring retraining. Experiments on the Bench2Drive benchmark demonstrate up to 28% transformer-layer sparsity and 29% latency reduction, while preserving planning quality and safety.
Read the full abstract

All authors Haibo HU, Lianming Huang, Nan Guan, Chun Jason Xue

Computer Vision

Video Object Recognition in Mobile Edge Networks: Local Tracking or Edge Detection?

Fast and accurate video object recognition, which relies on frame-by-frame video analytics, remains a challenge for resource-constrained devices such as traffic cameras. Recent advances in mobile edge computing have made it possible to offload computation-intensive object detection to edge servers equipped with high-accuracy neural networks, while lightweight and fast object tracking algorithms run locally on devices. This hybrid approach offers a promising solution but introduces a new challenge: deciding when to perform edge detection versus local tracking. To address this, we formulate two long-term optimization problems for both single-device and multi-device scenarios, taking into account the temporal correlation of consecutive frames and the dynamic conditions of mobile edge networks. Based on the formulation, we propose the LTED-Ada in single-device setting, a deep reinforcement learning-based algorithm that adaptively selects between local tracking and edge detection, according to the frame rate as well as recognition accuracy and delay requirement. In multi-device setting, we further enhance LTED-Ada using federated learning to enable collaborative policy training across devices, thereby improving its generalization to unseen frame rates and performance requirements. Finally, we conduct extensive hardware-in-the-loop experiments using multiple Raspberry Pi 4B devices and a personal computer as the edge server, demonstrating the superiority of LTED-Ada.
Read the full abstract

All authors Kun Guo, Yun Shen, Xijun Wang, Chaoqun You, Yun Rui, Tony Q. S. Quek

Computer Vision

Inferix: A Block-Diffusion based Next-Generation Inference Engine for World Simulation

World models serve as core simulators for fields such as agentic AI, embodied AI, and gaming, capable of generating long, physically realistic, and interactive high-quality videos. Moreover, scaling these models could unlock emergent capabilities in visual perception, understanding, and reasoning, paving the way for a new paradigm that moves beyond current LLM-centric vision foundation models. A key breakthrough empowering them is the semi-autoregressive (block-diffusion) decoding paradigm, which merges the strengths of diffusion and autoregressive methods by generating video tokens in block-applying diffusion within each block while conditioning on previous ones, resulting in more coherent and stable video sequences. Crucially, it overcomes limitations of standard video diffusion by reintroducing LLM-style KV Cache management, enabling efficient, variable-length, and high-quality generation. Therefore, Inferix is specifically designed as a next-generation inference engine to enable immersive world synthesis through optimized semi-autoregressive decoding processes. This dedicated focus on world simulation distinctly sets it apart from systems engineered for high-concurrency scenarios (like vLLM or SGLang) and from classic video diffusion models (such as xDiTs). Inferix further enhances its offering with interactive video streaming and profiling, enabling real-time interaction and realistic simulation to accurately model world dynamics. Additionally, it supports efficient benchmarking through seamless integration of LV-Bench, a new fine-grained evaluation benchmark tailored for minute-long video generation scenarios. We hope the community will work together to advance Inferix and foster world model exploration.
Read the full abstract

All authors Inferix Team: Tianyu Feng, Yizeng Han, Jiahao He, Yuanyu He, Xi Lin, Teng Liu, Hanfeng Lu, Jiasheng Tang, Wei Wang, Zhiyuan Wang, Jichao Wu, Mingyang Yang, Yinghao Yu, Zeyu Zhang, Bohan Zhuang

Computer Vision

RubricRL: Simple Generalizable Rewards for Text-to-Image Generation

Reinforcement learning (RL) has recently emerged as a promising approach for aligning text-to-image generative models with human preferences. A key challenge, however, lies in designing effective and interpretable rewards. Existing methods often rely on either composite metrics (e.g., CLIP, OCR, and realism scores) with fixed weights or a single scalar reward distilled from human preference models, which can limit interpretability and flexibility. We propose RubricRL, a simple and general framework for rubric-based reward design that offers greater interpretability, composability, and user control. Instead of using a black-box scalar signal, RubricRL dynamically constructs a structured rubric for each prompt–a decomposable checklist of fine-grained visual criteria such as object correctness, attribute accuracy, OCR fidelity, and realism–tailored to the input text. Each criterion is independently evaluated by a multimodal judge (e.g., o4-mini), and a prompt-adaptive weighting mechanism emphasizes the most relevant dimensions. This design not only produces interpretable and modular supervision signals for policy optimization (e.g., GRPO or PPO), but also enables users to directly adjust which aspects to reward or penalize. Experiments with an autoregressive text-to-image model demonstrate that RubricRL improves prompt faithfulness, visual detail, and generalizability, while offering a flexible and extensible foundation for interpretable RL alignment across text-to-image architectures.
Read the full abstract

All authors Xuelu Feng, Yunsheng Li, Ziyu Wan, Zixuan Gao, Junsong Yuan, Dongdong Chen, Chunming Qiao

Computer Vision

MedROV: Towards Real-Time Open-Vocabulary Detection Across Diverse Medical Imaging Modalities

Traditional object detection models in medical imaging operate within a closed-set paradigm, limiting their ability to detect objects of novel labels. Open-vocabulary object detection (OVOD) addresses this limitation but remains underexplored in medical imaging due to dataset scarcity and weak text-image alignment. To bridge this gap, we introduce MedROV, the first Real-time Open Vocabulary detection model for medical imaging. To enable open-vocabulary learning, we curate a large-scale dataset, Omnis, with 600K detection samples across nine imaging modalities and introduce a pseudo-labeling strategy to handle missing annotations from multi-source datasets. Additionally, we enhance generalization by incorporating knowledge from a large pre-trained foundation model. By leveraging contrastive learning and cross-modal representations, MedROV effectively detects both known and novel structures. Experimental results demonstrate that MedROV outperforms the previous state-of-the-art foundation model for medical image detection with an average absolute improvement of 40 mAP50, and surpasses closed-set detectors by more than 3 mAP50, while running at 70 FPS, setting a new benchmark in medical detection. Our source code, dataset, and trained model are available at https://github.com/toobatehreem/MedROV.
Read the full abstract

All authors Tooba Tehreem Sheikh, Jean Lahoud, Rao Muhammad Anwer, Fahad Shahbaz Khan, Salman Khan, Hisham Cholakkal

Computer Vision

Infinity-RoPE: Action-Controllable Infinite Video Generation Emerges From Autoregressive Self-Rollout

Current autoregressive video diffusion models are constrained by three core bottlenecks: (i) the finite temporal horizon imposed by the base model's 3D Rotary Positional Embedding (3D-RoPE), (ii) slow prompt responsiveness in maintaining fine-grained action control during long-form rollouts, and (iii) the inability to realize discontinuous cinematic transitions within a single generation stream. We introduce $\infty$-RoPE, a unified inference-time framework that addresses all three limitations through three interconnected components: Block-Relativistic RoPE, KV Flush, and RoPE Cut. Block-Relativistic RoPE reformulates temporal encoding as a moving local reference frame, where each newly generated latent block is rotated relative to the base model's maximum frame horizon while earlier blocks are rotated backward to preserve relative temporal geometry. This relativistic formulation eliminates fixed temporal positions, enabling continuous video generation far beyond the base positional limits. To obtain fine-grained action control without re-encoding, KV Flush renews the KV cache by retaining only two latent frames, the global sink and the last generated latent frame, thereby ensuring immediate prompt responsiveness. Finally, RoPE Cut introduces controlled discontinuities in temporal RoPE coordinates, enabling multi-cut scene transitions within a single continuous rollout. Together, these components establish $\infty$-RoPE as a training-free foundation for infinite-horizon, controllable, and cinematic video diffusion. Comprehensive experiments show that $\infty$-RoPE consistently surpasses previous autoregressive models in overall VBench scores.
Read the full abstract

All authors Hidir Yesiltepe, Tuna Han Salih Meral, Adil Kaan Akan, Kaan Oktay, Pinar Yanardag

Computer Vision

LocateAnything3D: Vision-Language 3D Detection with Chain-of-Sight

To act in the world, a model must name what it sees and know where it is in 3D. Today's vision-language models (VLMs) excel at open-ended 2D description and grounding, yet multi-object 3D detection remains largely missing from the VLM toolbox. We present LocateAnything3D, a VLM-native recipe that casts 3D detection as a next-token prediction problem. The key is a short, explicit Chain-of-Sight (CoS) sequence that mirrors how human reason from images: find an object in 2D, then infer its distance, size, and pose. The decoder first emits 2D detections as a visual chain-of-thought, then predicts 3D boxes under an easy-to-hard curriculum: across objects, a near-to-far order reduces early ambiguity and matches ego-centric utility; within each object, a center-from-camera, dimensions, and rotation factorization ranks information by stability and learnability. This VLM-native interface preserves open-vocabulary and visual-prompting capability without specialized heads. On the challenging Omni3D benchmark, our model achieves state-of-the-art results, with 38.90 AP_3D, surpassing the previous best by +13.98 absolute improvement even when the baseline is given ground-truth 2D boxes. It also generalizes zero-shot to held-out categories with strong robustness. By turning 3D detection into a disciplined next-token problem, LocateAnything3D offers a practical foundation for models to perceive in 3D.
Read the full abstract

All authors Yunze Man, Shihao Wang, Guowen Zhang, Johan Bjorck, Zhiqi Li, Liang-Yan Gui, Jim Fan, Jan Kautz, Yu-Xiong Wang, Zhiding Yu

Computer Vision

Diverse Video Generation with Determinantal Point Process-Guided Policy Optimization

While recent text-to-video (T2V) diffusion models have achieved impressive quality and prompt alignment, they often produce low-diversity outputs when sampling multiple videos from a single text prompt. We tackle this challenge by formulating it as a set-level policy optimization problem, with the goal of training a policy that can cover the diverse range of plausible outcomes for a given prompt. To address this, we introduce DPP-GRPO, a novel framework for diverse video generation that combines Determinantal Point Processes (DPPs) and Group Relative Policy Optimization (GRPO) theories to enforce explicit reward on diverse generations. Our objective turns diversity into an explicit signal by imposing diminishing returns on redundant samples (via DPP) while supplies groupwise feedback over candidate sets (via GRPO). Our framework is plug-and-play and model-agnostic, and encourages diverse generations across visual appearance, camera motions, and scene structure without sacrificing prompt fidelity or perceptual quality. We implement our method on WAN and CogVideoX, and show that our method consistently improves video diversity on state-of-the-art benchmarks such as VBench, VideoScore, and human preference studies. Moreover, we release our code and a new benchmark dataset of 30,000 diverse prompts to support future research.
Read the full abstract

Computer Vision

3D-Aware Multi-Task Learning with Cross-View Correlations for Dense Scene Understanding

This paper addresses the challenge of training a single network to jointly perform multiple dense prediction tasks, such as segmentation and depth estimation, i.e., multi-task learning (MTL). Current approaches mainly capture cross-task relations in the 2D image space, often leading to unstructured features lacking 3D-awareness. We argue that 3D-awareness is vital for modeling cross-task correlations essential for comprehensive scene understanding. We propose to address this problem by integrating correlations across views, i.e., cost volume, as geometric consistency in the MTL network. Specifically, we introduce a lightweight Cross-view Module (CvM), shared across tasks, to exchange information across views and capture cross-view correlations, integrated with a feature from MTL encoder for multi-task predictions. This module is architecture-agnostic and can be applied to both single and multi-view data. Extensive results on NYUv2 and PASCAL-Context demonstrate that our method effectively injects geometric consistency into existing MTL methods to improve performance.
Read the full abstract

All authors Xiaoye Wang, Chen Tang, Xiangyu Yue, Wei-Hong Li

Computer Vision

PixelDiT: Pixel Diffusion Transformers for Image Generation

Latent-space modeling has been the standard for Diffusion Transformers (DiTs). However, it relies on a two-stage pipeline where the pretrained autoencoder introduces lossy reconstruction, leading to error accumulation while hindering joint optimization. To address these issues, we propose PixelDiT, a single-stage, end-to-end model that eliminates the need for the autoencoder and learns the diffusion process directly in the pixel space. PixelDiT adopts a fully transformer-based architecture shaped by a dual-level design: a patch-level DiT that captures global semantics and a pixel-level DiT that refines texture details, enabling efficient training of a pixel-space diffusion model while preserving fine details. PixelDiT achieves 1.61 FID on ImageNet 256 and 1.81 FID on ImageNet 512, surpassing existing pixel generative models. We further extend PixelDiT to text-to-image generation and pretrain it at the 10242resolution in pixel space. It achieves 0.74 on GenEval and 83.5 on DPG-bench, approaching the best latent diffusion models. Code: https://github.com/NVlabs/PixelDiT
Read the full abstract

All authors Yongsheng Yu, Wei Xiong, Weili Nie, Yichen Sheng, Shiqiu Liu, Jiebo Luo

Computer Vision

Vision-Language Memory for Spatial Reasoning

Spatial reasoning is a critical capability for intelligent robots, yet current vision-language models (VLMs) still fall short of human-level performance in video-based spatial reasoning. This gap mainly stems from two challenges: a semantic-geometric misalignment that prevents consistent 3D understanding, and the absence of persistent memory to retain 3D representation and understanding across frames. To address these limitations, we present VLM$^2$, a Vision-Language Model with persistent Memory for spatial reasoning with a view-consistent, 3D-aware representation purely from 2D videos. Specifically, we incorporate a dual-memory module consisting of a working memory that operates as a sliding window to focus on immediate context, and an episodic memory that consolidates and stores critical information across frames. This design enables bounded and efficient spatial reasoning under a fixed computational cost. Extensive experiments on multiple benchmarks show that VLM$^2$ achieves state-of-the-art performance among video-based models, significantly advancing the frontier of visual-spatial intelligence.
Read the full abstract

All authors Zuntao Liu, Yi Du, Taimeng Fu, Shaoshu Su, Cherie Ho, Chen Wang

Computer Vision

Concept-Aware Batch Sampling Improves Language-Image Pretraining

What data should a vision-language model be trained on? To answer this question, many data curation efforts center on the quality of a dataset. However, most of these existing methods are (i) offline, i.e. they produce a static dataset from a set of predetermined filtering criteria, and (ii) concept-agnostic, i.e. they use model-based filters which induce additional data biases. In this work, we go beyond such offline, concept-agnostic methods and advocate for more flexible, task-adaptive online concept-based curation. Our first contribution is DataConcept, a collection of 128M web-crawled image-text pairs annotated with fine-grained details about their concept composition. Building on DataConcept, we introduce Concept-Aware Batch Sampling (CABS), a simple yet effective batch sampling framework that flexibly constructs batches on-the-fly based on specific target distributions. We propose two variants: (i) Diversity Maximization (CABS-DM) to curate batches with a broad coverage of available concepts, and (ii) Frequency Maximization (CABS-FM) to curate batches with high object multiplicity. Through extensive evaluations across 28 benchmarks, we demonstrate that our CABS method significantly benefits CLIP/SigLIP model classes and yields highly performant models. Overall, CABS represents a strong open-source alternative to proprietary online data curation algorithms, enabling practitioners to define custom concept distributions that optimize for specific downstream tasks.
Read the full abstract

All authors Adhiraj Ghosh, Vishaal Udandarao, Thao Nguyen, Matteo Farina, Mehdi Cherti, Jenia Jitsev, Sewoong Oh, Elisa Ricci, Ludwig Schmidt, Matthias Bethge

Computer Vision

Unleashing the Power of Vision-Language Models for Long-Tailed Multi-Label Visual Recognition

Long-tailed multi-label visual recognition poses a significant challenge, as images typically contain multiple labels with highly imbalanced class distributions, leading to biased models that favor head classes while underperforming on tail classes. Recent efforts have leveraged pre-trained vision-language models, such as CLIP, alongside long-tailed learning techniques to exploit rich visual-textual priors for improved performance. However, existing methods often derive semantic inter-class relationships directly from imbalanced datasets, resulting in unreliable correlations for tail classes due to data scarcity. Moreover, CLIP's zero-shot paradigm is optimized for single-label image-text matching, making it suboptimal for multi-label tasks. To address these issues, we propose the correlation adaptation prompt network (CAPNET), a novel end-to-end framework that explicitly models label correlations from CLIP's textual encoder. The framework incorporates a graph convolutional network for label-aware propagation and learnable soft prompts for refined embeddings. It utilizes a distribution-balanced Focal loss with class-aware re-weighting for optimized training under imbalance. Moreover, it improves generalization through test-time ensembling and realigns visual-textual modalities using parameter-efficient fine-tuning to avert overfitting on tail classes without compromising head class performance. Extensive experiments and ablation studies on benchmarks including VOC-LT, COCO-LT, and NUS-WIDE demonstrate that CAPNET achieves substantial improvements over state-of-the-art methods, validating its effectiveness for real-world long-tailed multi-label visual recognition.
Read the full abstract

All authors Wei Tang, Zuo-Zheng Wang, Kun Zhang, Tong Wei, Min-Ling Zhang