cs.CV · 2026-05-30 · No. 12

Computer Vision and Pattern Recognition, 2026-05-30.

16 new papers in cs.CV. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

16 entries
  1. 01

    VideoMLA: Low-Rank Latent KV Cache for Minute-Scale Autoregressive Video Diffusion

    Hidir Yesiltepe, Jiazhen Hu, Tuna Han Salih Meral, Adil Kaan Akan, Kaan Oktay, Hoda Eldardiry, Pinar Yanardag

    cs.CV · cs.AI

    Long-rollout causal video diffusion has converged on a fixed-size sliding-window KV cache, with recent progress innovating within this layout by changing which tokens occupy the window or how their positions are encoded. The per-head KV layout itself, a dominant contributor to streaming memory and latency, has been mostly left unchanged. In this paper, we present the first study of Multi-Head Latent Attention (MLA) in video diffusion....

    arxiv.org/abs/2605.30351 · PDF

  2. 02

    GPIC: A Giant Permissive Image Corpus for Visual Generation

    Keshigeyan Chandrasegaran, Kyle Sargent, Suchir Agarwal, Michael Jang, Michael Poli, Juan Carlos Niebles, Justin...

    cs.CV · cs.AI

    Studying scalable methods for visual generative modeling requires large, accessible, and stable datasets. We introduce GPIC, a Giant Permissive Image Corpus of approximately 28 trillion pixels. GPIC comprises diverse internet images captioned by a state-of-the-art vision-language model, including 100M training, 200K validation, and 1M test examples. Moreover, all GPIC images are permissively licensed for both research and commercial use. GPIC...

    arxiv.org/abs/2605.30341 · PDF

  3. 03

    Archon: A Unified Multimodal Model for Holistic Digital Human Generation

    Chong Bao, Shichen Liu, Lijun Yu, David Futschik, Stylianos Moschoglou, Shefali Srivastava, Ziqian Bai, Feitong Tan,...

    cs.CV · cs.AI

    Digital humans are fundamental to immersive interaction, yet creating a unified model for holistic modalities, including text, audio, motion, and visual content, remains an open challenge. In this paper, we present Archon, a fully pretrained, human-centric unified multimodal model for holistic avatar generation. Archon unifies seven modalities with modality-specific tokenizers, and a native autoregressive unified multimodal model pretrained...

    arxiv.org/abs/2605.30311 · PDF

  4. 04

    City-Mesh3R: Simulation-Ready City-Scale 3D Mesh Reconstruction from Multi-View Images

    Sayan Paul, Sourav Ghosh, Siddharth Katageri, Soumyadip Maity, Sanjana Sinha, Brojeshwar Bhowmick

    cs.CV · cs.AI · cs.GR

    City-scale 3D surface reconstruction from multiview images for downstream 3D simulation, poses highly challenging problems due to the scale and complexity of urban scenes. Existing city-scale 3D reconstruction methods based on NeRF, Gaussian Splatting etc. often fail to recover 3D meshes ready for simulation due to incomplete/missing geometry and irregular, noisy surfaces. Scaling existing small-scale 3D reconstruction methods to arbitrarily...

    arxiv.org/abs/2605.30310 · PDF

  5. 05

    PhyGenHOI: Physically-Aware 4D Generation of Dynamic Human-Object Interactions

    Omer Benishu, Gal Fiebelman, Sagie Benaim

    cs.CV · cs.AI

    We address the task of generating physically accurate and visually faithful 4D Human-Object Interaction (HOI). Given a static 3D human and target object represented as 3D Gaussian Splats (3DGS), our goal is to synthesize dynamic scenes where the human actively engages with the object through actions, such as punching or kicking, in accordance with a given input text. To this end, we introduce PhyGenHOI, a novel framework that couples...

    arxiv.org/abs/2605.30268 · PDF

  6. 06

    Reinforcement Learning with Robust Rubric Rewards

    Ya-Qi Yu, Hao Wang, Fangyu Hong, Xiangyang Qu, Gaojie Wu, Qiaoyu Luo, Nuo Xu, Huixin Wang, Wuheng Xu, Yongxin Liao,...

    cs.CV · cs.AI

    While Reinforcement Learning with Verifiable Rewards (RLVR) is effective for deterministically checkable tasks, many vision-language tasks are partially verifiable, demanding multi-criteria supervision (e.g., perceptual details, reasoning steps, and constraints). Rubrics provide a natural interface for this fine-grained supervision, but their effectiveness depends on the execution accuracy during online RL. We propose Reinforcement Learning...

    arxiv.org/abs/2605.30244 · PDF

  7. 07

    Beyond 3D VQAs: Injecting 3D Spatial Priors into Vision-Language Models for Enhanced Geometric Reasoning

    Chun-Hsiao Yeh, Shengyi Qian, Manchen Wang, Yi Ma, Joseph Tighe, Fanyi Xiao

    cs.CV · cs.AI

    Vision-Language Models (VLMs) often struggle with robust 3D spatial reasoning. Prevailing methods that rely on fine-tuning with 3D visual question-answering (VQA) datasets may overfit dataset-specific biases, while integrating specialized 3D visual encoders is often inflexible and cumbersome. In this paper, we argue that genuine spatial understanding should emerge from learning fundamental geometric priors, not only from high-level VQA...

    arxiv.org/abs/2605.30231 · PDF

  8. 08

    PARCEL: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language Understanding

    Selim Kuzucu, Alessio Tonioni, Vasile Lup, Bernt Schiele, Federico Tombari, Muhammad Ferjad Naeem

    cs.CV · cs.AI · cs.CL · cs.LG

    Large Vision-Language Models (LVLMs) map visual inputs into dense token sequences, imposing a quadratic computational bottleneck for inference. Elastic visual-token compression addresses this by training a single model that can run at multiple visual-token budgets. However, existing approaches struggle under aggressive compression. Spatial-only compression, as in nested pooling, behaves as an imperfect low-pass filter and induces spectral...

    arxiv.org/abs/2605.30126 · PDF

  9. 09

    SGMD: Score Gradient Matching Distillation for Few-Step Video Diffusion Distillation

    Zhuguanyu Wu, Ruihao Gong, Yang Yong, Yushi Huang, Xiangyu Fan, Lei Yang, Dahua Lin, Xianglong Liu

    cs.CV · cs.LG

    Distribution Matching Distillation (DMD) is a widely used paradigm for accelerating inference in few-step video diffusion models. However, DMD-style video distillation faces two coupled challenges: the fake score must track a continuously evolving generator, making training costly when frequent updates are required, while reverse-KL-style matching can be mode-seeking and conservative for preserving strong motion dynamics. To address these...

    arxiv.org/abs/2605.30116 · PDF

  10. 10

    xModel-KD: Cross-modal Knowledge Distillation for 3D Scene Perception using LiDAR

    Thenukan Pathmanathan, Kanchan Keisham, Thangarajah Akilan

    cs.CV · cs.AI

    Point cloud segmentation is a fundamental task in 3D scene understanding. Its progress is constrained by the high cost and time required for dense 3D annotations, making labeled samples difficult to obtain. Beyond annotation scarcity, different sensing modalities face inherent limitations. 2D images provide rich texture and appearance cues, yet they lack explicit depth and geometric structure. In contrast, 3D point clouds capture accurate...

    arxiv.org/abs/2605.30111 · PDF

  11. 11

    VisualThink-VLA: Visual Intermediate Reasoning for Effective and Low-Latency Vision-Language-Action Policies

    Mingjian Gao, Wenqiao Zhang, Yuqian Yuan, Yang Dai, Binhe Yu, Zheqi Lv, Haoyu Zheng, Jiaqi Zhu, Zhiqi Ge, Zixuan...

    cs.CV · cs.AI

    Recent work has begun to equip vision-language-action (VLA) policies with explicit intermediate reasoning. In embodied control, however, textual chain-of-thought is a poor fit: irrelevant or weakly textual information can interfere with action prediction, while autoregressive text decoding adds too much latency for real-time closed-loop execution. We present VISUALTHINK-VLA, a visual intermediate-reasoning framework for accurate, low-latency...

    arxiv.org/abs/2605.30011 · PDF

  12. 12

    Genetically Aligned Patient Representations Improve Hematological Diagnosis

    Muhammed Furkan Dasdelen, Fatih Ozlugedik, Ilaria Looser, Rao Muhammad Umer, Christian Pohlkamp, Carsten Marr

    cs.CV · cs.AI · cs.LG

    Multimodal alignment of histopathology encoders with transcriptomic and genomic data has been shown to significantly improve performance in downstream diagnostic tasks. Hematological cytology is unique in that visual single-cell evaluation is often paired with cytogenetics and molecular genetics for blood cancer diagnosis. In this study, we present a framework to align single white blood cell images with chromosomal aberrations (karyotype)...

    arxiv.org/abs/2605.29980 · PDF

  13. 13

    EVL-ECG: Efficient ECG Interpretation With Multi-Aspect Heterogeneous Knowledge Distillation

    Dang Hong Nguyen, Nhi Ngoc-Yen Nguyen, Huy-Hieu Pham

    cs.CV · cs.LG

    High-fidelity ECG interpretation is increasingly reliant on massive foundation models, yet their deployment in clinical edge-care remains hindered by extreme computational demands. While knowledge distillation (KD) is a promising solution, traditional methods fail to capture the complex spatio-temporal dependencies of ECG signals when transferring knowledge across heterogeneous architectures. In this paper, we propose EVL-ECG, a framework...

    arxiv.org/abs/2605.29977 · PDF

  14. 14

    CityGen: Structure-Guided City-Style Synthesis for Cross-City Autonomous Driving

    Zezhong Qian, Zhao Yang, Lu Tan, Zhihao Yan, Weiyi Hong, Haizhuang Liu, Yawei Jueluo

    cs.CV · cs.AI

    Autonomous driving systems are commonly trained and evaluated within limited geographic regions, which hinders their scalability when deployed in new cities. However, significant domain shifts in appearance, road topology, and traffic patterns often cause severe performance degradation under cross-city deployment. Existing approaches based on domain adaptation, data augmentation, or synthetic data generation typically rely on labeled target...

    arxiv.org/abs/2605.29935 · PDF

  15. 15

    Mitigating Hallucination in Vision-Language Models through Barrier-Regulated Adaptive Closed-form Steering

    Soumyadeep Jana, Pulkit Mittal, Sanasam Ranbir Singh

    cs.CV · cs.AI

    Large vision-language models (LVLMs) often hallucinate objects that are not present in the input image, largely because visual grounding weakens as decoding progresses. Existing inference-time mitigation methods modify logits or hidden states throughout generation, but they suffer from three key limitations: they lack an explicit grounding objective, intervene even when the model is already well-grounded, and use fixed correction strengths...

    arxiv.org/abs/2605.29881 · PDF

  16. 16

    Parameter-Efficient Subspace Decoupling ViT for Mitigating Multi-Task Negative Transfer in Histological Scoring

    Youhan Huang, Jiajun Li, Yilin Fang, Shuai Wang, Chuheng Li

    cs.CV · cs.LG · cs.MM

    Histological scoring is essential for diagnosing Non-Alcoholic Fatty Liver Disease (NAFLD), yet its automation remains challenging due to the high annotation cost and negative transfer among the strongly correlated NAFLD Activity Score (NAS) indicators in multi-task learning. To address this issue, we propose a subspace-decoupled multi-task Vision Transformer (ViT) that integrates lightweight task-specific Adapters with orthogonality-based...

    arxiv.org/abs/2605.29852 · PDF

This edition is part of The Daily Abstract — cs.CV archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.