Long-horizon robotic manipulation remains challenging for Vision-Language-Action (VLA) models despite recent progress in zero-shot generalization and simulation-to-real-world transfer. Current VLA models suffer from stage hallucination, where agents exploit coarse evaluation signals to shortcut multi-step tasks, reporting high progress without truly completing them. We present EvoVLA, a self-supervised VLA framework that addresses this issue through three complementary components: Stage-Aligned Reward (SAR), which uses triplet contrastive learning with Gemini-generated hard negatives to prevent visual shortcuts; Pose-Based Object Exploration (POE), which grounds curiosity in relative object-gripper pose instead of raw pixels; and Long-Horizon Memory, which uses selective context retention and gated fusion to stabilize intrinsic shaping during extended rollouts. Extensive evaluations on Discoverse-L, a long-horizon manipulation benchmark with three multi-stage tasks, show that EvoVLA improves average task success by 10.2 percentage points over the strongest baseline (OpenVLA-OFT), reaching 69.2 percent. EvoVLA also achieves one-and-a-half times better sample efficiency and reduces stage hallucination from 38.5 percent to 14.8 percent. Real-world deployment on physical robots reaches an average success rate of 54.6 percent across four manipulation tasks, outperforming OpenVLA-OFT by 11 points, demonstrating effective sim-to-real transfer and strong generalization. Code: https://github.com/AIGeeksGroup/EvoVLA. Website: https://aigeeksgroup.github.io/EvoVLA.
NavMorph: A Self-Evolving World Model for Vision-and-Language Navigation in Continuous Environments
State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA)(多模态人工智能系统国家重点实验室(MAIS)、自动化研究所、中国科学院(CASIA));School of Artificial Intelligence, University of Chinese Academy of Sciences (UCAS)(人工智能学院、中国科学院大学(UCAS));Peng Cheng Laboratory, ShenZhen, China(鹏城实验室、深圳中国)
Vision-R1: Evolving Human-Free Alignment in Large Vision-Language Models via Vision-Guided Reinforcement Learning
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);University of Chinese Academy of Sciences(中国科学院大学);Peng Cheng Laboratory(鹏城实验室);Wuhan AI Research(武汉人工智能研究院)
Active Zero: Self-Evolving Vision-Language Models through Active Environment Exploration
Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所基础模型研究中心);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);National University of Singapore(新加坡国立大学);Wuhan AI Research(武汉人工智能研究所);Tsinghua University(清华大学)
Two Sides of the Same Coin: Co-Evolving Search for Cross-Task Attacks on Vision-Language Models
College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算与数据科学学院);Center for Frontier AI Research, Agency for Science, Technology and Research (A*STAR)(新加坡科技研究局前沿人工智能研究中心);School of Electrical Engineering and Automation, Fuzhou University(福州大学电气工程与自动化学院);ByteDance(字节跳动)
Self-Evolving Spatial Reasoning in Vision Language Models via Geometric Logic Consistency
Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);The City University of New York(纽约城市大学);The Chinese University of Hong Kong(香港中文大学);Data61 CSIRO(Data61澳大利亚国家科学研究院);University of New South Wales(新南威尔士大学);Australian National University(澳大利亚国立大学)
MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data
University of Maryland(马里兰大学);Brown University(布朗大学);Washington University in St. Louis(圣路易斯华盛顿大学);Adobe;University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);University of Southern California(南加州大学);NVIDIA
VisPlay: Self-Evolving Vision-Language Models from Images
University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Washington University in St. Louis(华盛顿大学圣路易斯分校);University of Maryland(马里兰大学);National University of Singapore(新加坡国立大学)
Facial Affect Analysis for Service-Oriented Systems: Advances, Challenges, and Future Visions
International Hellenic University(国际希腊大学);Democritus University of Thrace(德谟克利特大学);Kingston University London(伦敦金斯顿大学);University of Western Macedonia(西马其顿大学)
AI can evolve without labels: self-evolving vision transformer for chest X-ray diagnosis through knowledge distillation
KAIST(韩国科学技术院);Asan Medical Center(峨山医学中心);University of Ulsan College of Medicine(蔚山大学医学院);Yeungnam University(岭南大学);Kyungpook National University(庆北国立大学);Seoul National University(首尔国立大学)
VICO: Visual Environments Co-Evolving for Vision-Language Model Reasoning
Virginia Tech(弗吉尼亚理工大学);Cisco(思科公司);NVIDIA(英伟达公司);UChicago(芝加哥大学);Georgia Tech(佐治亚理工学院);Abaka AI(Abaka人工智能公司);UC Berkeley(加州大学伯克利分校);UGA(佐治亚大学);WashU(华盛顿大学)
BayesTTA: Continual-Temporal Test-Time Adaptation for Vision-Language Models via Gaussian Discriminant Analysis
National Key Laboratory of Space Integrated Information System(国家空间信息集成系统重点实验室);Institute of Software Chinese Academy of Sciences(中国科学院软件研究所);University of Chinese Academy of Sciences(中国科学院大学);Wangxuan Institute of Computer Technology(计算机技术王轩研究所);Peking University(北京大学);Department of Computer Science and Technology(计算机科学与技术系);Tsinghua University(清华大学);Thrust of Artificial Intelligence, the Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州)人工智能方向);Department of Computer Science & Engineering, the Hong Kong University of Science and Technology(香港科技大学计算机科学与工程系)
ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environments
Center for Research on Intelligent Perception and Computing (CRIPAC), National Laboratory of Pattern Recognition (NLPR)(中国科学院大学未来技术学院、人工智能学院;模式识别国家重点实验室智能感知与计算研究中心);School of Future Technology and School of Artificial Intelligence, University of Chinese Academy of Sciences(北京理工大学);Beijing Institute of Technology(浙江大学);Zhejiang University(澳大利亚国立大学);Australian National University
SEKD: Self-Evolving Keypoint Detection and Description
A.I. Labs, Alibaba Group(阿里巴巴集团人工智能实验室);School of Computer Science and Engineering, Beihang University(北京航空航天大学计算机学院);School of Electronics Engineering and Computer Science, Peking University(北京大学电子工程与计算机科学学院)
Paying More Attention to Visual Tokens in Self-Evolving Large Multimodal Models
Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学);Aalto University(阿尔托大学);Australian National University(澳大利亚国立大学);Linköping University(林雪平大学)
AtlasVA: Self-Evolving Visual Skill Memory for Teacher-Free VLM Agents
Ant Group(蚂蚁集团);University of Science and Technology of China(中国科学技术大学);Westlake University(西湖大学);University of Michigan - Ann Arbor(密歇根大学-安娜堡分校);Sun Yat-sen University(中山大学)
OmniVL-Guard: Towards Unified Vision-Language Forgery Detection and Grounding via Balanced RL
School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China(合肥工业大学计算机科学与信息工程学院);Wuhan University, Wuhan, China(武汉大学);Lab for Intelligence and visiON (LION)(智能视觉实验室)
Dynamic Multimodal Evaluation with Flexible Complexity by Vision-Language Bootstrapping
School of Artificial Intelligence, Shanghai Jiao Tong University(上海交通大学人工智能学院);Shanghai AI Laboratory(上海人工智能实验室);Tongji University(同济大学);The University of Hong Kong(香港大学)
SynArtifact: Classifying and Alleviating Artifacts in Synthetic Images via Vision-Language Model
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);Beijing Academy of Artificial Intelligence(北京智源人工智能研究院);University of Oxford(牛津大学);YouTu Lab, Tencent(腾讯优图实验室)
Gemini vs GPT-4V: A Preliminary Comparison and Combination of Vision-Language Models Through Qualitative Cases
The University of Hong Kong(香港大学);Shanghai AI Laboratory(上海人工智能实验室);Fudan University(复旦大学);Zhejiang University(浙江大学);Shanghai Jiao Tong University(上海交通大学);The Chinese University of Hong Kong(香港中文大学);Nanyang Technological University(南洋理工大学)