Key papers

• ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU (2026)
  Fan Jiang et al.
  17.67
• Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents (2026)
  Hanzhang Zhou et al.
  15.56
• HiFi-UMI: Learning Deployable Manipulation Policies from High-Fidelity UMI Data Alone (2026)
  Simple AI et al.
  14.92
• JarvisHub: An Open Harness for Canvas-Native Multimodal Creative Agents (2026)
  Yunlong Lin et al.
  14.57
• ReDesign: Recovering Editable Design Structures from Images via Agentic Decomposition (2026)
  Jooyeol Yun et al.
  13.10
• StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents (2026)
  Yan Yang et al.
  12.91
• KnowAct-GUIClaw: Know Deeply, Act Perfectly, Personal GUI Assistant with Self-Evolving Memory and Skill (2026)
  Yunxin Li et al.
  12.06
• Data Pyramid for Embodied Manipulation (2026)
  Yifan Ye et al.
  11.91
• From Pixels to States: Rethinking Interactive World Models as Game Engines (2026)
  Zhen Li et al.
  11.64
• Wonder: Video World Model Done Better (2026)
  Jiacong Xu et al.
  9.78
• Shieldstral (2026)
  Antonia Calvi et al.
  9.12
• Hy-Embodied-VLM-1.0: Efficient Physical-World Agents (2026)
  Ziyi Wang et al.
  7.63
• LLM-Driven AutoML for Cross-Lingual Handwritten OCR: Closed-Loop Neural Architecture Search with GPT-5, GPT-4o, and Claude Sonnet 4 (2026)
  Mobina Kashaniyan et al.
  4.95
• Von Mises-Fisher Mixture Model with Dynamic Shrinkage for Realistic Test-Time Transduction (2026)
  Jiazhen Huang et al.
  4.95
• TAP-RAG: Task-Aware Policy Control for Long-Document Multimodal Question Answering (2026)
  Zhong Ji et al.
  4.95
• No Training, Better Flights: Test-Time Scaled VLMs for UAV Navigation (2026)
  Feinan Cheng et al.
  4.95
• PhysCoRe: Physics-Corrected Residual World Models for Material-Aware Deformable Dynamics (2026)
  Haocheng Yin et al.
  4.95
• Scale Up Strategically: Learning Compositional Generalization via Bias-Aware Evaluation and Data Collection for Robotic Manipulation (2026)
  Yu Qi et al.
  4.95
• Pixels for Programs? A Cross-Provider Case Study of Input-Token Accounting for Source Code as Text and Images (2026)
  Ronak Bhalgami
  4.95
• Filling Before Advancing: Capability-Gap-Driven Post-Training for Scenario-Specialized Remote Sensing MLLMs (2026)
  Yuheng Zong et al.
  4.95
• Robot-Factored World Models via Robot Rendering (2026)
  Byungjun Kim et al.
  4.95
• Cortex: Compact Behavior Cloning for Quake with Frozen Visual Features (2026)
  Dzmitry Malyshau
  4.95
• Speech2Grasp: Data-Efficient Transfer of Text-Conditioned Grasp Detection to Speech in Humanoid Robots (2026)
  Hung Nguyen et al.
  4.95
• Understanding Knowledge Transfer Mechanism in Heterogeneous MLLM Fusion: A Simple Linear Approach (2026)
  Yinghao Hou et al.
  4.95
• Progressive Multimodal Alignment for Continual Instruction Tuning (2026)
  Duzhen Zhang et al.
  4.95
• What Does Your Short-Answer VQA Score Actually Measure? Evaluator-Dependent Instability in Multimodal Short-Answer Benchmarks (2026)
  Guanhua Ye et al.
  4.33
• MM-ToolSandBox: A Unified Framework for Evaluating Visual Tool-Calling Agents (2026)
  Kaixin Ma et al.
  4.33
• Semantic Anchoring for Robotic Action Representations (2026)
  Yuan Xu et al.
  4.33
• Exploratory, Communicative, and Deployable: Vision-Driven Embodied Agents for Open-World Mobile Manipulation (2026)
  Boyu Mi et al.
  4.33
• EgoRecovery: Acquiring Failure Recovery Ability Through Human Recovery Demonstration (2026)
  Zuhao Ge et al.
  4.33
• Zero-Shot Mission-Level Evaluation for Aerial MLLM Agents (2026)
  Suman Navaratnarajah et al.
  4.33
• Child-Oriented AIGC Video Risk Reviewing: A Benchmark and Knowledge-Supported Iterative Reasoning Framework (2026)
  Lewen Mi et al.
  4.33
• CausalGate: Causal Importance Distillation for Transformer Module Pruning (2026)
  Kiran Nair et al.
  4.33
• Agentic Autoresearch for CT Reconstruction (2026)
  Andreas Maier et al.
  4.33
• Robustifying pathology foundation models via fine-tuning (2026)
  Alexandre Filiot et al.
  4.33
• Spatial-IQ: Deconstructing Spatial Intelligence via Hierarchical Capability Tests (2026)
  Patrick Rim et al.
  4.33
• Layering Virtual Try-On (2026)
  Chun Feng et al.
  4.33
• DispatchRAG: Grounding Emergency Dispatch Decisions in Real-World Protocols from Traffic Accident Video (2026)
  Muhammad Sulthan Adhipradhana et al.
  4.33
• Learning Sampling Parameters for Diffusion Models (2026)
  Arisrei Lim et al.
  4.33
• Markerless Motion Capture in Routine Clinical Upper Limb Assessments: Validity and Insights Beyond Ordinal Scoring (2026)
  Tim Unger et al.
  4.33
• LabRobFail: A Benchmark for Robotic Failure Analysis in Chemical Self-driving Laboratory (2026)
  Haobo Wang et al.
  4.33
• Source-Free Controlled Adaptation of Teachers for Continual Test-Time Adaptation (2026)
  Anurag Roy et al.
  4.33
• What Can I Edit? Open-Ended Strategy Discovery and the Emotion Editability Landscape (2026)
  Qing Li et al.
  4.33
• DeVA: Decoupled Video-Action Model with physical guidance for robot policy learning (2026)
  Mengqi Zhang et al.
  4.33
• Ambient pressure compensation and robust position control of oil-filled electric joint systems for underwater manipulators (2026)
  Hongrui Wu et al.
  4.33
• Mixture-of-Thought-Tokens: Unifying Perception and Reasoning for Free-form Multimodal Grounding (2026)
  Tianyi Gao et al.
  4.33
• Rethinking Expert Training for Model Merging with Prompt Learning (2026)
  Christos Georgakilas et al.
  4.33
• MMOE: Modernizing Diffusion Transformers with Efficient Expert Design (2026)
  Yanhao Jia et al.
  4.33
• Seen, Said, or Forgotten? A Causal Audit of Visual KV Memory Across Dialog Turns (2026)
  Hong Chen et al.
  4.33
• Agentic AI in medicine: architectures, applications, evaluation, and challenges for clinical translation (2026)
  Zheng Tong et al.
  4.33
• Beyond Counts: A Distributional Robustness Margin For Pathology Foundation Models (2026)
  Cl\'ement Grisi et al.
  4.33
• Evaluating VLMs for Autonomous Agent-Driven Geometry Clipping Detection in Video Game QA (2026)
  Carlos Celemin et al.
  4.33
• Lottery Tickets Are Not Deployment Tickets (2026)
  Bum Jun Kim
  4.33
• Thinking Once Is Enough: Intermediate-Layer Evidence Routing for High-Resolution VQA (2026)
  Zhongkuan Mao et al.
  4.33
• ViP-Rig: Visual-Prompted Controllable Rigging (2026)
  Zihan Qin et al.
  4.33
• OPLD: On-Policy Latent Distillation for Multimodal Reasoning (2026)
  Shoutai Zhu et al.
  4.33
• UniCross: Unified Cross-Skill Dexterous Manipulation Synthesis (2026)
  Hui Zhang et al.
  4.33
• When the Tool Decides: LLM Agents Defer Blindly to Graph Neural Network Tools, and Stronger Backbones Defer More (2026)
  Zhongyuan Wang et al.
  4.27
• Self-Aware Recursively Self-Improving Agents for Personal Singularity: A Goal-, Scope-, Tool-, and Benchmark-Driven Multi-Agent Architecture (2026)
  Chengshuai Yang
  3.45
• VanillaBench: The Hidden Accuracy Cost of Adversarial Robustness (2026)
  Niklas Bunzel
  3.45