Key papers

• ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU (2026)
  Fan Jiang et al.
  17.73
• AREX: Towards a Recursively Self-Improving Agent for Deep Research (2026)
  Shuqi Lu et al.
  15.66
• AlayaWorld: Interactive Long-Horizon World Modeling -- Full Technical Report (2026)
  AlayaWorld Team et al.
  12.71
• AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities (2026)
  Zichen Ding et al.
  12.26
• Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing (2026)
  Xinjie Zhang et al.
  12.23
• Subliminal Clocks: Latent Time Modelling in Diffusion Language Models (2026)
  Maximo Eduardo Rulli et al.
  11.15
• AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents (2026)
  Kunlun Zhu et al.
  10.15
• Video Generation Models are General-Purpose Vision Learners (2026)
  Letian Wang et al.
  9.80
• AutoIndex: Learning Representation Programs for Retrieval (2026)
  Sam O'Nuallain et al.
  9.48
• ISO: An RLVR-Native Optimization Stack (2026)
  Hanqing Zhu et al.
  9.11
• Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning (2026)
  Jian Hu et al.
  9.11
• FilmBench: A Film-Grade Benchmark for Cinematic Video Generation (2026)
  Shengyi Wang et al.
  8.24
• AnyGroundBench: A Specialized-Domain Benchmark for Video Grounding in Vision-Language Models (2026)
  Rintaro Otsubo et al.
  7.98
• Understanding Reasoning from Pretraining to Post-Training (2026)
  Jingyan Shen et al.
  7.98
• NexForge: Scaling Agent Capabilities through Requirement-Driven Task Synthesis for LLMs (2026)
  Jiarong Zhao et al.
  7.96
• Boogu-Image-0.1: Boosting Open-Source Unified Multimodal Understanding and Generation (2026)
  Guoxuan Chen et al.
  7.85
• EduPanel: A Three-Agent LLM Judge for Teaching Videos -- Reliability, Complementarity, and Human Trust Calibration (2026)
  Jia-Kai Dong et al.
  7.37
• IDEAgent: Agentic Quality-Diversity Search for Research Idea Generation (2026)
  Varun Gumma et al.
  7.37
• DocOps: A Verifiable Benchmark for Autonomous Agents in Complex Document Operations (2026)
  Jiazhen Jiang et al.
  6.95
• A Controlled Study of Attention-Only Transformers (2026)
  Henry Ndubuaku et al.
  5.96
• Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Mode (2026)
  Nanbeige Lab et al.
  5.88
• Every Time I Hire a Linguist, Inference Costs Go Down: On Linguistic Rules as Effective Prompt Compressors (2026)
  Jianfei Ma et al.
  5.88
• RetailSMV: Exocentric vs. Egocentric Adaptation of Foundation Video World Models in Retail (2026)
  Amirreza Rouhi et al.
  5.49
• World Wide Models: Literary Tools for Cultural AI (2026)
  Nina Begus
  5.49
• Gemma 4 Technical Report (2026)
  Gemma Team et al.
  5.49
• Lost in Context: Addressing Context Anxiety in Large Language Models (2026)
  Ifueko Igbinedion et al.
  5.49
• NeuroCogMap Reveals Cognitive Organization of Large Language Models (2026)
  Zhongxiang Sun et al.
  5.01
• Where to Intervene? Benchmarking Fairness-Aware Learning on Differentially Private Synthetic Tabular Data (2026)
  Vin\'icius Gabriel Angelozzi et al.
  5.01
• 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.
  5.01
• MILP-Evo: Closed-Loop Fully Automatic Design of MILP Solvers (2026)
  Jinbiao Nie et al.
  5.01
• Mitigating Matthew Effect: Multi-Hypergraph Boosted Multi-Interest Self-Supervised Learning for Conversational Recommendation (2026)
  Yongsen Zheng et al.
  5.01
• Decoupled Pipeline with Proposal Reranking and Score Fusion for Positive-Unlabeled Marine Species Detection (2026)
  Robert James Brock et al.
  5.01
• Dual Adversarial Fine-tuning for Enhancing Robustness of Large Vision Language Model (2026)
  Sibo Wang et al.
  5.01
• CoGoal3D: Collaborative 3D Object Detection with 3D-Aware Fusion and Refinement (2026)
  Zhihao Yang et al.
  5.01
• PathAgentBench: Benchmarking Evidence-Seeking Vision-Language Models on Whole-Slide Pathology Image (2026)
  Dankai Liao et al.
  5.01
• The Geometry of Personality: Activation Steering with Jungian Cognitive Functions (2026)
  Liu Zai (University of Glasgow) et al.
  5.01
• One More Turn, Less Regret: A Regret-Based Multi-Turn Benchmark for LLMs' Clarification Policies (2026)
  Minh Ngoc Ta et al.
  5.01
• Control panels to clarify user intent with Large Language Models (2026)
  Ben Shneiderman
  5.01
• Do VLMs Read or Rewrite? On Transcription Faithfulness in Vision-Language Models (2026)
  Gwang Gook Lee et al.
  5.01
• Adversarial Style Optimization: Enhancing VLM Jailbreaks by GRPO-based Stylistic Triggers Optimization (2026)
  Bingjun Luo et al.
  5.01
• Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems (2026)
  Xiaoyang Cao et al.
  5.01
• Ordered Action Tokens for Visuomotor Policy Learning (2026)
  Chaoqi Liu et al.
  5.01
• Pixels for Programs? A Cross-Provider Case Study of Input-Token Accounting for Source Code as Text and Images (2026)
  Ronak Bhalgami
  5.01
• Prior laundering: learned priors with inherited, undetectable overconfidence (2026)
  Ali Siahkoohi et al.
  5.01
• Probing Latent Colombian Identity Inferences in Qwen2.5-7B with Natural Language Autoencoders (2026)
  Pablo Santiago Potes Velasco et al.
  5.01
• From Seasonality to Semantics: Benchmarking a Hybrid Probabilistic Forecasting System for Roadblocks in Bolivia (2026)
  Rodrigo Vargas Sainz et al.
  5.01
• Data Quality over Capacity: Internalizing Documents into LoRA Adapters for Closed-Book QA (2026)
  Joan Figuerola Hurtado
  5.01
• Efficient Online LLM Watermark Detection via Rao-Blackwellized E-Processes (2026)
  Lu Luo et al.
  5.01
• Visual Saliency Steering Distillation for Multimodal Chain-of-Thought Reasoning (2026)
  Hao Yang et al.
  5.01
• Small Vision-Language Models Know When They Are Wrong But Cannot Say So: A Two-Model Study of Stated versus Internal Confidence Under Realistic Image Degradation (2026)
  M M Asif Ferdous
  5.01
• Benchmarking Fine-tuning and Retrieval Strategies for a Multimodal Language Model on the NRC Reactor Operator Licensing Examination (2026)
  Isak Hwang et al.
  5.01
• FSE: Continual Learning for Named Entity Recognition by Fast-Slow Experts (2026)
  Yunan Zhang et al.
  5.01
• Deconstructing Off-Policy Ratios: Entropy-Scaled Trust Regions for Asynchronous Reinforcement Learning (2026)
  Guanqun Zhao et al.
  5.01
• Filling Before Advancing: Capability-Gap-Driven Post-Training for Scenario-Specialized Remote Sensing MLLMs (2026)
  Yuheng Zong et al.
  5.01
• Simplex Demixing: Disentangling Multiple Light-Flavor Jets at Colliders (2026)
  Gregorio de la Fuente et al.
  5.01
• Comparing Large Language Models on Scrum Certification-Style Questions: Accuracy, Stability, and Error Patterns (2026)
  Robson Alves Vilar et al.
  4.39
• AI Native Games: A Survey and Roadmap (2026)
  Zhiyue Xu et al.
  4.39
• Multi-Label Node Classification with Label Influence Propagation (2026)
  Yifei Sun et al.
  4.39
• Sequentially-Controlled Interactive Multi-Particle Flow-Maps for Online Feedback-Driven Search (2026)
  Binglin Ji et al.
  4.39
• AI for Cultural Heritage Textiles: Fine-Tuned Latent Diffusion for Novel Ulos Motif Synthesis (2026)
  Humasak Tommy Argo Simanjuntak et al.
  4.39