Papers

• Model Merging in the Era of Large Language Models: Methods, Applications, and Future Directions

  Published on: 2026-03-10 2 authors
• DSH-Bench: A Difficulty- and Scenario-Aware Benchmark with Hierarchical Subject Taxonomy for Subject-Driven Text-to-Image Generation

  Published on: 2026-03-09 14 authors
• Model-based Offline RL via Robust Value-Aware Model Learning with Implicitly Differentiable Adaptive Weighting

  City University of Hong Kong, Hong Kong University of Science and Technology, University of Chicago

  Published on: 2026-03-09 6 authors
• FinToolBench: Evaluating LLM Agents for Real-World Financial Tool Use

  Hunan University, Shanghai AI Lab, Tongji University, Xiamen University

  Published on: 2026-03-09 12 authors
• M$^3$-ACE: Rectifying Visual Perception in Multimodal Math Reasoning via Multi-Agentic Context Engineering

  Harbin Institute of Technology

  Published on: 2026-03-09 4 authors
• This Looks Distinctly Like That: Grounding Interpretable Recognition in Stiefel Geometry against Neural Collapse

  Westlake University, Xi'an Jiaotong University

  Published on: 2026-03-09 7 authors
• SPIRAL: A Closed-Loop Framework for Self-Improving Action World Models via Reflective Planning Agents

  Chinese Academy of Sciences, Nanyang Technological University, National University of Singapore, Shanghai AI Lab, Zhejiang University

  Published on: 2026-03-09 13 authors
• Evaluating Generative Models via One-Dimensional Code Distributions

  Fudan University, Peking University

  Published on: 2026-03-09 5 authors
• EffectMaker: Unifying Reasoning and Generation for Customized Visual Effect Creation

  City University of Hong Kong

  Published on: 2026-03-06 6 authors
• Place-it-R1: Unlocking Environment-aware Reasoning Potential of MLLM for Video Object Insertion

  Hong Kong University of Science and Technology, Peking University

  Published on: 2026-03-06 8 authors
• FlashPrefill: Instantaneous Pattern Discovery and Thresholding for Ultra-Fast Long-Context Prefilling

  Chinese Academy of Sciences Institute of Automation

  Published on: 2026-03-06 6 authors
• Stem: Rethinking Causal Information Flow in Sparse Attention

  University of Science and Technology of China

  Published on: 2026-03-06 7 authors
• Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders

  Published on: 2026-03-06 8 authors
• Omni-Diffusion: Unified Multimodal Understanding and Generation with Masked Discrete Diffusion

  Chinese Academy of Sciences Institute of Automation, Nanjing University

  Published on: 2026-03-06 9 authors
• OneRanker: Unified Generation and Ranking with One Model in Industrial Advertising Recommendation

  Published on: 2026-03-03 1 author
• NOVA: Sparse Control, Dense Synthesis for Pair-Free Video Editing

  Nanjing University, The University of Hong Kong, University of Chinese Academy of Sciences

  Published on: 2026-03-03 1 author
• RubricBench: Aligning Model-Generated Rubrics with Human Standards

  University of Illinois Springfield

  Published on: 2026-03-02 1 author
• WorldStereo: Bridging Camera-Guided Video Generation and Scene Reconstruction via 3D Geometric Memorie

  Zhejiang University

  Published on: 2026-03-02 1 author
• AngelSlim: A more accessible, comprehensive, and efficient toolkit for large model compression

  Published on: 2026-02-26 1 author
• The Art of Efficient Reasoning: Data, Reward, and Optimization

  The University of Hong Kong

  Published on: 2026-02-25 1 author
• Haitao Lin

  Fudan University

  Published on: 2026-02-23 1 author
• HyTRec: A Hybrid Temporal-Aware Attention Architecture for Long Behavior Sequential Recommendation

  Wuhan University

  Published on: 2026-02-20 1 author
• GUI-GENESIS: Automated Synthesis of Efficient Environments with Verifiable Rewards for GUI Agent Post-Training

  Peking University

  Published on: 2026-02-15 1 author
• OmniVideo-R1: Reinforcing Audio-visual Reasoning with Query Intention and Modality Attention

  Hunan University, National University of Singapore, The Chinese University of Hong Kong, Tsinghua University, Xi'an Jiaotong University

  Published on: 2026-02-15 1 author
• Gradients Must Earn Their Influence: Unifying SFT with Generalized Entropic Objectives

  Harbin Institute of Technology

  Published on: 2026-02-11 1 author
• MotionCrafter: Dense Geometry and Motion Reconstruction with a 4D VAE

  Monash University

  Published on: 2026-02-09 1 author
• RISE-Video: Can Video Generators Decode Implicit World Rules?

  Shanghai Jiao Tong University

  Published on: 2026-02-05 1 author
• BlossomRec: Block-level Fused Sparse Attention Mechanism for Sequential Recommendations

  City University of Hong Kong

  Published on: 2026-02-03 1 author
• ReMiT: RL-Guided Mid-Training for Iterative LLM Evolution

  Shanghai Jiao Tong University

  Published on: 2026-02-03 1 author
• HY3D-Bench: Generation of 3D Assets

  Published on: 2026-02-03 1 author
• Small Generalizable Prompt Predictive Models Can Steer Efficient RL Post-Training of Large Reasoning Models

  Tsinghua University

  Published on: 2026-02-02 11 authors
• HunyuanImage 3.0 Technical Report

  Published on: 2026-02-02 1 author
• MAIN-VLA: Modeling Abstraction of Intention and eNvironment for Vision-Language-Action Models

  University of Science and Technology of China, Zhejiang University

  Published on: 2026-02-02 1 author
• AlignGemini: Generalizable AI-Generated Image Detection Through Task-Model Alignment

  East China University of Science and Technology, Hong Kong University of Science and Technology, Shenzhen University

  Published on: 2026-01-30 1 author
• PI-Light: Physics-Inspired Diffusion for Full-Image Relighting

  Nanyang Technological University

  Published on: 2026-01-29 1 author
• Youtu-Parsing: Perception, Structuring and Recognition via High-Parallelism Decoding

  Published on: 2026-01-28 1 author
• Youtu-VL: Unleashing Visual Potential via Unified Vision-Language Supervision

  Published on: 2026-01-27 1 author
• RISER: Orchestrating Latent Reasoning Skills for Adaptive Activation Steering

  Tongji University

  Published on: 2026-01-19 1 author
• FinVault: Benchmarking Financial Agent Safety in Execution-Grounded Environments

  Singapore University of Technology and Design

  Published on: 2026-01-09 1 author
• UniFinEval: Towards Unified Evaluation of Financial Multimodal Models across Text, Images and Videos

  Shanghai University of Finance and Economics

  Published on: 2026-01-09 1 author
• Rotate Your Character: Revisiting Video Diffusion Models for High-Quality 3D Character Generation

  The University of Hong Kong

  Published on: 2026-01-09 1 author
• One Language-Free Foundation Model Is Enough for Universal Vision Anomaly Detection

  Published on: 2026-01-09 1 author
• DocDancer: Towards Agentic Document-Grounded Information Seeking

  Peking University

  Published on: 2026-01-08 1 author
• Re-Align: Structured Reasoning-guided Alignment for In-Context Image Generation and Editing

  Institute of Information Engineering

  Published on: 2026-01-08 1 author
• FOREVER: Forgetting Curve-Inspired Memory Replay for Language Model Continual Learning

  The Hong Kong Polytechnic University

  Published on: 2026-01-07 1 author
• SmartSnap: Proactive Evidence Seeking for Self-Verifying Agents

  Peking University

  Published on: 2026-01-06 1 author
• A Versatile Multimodal Agent for Multimedia Content Generation

  University of Rochester

  Published on: 2026-01-06 1 author
• Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models

  Published on: 2026-01-05 1 author
• YOLO-Master: MOE-Accelerated with Specialized Transformers for Enhanced Real-time Detection

  Singapore Management University

  Published on: 2025-12-30 1 author
• HY-MT1.5 Technical Report

  Published on: 2025-12-30 1 author