Papers

• MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention

  1 author
• HER: Human-like Reasoning and Reinforcement Learning for LLM Role-playing

  Fudan University

  Published on: 2026-02-08 1 author
• What Does Vision Tool-Use Reinforcement Learning Really Learn? Disentangling Tool-Induced and Intrinsic Effects for Crop-and-Zoom

  Fudan University, Shanghai Jiao Tong University

  Published on: 2026-02-01 1 author
• OCTOBENCH: Benchmarking Scaffold-Aware Instruction Following in Repository-Grounded Agentic Coding

  Fudan University

  Published on: 2026-01-16 1 author
• Towards Scalable Pre-training of Visual Tokenizers for Generation

  Huazhong University of Science and Technology

  Published on: 2025-12-15 1 author
• ControlThinker: Unveiling Latent Semantics for Controllable Image Generation through Visual Reasoning

  Fudan University

  Published on: 2025-10-24 1 author
• WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents

  Hong Kong University of Science and Technology, University of Waterloo

  Published on: 2025-09-26 1 author
• Dynamic Parameter Memory: Temporary LoRA-Enhanced LLM for Long-Sequence Emotion Recognition in Conversation

  South China University of Technology

  Published on: 2025-09-24 1 author
• SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond

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

  Published on: 2025-05-26 1 author
• OmniGenBench: A Benchmark for Omnipotent Multimodal Generation across 50+ Tasks

  Fudan University

  Published on: 2025-05-24 1 author
• One RL to See Them All: Visual Triple Unified Reinforcement Learning

  Northwestern Polytechnical University, Shanghai Jiao Tong University

  Published on: 2025-05-23 1 author
• MiniMax-Speech: Intrinsic Zero-Shot Text-to-Speech with a Learnable Speaker Encoder

  Published on: 2025-05-12 1 author
• Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme

  Shanghai Jiao Tong University

  Published on: 2025-04-04 1 author
• MiniMax-01: Scaling Foundation Models with Lightning Attention

  Published on: 2025-01-14 1 author