EPO: Entropy-regularized Policy Optimization for LLM Agents Reinforcement Learning

MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing

Quantile Advantage Estimation for Entropy-Safe Reasoning

LongLive: Real-time Interactive Long Video Generation

Combinatorial Creativity: A New Frontier in Generalization Abilities

Causal Spatio-Temporal Prediction: An Effective and Efficient Multi-Modal Approach

Hunyuan3D-Omni: A Unified Framework for Controllable Generation of 3D Assets

Seedream 4.0: Toward Next-generation Multimodal Image Generation

Tree Search for LLM Agent Reinforcement Learning

SciReasoner: Laying the Scientific Reasoning Ground Across Disciplines

MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resources

VCRL: Variance-based Curriculum Reinforcement Learning for Large Language Models

MultiEdit: Advancing Instruction-based Image Editing on Diverse and Challenging Tasks

BRISC: Annotated Dataset for Brain Tumor Segmentation and Classification with Swin-HAFNet

EmoBench-M: Benchmarking Emotional Intelligence for Multimodal Large Language Models

FDABench: A Benchmark for Data Agents on Analytical Queries over Heterogeneous Data

Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?

UniVerse-1: Unified Audio-Video Generation via Stitching of Experts

How Good are Foundation Models in Step-by-Step Embodied Reasoning?

SpikingBrain Technical Report: Spiking Brain-inspired Large Models

SAGE: A Realistic Benchmark for Semantic Understanding

WAVECLIP: Wavelet Tokenization for Adaptive-Resolution CLIP

EmbeddingGemma: Powerful and Lightweight Text Representations

Advancing Speech Understanding in Speech-Aware Language Models with GRPO

How Far are VLMs from Visual Spatial Intelligence? A Benchmark-Driven Perspective

SIM-CoT: Supervised Implicit Chain-of-Thought

SWE-QA: Can Language Models Answer Repository-level Code Questions?

Video models are zero-shot learners and reasoners

An N-Plus-1 GPT Agency for Critical Solution of Mechanical Engineering Analysis Problems

Memory-QA: Answering Recall Questions Based on Multimodal Memories

EPO: Entropy-regularized Policy Optimization for LLM Agents Reinforcement Learning

MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing

Quantile Advantage Estimation for Entropy-Safe Reasoning

LongLive: Real-time Interactive Long Video Generation

Combinatorial Creativity: A New Frontier in Generalization Abilities

Causal Spatio-Temporal Prediction: An Effective and Efficient Multi-Modal Approach

Hunyuan3D-Omni: A Unified Framework for Controllable Generation of 3D Assets

Seedream 4.0: Toward Next-generation Multimodal Image Generation

Tree Search for LLM Agent Reinforcement Learning

SciReasoner: Laying the Scientific Reasoning Ground Across Disciplines

MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resources

VCRL: Variance-based Curriculum Reinforcement Learning for Large Language Models

MultiEdit: Advancing Instruction-based Image Editing on Diverse and Challenging Tasks

BRISC: Annotated Dataset for Brain Tumor Segmentation and Classification with Swin-HAFNet

EmoBench-M: Benchmarking Emotional Intelligence for Multimodal Large Language Models

FDABench: A Benchmark for Data Agents on Analytical Queries over Heterogeneous Data

Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?

UniVerse-1: Unified Audio-Video Generation via Stitching of Experts

How Good are Foundation Models in Step-by-Step Embodied Reasoning?

SpikingBrain Technical Report: Spiking Brain-inspired Large Models

SAGE: A Realistic Benchmark for Semantic Understanding

WAVECLIP: Wavelet Tokenization for Adaptive-Resolution CLIP

EmbeddingGemma: Powerful and Lightweight Text Representations

Advancing Speech Understanding in Speech-Aware Language Models with GRPO

How Far are VLMs from Visual Spatial Intelligence? A Benchmark-Driven Perspective

SIM-CoT: Supervised Implicit Chain-of-Thought

SWE-QA: Can Language Models Answer Repository-level Code Questions?

Video models are zero-shot learners and reasoners

An N-Plus-1 GPT Agency for Critical Solution of Mechanical Engineering Analysis Problems

Memory-QA: Answering Recall Questions Based on Multimodal Memories