Benchmark^2: Systematic Evaluation of LLM Benchmarks

MindWatcher: Toward Smarter Multimodal Tool-Integrated Reasoning

Entropy-Adaptive Fine-Tuning: Resolving Confident Conflicts to Mitigate Forgetting

Diversity or Precision? A Deep Dive into Next Token Prediction

Confucius Code Agent: Scalable Agent Scaffolding for Real-World Codebases

DreamStyle: A Unified Framework for Video Stylization

UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision

LTX-2: Efficient Joint Audio-Visual Foundation Model

SciEvalKit: An Open-source Evaluation Toolkit for Scientific General Intelligence

MOSS Transcribe Diarize: Accurate Transcription with Speaker Diarization

InfiniDepth: Arbitrary-Resolution and Fine-Grained Depth Estimation with Neural Implicit Fields

Adaptation of Agentic AI

Large Video Planner Enables Generalizable Robot Control

InfiniteVGGT: Visual Geometry Grounded Transformer for Endless Streams

GARDO: Reinforcing Diffusion Models without Reward Hacking

VAR RL Done Right: Tackling Asynchronous Policy Conflicts in Visual Autoregressive Generation

DreamID-V:Bridging the Image-to-Video Gap for High-Fidelity Face Swapping via Diffusion Transformer

NextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generation

K-EXAONE Technical Report

The Hunger Game Debate: On the Emergence of Over-Competition in Multi-Agent Systems

Training AI Co-Scientists Using Rubric Rewards

AdaGaR: Adaptive Gabor Representation for Dynamic Scene Reconstruction

Taming Hallucinations: Boosting MLLMs' Video Understanding via Counterfactual Video Generation

SenseNova-MARS: Empowering Multimodal Agentic Reasoning and Search via Reinforcement Learning

Avatar Forcing: Real-Time Interactive Head Avatar Generation for Natural Conversation

NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos

Youtu-Agent: Scaling Agent Productivity with Automated Generation and Hybrid Policy Optimization

IQuest-Coder-V1 Technical Report

Recursive Language Models

FlowBlending: Stage-Aware Multi-Model Sampling for Fast and High-Fidelity Video Generation

Benchmark^2: Systematic Evaluation of LLM Benchmarks

MindWatcher: Toward Smarter Multimodal Tool-Integrated Reasoning

Entropy-Adaptive Fine-Tuning: Resolving Confident Conflicts to Mitigate Forgetting

Diversity or Precision? A Deep Dive into Next Token Prediction

Confucius Code Agent: Scalable Agent Scaffolding for Real-World Codebases

DreamStyle: A Unified Framework for Video Stylization

UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision

LTX-2: Efficient Joint Audio-Visual Foundation Model

SciEvalKit: An Open-source Evaluation Toolkit for Scientific General Intelligence

MOSS Transcribe Diarize: Accurate Transcription with Speaker Diarization

InfiniDepth: Arbitrary-Resolution and Fine-Grained Depth Estimation with Neural Implicit Fields

Adaptation of Agentic AI

Large Video Planner Enables Generalizable Robot Control

InfiniteVGGT: Visual Geometry Grounded Transformer for Endless Streams

GARDO: Reinforcing Diffusion Models without Reward Hacking

VAR RL Done Right: Tackling Asynchronous Policy Conflicts in Visual Autoregressive Generation

DreamID-V:Bridging the Image-to-Video Gap for High-Fidelity Face Swapping via Diffusion Transformer

NextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generation

K-EXAONE Technical Report

The Hunger Game Debate: On the Emergence of Over-Competition in Multi-Agent Systems

Training AI Co-Scientists Using Rubric Rewards

AdaGaR: Adaptive Gabor Representation for Dynamic Scene Reconstruction

Taming Hallucinations: Boosting MLLMs' Video Understanding via Counterfactual Video Generation

SenseNova-MARS: Empowering Multimodal Agentic Reasoning and Search via Reinforcement Learning

Avatar Forcing: Real-Time Interactive Head Avatar Generation for Natural Conversation

NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos

Youtu-Agent: Scaling Agent Productivity with Automated Generation and Hybrid Policy Optimization

IQuest-Coder-V1 Technical Report

Recursive Language Models

FlowBlending: Stage-Aware Multi-Model Sampling for Fast and High-Fidelity Video Generation