UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning

OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling

LAVa: Layer-wise KV Cache Eviction with Dynamic Budget Allocation

World Modeling with Probabilistic Structure Integration

VStyle: A Benchmark for Voice Style Adaptation with Spoken Instructions

HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answering

InfGen: A Resolution-Agnostic Paradigm for Scalable Image Synthesis

X-Part: high fidelity and structure coherent shape decomposition

The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs

IntrEx: A Dataset for Modeling Engagement in Educational Conversations

Youtu-GraphRAG: Vertically Unified Agents for Graph Retrieval-Augmented Complex Reasoning

SceneSplat: Gaussian Splatting-based Scene Understanding with Vision-Language Pretraining

Virtual Agent Economies

Towards Understanding Visual Grounding in Visual Language Models

Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis

MachineLearningLM: Continued Pretraining Language Models on Millions of Synthetic Tabular Prediction Tasks Scales In-Context ML

EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for Speech-to-Speech LLMs

SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model

scSiameseClu: A Siamese Clustering Framework for Interpreting single-cell RNA Sequencing Data

ST-Raptor: LLM-Powered Semi-Structured Table Question Answering

OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models

Understanding Economic Tradeoffs Between Human and AI Agents in Bargaining Games

Jupiter: Enhancing LLM Data Analysis Capabilities via Notebook and Inference-Time Value-Guided Search

Hunyuan-MT Technical Report

P3-SAM: Native 3D Part Segmentation

AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning

3D and 4D World Modeling: A Survey

RewardDance: Reward Scaling in Visual Generation

Sharing is Caring: Efficient LM Post-Training with Collective RL Experience Sharing

UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning

OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling

LAVa: Layer-wise KV Cache Eviction with Dynamic Budget Allocation

World Modeling with Probabilistic Structure Integration

VStyle: A Benchmark for Voice Style Adaptation with Spoken Instructions

HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answering

InfGen: A Resolution-Agnostic Paradigm for Scalable Image Synthesis

X-Part: high fidelity and structure coherent shape decomposition

The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs

IntrEx: A Dataset for Modeling Engagement in Educational Conversations

Youtu-GraphRAG: Vertically Unified Agents for Graph Retrieval-Augmented Complex Reasoning

SceneSplat: Gaussian Splatting-based Scene Understanding with Vision-Language Pretraining

Virtual Agent Economies

Towards Understanding Visual Grounding in Visual Language Models

Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis

MachineLearningLM: Continued Pretraining Language Models on Millions of Synthetic Tabular Prediction Tasks Scales In-Context ML

EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for Speech-to-Speech LLMs

SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model

scSiameseClu: A Siamese Clustering Framework for Interpreting single-cell RNA Sequencing Data

ST-Raptor: LLM-Powered Semi-Structured Table Question Answering

OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models

Understanding Economic Tradeoffs Between Human and AI Agents in Bargaining Games

Jupiter: Enhancing LLM Data Analysis Capabilities via Notebook and Inference-Time Value-Guided Search

Hunyuan-MT Technical Report

P3-SAM: Native 3D Part Segmentation

AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning

3D and 4D World Modeling: A Survey

RewardDance: Reward Scaling in Visual Generation

Sharing is Caring: Efficient LM Post-Training with Collective RL Experience Sharing