LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

FlowScene: Style-Consistent Indoor Scene Generation with Multimodal Graph Rectified Flow

LumosX: Relate Any Identities with Their Attributes for Personalized Video Generation

The Y-Combinator for LLMs: Solving Long-Context Rot with λ-Calculus

ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models

TerraScope: Pixel-Grounded Visual Reasoning for Earth Observation

Astrolabe: Steering Forward-Process Reinforcement Learning for Distilled Autoregressive Video Models

HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning

Bridging Semantic and Kinematic Conditions with Diffusion-based Discrete Motion Tokenizer

FASTER: Rethinking Real-Time Flow VLAs

3DreamBooth: High-Fidelity 3D Subject-Driven Video Generation Model

SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editing

Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding

Efficient Reasoning with Balanced Thinking

Look Before Acting: Enhancing Vision Foundation Representations for Vision-Language-Action Models

Complementary Reinforcement Learning

Alignment Makes Language Models Normative, Not Descriptive

MosaicMem: Hybrid Spatial Memory for Controllable Video World Models

MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild

Video-CoE: Reinforcing Video Event Prediction via Chain of Events

FunCineForge: A Unified Dataset Toolkit and Model for Zero-Shot Movie Dubbing in Diverse Cinematic Scenes

In-Context Watermarks for Large Language Models

WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation

Demystifing Video Reasoning

Kinema4D: Kinematic 4D World Modeling for Spatiotemporal Embodied Simulation

Qianfan-OCR: A Unified End-to-End Model for Document Intelligence

InCoder-32B: Code Foundation Model for Industrial Scenarios

MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification

HSImul3R: Physics-in-the-Loop Reconstruction of Simulation-Ready Human-Scene Interactions

Mixture-of-Depths Attention

LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

FlowScene: Style-Consistent Indoor Scene Generation with Multimodal Graph Rectified Flow

LumosX: Relate Any Identities with Their Attributes for Personalized Video Generation

The Y-Combinator for LLMs: Solving Long-Context Rot with λ-Calculus

ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models

TerraScope: Pixel-Grounded Visual Reasoning for Earth Observation

Astrolabe: Steering Forward-Process Reinforcement Learning for Distilled Autoregressive Video Models

HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning

Bridging Semantic and Kinematic Conditions with Diffusion-based Discrete Motion Tokenizer

FASTER: Rethinking Real-Time Flow VLAs

3DreamBooth: High-Fidelity 3D Subject-Driven Video Generation Model

SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editing

Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding

Efficient Reasoning with Balanced Thinking

Look Before Acting: Enhancing Vision Foundation Representations for Vision-Language-Action Models

Complementary Reinforcement Learning

Alignment Makes Language Models Normative, Not Descriptive

MosaicMem: Hybrid Spatial Memory for Controllable Video World Models

MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild

Video-CoE: Reinforcing Video Event Prediction via Chain of Events

FunCineForge: A Unified Dataset Toolkit and Model for Zero-Shot Movie Dubbing in Diverse Cinematic Scenes

In-Context Watermarks for Large Language Models

WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation

Demystifing Video Reasoning

Kinema4D: Kinematic 4D World Modeling for Spatiotemporal Embodied Simulation

Qianfan-OCR: A Unified End-to-End Model for Document Intelligence

InCoder-32B: Code Foundation Model for Industrial Scenarios

MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification

HSImul3R: Physics-in-the-Loop Reconstruction of Simulation-Ready Human-Scene Interactions

Mixture-of-Depths Attention