VideoAgentTrek: Computer Use Pretraining from Unlabeled Videos

GigaBrain-0: A World Model-Powered Vision-Language-Action Model

LoongRL:Reinforcement Learning for Advanced Reasoning over Long Contexts

BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping

Every Attention Matters: An Efficient Hybrid Architecture for Long-Context Reasoning

Color Me Correctly: Bridging Perceptual Color Spaces and Text Embeddings for Improved Diffusion Generation

Spatial Reasoning with Vision-Language Models in Ego-Centric Multi-View Scenes

LoFT: Parameter-Efficient Fine-Tuning for Long-tailed Semi-Supervised Learning in Open-World Scenarios

FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policies

Inpainting-Guided Policy Optimization for Diffusion Large Language Models

MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated Tools

A Survey on Cache Methods in Diffusion Models: Toward Efficient Multi-Modal Generation

Rethinking Driving World Model as Synthetic Data Generator for Perception Tasks

Spatially-Varying Autofocus

When to Ensemble: Identifying Token-Level Points for Stable and Fast LLM Ensembling

Towards Mixed-Modal Retrieval for Universal Retrieval-Augmented Generation

FineVision: Open Data Is All You Need

Glyph: Scaling Context Windows via Visual-Text Compression

PICABench: How Far Are We from Physically Realistic Image Editing?

DeepAnalyze: Agentic Large Language Models for Autonomous Data Science

Self-Attention to Operator Learning-based 3D-IC Thermal Simulation

Earth AI: Unlocking Geospatial Insights with Foundation Models and Cross-Modal Reasoning

Rethinking Cross-lingual Gaps from a Statistical Viewpoint

Unleashing Scientific Reasoning for Bio-experimental Protocol Generation via Structured Component-based Reward Mechanism

Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery

Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs

NANO3D: A Training-Free Approach for Efficient 3D Editing Without Masks

Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset

OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM

A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning

VideoAgentTrek: Computer Use Pretraining from Unlabeled Videos

GigaBrain-0: A World Model-Powered Vision-Language-Action Model

LoongRL:Reinforcement Learning for Advanced Reasoning over Long Contexts

BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping

Every Attention Matters: An Efficient Hybrid Architecture for Long-Context Reasoning

Color Me Correctly: Bridging Perceptual Color Spaces and Text Embeddings for Improved Diffusion Generation

Spatial Reasoning with Vision-Language Models in Ego-Centric Multi-View Scenes

LoFT: Parameter-Efficient Fine-Tuning for Long-tailed Semi-Supervised Learning in Open-World Scenarios

FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policies

Inpainting-Guided Policy Optimization for Diffusion Large Language Models

MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated Tools

A Survey on Cache Methods in Diffusion Models: Toward Efficient Multi-Modal Generation

Rethinking Driving World Model as Synthetic Data Generator for Perception Tasks

Spatially-Varying Autofocus

When to Ensemble: Identifying Token-Level Points for Stable and Fast LLM Ensembling

Towards Mixed-Modal Retrieval for Universal Retrieval-Augmented Generation

FineVision: Open Data Is All You Need

Glyph: Scaling Context Windows via Visual-Text Compression

PICABench: How Far Are We from Physically Realistic Image Editing?

DeepAnalyze: Agentic Large Language Models for Autonomous Data Science

Self-Attention to Operator Learning-based 3D-IC Thermal Simulation

Earth AI: Unlocking Geospatial Insights with Foundation Models and Cross-Modal Reasoning

Rethinking Cross-lingual Gaps from a Statistical Viewpoint

Unleashing Scientific Reasoning for Bio-experimental Protocol Generation via Structured Component-based Reward Mechanism

Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery

Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs

NANO3D: A Training-Free Approach for Efficient 3D Editing Without Masks

Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset

OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM

A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning