Every Token Counts: Generalizing 16M Ultra-Long Context in Large Language Models

SimScale: Learning to Drive via Real-World Simulation at Scale

Skywork-R1V4: Toward Agentic Multimodal Intelligence through Interleaved Thinking with Images and DeepResearch

Guided Self-Evolving LLMs with Minimal Human Supervision

MultiShotMaster: A Controllable Multi-Shot Video Generation Framework

MG-Nav: Dual-Scale Visual Navigation via Sparse Spatial Memory

The Consistency Critic: Correcting Inconsistencies in Generated Images via Reference-Guided Attentive Alignment

How Far Are We from Genuinely Useful Deep Research Agents?

Stabilizing Reinforcement Learning with LLMs: Formulation and Practices

Envision: Benchmarking Unified Understanding & Generation for Causal World Process Insights

LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling

From Code Foundation Models to Agents and Applications: A Practical Guide to Code Intelligence

Physics-Driven Spatiotemporal Modeling for AI-Generated Video Detection

Mem-α: Learning Memory Construction via Reinforcement Learning

Search Self-play: Pushing the Frontier of Agent Capability without Supervision

CudaForge: An Agent Framework with Hardware Feedback for CUDA Kernel Optimization

ScaleNet: Scaling up Pretrained Neural Networks with Incremental Parameters

Optimizing Mixture of Block Attention

FractalForensics: Proactive Deepfake Detection and Localization via Fractal Watermarks

Chain-of-Thought Hijacking

InstanceAssemble: Layout-Aware Image Generation via Instance Assembling Attention

3EED: Ground Everything Everywhere in 3D

DetectiumFire: A Comprehensive Multi-modal Dataset Bridging Vision and Language for Fire Understanding

CHIP: A multi-sensor dataset for 6D pose estimation of chairs in industrial settings

Geometrically-Constrained Agent for Spatial Reasoning

DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

DiP: Taming Diffusion Models in Pixel Space

Architecture Decoupling Is Not All You Need For Unified Multimodal Model

Vision Bridge Transformer at Scale

AnyTalker: Scaling Multi-Person Talking Video Generation with Interactivity Refinement

Every Token Counts: Generalizing 16M Ultra-Long Context in Large Language Models

SimScale: Learning to Drive via Real-World Simulation at Scale

Skywork-R1V4: Toward Agentic Multimodal Intelligence through Interleaved Thinking with Images and DeepResearch

Guided Self-Evolving LLMs with Minimal Human Supervision

MultiShotMaster: A Controllable Multi-Shot Video Generation Framework

MG-Nav: Dual-Scale Visual Navigation via Sparse Spatial Memory

The Consistency Critic: Correcting Inconsistencies in Generated Images via Reference-Guided Attentive Alignment

How Far Are We from Genuinely Useful Deep Research Agents?

Stabilizing Reinforcement Learning with LLMs: Formulation and Practices

Envision: Benchmarking Unified Understanding & Generation for Causal World Process Insights

LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling

From Code Foundation Models to Agents and Applications: A Practical Guide to Code Intelligence

Physics-Driven Spatiotemporal Modeling for AI-Generated Video Detection

Mem-α: Learning Memory Construction via Reinforcement Learning

Search Self-play: Pushing the Frontier of Agent Capability without Supervision

CudaForge: An Agent Framework with Hardware Feedback for CUDA Kernel Optimization

ScaleNet: Scaling up Pretrained Neural Networks with Incremental Parameters

Optimizing Mixture of Block Attention

FractalForensics: Proactive Deepfake Detection and Localization via Fractal Watermarks

Chain-of-Thought Hijacking

InstanceAssemble: Layout-Aware Image Generation via Instance Assembling Attention

3EED: Ground Everything Everywhere in 3D

DetectiumFire: A Comprehensive Multi-modal Dataset Bridging Vision and Language for Fire Understanding

CHIP: A multi-sensor dataset for 6D pose estimation of chairs in industrial settings

Geometrically-Constrained Agent for Spatial Reasoning

DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

DiP: Taming Diffusion Models in Pixel Space

Architecture Decoupling Is Not All You Need For Unified Multimodal Model

Vision Bridge Transformer at Scale

AnyTalker: Scaling Multi-Person Talking Video Generation with Interactivity Refinement