BRFL: A Blockchain-based Byzantine-Robust Federated Learning Model

Multi-Granularity Distribution Modeling for Video Watch Time Prediction via Exponential-Gaussian Mixture Network

SAC Flow: Sample-Efficient Reinforcement Learning of Flow-Based Policies via Velocity-Reparameterized Sequential Modeling

Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment

Hail to the Thief: Exploring Attacks and Defenses in Decentralised GRPO

Black-Box On-Policy Distillation of Large Language Models

UniVA: Universal Video Agent towards Open-Source Next-Generation Video Generalist

PAN: A World Model for General, Interactable, and Long-Horizon World Simulation

One Small Step in Latent, One Giant Leap for Pixels: Fast Latent Upscale Adapter for Your Diffusion Models

YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception

MonkeyOCR: Document Parsing with a Structure-Recognition-Relation Triplet Paradigm

Consensus Sampling for Safer Generative AI

Argus: Resilience-Oriented Safety Assurance Framework for End-to-End ADSs

WMPO: World Model-based Policy Optimization for Vision-Language-Action Models

LoopTool: Closing the Data-Training Loop for Robust LLM Tool Calls

Beyond Fact Retrieval: Episodic Memory for RAG with Generative Semantic Workspaces

TiDAR: Think in Diffusion, Talk in Autoregression

Time-to-Move: Training-Free Motion Controlled Video Generation via Dual-Clock Denoising

Lumine: An Open Recipe for Building Generalist Agents in 3D Open Worlds

Generating an Image From 1,000 Words: Enhancing Text-to-Image With Structured Captions

KLASS: KL-Guided Fast Inference in Masked Diffusion Models

Grounding Computer Use Agents on Human Demonstrations

Wasm: A Pipeline for Constructing Structured Arabic Interleaved Multimodal Corpora

Adaptive Multi-Agent Response Refinement in Conversational Systems

SPAN: Spatial-Projection Alignment for Monocular 3D Object Detection

Efficient Approximation of Volterra Series for High-Dimensional Systems

SofT-GRPO: Surpassing Discrete-Token LLM Reinforcement Learning via Gumbel-Reparameterized Soft-Thinking Policy Optimization

RedOne 2.0: Rethinking Domain-specific LLM Post-Training in Social Networking Services

The Station: An Open-World Environment for AI-Driven Discovery

DRIVE: Data Curation Best Practices for Reinforcement Learning with Verifiable Reward in Competitive Code Generation

BRFL: A Blockchain-based Byzantine-Robust Federated Learning Model

Multi-Granularity Distribution Modeling for Video Watch Time Prediction via Exponential-Gaussian Mixture Network

SAC Flow: Sample-Efficient Reinforcement Learning of Flow-Based Policies via Velocity-Reparameterized Sequential Modeling

Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment

Hail to the Thief: Exploring Attacks and Defenses in Decentralised GRPO

Black-Box On-Policy Distillation of Large Language Models

UniVA: Universal Video Agent towards Open-Source Next-Generation Video Generalist

PAN: A World Model for General, Interactable, and Long-Horizon World Simulation

One Small Step in Latent, One Giant Leap for Pixels: Fast Latent Upscale Adapter for Your Diffusion Models

YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception

MonkeyOCR: Document Parsing with a Structure-Recognition-Relation Triplet Paradigm

Consensus Sampling for Safer Generative AI

Argus: Resilience-Oriented Safety Assurance Framework for End-to-End ADSs

WMPO: World Model-based Policy Optimization for Vision-Language-Action Models

LoopTool: Closing the Data-Training Loop for Robust LLM Tool Calls

Beyond Fact Retrieval: Episodic Memory for RAG with Generative Semantic Workspaces

TiDAR: Think in Diffusion, Talk in Autoregression

Time-to-Move: Training-Free Motion Controlled Video Generation via Dual-Clock Denoising

Lumine: An Open Recipe for Building Generalist Agents in 3D Open Worlds

Generating an Image From 1,000 Words: Enhancing Text-to-Image With Structured Captions

KLASS: KL-Guided Fast Inference in Masked Diffusion Models

Grounding Computer Use Agents on Human Demonstrations

Wasm: A Pipeline for Constructing Structured Arabic Interleaved Multimodal Corpora

Adaptive Multi-Agent Response Refinement in Conversational Systems

SPAN: Spatial-Projection Alignment for Monocular 3D Object Detection

Efficient Approximation of Volterra Series for High-Dimensional Systems

SofT-GRPO: Surpassing Discrete-Token LLM Reinforcement Learning via Gumbel-Reparameterized Soft-Thinking Policy Optimization

RedOne 2.0: Rethinking Domain-specific LLM Post-Training in Social Networking Services

The Station: An Open-World Environment for AI-Driven Discovery

DRIVE: Data Curation Best Practices for Reinforcement Learning with Verifiable Reward in Competitive Code Generation