Towards Predictive, Aligned, and Scalable Robot Learning

Flow Matching in Feature Space for Stochastic World Modeling

Full-Pipeline Inference Optimization for MiMo-V2.5 Series: Pushing Hybrid SWA Efficiency to the Limit

TRACE: TURN-LEVEL REWARD ASSIGNMENT VIA CREDIT ESTIMATION FOR LONG-HORIZON AGENTS

KeyFrame-Compass: Towards Comprehensive Evaluation of Keyframe-Conditioned Video Generation

BadWAM: When World-Action Models Dream Right but Act Wrong

SearchOS-V1 : Towards Robust Open-Domain Information-Seeking Agent Collaboration

SEED: SELF-EVOLVING ON-POLICY DISTILLATION FOR AGENTIC REINFORCEMENT LEARNING

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding

LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget

Deep Learning in Remote Sensing: A Review

A Regression Approach to Speech Enhancement Based on Deep Neural Networks

Deep Neural Networks for Acoustic Modeling in Speech Recognition

RoboTTT: Context Scaling for Robot Policies

SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering

Efficient Estimation of Word Representations in Vector Space

Depth Map Prediction from a Single Image using a Multi-Scale Deep Network

TabNet: Attentive Interpretable Tabular Learning

AudioPaLM: A Large Language Model That Can Speak and Listen

SQuAD: 100,000+ Questions for Machine Comprehension of Text

DeepPose: Human Pose Estimation via Deep Neural Networks

Self-Improvements in Modern Agentic Systems: A Survey

Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning

SparDA: Sparse Decoupled Attention for Efficient Long-Context LLM Inference

MetaView: Monocular Novel View Synthesis with Scale-Aware Implicit Geometry Priors

PolicyShiftGuard: Benchmarking and Improving Policy-Adaptive Image Guardrails

KnowAct-GUIClaw: Know Deeply, Act Perfectly, Personal GUI Assistant with Self-Evolving Memory and Skill

OvisOCR2 Technical Report

Boogu-Image-0.1: Boosting Open-Source Unified Multimodal Understanding and Generation

Harness Handbook: Making Evolving Agent Harnesses Readable, Navigable, and Editable

Qwen-Music Technical Report

Spectral Rewiring for Exploration, Purification, and Model Merging

Towards Predictive, Aligned, and Scalable Robot Learning

Flow Matching in Feature Space for Stochastic World Modeling

Full-Pipeline Inference Optimization for MiMo-V2.5 Series: Pushing Hybrid SWA Efficiency to the Limit

TRACE: TURN-LEVEL REWARD ASSIGNMENT VIA CREDIT ESTIMATION FOR LONG-HORIZON AGENTS

KeyFrame-Compass: Towards Comprehensive Evaluation of Keyframe-Conditioned Video Generation

BadWAM: When World-Action Models Dream Right but Act Wrong

SearchOS-V1 : Towards Robust Open-Domain Information-Seeking Agent Collaboration

SEED: SELF-EVOLVING ON-POLICY DISTILLATION FOR AGENTIC REINFORCEMENT LEARNING

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding

LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget

Deep Learning in Remote Sensing: A Review

A Regression Approach to Speech Enhancement Based on Deep Neural Networks

Deep Neural Networks for Acoustic Modeling in Speech Recognition

RoboTTT: Context Scaling for Robot Policies

SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering

Efficient Estimation of Word Representations in Vector Space

Depth Map Prediction from a Single Image using a Multi-Scale Deep Network

TabNet: Attentive Interpretable Tabular Learning

AudioPaLM: A Large Language Model That Can Speak and Listen

SQuAD: 100,000+ Questions for Machine Comprehension of Text

DeepPose: Human Pose Estimation via Deep Neural Networks

Self-Improvements in Modern Agentic Systems: A Survey

Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning

SparDA: Sparse Decoupled Attention for Efficient Long-Context LLM Inference

MetaView: Monocular Novel View Synthesis with Scale-Aware Implicit Geometry Priors

PolicyShiftGuard: Benchmarking and Improving Policy-Adaptive Image Guardrails

KnowAct-GUIClaw: Know Deeply, Act Perfectly, Personal GUI Assistant with Self-Evolving Memory and Skill

OvisOCR2 Technical Report

Boogu-Image-0.1: Boosting Open-Source Unified Multimodal Understanding and Generation

Harness Handbook: Making Evolving Agent Harnesses Readable, Navigable, and Editable

Qwen-Music Technical Report

Spectral Rewiring for Exploration, Purification, and Model Merging