NeuralOS: Towards Simulating Operating Systems via Neural Generative Models

CLiFT: Compressive Light-Field Tokens for Compute-Efficient and Adaptive Neural Rendering

Test-Time Scaling with Reflective Generative Model

System-of-systems Modeling and Optimization: An Integrated Framework for Intermodal Mobility

All-atom Diffusion Transformers: Unified generative modelling of molecules and materials

OST-Bench: Evaluating the Capabilities of MLLMs in Online Spatio-temporal Scene Understanding

Traceable Evidence Enhanced Visual Grounded Reasoning: Evaluation and Methodology

MIRIX: Multi-Agent Memory System for LLM-Based Agents

Skywork-R1V3 Technical Report

T-LoRA: Single Image Diffusion Model Customization Without Overfitting

Scaling RL to Long Videos

Critiques of World Models

Is Diversity All You Need for Scalable Robotic Manipulation?

Nile-Chat: Egyptian Language Models for Arabic and Latin Scripts

GTA1: GUI Test-time Scaling Agent

MedGen: Unlocking Medical Video Generation by Scaling Granularly-annotated Medical Videos

RLVER: Reinforcement Learning with Verifiable Emotion Rewards for Empathetic Agents

The User-Centric Geo-Experience: An LLM-Powered Framework for Enhanced Planning, Navigation, and Dynamic Adaptation

PLAME: Leveraging Pretrained Language Models to Generate Enhanced Protein Multiple Sequence Alignments

CriticLean: Critic-Guided Reinforcement Learning for Mathematical Formalization

StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling

OmniPart: Part-Aware 3D Generation with Semantic Decoupling and Structural Cohesion

SingLoRA: Low Rank Adaptation Using a Single Matrix

A Survey on Latent Reasoning

Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving

ChipSeek-R1: Generating Human-Surpassing RTL with LLM via Hierarchical Reward-Driven Reinforcement Learning

MedGemma Technical Report

BMMR: A Large-Scale Bilingual Multimodal Multi-Discipline Reasoning Dataset

Pre-Trained Policy Discriminators are General Reward Models

DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge

NeuralOS: Towards Simulating Operating Systems via Neural Generative Models

CLiFT: Compressive Light-Field Tokens for Compute-Efficient and Adaptive Neural Rendering

Test-Time Scaling with Reflective Generative Model

System-of-systems Modeling and Optimization: An Integrated Framework for Intermodal Mobility

All-atom Diffusion Transformers: Unified generative modelling of molecules and materials

OST-Bench: Evaluating the Capabilities of MLLMs in Online Spatio-temporal Scene Understanding

Traceable Evidence Enhanced Visual Grounded Reasoning: Evaluation and Methodology

MIRIX: Multi-Agent Memory System for LLM-Based Agents

Skywork-R1V3 Technical Report

T-LoRA: Single Image Diffusion Model Customization Without Overfitting

Scaling RL to Long Videos

Critiques of World Models

Is Diversity All You Need for Scalable Robotic Manipulation?

Nile-Chat: Egyptian Language Models for Arabic and Latin Scripts

GTA1: GUI Test-time Scaling Agent

MedGen: Unlocking Medical Video Generation by Scaling Granularly-annotated Medical Videos

RLVER: Reinforcement Learning with Verifiable Emotion Rewards for Empathetic Agents

The User-Centric Geo-Experience: An LLM-Powered Framework for Enhanced Planning, Navigation, and Dynamic Adaptation

PLAME: Leveraging Pretrained Language Models to Generate Enhanced Protein Multiple Sequence Alignments

CriticLean: Critic-Guided Reinforcement Learning for Mathematical Formalization

StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling

OmniPart: Part-Aware 3D Generation with Semantic Decoupling and Structural Cohesion

SingLoRA: Low Rank Adaptation Using a Single Matrix

A Survey on Latent Reasoning

Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving

ChipSeek-R1: Generating Human-Surpassing RTL with LLM via Hierarchical Reward-Driven Reinforcement Learning

MedGemma Technical Report

BMMR: A Large-Scale Bilingual Multimodal Multi-Discipline Reasoning Dataset

Pre-Trained Policy Discriminators are General Reward Models

DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge