Latest Papers

DesignLab: Designing Slides Through Iterative Detection and Correction

Yume: An Interactive World Generation Model

Pixels, Patterns, but No Poetry: To See The World like Humans

Constructing Ophthalmic MLLM for Positioning-diagnosis Collaboration Through Clinical Cognitive Chain Reasoning

HySafe-AI: Hybrid Safety Architectural Analysis Framework for AI Systems: A Case Study

Zebra-CoT: A Dataset for Interleaved Vision Language Reasoning

Semi-off-Policy Reinforcement Learning for Vision-Language Slow-thinking Reasoning

Upsample What Matters: Region-Adaptive Latent Sampling for Accelerated Diffusion Transformers

MegaScience: Pushing the Frontiers of Post-Training Datasets for Science Reasoning

Step-Audio 2 Technical Report

Beyond Context Limits: Subconscious Threads for Long-Horizon Reasoning

Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report

Uncertainty-Aware Knowledge Transformers for Peer-to-Peer Energy Trading with Multi-Agent Reinforcement Learning

NoHumansRequired: Autonomous High-Quality Image Editing Triplet Mining

Robust 3D-Masked Part-level Editing in 3D Gaussian Splatting with Regularized Score Distillation Sampling

WebShaper: Agentically Data Synthesizing via Information-Seeking Formalization

The Invisible Leash: Why RLVR May Not Escape Its Origin

GUI-G^2: Gaussian Reward Modeling for GUI Grounding

MiroMind-M1: An Open-Source Advancement in Mathematical Reasoning via Context-Aware Multi-Stage Policy Optimization

Design of intrinsically disordered region binding proteins

An All-Atom Generative Model for Designing Protein Complexes

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

CSD-VAR: Content-Style Decomposition in Visual Autoregressive Models

Mono-InternVL-1.5: Towards Cheaper and Faster Monolithic Multimodal Large Language Models

Franca: Nested Matryoshka Clustering for Scalable Visual Representation Learning

A Data-Centric Framework for Addressing Phonetic and Prosodic Challenges in Russian Speech Generative Models

The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs

PrefPalette: Personalized Preference Modeling with Latent Attributes

CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning

AnyCap Project: A Unified Framework, Dataset, and Benchmark for Controllable Omni-modal Captioning