Hyper-Bagel: A Unified Acceleration Framework for Multimodal Understanding and Generation

Reinforcement Learning on Pre-Training Data

Do You Need Proprioceptive States in Visuomotor Policies?

Baseer: A Vision-Language Model for Arabic Document-to-Markdown OCR

GenExam: A Multidisciplinary Text-to-Image Exam

Nav-R1: Reasoning and Navigation in Embodied Scenes

MoEs Are Stronger than You Think: Hyper-Parallel Inference Scaling with RoE

ARE: Scaling Up Agent Environments and Evaluations

DiffusionNFT: Online Diffusion Reinforcement with Forward Process

TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs

OnePiece: Bringing Context Engineering and Reasoning to Industrial Cascade Ranking System

OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models

LIMI: Less is More for Agency

A Modular Fusion Neural Network Approach to Efficiently Predict Multi-Metal Binding Sites in Protein Sequences

IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech

Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference

A Multi-Scale Graph Neural Process with Cross-Drug Co-Attention for Drug-Drug Interactions Prediction

GenCAD-3D: CAD Program Generation using Multimodal Latent Space Alignment and Synthetic Dataset Balancing

BTL-UI: Blink-Think-Link Reasoning Model for GUI Agent

Lynx: Towards High-Fidelity Personalized Video Generation

SPATIALGEN: Layout-guided 3D Indoor Scene Generation

BaseReward: A Strong Baseline for Multimodal Reward Model

Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification

MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer

Oyster-I: Beyond Refusal - Constructive Safety Alignment for Responsible Language Models

Compute as Teacher: Turning Inference Compute Into Reference-Free Supervision

RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation

Synthetic bootstrapped pretraining

Skilful global seasonal predictions from a machine learning weather model trained on reanalysis data

FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoning

Hyper-Bagel: A Unified Acceleration Framework for Multimodal Understanding and Generation

Reinforcement Learning on Pre-Training Data

Do You Need Proprioceptive States in Visuomotor Policies?

Baseer: A Vision-Language Model for Arabic Document-to-Markdown OCR

GenExam: A Multidisciplinary Text-to-Image Exam

Nav-R1: Reasoning and Navigation in Embodied Scenes

MoEs Are Stronger than You Think: Hyper-Parallel Inference Scaling with RoE

ARE: Scaling Up Agent Environments and Evaluations

DiffusionNFT: Online Diffusion Reinforcement with Forward Process

TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs

OnePiece: Bringing Context Engineering and Reasoning to Industrial Cascade Ranking System

OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models

LIMI: Less is More for Agency

A Modular Fusion Neural Network Approach to Efficiently Predict Multi-Metal Binding Sites in Protein Sequences

IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech

Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference

A Multi-Scale Graph Neural Process with Cross-Drug Co-Attention for Drug-Drug Interactions Prediction

GenCAD-3D: CAD Program Generation using Multimodal Latent Space Alignment and Synthetic Dataset Balancing

BTL-UI: Blink-Think-Link Reasoning Model for GUI Agent

Lynx: Towards High-Fidelity Personalized Video Generation

SPATIALGEN: Layout-guided 3D Indoor Scene Generation

BaseReward: A Strong Baseline for Multimodal Reward Model

Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification

MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer

Oyster-I: Beyond Refusal - Constructive Safety Alignment for Responsible Language Models

Compute as Teacher: Turning Inference Compute Into Reference-Free Supervision

RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation

Synthetic bootstrapped pretraining

Skilful global seasonal predictions from a machine learning weather model trained on reanalysis data

FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoning