Where Vision Becomes Text: Locating the OCR Routing Bottleneck in Vision-Language Models

OCR or Not? Rethinking Document Information Extraction in the MLLMs Era with Real-World Large-Scale Datasets

dnaHNet: A Scalable and Hierarchical Foundation Model for Genomic Sequence Learning

Neural Computers

ASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking Attack

GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens

How to Fine-Tune a Reasoning Model? A Teacher-Student Cooperation Framework to Synthesize Student-Consistent SFT Data

RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Framework

DR$^{3}$3-Eval: Towards Realistic and Reproducible Deep Research Evaluation

HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds

pi0.7: a Steerable Generalist Robotic Foundation Model with Emergent Capabilities

GTR: Guided Thought Reinforcement Prevents Thought Collapse in RL-based VLM Agent Training

Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward

Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration?

Memory Transfer Learning: How Memories are Transferred Across Domains in Coding Agents

OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language World Models

SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environments

RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time

Seedance 2.0: Advancing Video Generation for World Complexity

GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents

Cross-Scale Pansharpening via ScaleFormer and the PanScale Benchmark

ParseBench: A Document Parsing Benchmark for AI Agents

Memory Intelligence Agent

PROPELLA-1: MULTI-PROPERTY DOCUMENT ANNOTATION FOR LLM DATA CURATION AT SCALE

Internalized Reasoning for Long-Context Visual Document Understanding

TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate

BERT-as-a-Judge: A Robust Alternative to Lexical Methods for Efficient Reference-Based LLM Evaluation

SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks

Turing Test on Screen: A Benchmark for Mobile GUI Agent Humanization

Audio-Omni: Extending Multi-modal Understanding to Versatile Audio Generation and Editing

Where Vision Becomes Text: Locating the OCR Routing Bottleneck in Vision-Language Models

OCR or Not? Rethinking Document Information Extraction in the MLLMs Era with Real-World Large-Scale Datasets

dnaHNet: A Scalable and Hierarchical Foundation Model for Genomic Sequence Learning

Neural Computers

ASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking Attack

GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens

How to Fine-Tune a Reasoning Model? A Teacher-Student Cooperation Framework to Synthesize Student-Consistent SFT Data

RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Framework

DR$^{3}$3-Eval: Towards Realistic and Reproducible Deep Research Evaluation

HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds

pi0.7: a Steerable Generalist Robotic Foundation Model with Emergent Capabilities

GTR: Guided Thought Reinforcement Prevents Thought Collapse in RL-based VLM Agent Training

Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward

Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration?

Memory Transfer Learning: How Memories are Transferred Across Domains in Coding Agents

OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language World Models

SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environments

RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time

Seedance 2.0: Advancing Video Generation for World Complexity

GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents

Cross-Scale Pansharpening via ScaleFormer and the PanScale Benchmark

ParseBench: A Document Parsing Benchmark for AI Agents

Memory Intelligence Agent

PROPELLA-1: MULTI-PROPERTY DOCUMENT ANNOTATION FOR LLM DATA CURATION AT SCALE

Internalized Reasoning for Long-Context Visual Document Understanding

TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate

BERT-as-a-Judge: A Robust Alternative to Lexical Methods for Efficient Reference-Based LLM Evaluation

SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks

Turing Test on Screen: A Benchmark for Mobile GUI Agent Humanization

Audio-Omni: Extending Multi-modal Understanding to Versatile Audio Generation and Editing