Blog
No more endless PDFs. Discover the core value of the latest top-tier research in one article.
Seeing Realism from Simulation: Efficient Video Transfer for Vision-Language-Action Data Augmentation
AcademiClaw: When Students Set Challenges for AI Agents
Latent Bridge: Feature Delta Prediction for Efficient Dual-System Vision-Language-Action Model Inference
Conditional Diffusion Sampling
Contextual Agentic Memory is a Memo, Not True Memory
Lectures on Condensed Mathematics
Lectures on Analytic Geometry
Toward a Community Roadmap for High Energy Physics and Artificial Intelligence in China and Beyond
Agentic AI Systems Should Be Designed as Marginal Token Allocators
AniMatrix: An Anime Video Generation Model that Thinks in Art, Not Physics
VideoNet: A Large-Scale Dataset for Domain-Specific Action Recognition
Hallucinations Undermine Trust; Metacognition is a Way Forward
Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems
Foundations of Riemannian Geometry for Riemannian Optimization: A Monograph with Detailed Derivations
OGPO: Sample Efficient Full-Finetuning of Generative Control Policies
Skills-Coach: A Self-Evolving Skill Optimizer via Training-Free GRPO
Learning Reactive Dexterous Grasping via Hierarchical Task-Space RL Planning and Joint-Space QP Control
Workspace-Bench 1.0: Benchmarking AI Agents on Workspace Tasks with Large-Scale File Dependencies
A Theory of Saddle Escape in Deep Nonlinear Networks
UniCorrn: Unified Correspondence Transformer Across 2D and 3D
VOFA: Visual Object Goal Pushing with Force-Adaptive Control for Humanoids
OmniEncoder: See, Hear, and Feel Continuous Motion Like Humans With One Encoder
The Fate of Nucleated Black Holes in de Sitter Quantum Gravity
Odysseus: Scaling VLMs to 100+ Turn Decision-Making in Games via Reinforcement Learning
Unified Map Prior Encoder for Mapping and Planning
Linear-Time Global Visual Modeling without Explicit Attention
Omni-Fake: Benchmarking Unified Multimodal Social Media Deepfake Detection
Training Non-Differentiable Networks via Optimal Transport
DGPO: Distribution Guided Policy Optimization for Fine Grained Credit Assignment
Nora: Normalized Orthogonal Row Alignment for Scalable Matrix Optimizer