Blog
No more endless PDFs. Discover the core value of the latest top-tier research in one article.
Rethinking the Practicality of Vision-language-action Model: A Comprehensive Benchmark and An Improved Baseline
Implicit Intelligence -- Evaluating Agents on What Users Don't Say
ThinkOmni: Lifting Textual Reasoning to Omni-modal Scenarios via Guidance Decoding
Force Policy: Learning Hybrid Force-Position Control Policy under Interaction Frame for Contact-Rich Manipulation
Fine-Tuning Without Forgetting In-Context Learning: A Theoretical Analysis of Linear Attention Models
Accelerating LLM Pre-Training through Flat-Direction Dynamics Enhancement
Geometry-as-context: Modulating Explicit 3D in Scene-consistent Video Generation to Geometry Context
Toward Expert Investment Teams:A Multi-Agent LLM System with Fine-Grained Trading Tasks
Search More, Think Less: Rethinking Long-Horizon Agentic Search for Efficiency and Generalization
Transformers converge to invariant algorithmic cores
Learning Physical Principles from Interaction: Self-Evolving Planning via Test-Time Memory
LLMs Can Learn to Reason Via Off-Policy RL
FlashOptim: Optimizers for Memory Efficient Training
Spa3R: Predictive Spatial Field Modeling for 3D Visual Reasoning
Spin Glass Concepts in Computer Science, Statistics, and Learning
Scaling View Synthesis Transformers
A Dataset is Worth 1 MB
MediX-R1: Open Ended Medical Reinforcement Learning
Robust Human Trajectory Prediction via Self-Supervised Skeleton Representation Learning
Flow3r: Factored Flow Prediction for Scalable Visual Geometry Learning
MiroFlow: Towards High-Performance and Robust Open-Source Agent Framework for General Deep Research Tasks
Devling into Adversarial Transferability on Image Classification: Review, Benchmark, and Evaluation
Code World Models for Parameter Control in Evolutionary Algorithms
GIFSplat: Generative Prior-Guided Iterative Feed-Forward 3D Gaussian Splatting from Sparse Views
Thermodynamic Uncertainty Relation with Quantum Feedback
TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics
A Researcher's Guide to Empirical Risk Minimization
Learning in the Null Space: Small Singular Values for Continual Learning
Risk-Aware World Model Predictive Control for Generalizable End-to-End Autonomous Driving
UniVBench: Towards Unified Evaluation for Video Foundation Models