Blog
告别冗长 PDF，一文读懂最新顶会与核心期刊的创新价值。
DCARL: A Divide-and-Conquer Framework for Autoregressive Long-Trajectory Video Generation
A Graphical Coaction for FRW Wavefunction Coefficients
Automating Computational Chemistry Workflows via OpenClaw and Domain-Specific Skills
Reaching Beyond the Mode: RL for Distributional Reasoning in Language Models
Voxtral TTS
Shaping the Future of Mathematics in the Age of AI
From AI Assistant to AI Scientist: Autonomous Discovery of LLM-RL Algorithms with LLM Agents
The Rules-and-Facts Model for Simultaneous Generalization and Memorization in Neural Networks
From Weights to Concepts: Data-Free Interpretability of CLIP via Singular Vector Decomposition
SoftMimicGen: A Data Generation System for Scalable Robot Learning in Deformable Object Manipulation
MegaFlow: Zero-Shot Large Displacement Optical Flow
GaussFusion: Improving 3D Reconstruction in the Wild with A Geometry-Informed Video Generator
Training the Knowledge Base through Evidence Distillation and Write-Back Enrichment
MMaDA-VLA: Large Diffusion Vision-Language-Action Model with Unified Multi-Modal Instruction and Generation
Demystifying When Pruning Works via Representation Hierarchies
LaMP: Learning Vision-Language-Action Policies with 3D Scene Flow as Latent Motion Prior
Mapping cone Thom forms
ViewSplat: View-Adaptive Dynamic Gaussian Splatting for Feed-Forward Synthesis
Weak distillation of quantum resources
Pixelis: Reasoning in Pixels, from Seeing to Acting
Learning domain-invariant features through channel-level sparsification for Out-Of Distribution Generalization
Bridging Perception and Reasoning: Token Reweighting for RLVR in Multimodal LLMs
Spatiotemporal System Forecasting with Irregular Time Steps via Masked Autoencoder
HiSpatial: Taming Hierarchical 3D Spatial Understanding in Vision-Language Models
The Kitchen Loop: User-Spec-Driven Development for a Self-Evolving Codebase
IslamicMMLU: A Benchmark for Evaluating LLMs on Islamic Knowledge
The Four Color Theorem with Linearly Many Reducible Configurations and Near-Linear Time Coloring
Towards Effective Experiential Learning: Dual Guidance for Utilization and Internalization
Sparse Visual Thought Circuits in Vision-Language Models
The Geometry of Efficient Nonconvex Sampling