Blog
No more endless PDFs. Discover the core value of the latest top-tier research in one article.
Think over Trajectories: Leveraging Video Generation to Reconstruct GPS Trajectories from Cellular Signaling
MemCam: Memory-Augmented Camera Control for Consistent Video Generation
Chasing Autonomy: Dynamic Retargeting and Control Guided RL for Performant and Controllable Humanoid Running
Sign control of photocurrents by spin-group-symmetry breaking in altermagnetic insulators
Recoil geometry determines electromagnetic counterparts from supermassive black hole merger remnants
DiffusionAnything: End-to-End In-context Diffusion Learning for Unified Navigation and Pre-Grasp Motion
Generative Score Inference for Multimodal Data
Working Notes on Late Interaction Dynamics: Analyzing Targeted Behaviors of Late Interaction Models
HoĊava-Witten theory on ${\mathbf{S}}^1\vee{\mathbf{S}}^1$ as type 0 orientifold
Towards Generalizable Robotic Data Flywheel: High-Dimensional Factorization and Composition
Identifying Surface Degeneracies in Single-Visit Reflected Light Observations of Modern Earth using the Habitable Worlds Observatory
Towards GUI Agents: Vision-Language Diffusion Models for GUI Grounding
SparseCam4D: Spatio-Temporally Consistent 4D Reconstruction from Sparse Cameras
Reinforcing Structured Chain-of-Thought for Video Understanding
Automated near-term quantum algorithm discovery for molecular ground states
Scene Grounding In the Wild
Geo$^\textbf{2}$: Geometry-Guided Cross-view Geo-Localization and Image Synthesis
How libraries classified physics preprints before arXiv and set the stage for distinguishing insiders from outsiders
Fus3D: Decoding Consolidated 3D Geometry from Feed-forward Geometry Transformer Latents
Absence of Far-Detuned Attractive Optical Traps for Alkali Rydberg Atoms
Generation Is Compression: Zero-Shot Video Coding via Stochastic Rectified Flow
MPDiT: Multi-Patch Global-to-Local Transformer Architecture For Efficient Flow Matching and Diffusion Model
ArtHOI: Taming Foundation Models for Monocular 4D Reconstruction of Hand-Articulated-Object Interactions
QuitoBench: A High-Quality Open Time Series Forecasting Benchmark
Conditional Diffusion for 3D CT Volume Reconstruction from 2D X-rays
Cosmological Correlators Using Tensor Networks
DiReCT: Disentangled Regularization of Contrastive Trajectories for Physics-Refined Video Generation
SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
Neural Computers
Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering