Blog
No more endless PDFs. Discover the core value of the latest top-tier research in one article.
Anti-I2V: Safeguarding your photos from malicious image-to-video generation
Trust as Monitoring: Evolutionary Dynamics of User Trust and AI Developer Behaviour
World Reasoning Arena
Mathematical methods and human thought in the age of AI
Realtime-VLA V2: Learning to Run VLAs Fast, Smooth, and Accurate
VLA-OPD: Bridging Offline SFT and Online RL for Vision-Language-Action Models via On-Policy Distillation
GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation
VGGRPO: Towards World-Consistent Video Generation with 4D Latent Reward
AIRA_2: Overcoming Bottlenecks in AI Research Agents
Zero-Shot Depth from Defocus
DFM-VLA: Iterative Action Refinement for Robot Manipulation via Discrete Flow Matching
Make Geometry Matter for Spatial Reasoning
LLaDA-TTS: Unifying Speech Synthesis and Zero-Shot Editing via Masked Diffusion Modeling
Stabilizing Rubric Integration Training via Decoupled Advantage Normalization
Dark energy from string theory: an introductory review
PerceptionComp: A Video Benchmark for Complex Perception-Centric Reasoning
EVERY CFT$_3$ HAS AN $ \mathcal{L}_Λw_{1+\infty}$ SYMMETRY
Detailed Geometry and Appearance from Opportunistic Motion
Typical entanglement in anyon chains: Page curves beyond Lie group symmetries
Imaging the Meissner effect and local superfluid stiffness in a graphene superconductor
THFM: A Unified Video Foundation Model for 4D Human Perception and Beyond
Can LLMs Produce Original Astronomy Research in a Semester? A Graduate Class Experiment
Symmetry-resolved properties of the trace distance in thermalizing SU(2) systems
Beyond Language: Grounding Referring Expressions with Hand Pointing in Egocentric Vision
T-800: An 800 Hz Data Glove for Precise Hand Gesture Tracking
Theory of (Co)homological Invariants on Quantum LDPC Codes
Dynamic Token Compression for Efficient Video Understanding through Reinforcement Learning
Negative energies and the breakdown of bulk geometry
Reflect to Inform: Boosting Multimodal Reasoning via Information-Gain-Driven Verification
ARC-AGI-3: A New Challenge for Frontier Agentic Intelligence