Blog
No more endless PDFs. Discover the core value of the latest top-tier research in one article.
SpikeTrack: A Spike-driven Framework for Efficient Visual Tracking
AHAP: Reconstructing Arbitrary Humans from Arbitrary Perspectives with Geometric Priors
A Menagerie of Wormholes and Cosmologies in the Gravitational Path Integral
Human or Machine? A Preliminary Turing Test for Speech-to-Speech Interaction
EgoGraph: Temporal Knowledge Graph for Egocentric Video Understanding
SwitchCraft: Training-Free Multi-Event Video Generation with Attention Controls
Pessimistic Auxiliary Policy for Offline Reinforcement Learning
Combination of ATLAS and CMS searches for Higgs boson pair production at $\sqrt{s} = 13$ TeV
Probing power spectrum enhancement at small scales with SKA
SR3R: Rethinking Super-Resolution 3D Reconstruction With Feed-Forward Gaussian Splatting
A Unified Origin of Primordial Black Hole Dark Matter and Nanohertz Gravitational Waves
Asymptotically Solvable Quantum Circuits
StemVLA:An Open-Source Vision-Language-Action Model with Future 3D Spatial Geometry Knowledge and 4D Historical Representation
FlexGuard: Continuous Risk Scoring for Strictness-Adaptive LLM Content Moderation
UTPTrack: Towards Simple and Unified Token Pruning for Visual Tracking
InfoNCE Induces Gaussian Distribution
Annotation-Free Visual Reasoning for High-Resolution Large Multimodal Models via Reinforcement Learning
Beyond Explainable AI (XAI): An Overdue Paradigm Shift and Post-XAI Research Directions
Improving Parametric Knowledge Access in Reasoning Language Models
SSKG Hub: An Expert-Guided Platform for LLM-Empowered Sustainability Standards Knowledge Graphs
Understanding LoRA as Knowledge Memory: An Empirical Analysis
RubricBench: Aligning Model-Generated Rubrics with Human Standards
WorldStereo: Bridging Camera-Guided Video Generation and Scene Reconstruction via 3D Geometric Memories
Symbol-Equivariant Recurrent Reasoning Models
Spectral Condition for $μ$P under Width-Depth Scaling
Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons
LLaDA-o: An Effective and Length-Adaptive Omni Diffusion Model
Learn Hard Problems During RL with Reference Guided Fine-tuning
OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens
Organizing, Orchestrating, and Benchmarking Agent Skills at Ecosystem Scale