Blog
No more endless PDFs. Discover the core value of the latest top-tier research in one article.
Tracking the Lithiation State of Li$_x$Si from Machine-Learned XPS Binding Energies
A Model-Free Universal AI
Frequency-Ordered Tokenization for Better Text Compression
LiLo-VLA: Compositional Long-Horizon Manipulation via Linked Object-Centric Policies
One Brain, Omni Modalities: Towards Unified Non-Invasive Brain Decoding with Large Language Models
Bridging Latent Reasoning and Target-Language Generation via Retrieval-Transition Heads
Learning Continuous Wasserstein Barycenter Space for Generalized All-in-One Image Restoration
Latent Matters: Learning Deep State-Space Models
Cognitive Models and AI Algorithms Provide Templates for Designing Language Agents
Hierarchy-of-Groups Policy Optimization for Long-Horizon Agentic Tasks
Learning Physical Operators using Neural Operators
Enhancing Multi-Modal LLMs Reasoning via Difficulty-Aware Group Normalization
Dynamic Multimodal Activation Steering for Hallucination Mitigation in Large Vision-Language Models
CrystaL: Spontaneous Emergence of Visual Latents in MLLMs
SCOPE: Skeleton Graph-Based Computation-Efficient Framework for Autonomous UAV Exploration
Closing the gap on tabular data with Fourier and Implicit Categorical Features
CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation
Mode Seeking meets Mean Seeking for Fast Long Video Generation
Enhancing Spatial Understanding in Image Generation via Reward Modeling
UFO-4D: Unposed Feedforward 4D Reconstruction from Two Images
OmniXtreme: Breaking the Generality Barrier in High-Dynamic Humanoid Control
AoE: Always-on Egocentric Human Video Collection for Embodied AI
Memory Caching: RNNs with Growing Memory
CC-VQA: Conflict- and Correlation-Aware Method for Mitigating Knowledge Conflict in Knowledge-Based Visual Question Answering
A Mixed Diet Makes DINO An Omnivorous Vision Encoder
Quant Experts: Token-aware Adaptive Error Reconstruction with Mixture of Experts for Large Vision-Language Models Quantization
Taming Momentum: Rethinking Optimizer States Through Low-Rank Approximation
DiffusionHarmonizer: Bridging Neural Reconstruction and Photorealistic Simulation with Online Diffusion Enhancer
The Auton Agentic AI Framework
Planning from Observation and Interaction