Blog
告别冗长 PDF，一文读懂最新顶会与核心期刊的创新价值。
Infinite Gaze Generation for Videos with Autoregressive Diffusion
The Price Reversal Phenomenon: When Cheaper Reasoning Models End Up Costing More
Residual-as-Teacher: Mitigating Bias Propagation in Student--Teacher Estimation
Offline Decision Transformers for Neural Combinatorial Optimization: Surpassing Heuristics on the Traveling Salesman Problem
Agent Factories for High Level Synthesis: How Far Can General-Purpose Coding Agents Go in Hardware Optimization?
From Pixels to Digital Agents: An Empirical Study on the Taxonomy and Technological Trends of Reinforcement Learning Environments
Non-linear Sigma Model for the Surface Code with Coherent Errors
From Untamed Black Box to Interpretable Pedagogical Orchestration: The Ensemble of Specialized LLMs Architecture for Adaptive Tutoring
Large Language Model as Token Compressor and Decompressor
FSGNet: A Frequency-Aware and Semantic Guidance Network for Infrared Small Target Detection
Lingshu-Cell: A generative cellular world model for transcriptome modeling toward virtual cells
Scalable Object Relation Encoding for Better 3D Spatial Reasoning in Large Language Models
$π$, But Make It Fly: Physics-Guided Transfer of VLA Models to Aerial Manipulation
Self-Improvement of Large Language Models: A Technical Overview and Future Outlook
GlowQ: Group-Shared LOw-Rank Approximation for Quantized LLMs
Mirage The Illusion of Visual Understanding
DRoPS: Dynamic 3D Reconstruction of Pre-Scanned Objects
SABER: A Stealthy Agentic Black-Box Attack Framework for Vision-Language-Action Models
MedOpenClaw: Auditable Medical Imaging Agents Reasoning over Uncurated Full Studies
RVLM: Recursive Vision-Language Models with Adaptive Depth
SEVerA: Verified Synthesis of Self-Evolving Agents
GeoNDC: A Queryable Neural Data Cube for Planetary-Scale Earth Observation
Chern-Simons theory in mathematics, condensed matter theory and cosmology
Geometric Points in Tensor Triangular Geometry
VolDiT: Controllable Volumetric Medical Image Synthesis with Diffusion Transformers
Rethinking Token-Level Policy Optimization for Multimodal Chain-of-Thought
Experiential Reflective Learning for Self-Improving LLM Agents
A Gait Foundation Model Predicts Multi-System Health Phenotypes from 3D Skeletal Motion
MoE-GRPO: Optimizing Mixture-of-Experts via Reinforcement Learning in Vision-Language Models
PSDesigner: Automated Graphic Design with a Human-Like Creative Workflow