Blog
告别冗长 PDF，一文读懂最新顶会与核心期刊的创新价值。
Perceptual Quality Enhancement for Compressed Video With High-Frequency Details and High-Dimensional Features
Toward accurate prediction of N2 uptake capacity in metal-organic frameworks
Dense Supervision, Sparse Updates: On the Sparsity and Geometry of On-Policy Distillation
MiniMax Sparse Attention
CAMixerSR: Only Details Need More “Attention”
From AGI to ASI
Unsupervised Anomaly Prediction with N-BEATS and Graph Neural Network in Multi-variate Semiconductor Process Time Series
Effects and Mechanism of the Leontopodium alpinum Callus Culture Extract on Blue Light Damage in Human Foreskin Fibroblasts
Retrieval-Augmented Generation Meets Data-Driven Tabula Rasa Approach for Temporal Knowledge Graph Forecasting
Evaluation of rag metrics for question answering in the telecom domain
Chain-of-Retrieval Augmented Generation
Deep Beamforming for Real-Time 3-D Passive Acoustic Mapping With Row-Column-Addressed Arrays
ArtifactLinker: Linking Scientific Artifacts for Automatic State-of-the-Art Discovery
铁氨转化途径：长期以Feammox为主的系统中的关键中间体及拟合的多物种代谢协同作用
Alleviating carbon competition between nitrogen and phosphorus removal: dual roles of microaerobic for anammox activation and pre-anaerobic endogenous carbon redirection
Mechanical Resonator-based Quantum Computing
Federated Learning for Feature Generalization with Convex Constraints
Opus 4.8 Models
Structure of the Pre-Initiation Complex Explains CMGE Biogenesis
Distributed by Beijing Bureau for Distribution of Newspapers and Journals Domestic All Local Post Offices in China
Towards Reliable Detection of LLM-Generated Texts: A Comprehensive Evaluation Framework with CUDRT
Sub-second volumetric 3D printing by synthesis of holographic light fields
Post-Training Local LLM Agents for Linux Privilege Escalation with Verifiable Rewards
URSA: Chemistry-Aware Benchmark for Utilitarian Retrosynthesis Assessment
Think Deep, Not Just Long: Measuring LLM Reasoning Effort via Deep-Thinking Tokens
In vivo feasibility study of humanoid robots in surgery
Verbalizable Representations Form a Global Workspace in Language Models
Psyche-R1: Towards Reliable Psychological LLMs through Unified Empathy, Expertise, and Reasoning
LLM-as-a-Coach: Experiential Learning for Non-Verifiable Tasks
Trains and cameras: Photography and the creation of a railway landscape in Portugal (late nineteenth–early twentieth centuries)