Blog
告别冗长 PDF，一文读懂最新顶会与核心期刊的创新价值。
Lecanemab in Early Alzheimer’s Disease
SoK: On the Role and Future of AIGC Watermarking in the Era of Gen-AI
Trial of Psilocybin versus Escitalopram for Depression
Two-qubit logic and teleportation with mobile spin qubits in silicon
Two-qubit logic and teleportation with mobile spin qubits in silicon
World Action Models: The Next Frontier in Embodied AI
Don't Pass@k: A Bayesian Framework for Large Language Model Evaluation
IOPO: Empowering LLMs with Complex Instruction Following via Input-Output Preference Optimization
Deep Delta Learning
Two-qubit logic and teleportation with mobile spin qubits in silicon
Quantum gravitational contrast in creating Schrödinger cat state
Two-qubit logic and teleportation with mobile spin qubits in silicon
Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
Understanding Parametric and Contextual Knowledge Reconciliation within Large Language Models
RAG-HAT: A Hallucination-Aware Tuning Pipeline for LLM in Retrieval-Augmented Generation
SilverSpeak: Evading AI-Generated Text Detectors using Homoglyphs
Towards Reliable Detection of LLM-Generated Texts: A Comprehensive Evaluation Framework with CUDRT
SURVEY ON PLAGIARISM DETECTION IN LARGE LANGUAGE MODELS: THE IMPACT OF CHATGPT AND GEMINI ON ACADEMIC INTEGRITY
RaFe: Ranking Feedback Improves Query Rewriting for RAG
Active Context Compression: Autonomous Memory Management in LLM Agents
BoostDream: Efficient Refining for High-Quality Text-to-3D Generation from Multi-View Diffusion
Is ChatGPT Transforming Academics' Writing Style?
Mapping the increasing use of LLMs in scientific papers
SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer
Does RAG Know When Retrieval Is Wrong? Diagnosing Context Compliance under Knowledge Conflict
A Survey on Evaluation of LLM-based Agents
VGGT- Ω
SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer
ILLUSTRating red nugget assembly through observations and simulations
VIST3A: Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video Generator