Blog

No more endless PDFs. Discover the core value of the latest top-tier research in one article.

Are AI-Generated Text Detectors Robust to Adversarial Perturbations?
DeTeCtive: Detecting AI-generated Text via Multi-Level Contrastive Learning
Active Context Compression: Autonomous Memory Management in LLM Agents
Can Model Compression Improve NLP Fairness
Mapping the increasing use of LLMs in scientific papers
Two-qubit logic and teleportation with mobile spin qubits in silicon
Attention Is All You Need
STREET-LEVEL BUREAUCRACY AND PUBLIC POLICIES: ANALYZING EDUCATIONAL POLICY IMPLEMENTATION FROM THE PERSPECTIVE OF SCHOOLS AND TEACHERS
A survey on llm-as-a-judge
IOPO: Empowering LLMs with Complex Instruction Following via Input-Output Preference Optimization
Prediction of Hidden Liquidity in theLimit Order Book of GLOBEX Futures
Quantum gravitational contrast in creating Schrödinger cat state
Two-qubit logic and teleportation with mobile spin qubits in silicon
Solve the Loop: Attractor Models for Language and Reasoning
Towards Reliable Detection of LLM-Generated Texts: A Comprehensive Evaluation Framework with CUDRT
Using generative adversarial network to improve the accuracy of detecting AI-generated tweets
SynCode: LLM Generation with Grammar Augmentation
SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer
Group Testing: An Information Theory Perspective
SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer
VGGT- Ω
World Action Models: The Next Frontier in Embodied AI
Deep Learning Alternatives of the Kolmogorov Superposition Theorem
DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
AGILE: A Novel Reinforcement Learning Framework of LLM Agents
RAG-HAT: A Hallucination-Aware Tuning Pipeline for LLM in Retrieval-Augmented Generation
PaSa: An LLM Agent for Comprehensive Academic Paper Search
Divergent urban storm response to convective, frontal and tropical systems
XB5748ISZ11-REV0.1
LLM-based Intelligent Agents for Academic Paper Retrieval-survey