Shortcuts and Identifiability in Concept-based Models from a Neuro-Symbolic Lens
"模型准确性" 相关文章
EdgeSync: Accelerating Edge-Model Updates for Data Drift through Adaptive Continuous Learning
Federated Learning via Meta-Variational Dropout
Rethinking Cross-lingual Gaps from a Statistical Viewpoint
All Code, No Thought: Current Language Models Struggle to Reason in Ciphered Language
Faver: Boosting LLM-based RTL Generation with Function Abstracted Verifiable Middleware
Unveiling the Response of Large Vision-Language Models to Visually Absent Tokens
NEUBORN: The Neurodevelopmental Evolution framework Using BiOmechanical RemodelliNg
Crisp Attention: Regularizing Transformers via Structured Sparsity
DAG-AFL:Directed Acyclic Graph-based Asynchronous Federated Learning
Log-linear Scaling is Worth the Cost due to Gains in Long-Horizon Tasks
Build your gen AI–based text-to-SQL application using RAG, powered by Amazon Bedrock (Claude 3 Sonnet and Amazon Titan for embedding)
Method prevents an AI model from being overconfident about wrong answers
专治 AI 大模型对错误答案“过于自信”，麻省理工学院提出新型高效低耗校准方法
Navigating the Challenges of Selective Classification Under Differential Privacy: An Empirical Study
