AnaFlow: Agentic LLM-based Workflow for Reasoning-Driven Explainable and Sample-Efficient Analog Circuit Sizing
"可解释性" 相关文章
AILA--First Experiments with Localist Language Models
Interpretable end-to-end Neurosymbolic Reinforcement Learning agents
Automatically Finding Rule-Based Neurons in OthelloGPT
ExplicitLM: Decoupling Knowledge from Parameters via Explicit Memory Banks
【ICML25】使用信息瓶颈理论为点云模型进行错误归因，为安全问题构建可解释工具
Atlas-Alignment: Making Interpretability Transferable Across Language Models
36氪出海·AI｜对话Sheet0.com创始人王文锋：Agent下一阶段的关键要素：可解释、造工具和100%确认美学
Predicate Renaming via Large Language Models
Anthropic scientists hacked Claude’s brain — and it noticed. Here’s why that’s huge
Explainable Detection of AI-Generated Images with Artifact Localization Using Faster-Than-Lies and Vision-Language Models for Edge Devices
From Observability Data to Diagnosis: An Evolving Multi-agent System for Incident Management in Cloud Systems
Intuit learned to build AI agents for finance the hard way: Trust lost in buckets, earned back in spoonfuls
A Theory of the Mechanics of Information: Generalization Through Measurement of Uncertainty (Learning is Measuring)
Automatic Assessment of Students' Classroom Engagement with Bias Mitigated Multi-task Model
Unlocking Biomedical Insights: Hierarchical Attention Networks for High-Dimensional Data Interpretation
Towards Error-Centric Intelligence II: Energy-Structured Causal Models
Exploring the multi-dimensional refusal subspace in reasoning models
List of lists of project ideas in AI Safety
How to Auto-optimize Prompts for Domain Tasks? Adaptive Prompting and Reasoning through Evolutionary Domain Knowledge Adaptation
