会员服务
MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory
Arxiv
0+阅读 · 1月6日
It's Not All Black and White: Degree of Truthfulness for Risk-Avoiding Agents
Arxiv
0+阅读 · 1月6日
FLUID: Training-Free Face De-identification via Latent Identity Substitution
Arxiv
0+阅读 · 1月6日
Maximizing Local Entropy Where It Matters: Prefix-Aware Localized LLM Unlearning
Arxiv
0+阅读 · 1月6日
Auditing for Core Stability in Participatory Budgeting
Arxiv
0+阅读 · 1月6日
Coordinated Multi-Domain Deception: A Stackelberg Game Approach
Arxiv
0+阅读 · 1月5日
Selling Privacy in Blockchain Transactions
Arxiv
0+阅读 · 1月5日
The Optimal Sample Complexity of Linear Contracts
Arxiv
0+阅读 · 1月4日
Local Layer-wise Differential Privacy in Federated Learning
Arxiv
0+阅读 · 1月5日
Rotation Control Unlearning: Quantifying and Controlling Continuous Unlearning for LLM with The Cognitive Rotation Space
Arxiv
0+阅读 · 1月4日
Auditing Human Decision-Making in High-Stakes Environments via Prescriptive AI: A Stress-Test on Real-Time Tactical Management
Arxiv
0+阅读 · 1月4日
InfoDecom: Decomposing Information for Defending Against Privacy Leakage in Split Inference
Arxiv
0+阅读 · 1月3日
Utility Maximization in Wireless Backhaul Networks with Service Guarantees
Arxiv
0+阅读 · 1月4日
PrivTune: Efficient and Privacy-Preserving Fine-Tuning of Large Language Models via Device-Cloud Collaboration
Arxiv
0+阅读 · 1月2日
Exploring the Integration of Differential Privacy in Cybersecurity Analytics: Balancing Data Utility and Privacy in Threat Intelligence
Arxiv
0+阅读 · 1月1日
参考链接
微信扫码咨询专知VIP会员
Top