会员服务
Learning through Internalization
Arxiv
0+阅读 · 6月18日
Heterogeneous LLM Debate Under Adversarial Peers: Honest Gains, Replacement Costs, and Resilience
Arxiv
0+阅读 · 6月18日
FLiP: Towards understanding and interpreting multimodal multilingual sentence embeddings
Arxiv
0+阅读 · 6月17日
An Epistemic Analysis of Random Coordinated Attack
Arxiv
0+阅读 · 6月16日
AUTOGATE: Automated Clock Gating via Toggling-Aware LLM-based RTL Rewriting
Arxiv
0+阅读 · 6月16日
Who Flips? Self- and Cross-Model Counterarguments Reveal Answer Instability in LLMs
Arxiv
0+阅读 · 6月14日
Greed Is Learned: Visible Incentives as Reward-Hacking Triggers
Arxiv
0+阅读 · 6月15日
Semantic Flip: Synthetic OOD Generation for Robust Refusal in Embodied Question Answering and Spatial Localization
Arxiv
0+阅读 · 6月15日
Reflective Numeration Systems I: a Global Standpoint
Arxiv
0+阅读 · 6月2日
Stable Geometry, Reversing Poles: The Bipolar Structure of AI Occupational Substitutability and Its Decade-Scale Inversion
Arxiv
0+阅读 · 6月6日
The Privacy Subsidy in Glosten-Milgrom: Bid-Ask Spread and Welfare under Flip-Noise Direction Observation
Arxiv
0+阅读 · 5月31日
Right Regions, Wrong Labels: Semantic Label Flips in Segmentation under Correlation Shift
Arxiv
0+阅读 · 6月10日
ARTA: Adaptive Reinforcement-Learning-Based Throttling Agent for RowHammer Vulnerabilities
Arxiv
0+阅读 · 6月6日
Fantastic Flips and Where to Find Them: A General Framework for Parameterized Local Search on Partitioning Problems
Arxiv
0+阅读 · 5月5日
Increasing arc-connectivity by bounded- and fixed-size inversions
Arxiv
0+阅读 · 4月24日
参考链接
微信扫码咨询专知VIP会员
Top