会员服务
LLMs Can Leak Training Data But Do They Want To? Evaluating Memorization Propensity in LLMs
Arxiv
0+阅读 · 10月27日
LLM knowledge for improved Out-of-Distribution Tabular Prediction - A Cross-Validated Regularisation Approach
Arxiv
0+阅读 · 10月27日
Follow the Gradient: Tracing Safety Degradation Back to Training Data
Arxiv
0+阅读 · 10月27日
Zooming without Zooming v2: From Seeing Details to Connecting Evidence for Generalizable Multimodal Perception
Arxiv
0+阅读 · 10月27日
Dr. Post-Training: A Data Regularization Perspective on LLM Post-Training
Arxiv
0+阅读 · 10月26日
Spiking Neural Networks Are Harder to Steal: A Benchmark Study of Model Stealing Attacks
Arxiv
0+阅读 · 10月26日
OmniReasoning: Pushing the Limits of Audio-Visual Joint Reasoning
Arxiv
0+阅读 · 10月26日
SkillQR: Agentic Skill Discovery for Reason-Intensive Query Rewriting
Arxiv
0+阅读 · 10月24日
WebUniverse: Scaling Verified Training Data for Agentic Web Development
Arxiv
0+阅读 · 10月23日
MarineSet: Large-Scale Underwater Acoustic Data Curation and evaluation
Arxiv
0+阅读 · 10月21日
Software Engineering LLMs: Why We Need Them and How Software Engineering Helps Build Them
Arxiv
0+阅读 · 10月24日
Counterfactual Test-Time Augmentation for Shortcut Removal in Language Models
Arxiv
0+阅读 · 10月24日
Reading Between the Layers: Cross-Modal Alignment and Representational Hierarchy in Vision Transformers
Arxiv
0+阅读 · 10月23日
Anti-coherence Regularized Absolute Scaling for Out-of-Distribution Detection
Arxiv
0+阅读 · 10月23日
Inherited, Not Invented: Tracing the Provenance of Wait in Reasoning Models
Arxiv
0+阅读 · 10月22日
参考链接
微信扫码咨询专知VIP会员
Top