会员服务
Patterning in Practice: Debiasing Reward Models with Susceptibilities
Arxiv
0+阅读 · 9月1日
Balancing Privacy, Utility, and Safety in LLM Alignment through Preference Optimization
Arxiv
0+阅读 · 8月31日
GeBDA: Building Damage Assessment as Text-Based Sequence Prediction
Arxiv
0+阅读 · 8月28日
MAM-AI: An On-Device Medical Retrieval-Augmented Generation System for Nurses and Midwives in Zanzibar
Arxiv
0+阅读 · 7月2日
MAM-AI: An On-Device Medical Retrieval-Augmented Generation System for Nurses and Midwives in Zanzibar
Arxiv
0+阅读 · 6月28日
MAM-AI: An On-Device Medical Retrieval-Augmented Generation System for Nurses and Midwives in Zanzibar
Arxiv
0+阅读 · 7月6日
XTC: Head-Aware Sampling by Excluding Top Choices
Arxiv
0+阅读 · 8月24日
How Transparent is DiffusionGemma?
Arxiv
0+阅读 · 6月18日
Evaluating Gemma4 Models as AI Teaching Assistants for Introductory Parallel Programming: A DataRaceBench Study
Arxiv
0+阅读 · 6月12日
The Vision Encoder as a Privacy Boundary: Visual-Token Side Channels in Encoder-Free Vision-Language Models
Arxiv
0+阅读 · 6月10日
Thinking with Visual Grounding
Arxiv
0+阅读 · 6月15日
Cross-Generational Transfer of Adversarial Attacks Reveals Non-Monotonic Safety Alignment in LLMs
Arxiv
0+阅读 · 5月30日
SpectrumKV: Per-Token Mixed-Precision KV Cache Transfer for Prefill-Decode Disaggregated LLM Serving
Arxiv
0+阅读 · 6月7日
Where's the Plan? Locating Latent Planning in Language Models with Lightweight Mechanistic Interventions
Arxiv
0+阅读 · 6月11日
SomaliBench Eval: Measuring English-to-Somali Refusal Gaps in Open-Weight Language Models
Arxiv
0+阅读 · 5月25日
参考链接
微信扫码咨询专知VIP会员
Top