会员服务
MixtureVitae: Open Web-Scale Pretraining Dataset With High Quality Instruction and Reasoning Data Built from Permissive-First Text Sources
Arxiv
0+阅读 · 12月15日
Arbitrage: Efficient Reasoning via Advantage-Aware Speculation
Arxiv
0+阅读 · 12月4日
PrivTune: Efficient and Privacy-Preserving Fine-Tuning of Large Language Models via Device-Cloud Collaboration
Arxiv
0+阅读 · 12月9日
What Really Counts? Examining Step and Token Level Attribution in Multilingual CoT Reasoning
Arxiv
0+阅读 · 11月19日
Dynamics of Spontaneous Topic Changes in Next Token Prediction with Self-Attention
Arxiv
0+阅读 · 12月11日
MixtureVitae: Open Web-Scale Pretraining Dataset With High Quality Instruction and Reasoning Data Built from Permissive-First Text Sources
Arxiv
0+阅读 · 12月12日
MixtureVitae: Open Web-Scale Pretraining Dataset With High Quality Instruction and Reasoning Data Built from Permissive-First Text Sources
Arxiv
0+阅读 · 12月9日
Lightweight Latent Reasoning for Narrative Tasks
Arxiv
0+阅读 · 12月1日
Information Capacity: Evaluating the Efficiency of Large Language Models via Text Compression
Arxiv
0+阅读 · 11月13日
Modeling Uncertainty Trends for Timely Retrieval in Dynamic RAG
Arxiv
0+阅读 · 11月13日
Learning from Sufficient Rationales: Analysing the Relationship Between Explanation Faithfulness and Token-level Regularisation Strategies
Arxiv
0+阅读 · 11月20日
Inductive Generative Recommendation via Retrieval-based Speculation
Arxiv
0+阅读 · 11月21日
SemShareKV: Efficient KVCache Sharing for Semantically Similar Prompts via Token-Level LSH Matching
Arxiv
0+阅读 · 12月16日
VL-JEPA: Joint Embedding Predictive Architecture for Vision-language
Arxiv
0+阅读 · 12月11日
Positional Bias in Long-Document Ranking: Impact, Assessment, and Mitigation
Arxiv
0+阅读 · 11月12日
参考链接
微信扫码咨询专知VIP会员
Top