Disentangling the Roles of Target-Side Transfer and Regularization in Multilingual Machine Translationby Yan Meng, Christof…
Decoding Speculative Decodingby Minghao Yan, Saurabh Agarwal, Shivaram VenkataramanFirst submitted to arxiv on: 2 Feb…
L-TUNING: Synchronized Label Tuning for Prompt and Prefix in LLMsby Md. Kowsher, Md. Shohanur Islam…
Integrating Large Language Models in Causal Discovery: A Statistical Causal Approachby Masayuki Takayama, Tadahisa Okuda,…
Connecting the Dots: Is Mode-Connectedness the Key to Feasible Sample-Based Inference in Bayesian Neural Networks?by…
A Differentiable Partially Observable Generalized Linear Model with Forward-Backward Message Passingby Chengrui Li, Weihan Li,…
Bi-CryptoNets: Leveraging Different-Level Privacy for Encrypted Inferenceby Man-Jie Yuan, Zheng Zou, Wei GaoFirst submitted to…
Efficient Prompt Caching via Embedding Similarityby Hanlin Zhu, Banghua Zhu, Jiantao JiaoFirst submitted to arxiv…
Two Heads Are Better Than One: Boosting Graph Sparse Training via Semantic and Topological Awarenessby…
Need a Small Specialized Language Model? Plan Early!by David Grangier, Angelos Katharopoulos, Pierre Ablin, Awni…