16 citations · 22 across the 16 of their papers we have counts for
8 papers · 1 filter
Autoregressive Decoding as a Martingale: Characterizing the Stochastic Dynamics of LLM Generation
Xiahui Zhu, Zhenyi Qi, Wanwei Liu +4
Large language models (LLMs) have achieved remarkable success across a wide range of language tasks. At their core, autoregressive LLMs are conditional probability models that lear…
You Only Edit Once: Incentivizing In-Context Capability of LLMs via Local Demonstration Refinement
Jiarong Wen, Qi Wang, Yun Qu +8
In-context learning (ICL) is crucial for boosting the inference performance of large language models (LLMs). However, the effectiveness of ICL in LLMs is greatly influenced by the…
Causal Representation Learning with Optimal Compression under Complex Treatments
Wanting Liang, Haoang Chi, Zhiheng Zhang
Estimating Individual Treatment Effects (ITE) in multi-treatment scenarios faces two critical challenges: the Hyperparameter Selection Dilemma for balancing weights and the Curse o…
Breaking the Gradient Barrier: Unveiling Large Language Models for Strategic Classification
Xinpeng Lv, Yunxin Mao, Haoxuan Li +9
Strategic classification~(SC) explores how individuals or entities modify their features strategically to achieve favorable classification outcomes. However, existing SC methods, w…
Mixture Data for Training Cannot Ensure Out-of-distribution Generalization
Songming Zhang, Yuxiao Luo, Qizhou Wang +4
Deep neural networks often face generalization problems to handle out-of-distribution (OOD) data, and there remains a notable theoretical gap between the contributing factors and t…
Diversity-enhancing Generative Network for Few-shot Hypothesis Adaptation
Ruijiang Dong, Feng Liu, Haoang Chi +5
Generating unlabeled data has been recently shown to help address the few-shot hypothesis adaptation (FHA) problem, where we aim to train a classifier for the target domain with a…
TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation
Haoang Chi, Feng Liu, Wenjing Yang +5
In few-shot domain adaptation (FDA), classifiers for the target domain are trained with accessible labeled data in the source domain (SD) and few labeled data in the target domain…
Meta Discovery: Learning to Discover Novel Classes given Very Limited Data
Haoang Chi, Feng Liu, Bo Han +6
In novel class discovery (NCD), we are given labeled data from seen classes and unlabeled data from unseen classes, and we train clustering models for the unseen classes. However,…