Discrete Multimodal Transformers with a Pretrained Large Language Model for Mixed-Supervision Speech Processingby Viet Anh…
Aligning Large Language Models with Representation Editing: A Control Perspectiveby Lingkai Kong, Haorui Wang, Wenhao…
MATES: Model-Aware Data Selection for Efficient Pretraining with Data Influence Modelsby Zichun Yu, Spandan Das,…
Aligning Human Knowledge with Visual Concepts Towards Explainable Medical Image Classificationby Yunhe Gao, Difei Gu,…
SUMIE: A Synthetic Benchmark for Incremental Entity Summarizationby Eunjeong Hwang, Yichao Zhou, Beliz Gunel, James…
Self-Play with Adversarial Critic: Provable and Scalable Offline Alignment for Language Modelsby Xiang Ji, Sanjeev…
Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptationby Can Yaras, Peng Wang, Laura Balzano,…
What Should Embeddings Embed? Autoregressive Models Represent Latent Generating Distributionsby Liyi Zhang, Michael Y. Li,…
Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Modelsby Jinhao Li, Haopeng Li, Sarah…
Adversarial Moment-Matching Distillation of Large Language Modelsby Chen JiaFirst submitted to arxiv on: 5 Jun…