6 papers
UNA: A Unified Supervised Framework for Efficient LLM Alignment Across Feedback Types
Zhichao Wang, Bin Bi, Can Huang +7
RL alignment methods, including RLHF and DPO, are primarily based on pairwise preference data. Although scalar or score-based feedback has been collected in some settings, it is ra…
Alada: Alternating Adaptation of Momentum Method for Memory-Efficient Matrix Optimization
Xiaoyu He, Yu Cai, Jin Jia +3
This work proposes Alada, an adaptive momentum method for stochastic optimization over large-scale matrices. Alada employs a rank-one factorization approach to estimate the second…
EVE: Towards End-to-End Video Subtitle Extraction with Vision-Language Models
Haiyang Yu, Mengyang Zhao, Jinghui Lu +8
Video subtitles play a crucial role in short videos and movies, as they not only help models better understand video content but also support applications such as video translation…
Vision as LoRA
Han Wang, Yongjie Ye, Bingru Li +5
We introduce Vision as LoRA (VoRA), a novel paradigm for transforming an LLM into an MLLM. Unlike prevalent MLLM architectures that rely on external vision modules for vision encod…
Dynamic-VLM: Simple Dynamic Visual Token Compression for VideoLLM
Han Wang, Yuxiang Nie, Yongjie Ye +6
The application of Large Vision-Language Models (LVLMs) for analyzing images and videos is an exciting and rapidly evolving field. In recent years, we've seen significant growth in…
PaDeLLM-NER: Parallel Decoding in Large Language Models for Named Entity Recognition
Jinghui Lu, Ziwei Yang, Yanjie Wang +3
In this study, we aim to reduce generation latency for Named Entity Recognition (NER) with Large Language Models (LLMs). The main cause of high latency in LLMs is the sequential de…