paper-with-me

Papers

Auto-Encoding Morph-Tokens for Multimodal LLM

2024-05-03 · Kaihang Pan, Siliang Tang, Juncheng Li, Zhaoyu Fan, Wei Chow, Shuicheng Yan, Tat-Seng Chua, Yueting Zhuang, Hanwang Zhang

For multimodal LLMs, the synergy of visual comprehension (textual output) and generation (visual output) presents an ongoing challenge. This is due to a conflicting objective: for comprehension, an MLLM needs to abstract the visuals; for generation, it needs to preserve the visuals as much as possible. Thus, the objective is a dilemma for visual-tokens. To resolve the conflict, we propose encoding images into morph-tokens to serve a dual purpose: for comprehension, they act as visual prompts instructing MLLM to generate texts; for generation, they take on a different, non-conflicting role as complete visual-tokens for image reconstruction, where the missing visual cues are recovered by the MLLM. Extensive experiments show that morph-tokens can achieve a new SOTA for multimodal comprehension and generation simultaneously. Our project is available at https://github.com/DCDmllm/MorphTokens.

📄 PDF Abstract BibTeX arXiv:2405.01926

Code (1)

dcdmllm/morphtokens 공식 구현 pytorch

Tasks

Image ReconstructionMORPH

Similar Papers 제목 키워드 기반

Multimodal Prototyping for cancer survival prediction

2024-06-28 · Andrew H. Song, Richard J. Chen, Guillaume Jaume, Anurag J. Vaidya 외

Multimodal survival methods combining gigapixel histology whole-slide images (WSIs) and transcriptomic profiles are particularly promising for patient prognostication and stratification. Current approaches involve tokeni…

PredictionSurvival Predictionwhole slide images

Byte Pair Encoding Is All You Need For Automatic Bengali Speech Recognition

2024-01-28 · Ahnaf Mozib Samin

Byte pair encoding (BPE) emerges as an effective tokenization method for tackling the out-of-vocabulary (OOV) challenge in various natural language and speech processing tasks. Recent research highlights the dependency o…

AllAutomatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognition+1

V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding

2024-12-12 · Junqi Ge, Ziyi Chen, Jintao Lin, Jinguo Zhu 외

Vision-Language Models (VLMs) have shown promising capabilities in handling various multimodal tasks, yet they struggle in long-context scenarios, particularly in tasks involving videos, high-resolution images, or length…

Position

Composing Byte-Pair Encodings for Morphological Sequence Classification

2020-12-01 · UDW (COLING) 2020 12 · Adam Ek, Jean-Philippe Bernardy

Byte-pair encodings is a method for splitting a word into sub-word tokens, a language model then assigns contextual representations separately to each of these tokens. In this paper, we evaluate four different methods of…

ClassificationLanguage ModelingLanguage Modelling

Unlabeled Data for Morphological Generation With Character-Based Sequence-to-Sequence Models

2017-05-17 · WS 2017 9 · Katharina Kann, Hinrich Schütze

We present a semi-supervised way of training a character-based encoder-decoder recurrent neural network for morphological reinflection, the task of generating one inflected word form from another. This is achieved by usi…

Decoder