paper-with-me

Papers

EasyGen: Easing Multimodal Generation with BiDiffuser and LLMs

2023-10-13 · Xiangyu Zhao, Bo Liu, Qijiong Liu, Guangyuan Shi, Xiao-Ming Wu

We present EasyGen, an efficient model designed to enhance multimodal understanding and generation by harnessing the capabilities of diffusion models and large language models (LLMs), Unlike existing multimodal models that predominately depend on encoders like CLIP or ImageBind and need ample amounts of training data to bridge modalities,EasyGen leverages BiDiffuser,a bidirectional conditional diffusion model, to foster more efficient modality interactions. Easygen achieves text generation by training a projection layer linking BiDiffuser and an LLM, and facilities image generation by training an adapter to align the LLM's text space with the BiDiffuser's image space, Comprehensive quantitative and qualitative experiments show that EasyGen excels in data-efficient training, high-quality image generation, and extendibility, effectively addressing the challenges in multimodal generation. The source code is available at https://github.com/zxy556677/EasyGen.

📄 PDF Abstract BibTeX arXiv:2310.08949

Code (1)

zxy556677/easygen 공식 구현 pytorch

Tasks

Image Generationmultimodal generationText GenerationText-to-Image Generation

Methods 이 논문이 사용한 방법론

Adapter 설명 없음
ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

EasyGenNet: An Efficient Framework for Audio-Driven Gesture Video Generation Based on Diffusion Model

2025-04-11 · Renda Li, Xiaohua Qi, Qiang Ling, Jun Yu 외

Audio-driven cospeech video generation typically involves two stages: speech-to-gesture and gesture-to-video. While significant advances have been made in speech-to-gesture generation, synthesizing natural expressions an…

Gesture GenerationVideo Generation

"Haet Bhasha aur Diskrimineshun": Phonetic Perturbations in Code-Mixed Hinglish to Red-Team LLMs

2025-05-20 · Darpan Aswal, Siddharth D Jaiswal

Large Language Models (LLMs) have become increasingly powerful, with multilingual and multimodal capabilities improving by the day. These models are being evaluated through audits, alignment studies and red-teaming effor…

Image GenerationRed TeamingSafety AlignmentText Generation

SNS-Bench-VL: Benchmarking Multimodal Large Language Models in Social Networking Services

2025-05-29 · Hongcheng Guo, Zheyong Xie, Shaosheng Cao, Boyang Wang 외

With the increasing integration of visual and textual content in Social Networking Services (SNS), evaluating the multimodal capabilities of Large Language Models (LLMs) is crucial for enhancing user experience, content …

BenchmarkingInformation RetrievalMultiple-choice

Multimodal Fact-Level Attribution for Verifiable Reasoning

2026-02-12 · David Wan, Han Wang, Ziyang Wang, Elias Stengel-Eskin 외 arxiv

Multimodal large language models (MLLMs) are increasingly used for real-world tasks involving multi-step reasoning and long-form generation, where reliability requires grounding model outputs in heterogeneous input sourc…

Multimodal Reasoning

LLMs Meet Multimodal Generation and Editing: A Survey

2024-05-29 · Yingqing He, Zhaoyang Liu, Jingye Chen, Zeyue Tian 외

With the recent advancement in large language models (LLMs), there is a growing interest in combining LLMs with multimodal learning. Previous surveys of multimodal large language models (MLLMs) mainly focus on multimodal…

multimodal generationSurvey