paper-with-me

Papers

Multimodal Knowledge Alignment with Reinforcement Learning

2022-05-25 · Youngjae Yu, Jiwan Chung, Heeseung Yun, Jack Hessel, JaeSung Park, Ximing Lu, Prithviraj Ammanabrolu, Rowan Zellers, Ronan Le Bras, Gunhee Kim, Yejin Choi

Large language models readily adapt to novel settings, even without task-specific training data. Can their zero-shot capacity be extended to multimodal inputs? In this work, we propose ESPER which extends language-only zero-shot models to unseen multimodal tasks, like image and audio captioning. Our key novelty is to use reinforcement learning to align multimodal inputs to language model generations without direct supervision: for example, in the image case our reward optimization relies only on cosine similarity derived from CLIP, and thus requires no additional explicitly paired (image, caption) data. Because the parameters of the language model are left unchanged, the model maintains its capacity for zero-shot generalization. Experiments demonstrate that ESPER outperforms baselines and prior work on a variety of zero-shot tasks; these include a new benchmark we collect+release, ESP dataset, which tasks models with generating several diversely-styled captions for each image.

📄 PDF Abstract BibTeX arXiv:2205.12630

Code (1)

jiwanchung/esper 공식 구현 jax

Tasks

Audio captioningLanguage ModelingLanguage Modellingreinforcement-learningReinforcement LearningReinforcement Learning (RL)Zero-shot Generalization

Methods 이 논문이 사용한 방법론

Dilated Convolution 설명 없음
Hierarchical Feature Fusion Hierarchical Feature Fusion (HFF) is a feature fusion method employed in ESP and EESP image…
Pointwise Convolution Pointwise Convolution is a type of convolution that uses a 1x1 kernel: a kernel that iterates through every single point. This…
ESP 설명 없음
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…
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…

Similar Papers 제목 키워드 기반

Embodied Multimodal Multitask Learning

2019-02-04 · Devendra Singh Chaplot, Lisa Lee, Ruslan Salakhutdinov, Devi Parikh 외

Recent efforts on training visual navigation agents conditioned on language using deep reinforcement learning have been successful in learning policies for different multimodal tasks, such as semantic goal navigation and…

Deep Reinforcement LearningDisentanglementEmbodied Question AnsweringQuestion Answering+3

LVRPO: Language-Visual Alignment with GRPO for Multimodal Understanding and Generation

2026-03-29 · Shentong Mo, Sukmin Yun arxiv

Unified multimodal pretraining has emerged as a promising paradigm for jointly modeling language and vision within a single foundation model. However, existing approaches largely rely on implicit or indirect alignment si…

Visual Reasoning

Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI Feedback

2024-02-06 · Daechul Ahn, Yura Choi, Youngjae Yu, Dongyeop Kang 외

Recent advancements in large language models have influenced the development of video large multimodal models (VLMMs). The previous approaches for VLMMs involved Supervised Fine-Tuning (SFT) with instruction-tuned datase…

Video-based Generative Performance Benchmarking

Effective Multimodal Reinforcement Learning with Modality Alignment and Importance Enhancement

2023-02-18 · Jinming Ma, Feng Wu, Yingfeng Chen, Xianpeng Ji 외

Many real-world applications require an agent to make robust and deliberate decisions with multimodal information (e.g., robots with multi-sensory inputs). However, it is very challenging to train the agent via reinforce…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Chain-of-Adaptation: Surgical Vision-Language Adaptation with Reinforcement Learning

2026-03-20 · Jiajie Li, Chenhui Xu, Meihuan Liu, Jinjun Xiong arxiv

Conventional fine-tuning on domain-specific datasets can inadvertently alter a model's pretrained multimodal priors, leading to reduced generalization. To address this, we propose Chain-of-Adaptation (CoA), an adaptation…

Reinforcement Learning