TWIST & SCOUT: Grounding Multimodal LLM-Experts by Forget-Free Tuning

• URL: http://arxiv.org/abs/2410.10491v2
• Date: Thu, 20 Mar 2025 15:32:47 GMT
• Title: TWIST & SCOUT: Grounding Multimodal LLM-Experts by Forget-Free Tuning
• Authors: Aritra Bhowmik, Mohammad Mahdi Derakhshani, Dennis Koelma, Yuki M. Asano, Martin R. Oswald, Cees G. M. Snoek,
• Abstract summary: We introduce TWIST & SCOUT, a framework that equips pre-trained MLLMs with visual grounding ability.<n>To fine-tune the model effectively, we generate a high-quality synthetic dataset we call SCOUT.<n>This dataset provides rich supervision signals, describing a step-by-step multimodal reasoning process.
• Score: 54.033346088090674
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Spatial awareness is key to enable embodied multimodal AI systems. Yet, without vast amounts of spatial supervision, current Multimodal Large Language Models (MLLMs) struggle at this task. In this paper, we introduce TWIST & SCOUT, a framework that equips pre-trained MLLMs with visual grounding ability without forgetting their existing image and language understanding skills. To this end, we propose TWIST, a twin-expert stepwise tuning module that modifies the decoder of the language model using one frozen module pre-trained on image understanding tasks and another learnable one for visual grounding tasks. This allows the MLLM to retain previously learned knowledge and skills, while acquiring what is missing. To fine-tune the model effectively, we generate a high-quality synthetic dataset we call SCOUT, which mimics human reasoning in visual grounding. This dataset provides rich supervision signals, describing a step-by-step multimodal reasoning process, thereby simplifying the task of visual grounding. We evaluate our approach on several standard benchmark datasets, encompassing grounded image captioning, zero-shot localization, and visual grounding tasks. Our method consistently delivers strong performance across all tasks, while retaining the pre-trained image understanding capabilities.

Related papers

• Do we Really Need Visual Instructions? Towards Visual Instruction-Free Fine-tuning for Large Vision-Language Models [127.38740043393527]
  We propose ViFT, a visual instruction-free fine-tuning framework for LVLMs. We only require the text-only instructions and image caption data during training, to separately learn the task-solving and visual perception abilities. Experimental results demonstrate that ViFT can achieve state-of-the-art performance on several visual reasoning and visual instruction following benchmarks.
  arXiv  Detail & Related papers  (2025-02-17T04:38:12Z)
• Response Wide Shut: Surprising Observations in Basic Vision Language Model Capabilities [30.176918208200604]
  Vision-Language Models (VLMs) have emerged as general purpose tools for addressing a variety of complex computer vision problems. These models have been shown to be highly capable, but also lacking some basic visual understanding skills. This paper sets out to understand the limitations of SoTA VLMs on fundamental visual tasks.
  arXiv  Detail & Related papers  (2024-08-13T08:26:32Z)
• Learning Visual Grounding from Generative Vision and Language Model [29.2712567454021]
  Visual grounding tasks aim to localize image regions based on natural language references. We find that grounding knowledge already exists in generative VLM and can be elicited by proper prompting. Our results demonstrate the promise of generative VLM to scale up visual grounding in the real world.
  arXiv  Detail & Related papers  (2024-07-18T20:29:49Z)
• Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs [56.391404083287235]
  We introduce Cambrian-1, a family of multimodal LLMs (MLLMs) designed with a vision-centric approach. Our study uses LLMs and visual instruction tuning as an interface to evaluate various visual representations. We provide model weights, code, supporting tools, datasets, and detailed instruction-tuning and evaluation recipes.
  arXiv  Detail & Related papers  (2024-06-24T17:59:42Z)
• Improving Visual Commonsense in Language Models via Multiple Image Generation [41.565399860320966]
  Existing large language models (LLMs) are primarily trained using textual data only. Visual Language Models, which excel at visually-oriented tasks, often fail at non-visual tasks such as basic commonsense reasoning. This divergence highlights a critical challenge - the integration of robust visual understanding with foundational text-based language reasoning.
  arXiv  Detail & Related papers  (2024-06-19T15:17:10Z)
• ClawMachine: Fetching Visual Tokens as An Entity for Referring and Grounding [67.63933036920012]
  Existing methods, including proxy encoding and geometry encoding, incorporate additional syntax to encode the object's location. This study presents ClawMachine, offering a new methodology that notates an entity directly using the visual tokens. ClawMachine unifies visual referring and grounding into an auto-regressive format and learns with a decoder-only architecture.
  arXiv  Detail & Related papers  (2024-06-17T08:39:16Z)
• VCoder: Versatile Vision Encoders for Multimodal Large Language Models [46.95488342139727]
  Multimodal Large Language Models (MLLM) have recently achieved impressive performance on vision-language tasks. However, when prompted to identify or count (perceive) the entities in a given image, existing MLLM systems fail. We propose using Versatile vision enCoders (VCoder) as perception eyes for Multimodal LLMs.
  arXiv  Detail & Related papers  (2023-12-21T18:49:47Z)
• Machine Vision Therapy: Multimodal Large Language Models Can Enhance Visual Robustness via Denoising In-Context Learning [67.0609518552321]
  We propose to conduct Machine Vision Therapy which aims to rectify the noisy predictions from vision models. By fine-tuning with the denoised labels, the learning model performance can be boosted in an unsupervised manner.
  arXiv  Detail & Related papers  (2023-12-05T07:29:14Z)
• u-LLaVA: Unifying Multi-Modal Tasks via Large Language Model [17.3535277338312]
  u-LLaVA is an innovative unifying multi-task framework that integrates pixel, regional, and global features to refine the perceptual faculties of MLLMs. This work contributes a novel mask-based multi-task dataset comprising 277K samples, crafted to challenge and assess the fine-grained perception capabilities of MLLMs.
  arXiv  Detail & Related papers  (2023-11-09T13:18:27Z)
• Large Language Models are Visual Reasoning Coordinators [144.67558375045755]
  We propose a novel paradigm that coordinates multiple vision-language models for visual reasoning. We show that our instruction tuning variant, Cola-FT, achieves state-of-the-art performance on visual question answering. We also show that our in-context learning variant, Cola-Zero, exhibits competitive performance in zero and few-shot settings.
  arXiv  Detail & Related papers  (2023-10-23T17:59:31Z)
• Frozen Transformers in Language Models Are Effective Visual Encoder Layers [26.759544759745648]
  Large language models (LLMs) are surprisingly strong encoders for purely visual tasks in the absence of language. Our work pushes the boundaries of leveraging LLMs for computer vision tasks. We propose the information filtering hypothesis to explain the effectiveness of pre-trained LLMs in visual encoding.
  arXiv  Detail & Related papers  (2023-10-19T17:59:05Z)
• Mastering Robot Manipulation with Multimodal Prompts through Pretraining and Multi-task Fine-tuning [49.92517970237088]
  We tackle the problem of training a robot to understand multimodal prompts. This type of task poses a major challenge to robots' capability to understand the interconnection and complementarity between vision and language signals. We introduce an effective framework that learns a policy to perform robot manipulation with multimodal prompts.
  arXiv  Detail & Related papers  (2023-10-14T22:24:58Z)
• BuboGPT: Enabling Visual Grounding in Multi-Modal LLMs [101.50522135049198]
  BuboGPT is a multi-modal LLM with visual grounding that can perform cross-modal interaction between vision, audio and language. Our contributions are two-fold: 1) An off-the-shelf visual grounding module based on SAM that extracts entities in a sentence and find corresponding masks in the image. Our experiments show that BuboGPT achieves impressive multi-modality understanding and visual grounding abilities during the interaction with human.
  arXiv  Detail & Related papers  (2023-07-17T15:51:47Z)
• Look, Remember and Reason: Grounded reasoning in videos with language models [5.3445140425713245]
  Multi-temporal language models (LM) have recently shown promising performance in high-level reasoning tasks on videos. We propose training an LM end-to-end on low-level surrogate tasks, including object detection, re-identification, tracking, to endow the model with the required low-level visual capabilities. We demonstrate the effectiveness of our framework on diverse visual reasoning tasks from the ACRE, CATER, Something-Else and STAR datasets.
  arXiv  Detail & Related papers  (2023-06-30T16:31:14Z)
• Learning without Forgetting for Vision-Language Models [65.49600786387106]
  Class-Incremental Learning (CIL) or continual learning is a desired capability in the real world. Recent advances in Vision-Language Models (VLM) have shown promising capabilities in learning generalizable representations. We propose PROjectiOn Fusion (PROOF) that enables VLMs to learn without forgetting.
  arXiv  Detail & Related papers  (2023-05-30T17:59:32Z)
• mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality [95.76661165594884]
  mPLUG-Owl is a training paradigm that equips large language models (LLMs) with multi-modal abilities. The training paradigm involves a two-stage method for aligning image and text, which learns visual knowledge with the assistance of LLM. Experimental results show that our model outperforms existing multi-modal models.
  arXiv  Detail & Related papers  (2023-04-27T13:27:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.