Towards Multimodal In-Context Learning for Vision & Language Models

• URL: http://arxiv.org/abs/2403.12736v2
• Date: Wed, 17 Jul 2024 08:13:02 GMT
• Title: Towards Multimodal In-Context Learning for Vision & Language Models
• Authors: Sivan Doveh, Shaked Perek, M. Jehanzeb Mirza, Wei Lin, Amit Alfassy, Assaf Arbelle, Shimon Ullman, Leonid Karlinsky,
• Abstract summary: State-of-the-art Vision-Language Models (VLMs) ground the vision and the language modality. We propose a simple yet surprisingly effective multi-turn curriculum-based learning methodology with effective data mixes.
• Score: 21.69457980865084
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: State-of-the-art Vision-Language Models (VLMs) ground the vision and the language modality primarily via projecting the vision tokens from the encoder to language-like tokens, which are directly fed to the Large Language Model (LLM) decoder. While these models have shown unprecedented performance in many downstream zero-shot tasks (eg image captioning, question answers, etc), still little emphasis has been put on transferring one of the core LLM capability of In-Context Learning (ICL). ICL is the ability of a model to reason about a downstream task with a few examples demonstrations embedded in the prompt. In this work, through extensive evaluations, we find that the state-of-the-art VLMs somewhat lack the ability to follow ICL instructions. In particular, we discover that even models that underwent large-scale mixed modality pre-training and were implicitly guided to make use of interleaved image and text information (intended to consume helpful context from multiple images) under-perform when prompted with few-shot demonstrations (in an ICL way), likely due to their lack of direct ICL instruction tuning. To enhance the ICL abilities of the present VLM, we propose a simple yet surprisingly effective multi-turn curriculum-based learning methodology with effective data mixes, leading up to a significant 21.03% (and 11.3% on average) ICL performance boost over the strongest VLM baselines and a variety of ICL benchmarks. Furthermore, we also contribute new benchmarks for ICL evaluation in VLMs and discuss their advantages over the prior art.

Related papers

• Multimodal Contrastive In-Context Learning [0.9120312014267044]
  This paper introduces a novel multimodal contrastive in-context learning framework to enhance our understanding of gradient-free in-context learning (ICL) in Large Language Models (LLMs) First, we present a contrastive learning-based interpretation of ICL in real-world settings, marking the distance of the key-value representation as the differentiator in ICL. Second, we develop an analytical framework to address biases in multimodal input formatting for real-world datasets. Third, we propose an on-the-fly approach for ICL that demonstrates effectiveness in detecting hateful memes.
  arXiv  Detail & Related papers  (2024-08-23T10:10:01Z)
• X-Former: Unifying Contrastive and Reconstruction Learning for MLLMs [49.30255148577368]
  X-Former is a lightweight transformer module designed to exploit the complementary strengths of CL and MIM. X-Former first bootstraps vision-language representation learning and multimodal-to-multimodal generative learning from two frozen vision encoders. It further bootstraps vision-to-language generative learning from a frozen LLM to ensure visual features from X-Former can be interpreted by the LLM.
  arXiv  Detail & Related papers  (2024-07-18T18:39:54Z)
• Evaluating Linguistic Capabilities of Multimodal LLMs in the Lens of Few-Shot Learning [15.919493497867567]
  This study aims to evaluate the performance of Multimodal Large Language Models (MLLMs) on the VALSE benchmark. We conducted a comprehensive assessment of state-of-the-art MLLMs, varying in model size and pretraining datasets.
  arXiv  Detail & Related papers  (2024-07-17T11:26:47Z)
• ICLEval: Evaluating In-Context Learning Ability of Large Language Models [68.7494310749199]
  In-Context Learning (ICL) is a critical capability of Large Language Models (LLMs) as it empowers them to comprehend and reason across interconnected inputs. Existing evaluation frameworks primarily focus on language abilities and knowledge, often overlooking the assessment of ICL ability. We introduce the ICLEval benchmark to evaluate the ICL abilities of LLMs, which encompasses two key sub-abilities: exact copying and rule learning.
  arXiv  Detail & Related papers  (2024-06-21T08:06:10Z)
• VL-ICL Bench: The Devil in the Details of Multimodal In-Context Learning [12.450293825734313]
  Large language models (LLMs) famously exhibit emergent in-context learning (ICL) This study introduces a benchmark VL-ICL Bench for multimodal in-context learning. We evaluate the abilities of state-of-the-art VLLMs against this benchmark suite.
  arXiv  Detail & Related papers  (2024-03-19T21:31:56Z)
• VILA: On Pre-training for Visual Language Models [74.08039416548209]
  We study the design options for VLM pre-training through step-by-step controllable comparisons. We build VILA, a Visual Language model family that consistently outperforms the state-of-the-art models.
  arXiv  Detail & Related papers  (2023-12-12T18:58:18Z)
• Towards More Unified In-context Visual Understanding [74.55332581979292]
  We present a new ICL framework for visual understanding with multi-modal output enabled. First, we quantize and embed both text and visual prompt into a unified representational space. Then a decoder-only sparse transformer architecture is employed to perform generative modeling on them.
  arXiv  Detail & Related papers  (2023-12-05T06:02:21Z)
• Behind the Magic, MERLIM: Multi-modal Evaluation Benchmark for Large Image-Language Models [50.653838482083614]
  This paper introduces a scalable test-bed to assess the capabilities of IT-LVLMs on fundamental computer vision tasks. MERLIM contains over 300K image-question pairs and has a strong focus on detecting cross-modal "hallucination" events in IT-LVLMs.
  arXiv  Detail & Related papers  (2023-12-03T16:39:36Z)
• Understanding and Improving In-Context Learning on Vision-language Models [42.7212469140844]
  In-context learning (ICL) on large language models (LLMs) has received great attention, and this technique can be applied to vision-language models (VLMs) This study investigates the significance of both visual and language information. We propose a simple yet effective approach, termed Mixed Modality In-Context Example Selection (MMICES)
  arXiv  Detail & Related papers  (2023-11-29T19:08:11Z)
• Link-Context Learning for Multimodal LLMs [40.923816691928536]
  Link-context learning (LCL) emphasizes "reasoning from cause and effect" to augment the learning capabilities of MLLMs. LCL guides the model to discern not only the analogy but also the underlying causal associations between data points. To facilitate the evaluation of this novel approach, we introduce the ISEKAI dataset.
  arXiv  Detail & Related papers  (2023-08-15T17:33:24Z)
• Iterative Forward Tuning Boosts In-Context Learning in Language Models [88.25013390669845]
  In this study, we introduce a novel two-stage framework to boost in-context learning in large language models (LLMs) Specifically, our framework delineates the ICL process into two distinct stages: Deep-Thinking and test stages. The Deep-Thinking stage incorporates a unique attention mechanism, i.e., iterative enhanced attention, which enables multiple rounds of information accumulation.
  arXiv  Detail & Related papers  (2023-05-22T13:18:17Z)

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.