Towards Truly Zero-shot Compositional Visual Reasoning with LLMs as Programmers

• URL: http://arxiv.org/abs/2401.01974v2
• Date: Tue, 14 May 2024 22:43:40 GMT
• Title: Towards Truly Zero-shot Compositional Visual Reasoning with LLMs as Programmers
• Authors: Aleksandar Stanić, Sergi Caelles, Michael Tschannen,
• Abstract summary: Even the largest models struggle with compositional reasoning, generalization, fine-grained spatial and temporal reasoning, and counting. Visual reasoning with large language models (LLMs) as controllers can, in principle, address these limitations by decomposing the task and solving subtasks by orchestrating a set of (visual) tools. We present a framework that mitigates these issues by introducing spatially and temporally abstract routines and by leveraging a small number of labeled examples to automatically generate in-context examples.
• Score: 54.83459025465947
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Visual reasoning is dominated by end-to-end neural networks scaled to billions of model parameters and training examples. However, even the largest models struggle with compositional reasoning, generalization, fine-grained spatial and temporal reasoning, and counting. Visual reasoning with large language models (LLMs) as controllers can, in principle, address these limitations by decomposing the task and solving subtasks by orchestrating a set of (visual) tools. Recently, these models achieved great performance on tasks such as compositional visual question answering, visual grounding, and video temporal reasoning. Nevertheless, in their current form, these models heavily rely on human engineering of in-context examples in the prompt, which are often dataset- and task-specific and require significant labor by highly skilled programmers. In this work, we present a framework that mitigates these issues by introducing spatially and temporally abstract routines and by leveraging a small number of labeled examples to automatically generate in-context examples, thereby avoiding human-created in-context examples. On a number of visual reasoning tasks, we show that our framework leads to consistent gains in performance, makes LLMs as controllers setup more robust, and removes the need for human engineering of in-context examples.

Related papers

• Visual RAG: Expanding MLLM visual knowledge without fine-tuning [5.341192792319891]
  This paper introduces Visual RAG, that synergically combines the MLLMs capability to learn from the context, with a retrieval mechanism. In this way, the resulting system is not limited to the knowledge extracted from the training data, but can be updated rapidly and easily without fine-tuning. It greatly reduces the computational costs for improving the model image classification performance, and augments the model knowledge to new visual domains and tasks it was not trained for.
  arXiv  Detail & Related papers  (2025-01-18T17:43:05Z)
• The Inherent Limits of Pretrained LLMs: The Unexpected Convergence of Instruction Tuning and In-Context Learning Capabilities [51.594836904623534]
  We investigate whether instruction-tuned models possess fundamentally different capabilities from base models that are prompted using in-context examples. We show that the performance of instruction-tuned models is significantly correlated with the in-context performance of their base counterparts. Specifically, we extend this understanding to instruction-tuned models, suggesting that their pretraining data similarly sets a limiting boundary on the tasks they can solve.
  arXiv  Detail & Related papers  (2025-01-15T10:57:55Z)
• Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More? [54.667202878390526]
  Long-context language models (LCLMs) have the potential to revolutionize our approach to tasks traditionally reliant on external tools like retrieval systems or databases. We introduce LOFT, a benchmark of real-world tasks requiring context up to millions of tokens designed to evaluate LCLMs' performance on in-context retrieval and reasoning. Our findings reveal LCLMs' surprising ability to rival state-of-the-art retrieval and RAG systems, despite never having been explicitly trained for these tasks.
  arXiv  Detail & Related papers  (2024-06-19T00:28:58Z)
• UniFS: Universal Few-shot Instance Perception with Point Representations [36.943019984075065]
  We propose UniFS, a universal few-shot instance perception model that unifies a wide range of instance perception tasks. Our approach makes minimal assumptions about the tasks, yet it achieves competitive results compared to highly specialized and well optimized specialist models.
  arXiv  Detail & Related papers  (2024-04-30T09:47:44Z)
• Auto-ICL: In-Context Learning without Human Supervision [93.05202223767463]
  We propose Automatic In-Context Learning framework that enables the model to autonomously generate examples and instructions for problem-solving. With experiments across various models and datasets, results show that model-generated contexts outperform human-annotated contexts.
  arXiv  Detail & Related papers  (2023-11-15T07:37:28Z)
• Evaluating the Capabilities of Multi-modal Reasoning Models with Synthetic Task Data [0.0]
  We leverage advances in high resolution text-to-image generation to develop a framework for generating evaluation data for multi-modal reasoning tasks. We apply this framework to generate context-dependent anomaly data, creating a synthetic dataset on a challenging task. We demonstrate that while the task is tractable, the model performs significantly worse on the context-dependent anomaly detection task than on standard VQA tasks.
  arXiv  Detail & Related papers  (2023-06-01T20:56:34Z)
• RetICL: Sequential Retrieval of In-Context Examples with Reinforcement Learning [53.52699766206808]
  We propose Retrieval for In-Context Learning (RetICL), a learnable method for modeling and optimally selecting examples sequentially for in-context learning. We evaluate RetICL on math word problem solving and scientific question answering tasks and show that it consistently outperforms or matches and learnable baselines.
  arXiv  Detail & Related papers  (2023-05-23T20:15:56Z)
• Efficient Prompting via Dynamic In-Context Learning [76.83516913735072]
  We propose DynaICL, a recipe for efficient prompting with black-box generalist models. DynaICL dynamically allocates in-context examples according to the input complexity and the computational budget. We find that DynaICL saves up to 46% token budget compared to the common practice that allocates the same number of in-context examples to each input.
  arXiv  Detail & Related papers  (2023-05-18T17:58:31Z)

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.