From Static to Interactive: Adapting Visual in-Context Learners for User-Driven Tasks

• URL: http://arxiv.org/abs/2604.06748v1
• Date: Wed, 08 Apr 2026 07:13:56 GMT
• Title: From Static to Interactive: Adapting Visual in-Context Learners for User-Driven Tasks
• Abstract summary: We transform static visual in-context learners into user-driven systems, i.e., Interactive DeLVM.<n>Our work bridges the gap between rigid static task adaptation and fluid interactivity for user-centric visual in-context learning.
• Score: 5.208702297063032
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Visual in-context learning models are designed to adapt to new tasks by leveraging a set of example input-output pairs, enabling rapid generalization without task-specific fine-tuning. However, these models operate in a fundamentally static paradigm: while they can adapt to new tasks, they lack any mechanism to incorporate user-provided guidance signals such as scribbles, clicks, or bounding boxes to steer or refine the prediction process. This limitation is particularly restrictive in real-world applications, where users want to actively guide model predictions, e.g., by highlighting the target object for segmentation, indicating a region which should be visually altered, or isolating a specific person in a complex scene to run targeted pose estimation. In this work, we propose a simple method to transform static visual in-context learners, particularly the DeLVM approach, into highly controllable, user-driven systems, i.e., Interactive DeLVM, enabling seamless interaction through natural visual cues such as scribbles, clicks, or drawing boxes. Specifically, by encoding interactions directly into the example input-output pairs, we keep the philosophy of visual in-context learning intact: enabling users to prompt models with unseen interactions without fine-tuning and empowering them to dynamically steer model predictions with personalized interactions. Our experiments demonstrate that SOTA visual in-context learning models fail to effectively leverage interaction cues, often ignoring user guidance entirely. In contrast, our method excels in controllable, user-guided scenarios, achieving improvements of $+7.95%$ IoU for interactive segmentation, $+2.46$ PSNR for directed super-resolution, and $-3.14%$ LPIPS for interactive object removal. With this, our work bridges the gap between rigid static task adaptation and fluid interactivity for user-centric visual in-context learning.

Related papers

• Athanor: Authoring Action Modification-based Interactions on Static Visualizations via Natural Language [9.92682960014568]
  Athanor is a novel approach to transform existing static visualizations into interactive ones using multimodal large language models and natural language instructions.<n>Athanor allows users to effortlessly author interactions through natural language instructions, eliminating the need for programming.
  arXiv  Detail & Related papers  (2026-01-25T08:08:42Z)
• VITA-E: Natural Embodied Interaction with Concurrent Seeing, Hearing, Speaking, and Acting [66.90028121194636]
  Current Vision-Language-Action (VLA) models are often constrained by a rigid, static interaction paradigm.<n>VITA-E is a novel embodied interaction framework designed for both behavioral and nearly real-time interruption.
  arXiv  Detail & Related papers  (2025-10-21T17:59:56Z)
• Personalized Vision via Visual In-Context Learning [62.85784251383279]
  We present a visual in-context learning framework for personalized vision.<n>PICO infers the underlying transformation and applies it to new inputs without retraining.<n>We also propose an attention-guided seed scorer that improves reliability via efficient inference scaling.
  arXiv  Detail & Related papers  (2025-09-29T17:58:45Z)
• Precise Action-to-Video Generation Through Visual Action Prompts [62.951609704196485]
  Action-driven video generation faces a precision-generality trade-off.<n>Agent-centric action signals provide precision at the cost of cross-domain transferability.<n>We "render" actions into precise visual prompts as domain-agnostic representations.
  arXiv  Detail & Related papers  (2025-08-18T17:12:28Z)
• Dynamic Scoring with Enhanced Semantics for Training-Free Human-Object Interaction Detection [51.52749744031413]
  Human-Object Interaction (HOI) detection aims to identify humans and objects within images and interpret their interactions.<n>Existing HOI methods rely heavily on large datasets with manual annotations to learn interactions from visual cues.<n>We propose a novel training-free HOI detection framework for Dynamic Scoring with enhanced semantics.
  arXiv  Detail & Related papers  (2025-07-23T12:30:19Z)
• Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction [69.57190742976091]
  Aguvis is a vision-based framework for autonomous GUI agents.<n>It standardizes cross-platform interactions and incorporates structured reasoning via inner monologue.<n>It achieves state-of-the-art performance across offline and real-world online benchmarks.
  arXiv  Detail & Related papers  (2024-12-05T18:58:26Z)
• Collaborative Instance Object Navigation: Leveraging Uncertainty-Awareness to Minimize Human-Agent Dialogues [54.81155589931697]
  Collaborative Instance object Navigation (CoIN) is a new task setting where the agent actively resolve uncertainties about the target instance.<n>We propose a novel training-free method, Agent-user Interaction with UncerTainty Awareness (AIUTA)<n>First, upon object detection, a Self-Questioner model initiates a self-dialogue within the agent to obtain a complete and accurate observation description.<n>An Interaction Trigger module determines whether to ask a question to the human, continue or halt navigation.
  arXiv  Detail & Related papers  (2024-12-02T08:16:38Z)
• Flex: End-to-End Text-Instructed Visual Navigation from Foundation Model Features [59.892436892964376]
  We investigate the minimal data requirements and architectural adaptations necessary to achieve robust closed-loop performance with vision-based control policies.<n>Our findings are synthesized in Flex (Fly lexically), a framework that uses pre-trained Vision Language Models (VLMs) as frozen patch-wise feature extractors.<n>We demonstrate the effectiveness of this approach on a quadrotor fly-to-target task, where agents trained via behavior cloning successfully generalize to real-world scenes.
  arXiv  Detail & Related papers  (2024-10-16T19:59:31Z)
• Spatio-Temporal Context Prompting for Zero-Shot Action Detection [13.22912547389941]
  We propose a method which can effectively leverage the rich knowledge of visual-language models to perform Person-Context Interaction.<n>To address the challenge of recognizing distinct actions by multiple people at the same timestamp, we design the Interest Token Spotting mechanism.<n>Our method achieves superior results compared to previous approaches and can be further extended to multi-action videos.
  arXiv  Detail & Related papers  (2024-08-28T17:59:05Z)
• Zero Experience Required: Plug & Play Modular Transfer Learning for Semantic Visual Navigation [97.17517060585875]
  We present a unified approach to visual navigation using a novel modular transfer learning model. Our model can effectively leverage its experience from one source task and apply it to multiple target tasks. Our approach learns faster, generalizes better, and outperforms SoTA models by a significant margin.
  arXiv  Detail & Related papers  (2022-02-05T00:07:21Z)

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.