paper-with-me

Papers

Learning What Helps: Task-Aligned Context Selection for Vision Tasks

2025-11-29 · Jingyu Guo, Emir Konuk, Fredrik Strand, Christos Matsoukas, Kevin Smith arxiv

Humans often resolve visual uncertainty by comparing an image with relevant examples, but ViTs lack the ability to identify which examples would improve their predictions. We present Task-Aligned Context Selection (TACS), a framework that learns to select paired examples which truly improve task performance rather than those that merely appear similar. TACS jointly trains a selector network with the task model through a hybrid optimization scheme combining gradient-based supervision and reinforcement learning, making retrieval part of the learning objective. By aligning selection with task rewards, TACS enables discriminative models to discover which contextual examples genuinely help. Across 18 datasets covering fine-grained recognition, medical image classification, and medical image segmentation, TACS consistently outperforms similarity-based retrieval, particularly in challenging or data-limited settings.

📄 PDF Abstract BibTeX arXiv:2512.00489

Code (0)

등록된 구현이 없습니다.

Tasks

Medical Image ClassificationMedical Image SegmentationReinforcement Learning

Similar Papers 제목 키워드 기반

A Good Plan is Hard to Find: Aligning Models with Preferences is Misaligned with What Helps Users

2025-09-23 · Nishant Balepur, Matthew Shu, Yoo Yeon Sung, Seraphina Goldfarb-Tarrant 외 arxiv

To assist users in complex tasks, LLMs generate plans: step-by-step instructions towards a goal. While alignment methods aim to ensure LLM plans are helpful, they train (RLHF) or evaluate (ChatbotArena) on what users pre…

Question Similarity

What to talk about and how? Selective Generation using LSTMs with Coarse-to-Fine Alignment

2015-09-02 · NAACL 2016 6 · Hongyuan Mei, Mohit Bansal, Matthew R. Walter

We propose an end-to-end, domain-independent neural encoder-aligner-decoder model for selective generation, i.e., the joint task of content selection and surface realization. Our model first encodes a full set of over-de…

Data-to-Text GenerationDecoder

TRAD: Enhancing LLM Agents with Step-Wise Thought Retrieval and Aligned Decision

2024-03-10 · Ruiwen Zhou, Yingxuan Yang, Muning Wen, Ying Wen 외

Numerous large language model (LLM) agents have been built for different tasks like web navigation and online shopping due to LLM's wide knowledge and text-understanding ability. Among these works, many of them utilize i…

Language ModellingLarge Language ModelRetrievalSequential Decision Making

Simple and Effective Text Matching with Richer Alignment Features

2019-08-01 · ACL 2019 7 · Runqi Yang, Jianhai Zhang, Xing Gao, Feng Ji 외

In this paper, we present a fast and strong neural approach for general purpose text matching applications. We explore what is sufficient to build a fast and well-performed text matching model and propose to keep three k…

Answer SelectionNatural Language InferenceParaphrase IdentificationQuestion Answering+1

A Reduced-Dimension fMRI Shared Response Model

2015-12-01 · NeurIPS 2015 12 · Po-Hsuan (Cameron) Chen, Janice Chen, Yaara Yeshurun, Uri Hasson 외

Multi-subject fMRI data is critical for evaluating the generality and validity of findings across subjects, and its effective utilization helps improve analysis sensitivity. We develop a shared response model for aggrega…

modelSensitivity