paper-with-me

Papers

Finetune-Informed Pretraining Boosts Downstream Performance

2026-01-27 · Atik Faysal, Mohammad Rostami, Reihaneh Gh. Roshan, Nikhil Muralidhar, Huaxia Wang arxiv

Multimodal pretraining is effective for building general-purpose representations, but in many practical deployments, only one modality is heavily used during downstream fine-tuning. Standard pretraining strategies treat all modalities uniformly, which can lead to under-optimized representations for the modality that actually matters. We propose Finetune-Informed Pretraining (FIP), a model-agnostic method that biases representation learning toward a designated target modality needed at fine-tuning time. FIP combines higher masking difficulty, stronger loss weighting, and increased decoder capacity for the target modality, without modifying the shared encoder or requiring additional supervision. When applied to masked modeling on constellation diagrams for wireless signals, FIP consistently improves downstream fine-tuned performance with no extra data or compute. FIP is simple to implement, architecture-compatible, and broadly applicable across multimodal masked modeling pipelines.

📄 PDF Abstract BibTeX arXiv:2601.20884

Code (0)

등록된 구현이 없습니다.

Tasks

Representation Learning

Similar Papers 제목 키워드 기반

Downstream Datasets Make Surprisingly Good Pretraining Corpora

2022-09-28 · Kundan Krishna, Saurabh Garg, Jeffrey P. Bigham, Zachary C. Lipton

For most natural language processing tasks, the dominant practice is to finetune large pretrained transformer models (e.g., BERT) using smaller downstream datasets. Despite the success of this approach, it remains unclea…

Question Answering

Scaling Laws for Downstream Task Performance of Large Language Models

2024-02-06 · Berivan Isik, Natalia Ponomareva, Hussein Hazimeh, Dimitris Paparas 외

Scaling laws provide important insights that can guide the design of large language models (LLMs). Existing work has primarily focused on studying scaling laws for pretraining (upstream) loss. However, in transfer learni…

Machine TranslationTransfer LearningTranslation

VILA$^2$: VILA Augmented VILA

2024-07-24 · Yunhao Fang, Ligeng Zhu, Yao Lu, Yan Wang 외

While visual language model architectures and training infrastructures advance rapidly, data curation remains under-explored where quantity and quality become a bottleneck. Existing work either crawls extra Internet data…

HallucinationOptical Character Recognition (OCR)Visual Question Answering

TMI! Finetuned Models Leak Private Information from their Pretraining Data

2023-06-01 · John Abascal, Stanley Wu, Alina Oprea, Jonathan Ullman

Transfer learning has become an increasingly popular technique in machine learning as a way to leverage a pretrained model trained for one task to assist with building a finetuned model for a related task. This paradigm …

Transfer Learning

A Small but Informed and Diverse Model: The Case of the Multimodal GuessWhat!? Guessing Game

2022-09-01 · CLASP 2022 9 · Claudio Greco, Alberto Testoni, Raffaella Bernardi, Stella Frank

Pre-trained Vision and Language Transformers achieve high performance on downstream tasks due to their ability to transfer representational knowledge accumulated during pretraining on substantial amounts of data. In this…

Diversity