paper-with-me

홈 › Papers

How (not) to ensemble LVLMs for VQA

2023-10-10 · Lisa Alazraki, Lluis Castrejon, Mostafa Dehghani, Fantine Huot, Jasper Uijlings, Thomas Mensink

This paper studies ensembling in the era of Large Vision-Language Models (LVLMs). Ensembling is a classical method to combine different models to get increased performance. In the recent work on Encyclopedic-VQA the authors examine a wide variety of models to solve their task: from vanilla LVLMs, to models including the caption as extra context, to models augmented with Lens-based retrieval of Wikipedia pages. Intuitively these models are highly complementary, which should make them ideal for ensembling. Indeed, an oracle experiment shows potential gains from 48.8% accuracy (the best single model) all the way up to 67% (best possible ensemble). So it is a trivial exercise to create an ensemble with substantial real gains. Or is it?

📄 PDF Abstract BibTeX arXiv:2310.06641

Code (0)

등록된 구현이 없습니다.

Tasks

RetrievalVisual Question Answering (VQA)

Similar Papers 제목 키워드 기반

Improving Generalization in Visual Reasoning via Self-Ensemble

2024-10-28 · Tien-Huy Nguyen, Quang-Khai Tran, Anh-Tuan Quang-Hoang

The cognitive faculty of visual reasoning necessitates the integration of multimodal perceptual processing and commonsense and external knowledge of the world. In recent years, a plethora of large vision-language models …

Visual Question Answering (VQA)Visual Reasoning

CARPE: Context-Aware Image Representation Prioritization via Ensemble for Large Vision-Language Models

2026-01-20 · Donghee Lee, Rui Cai, Zhe Zhao arxiv

Large vision-language models (LVLMs) are typically trained using autoregressive language modeling objectives, which align visual representations with linguistic space. While effective for multimodal reasoning, this align…

Multimodal ReasoningImage Classification

Unlocking Few-Shot Capabilities in LVLMs via Prompt Conditioning and Head Selection

2026-03-25 · Adhemar de Senneville, Xavier Bou, Jérémy Anger, Rafael Grompone 외 arxiv

Current Large Vision Language Models (LVLMs) excel at many zero-shot tasks like image captioning, visual question answering and OCR. However, these same models suffer from poor performance at image classification tasks, …

Visual Question AnsweringImage ClassificationImage Captioning

TABED: Test-Time Adaptive Ensemble Drafting for Robust Speculative Decoding in LVLMs

2026-01-28 · Minjae Lee, Wonjun Kang, Byeongkeun Ahn, Christian Classen 외 arxiv

Speculative decoding (SD) has proven effective for accelerating LLM inference by quickly generating draft tokens and verifying them in parallel. However, SD remains largely unexplored for Large Vision-Language Models (LV…

Benchmarking and Mitigating MCQA Selection Bias of Large Vision-Language Models

2025-09-20 · Md. Atabuzzaman, Ali Asgarov, Chris Thomas arxiv

Large Vision-Language Models (LVLMs) have achieved strong performance on vision-language tasks, particularly Visual Question Answering (VQA). While prior work has explored unimodal biases in VQA, the problem of selection…

Visual Question AnsweringSemantic SimilarityVisual Reasoning