paper-with-me

홈 › Papers

Sequential Modeling Enables Scalable Learning for Large Vision Models

2023-12-01 · CVPR 2024 1 · Yutong Bai, Xinyang Geng, Karttikeya Mangalam, Amir Bar, Alan Yuille, Trevor Darrell, Jitendra Malik, Alexei A Efros

We introduce a novel sequential modeling approach which enables learning a Large Vision Model (LVM) without making use of any linguistic data. To do this, we define a common format, "visual sentences", in which we can represent raw images and videos as well as annotated data sources such as semantic segmentations and depth reconstructions without needing any meta-knowledge beyond the pixels. Once this wide variety of visual data (comprising 420 billion tokens) is represented as sequences, the model can be trained to minimize a cross-entropy loss for next token prediction. By training across various scales of model architecture and data diversity, we provide empirical evidence that our models scale effectively. Many different vision tasks can be solved by designing suitable visual prompts at test time.

📄 PDF Abstract BibTeX arXiv:2312.00785

Code (1)

ytongbai/LVM 공식 구현 jax

Tasks

Diversity

Similar Papers 제목 키워드 기반

RSRWKV: A Linear-Complexity 2D Attention Mechanism for Efficient Remote Sensing Vision Task

2025-03-26 · Chunshan Li, Rong Wang, Xiaofei Yang, Dianhui Chu

High-resolution remote sensing analysis faces challenges in global context modeling due to scene complexity and scale diversity. While CNNs excel at local feature extraction via parameter sharing, their fixed receptive f…

Spatial Reasoning

Scalable Sequential Recommendation under Latency and Memory Constraints

2026-01-13 · Adithya Parthasarathy, Aswathnarayan Muthukrishnan Kirubakaran, Vinoth Punniyamoorthy, Nachiappan Chockalingam 외 arxiv

Sequential recommender systems must model long-range user behavior while operating under strict memory and latency constraints. Transformer-based approaches achieve strong accuracy but suffer from quadratic attention com…

Sequential Recommendation

UniVid: Unifying Vision Tasks with Pre-trained Video Generation Models

2025-09-26 · Lan Chen, Yuchao Gu, Qi Mao arxiv

Large language models, trained on extensive corpora, successfully unify diverse linguistic tasks within a single generative framework. Inspired by this, recent works like Large Vision Model (LVM) extend this paradigm to …

Video Generation

BézierSketch: A generative model for scalable vector sketches

2020-07-04 · ECCV 2020 8 · Ayan Das, Yongxin Yang, Timothy Hospedales, Tao Xiang 외

The study of neural generative models of human sketches is a fascinating contemporary modeling problem due to the links between sketch image generation and the human drawing process. The landmark SketchRNN provided break…

Image Generationmodel

Task-Attentive Transformer Architecture for Continual Learning of Vision-and-Language Tasks Using Knowledge Distillation

2023-03-25 · Yuliang Cai, Jesse Thomason, Mohammad Rostami

The size and the computational load of fine-tuning large-scale pre-trained neural network are becoming two major obstacles in adopting machine learning in many applications. Continual learning (CL) can serve as a remedy …

Continual LearningKnowledge DistillationTransfer Learning