English
Related papers

Related papers: VL-JEPA: Joint Embedding Predictive Architecture f…

200 papers

Video Large Language Models (VideoLLMs) excel at video understanding tasks where outputs are textual, such as Video Question Answering and Video Captioning. However, they underperform specialized embedding-based models in Retrieval tasks,…

Computer Vision and Pattern Recognition · Computer Science 2026-04-15 Rohit Gupta , Jayakrishnan Unnikrishnan , Fan Fei , Sheng Liu , Son Tran , Mubarak Shah

Large Language Model (LLM)-based Vision-Language Models (VLMs) have substantially extended the boundaries of visual understanding capabilities. However, their high computational demands hinder deployment on resource-constrained edge…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Haotong Qin , Cheng Hu , Michele Magno

Accurate diagnosis of heart arrhythmias requires the interpretation of electrocardiograms (ECG), which capture the electrical activity of the heart. Automating this process through machine learning is challenging due to the need for large…

Signal Processing · Electrical Eng. & Systems 2024-10-21 Kuba Weimann , Tim O. F. Conrad

Tool-augmented multimodal reasoning enables visual language models (VLMs) to improve perception by interacting with external tools (e.g., cropping, depth estimation). However, such approaches incur substantial inference overhead, require…

Machine Learning · Computer Science 2026-04-10 Ashutosh Adhikari , Mirella Lapata

Recently, vision-language joint representation learning has proven to be highly effective in various scenarios. In this paper, we specifically adapt vision-language joint learning for scene text detection, a task that intrinsically involves…

Computer Vision and Pattern Recognition · Computer Science 2022-05-02 Sibo Song , Jianqiang Wan , Zhibo Yang , Jun Tang , Wenqing Cheng , Xiang Bai , Cong Yao

We introduce a two-stage self-supervised framework that combines the Joint-Embedding Predictive Architecture (JEPA) with a Density Adaptive Attention Mechanism (DAAM) for learning robust speech representations. Stage~1 uses JEPA with DAAM…

Current multimodal learning strategies primarily optimize in the original token space. Such a framework is easy to incorporate with the backbone of pretrained language model, but might result in modality collapse. To alleviate such issues,…

Machine Learning · Computer Science 2025-06-19 Hongyang Lei , Xiaolong Cheng , Qi Qin , Dan Wang , Kun Fan , Huazhen Huang , Qingqing Gu , Yetao Wu , Zhonglin Jiang , Yong Chen , Luo Ji

Joint Embedding Predictive Architectures (JEPAs) offer a compelling framework for learning world models in compact latent spaces, yet existing methods remain fragile, relying on complex multi-term losses, exponential moving averages,…

Machine Learning · Computer Science 2026-03-26 Lucas Maes , Quentin Le Lidec , Damien Scieur , Yann LeCun , Randall Balestriero

Vision-language pre-training (VLP) has shown impressive performance on a wide range of cross-modal tasks, where VLP models without reliance on object detectors are becoming the mainstream due to their superior computation efficiency and…

Computer Vision and Pattern Recognition · Computer Science 2022-11-23 Yuan Yao , Qianyu Chen , Ao Zhang , Wei Ji , Zhiyuan Liu , Tat-Seng Chua , Maosong Sun

Large Language Models (LLMs) obey consistent scaling laws -- empirical power-law fits that predict how loss decreases with compute, data, and parameters. While predictive, these laws are descriptive rather than prescriptive: they…

Machine Learning · Computer Science 2026-02-27 Hai Huang , Yann LeCun , Randall Balestriero

Vision Language Models (VLMs), which extend Large Language Models (LLM) by incorporating visual understanding capability, have demonstrated significant advancements in addressing open-ended visual question-answering (VQA) tasks. However,…

Computer Vision and Pattern Recognition · Computer Science 2023-12-19 Wenbo Hu , Yifan Xu , Yi Li , Weiyue Li , Zeyuan Chen , Zhuowen Tu

Building generalist robot policies that can handle diverse tasks in open-ended environments is a central challenge in robotics. To leverage knowledge from large-scale pretraining, prior work (VLA) has typically built generalist policies…

Robotics · Computer Science 2026-05-14 Jianke Zhang , Yucheng Hu , Yanjiang Guo , Xiaoyu Chen , Yichen Liu , Wenna Chen , Chaochao Lu , Jianyu Chen

Vision-Language Models (VLMs) have shown promising capabilities in handling various multimodal tasks, yet they struggle in long-context scenarios, particularly in tasks involving videos, high-resolution images, or lengthy image-text…

Computer Vision and Pattern Recognition · Computer Science 2024-12-16 Junqi Ge , Ziyi Chen , Jintao Lin , Jinguo Zhu , Xihui Liu , Jifeng Dai , Xizhou Zhu

Recent advancements in self-supervised learning in the point cloud domain have demonstrated significant potential. However, these methods often suffer from drawbacks, including lengthy pre-training time, the necessity of reconstruction in…

Computer Vision and Pattern Recognition · Computer Science 2025-02-11 Ayumu Saito , Prachi Kudeshia , Jiju Poovvancheri

The increasing availability of multimodal data across text, tables, and images presents new challenges for developing models capable of complex cross-modal reasoning. Existing methods for Multimodal Multi-hop Question Answering (MMQA) often…

Computer Vision and Pattern Recognition · Computer Science 2025-04-14 Qi Zhi Lim , Chin Poo Lee , Kian Ming Lim , Kalaiarasi Sonai Muthu Anbananthen

English-based Vision-Language Pre-training (VLP) has achieved great success in various downstream tasks. Some efforts have been taken to generalize this success to non-English languages through Multilingual Vision-Language Pre-training…

Computation and Language · Computer Science 2022-06-23 Liang Zhang , Anwen Hu , Qin Jin

Pre-trained language models (PLMs) have played an increasing role in multimedia research. In terms of vision-language (VL) tasks, they often serve as a language encoder and still require an additional fusion network for VL reasoning,…

Computer Vision and Pattern Recognition · Computer Science 2023-08-23 Shubin Huang , Qiong Wu , Yiyi Zhou , Weijie Chen , Rongsheng Zhang , Xiaoshuai Sun , Rongrong Ji

Joint-embedding predictive architectures (JEPAs) have shown substantial promise in self-supervised representation learning, yet their application in generative modeling remains underexplored. Conversely, diffusion models have demonstrated…

Machine Learning · Computer Science 2025-02-05 Dengsheng Chen , Jie Hu , Xiaoming Wei , Enhua Wu

Joint-embedding predictive architectures (JEPAs) propose that a model should learn more useful abstractions when trained to predict latent representations rather than observed outputs. For autoregressive language-model fine-tuning the…

Machine Learning · Computer Science 2026-05-18 Biswa Sengupta

Joint Embedding Predictive Architectures (JEPAs) learn representations able to solve numerous downstream tasks out-of-the-box. JEPAs combine two objectives: (i) a latent-space prediction term, i.e., the representation of a slightly…

Machine Learning · Computer Science 2025-10-08 Randall Balestriero , Nicolas Ballas , Mike Rabbat , Yann LeCun
‹ Prev 1 3 4 5 6 7 10 Next ›