English
Related papers

Related papers: A Comparative Study of Training Objectives for Cla…

200 papers

Prompt tuning has become a new paradigm for model tuning and it has demonstrated success in natural language pretraining and even vision pretraining. In this work, we explore the transfer of prompt tuning to multimodal pretraining, with a…

Computation and Language · Computer Science 2022-08-05 Hao Yang , Junyang Lin , An Yang , Peng Wang , Chang Zhou , Hongxia Yang

We study the training objectives of denoising-based generative models, with a particular focus on loss weighting and output parameterization, including noise-, clean image-, and velocity-based formulations. Through a systematic numerical…

Computer Vision and Pattern Recognition · Computer Science 2026-04-20 Anne Gagneux , Ségolène Martin , Rémi Gribonval , Mathurin Massias

Generative models can serve as surrogates for some real data sources by creating synthetic training datasets, but in doing so they may transfer biases to downstream tasks. We focus on protecting quality and diversity when generating…

Computers and Society · Computer Science 2025-09-08 Allen Chang , Matthew C. Fontaine , Serena Booth , Maja J. Matarić , Stefanos Nikolaidis

Many natural language processing applications use language models to generate text. These models are typically trained to predict the next word in a sequence, given the previous words and some context such as an image. However, at test time…

Machine Learning · Computer Science 2016-05-10 Marc'Aurelio Ranzato , Sumit Chopra , Michael Auli , Wojciech Zaremba

Question Generation (QG), as a challenging Natural Language Processing task, aims at generating questions based on given answers and context. Existing QG methods mainly focus on building or training models for specific QG datasets. These…

Computation and Language · Computer Science 2022-12-06 Wei Yuan , Hongzhi Yin , Tieke He , Tong Chen , Qiufeng Wang , Lizhen Cui

Due to the subjective crowdsourcing annotations and the inherent inter-class similarity of facial expressions, the real-world Facial Expression Recognition (FER) datasets usually exhibit ambiguous annotation. To simplify the learning…

Computer Vision and Pattern Recognition · Computer Science 2025-12-04 Weijie Wang , Bo Li , Nicu Sebe , Bruno Lepri

We propose CHRT (Control Hidden Representation Transformation) - a controlled language generation framework that steers large language models to generate text pertaining to certain attributes (such as toxicity). CHRT gains attribute control…

Computation and Language · Computer Science 2023-06-01 Vaibhav Kumar , Hana Koorehdavoudi , Masud Moshtaghi , Amita Misra , Ankit Chadha , Emilio Ferrara

Generating 3D faces from textual descriptions has a multitude of applications, such as gaming, movie, and robotics. Recent progresses have demonstrated the success of unconditional 3D face generation and text-to-3D shape generation.…

Computer Vision and Pattern Recognition · Computer Science 2023-09-01 Cuican Yu , Guansong Lu , Yihan Zeng , Jian Sun , Xiaodan Liang , Huibin Li , Zongben Xu , Songcen Xu , Wei Zhang , Hang Xu

Multimodal pretraining is an effective strategy for the trinity of goals of representation learning in autonomous robots: 1) extracting both local and global task progressions; 2) enforcing temporal consistency of visual representation; 3)…

While machine learning models have achieved unprecedented success in real-world applications, they might make biased/unfair decisions for specific demographic groups and hence result in discriminative outcomes. Although research efforts…

Machine Learning · Computer Science 2022-12-08 Yuying Zhao , Yu Wang , Tyler Derr

Scientific expertise often requires recognizing subtle visual differences that remain challenging to articulate even for domain experts. We present a system that leverages generative models to automatically discover and visualize minimal…

Computer Vision and Pattern Recognition · Computer Science 2025-05-16 Mia Chiquier , Orr Avrech , Yossi Gandelsman , Berthy Feng , Katherine Bouman , Carl Vondrick

Recent approaches to question generation have used modifications to a Seq2Seq architecture inspired by advances in machine translation. Models are trained using teacher forcing to optimise only the one-step-ahead prediction. However, at…

Computation and Language · Computer Science 2019-06-04 Tom Hosking , Sebastian Riedel

Face recognition (FR) models are vulnerable to performance variations across demographic groups. The causes for these performance differences are unclear due to the highly complex deep learning-based structure of face recognition models.…

Computer Vision and Pattern Recognition · Computer Science 2025-01-29 Marco Huber , Fadi Boutros , Naser Damer

In dialogue systems, utterances with similar semantics may have distinctive emotions under different contexts. Therefore, modeling long-range contextual emotional relationships with speaker dependency plays a crucial part in dialogue…

Computation and Language · Computer Science 2022-01-25 Shimin Li , Hang Yan , Xipeng Qiu

The two underlying requirements of face age progression, i.e. aging accuracy and identity permanence, are not well studied in the literature. In this paper, we present a novel generative adversarial network based approach. It separately…

Computer Vision and Pattern Recognition · Computer Science 2019-01-11 Hongyu Yang , Di Huang , Yunhong Wang , Anil K. Jain

Long-horizon AI agents execute complex workflows spanning hundreds of sequential actions, yet a single wrong assumption early on can cascade into irreversible errors. When instructions are incomplete, the agent must decide not only whether…

Computation and Language · Computer Science 2026-05-11 Anmol Gulati , Hariom Gupta , Elias Lumer , Sahil Sen , Vamse Kumar Subbiah

Unsupervised learning objectives like autoregressive and masked language modeling constitute a significant part in producing pre-trained representations that perform various downstream applications from natural language understanding to…

Computation and Language · Computer Science 2025-04-01 Junghyun Min , Minho Lee , Woochul Lee , Yeonsoo Lee

Counterfactual explanations (CFs) provide human-interpretable insights into model's predictions by identifying minimal changes to input features that would alter the model's output. However, existing methods struggle to generate multiple…

Machine Learning · Computer Science 2026-02-20 Oleksii Furman , Patryk Marszałek , Jan Masłowski , Piotr Gaiński , Maciej Zięba , Marek Śmieja

Conditioning image generation on specific features of the desired output is a key ingredient of modern generative models. However, existing approaches lack a general and unified way of representing structural and semantic conditioning at…

Computer Vision and Pattern Recognition · Computer Science 2024-07-08 Luca Butera , Andrea Cini , Alberto Ferrante , Cesare Alippi

This paper proposes a step toward obtaining general models of knowledge for facial analysis, by addressing the question of multi-source transfer learning. More precisely, the proposed approach consists in two successive training steps: the…

Machine Learning · Computer Science 2019-11-11 Valentin Vielzeuf , Alexis Lechervy , Stéphane Pateux , Frédéric Jurie