English
Related papers

Related papers: RankE: End-to-End Post-Training for Discrete Text-…

200 papers

Maximum likelihood estimation (MLE) is the predominant algorithm for training text generation models. This paradigm relies on direct supervision examples, which is not applicable to many emerging applications, such as generating adversarial…

Computation and Language · Computer Science 2022-10-25 Han Guo , Bowen Tan , Zhengzhong Liu , Eric P. Xing , Zhiting Hu

World model-based policy evaluation is a practical proxy for testing real-world robot control by rolling out candidate actions in action-conditioned video diffusion models. As these models increasingly adopt latent diffusion modeling (LDM),…

Computer Vision and Pattern Recognition · Computer Science 2026-05-08 Nilaksh , Saurav Jha , Artem Zholus , Sarath Chandar

Text-to-image generative models often struggle with long prompts detailing complex scenes, diverse objects with distinct visual characteristics and spatial relationships. In this work, we propose SCoPE (Scheduled interpolation of…

Computer Vision and Pattern Recognition · Computer Science 2025-06-02 Ketan Suhaas Saichandran , Xavier Thomas , Prakhar Kaushik , Deepti Ghadiyaram

Text-to-motion generation has advanced with diffusion- and flow-based generative models, yet supervised pretraining remains insufficient to align models with high-level objectives such as semantic consistency, realism, and human preference.…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Xiaofeng Tan , Wanjiang Weng , Hongsong Wang , Fang Zhao , Xin Geng , Liang Wang

Recently, instruction-based image editing (IIE) has received widespread attention. In practice, IIE often modifies only specific regions of an image, while the remaining areas largely remain unchanged. Although these two types of regions…

Computer Vision and Pattern Recognition · Computer Science 2025-10-30 Pengtao Chen , Xianfang Zeng , Maosen Zhao , Mingzhu Shen , Peng Ye , Bangyin Xiang , Zhibo Wang , Wei Cheng , Gang Yu , Tao Chen

Although autoregressive models have achieved promising results on image generation, their unidirectional generation process prevents the resultant images from fully reflecting global contexts. To address the issue, we propose an effective…

Computer Vision and Pattern Recognition · Computer Science 2022-06-10 Doyup Lee , Chiheon Kim , Saehoon Kim , Minsu Cho , Wook-Shin Han

We present Deep Compression Autoencoder (DC-AE), a new family of autoencoder models for accelerating high-resolution diffusion models. Existing autoencoder models have demonstrated impressive results at a moderate spatial compression ratio…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Junyu Chen , Han Cai , Junsong Chen , Enze Xie , Shang Yang , Haotian Tang , Muyang Li , Yao Lu , Song Han

Recently, post-training methods based on reinforcement learning, with a particular focus on Group Relative Policy Optimization (GRPO), have emerged as the robust paradigm for further advancement of text-to-image (T2I) models. However, these…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Haoyuan Sun , Jing Wang , Yuxin Song , Yu Lu , Bo Fang , Yifu Luo , Jun Yin , Pengyu Zeng , Miao Zhang , Tiantian Zhang , Xueqian Wang , Shijian Lu

Masked Autoencoders (MAEs) learn generalizable representations for image, text, audio, video, etc., by reconstructing masked input data from tokens of the visible data. Current MAE approaches for videos rely on random patch, tube, or…

Computer Vision and Pattern Recognition · Computer Science 2022-11-17 Wele Gedara Chaminda Bandara , Naman Patel , Ali Gholami , Mehdi Nikkhah , Motilal Agrawal , Vishal M. Patel

Flexible image tokenizers aim to represent an image using an ordered 1D variable-length token sequence. This flexible tokenization is typically achieved through nested dropout, where a portion of trailing tokens is randomly truncated during…

Computer Vision and Pattern Recognition · Computer Science 2026-01-06 Zixuan Fu , Lanqing Guo , Chong Wang , Binbin Song , Ding Liu , Bihan Wen

Existing text-guided image editing methods primarily rely on end-to-end pixel-level inpainting paradigm. Despite its success in simple scenarios, this paradigm still significantly struggles with compositional editing tasks that require…

Computer Vision and Pattern Recognition · Computer Science 2026-04-08 Jinghan Yu , Junhao Xiao , Chenyu Zhu , Jiaming Li , Jia Li , HanMing Deng , Xirui Wang , Guoli Jia , Jianjun Li , Xiang Bai , Bowen Zhou , Zhiyuan Ma

Autoregressive models excel in sequential modeling and have proven to be effective for vision-language data. However, the spatial nature of visual signals conflicts with the sequential dependencies of next-token prediction, leading to…

Computer Vision and Pattern Recognition · Computer Science 2025-10-02 Jiamian Wang , Ziqi Zhou , Chaithanya Kumar Mummadi , Sohail Dianat , Majid Rabbani , Raghuveer Rao , Chen Qiu , Zhiqiang Tao

Text-to-image (T2I) models can effectively capture the content or style of reference images to perform high-quality customization. A representative technique for this is fine-tuning using low-rank adaptations (LoRA), which enables efficient…

Computer Vision and Pattern Recognition · Computer Science 2024-12-13 Geonhui Jang , Jin-Hwa Kim , Yong-Hyun Park , Junho Kim , Gayoung Lee , Yonghyun Jeong

Visual generation grounded in Visual Foundation Model (VFM) representations offers a highly promising unified pathway for integrating visual understanding, perception, and generation. Despite this potential, training large-scale…

Computer Vision and Pattern Recognition · Computer Science 2025-12-15 Minglei Shi , Haolin Wang , Borui Zhang , Wenzhao Zheng , Bohan Zeng , Ziyang Yuan , Xiaoshi Wu , Yuanxing Zhang , Huan Yang , Xintao Wang , Pengfei Wan , Kun Gai , Jie Zhou , Jiwen Lu

Latent Diffusion Models (LDMs) rely heavily on the compressed latent space provided by Variational Autoencoders (VAEs) for high-quality image generation. Recent studies have attempted to obtain generation-friendly VAEs by directly adopting…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 John Page , Xuesong Niu , Kai Wu , Kun Gai

This work aims to learn a high-quality text-to-video (T2V) generative model by leveraging a pre-trained text-to-image (T2I) model as a basis. It is a highly desirable yet challenging task to simultaneously a) accomplish the synthesis of…

Although end-to-end (E2E) trainable automatic speech recognition (ASR) has shown great success by jointly learning acoustic and linguistic information, it still suffers from the effect of domain shifts, thus limiting potential applications.…

Audio and Speech Processing · Electrical Eng. & Systems 2023-08-28 Keqi Deng , Philip C. Woodland

Video understanding has witnessed significant progress with recent video foundation models demonstrating strong performance owing to self-supervised pre-training objectives; Masked Autoencoders (MAE) being the design of choice.…

Deterministic Rank Reduction Autoencoders (RRAEs) enforce by construction a regularization on the latent space by applying a truncated SVD. While this regularization makes Autoencoders more powerful, using them for generative purposes is…

Machine Learning · Computer Science 2025-10-15 Jad Mounayer , Alicia Tierz , Jerome Tomezyk , Chady Ghnatios , Francisco Chinesta

Recent advances in image tokenizers, such as VQ-VAE, have enabled text-to-image generation using auto-regressive methods, similar to language modeling. However, these methods have yet to leverage pre-trained language models, despite their…

Computer Vision and Pattern Recognition · Computer Science 2024-09-26 Yuhui Zhang , Brandon McKinzie , Zhe Gan , Vaishaal Shankar , Alexander Toshev