English
Related papers

Related papers: Reward-Agnostic Prompt Optimization for Text-to-Im…

200 papers

RLHF techniques like DPO can significantly improve the generation quality of text-to-image diffusion models. However, these methods optimize for a single reward that aligns model generation with population-level preferences, neglecting the…

Machine Learning · Computer Science 2025-01-14 Meihua Dang , Anikait Singh , Linqi Zhou , Stefano Ermon , Jiaming Song

A reliable reward function is essential for reinforcement learning (RL) in image generation. Most current RL approaches depend on pre-trained preference models that output scalar rewards to approximate human preferences. However, these…

Computer Vision and Pattern Recognition · Computer Science 2025-11-26 Weijia Mao , Hao Chen , Zhenheng Yang , Mike Zheng Shou

Recently, text-to-motion models have opened new possibilities for creating realistic human motion with greater efficiency and flexibility. However, aligning motion generation with event-level textual descriptions presents unique challenges…

Computer Vision and Pattern Recognition · Computer Science 2024-12-02 Haonan Han , Xiangzuo Wu , Huan Liao , Zunnan Xu , Zhongyuan Hu , Ronghui Li , Yachao Zhang , Xiu Li

Finding effective prompts for language models (LMs) is critical yet notoriously difficult: the prompt space is combinatorially large, rewards are sparse due to expensive target-LM evaluation. Yet, existing RL-based prompt optimizers often…

Artificial Intelligence · Computer Science 2026-02-04 Junmo Cho , Suhan Kim , Sangjune An , Minsu Kim , Dong Bok Lee , Heejun Lee , Sung Ju Hwang , Hae Beom Lee

Text-to-image (T2I) generation has made significant advances in recent years, but challenges still remain in the generation of perceptual artifacts, misalignment with complex prompts, and safety. The prevailing approach to address these…

Computer Vision and Pattern Recognition · Computer Science 2025-01-14 Xiaoying Xing , Avinab Saha , Junfeng He , Susan Hao , Paul Vicol , Moonkyung Ryu , Gang Li , Sahil Singla , Sarah Young , Yinxiao Li , Feng Yang , Deepak Ramachandran

Looped Language Models (LoopLMs) perform multi-step latent reasoning prior to token generation and outperform conventional LLMs on reasoning benchmarks at smaller parameter budgets. However, attempts to further improve LoopLM reasoning with…

Machine Learning · Computer Science 2026-05-29 Jonathan Williams , Esin Tureci

We address the problem of interactive text-to-image (T2I) generation, designing a reinforcement learning (RL) agent which iteratively improves a set of generated images for a user through a sequence of prompt expansions. Using human raters,…

Computer Vision and Pattern Recognition · Computer Science 2025-05-29 Ofir Nabati , Guy Tennenholtz , ChihWei Hsu , Moonkyung Ryu , Deepak Ramachandran , Yinlam Chow , Xiang Li , Craig Boutilier

Text-to-image generative models have recently garnered significant attention due to their ability to generate images based on prompt descriptions. While these models have shown promising performance, concerns have been raised regarding the…

Computer Vision and Pattern Recognition · Computer Science 2025-09-09 Meiling Li , Zhenxing Qian , Xinpeng Zhang

Recently, Group Relative Policy Optimization (GRPO) has shown promising potential for aligning text-to-image (T2I) models, yet existing GRPO-based methods suffer from two critical limitations. (1) \textit{Shared credit assignment}:…

Computer Vision and Pattern Recognition · Computer Science 2025-12-02 Qiang Lyu , Zicong Chen , Chongxiao Wang , Haolin Shi , Shibo Gao , Ran Piao , Youwei Zeng , Jianlou Si , Fei Ding , Jing Li , Chun Pong Lau , Weiqiang Wang

This paper proposes a GRPO-based approach to enhance the performance of large language model (LLM)-based text-to-speech (TTS) models by deriving rewards from an off-the-shelf automatic speech recognition (ASR) model. Compared to previous…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-24 Chang Liu , Ya-Jun Hu , Ying-Ying Gao , Shi-Lei Zhang , Zhen-Hua Ling

Recent advancements adopt online reinforcement learning (RL) from LLMs to text-to-image rectified flow diffusion models for reward alignment. The use of group-level rewards successfully aligns the model with the targeted reward. However, it…

Machine Learning · Computer Science 2026-01-06 Yiyang Wang , Xi Chen , Xiaogang Xu , Yu Liu , Hengshuang Zhao

Diffusion models generate highly realistic images but often struggle with precise text-image alignment. While recent post-training methods improve alignment using external rewards or human preference signals, their performance heavily…

Machine Learning · Computer Science 2026-05-29 Jaa-Yeon Lee , Yeobin Hong , Taesung Kwon , Jong Chul Ye

Reward design in reinforcement learning (RL) is challenging since specifying human notions of desired behavior may be difficult via reward functions or require many expert demonstrations. Can we instead cheaply design rewards using a…

Machine Learning · Computer Science 2023-03-02 Minae Kwon , Sang Michael Xie , Kalesha Bullard , Dorsa Sadigh

The rapid evolution of Text-to-Video (T2V) diffusion models has driven remarkable advancements in generating high-quality, temporally coherent videos from natural language descriptions. Despite these achievements, their vulnerability to…

Computer Vision and Pattern Recognition · Computer Science 2026-01-01 Changzhen Li , Yuecong Min , Jie Zhang , Zheng Yuan , Shiguang Shan , Xilin Chen

Text-to-image (T2I) models can generate not-safe-for-work (NSFW) content, motivating multi-stage safety pipelines with both text and image filters. Newer LLM-based filters detect latent intent beyond keywords, making token-level…

Machine Learning · Computer Science 2026-05-26 Zixuan Chen , Hao Lin , Ke Xu , Xinghao Jiang , Tanfeng Sun

Text-to-Image (T2I) models, represented by DALL$\cdot$E and Midjourney, have gained huge popularity for creating realistic images. The quality of these images relies on the carefully engineered prompts, which have become valuable…

Cryptography and Security · Computer Science 2026-01-22 Shiqian Zhao , Chong Wang , Yiming Li , Yihao Huang , Wenjie Qu , Siew-Kei Lam , Yi Xie , Kangjie Chen , Jie Zhang , Tianwei Zhang

Intent detection, a critical component in task-oriented dialogue (TOD) systems, faces significant challenges in adapting to the rapid influx of integrable tools with complex interrelationships. Existing approaches, such as zero-shot…

Computation and Language · Computer Science 2025-04-22 Zihao Feng , Xiaoxue Wang , Ziwei Bai , Donghang Su , Bowen Wu , Qun Yu , Baoxun Wang

Text-to-image (T2I) generation models have made significant strides but still struggle with prompt sensitivity: even minor changes in prompt wording can yield inconsistent or inaccurate outputs. To address this challenge, we introduce a…

Machine Learning · Computer Science 2025-07-31 Mohammad Abdul Hafeez Khan , Yash Jain , Siddhartha Bhattacharyya , Vibhav Vineet

Recent advances have shown that optimizing prompts for Large Language Models (LLMs) can significantly improve task performance, yet many optimization techniques rely on heuristics or manual exploration. We present LatentPrompt, a…

Computation and Language · Computer Science 2025-08-05 Mateusz Bystroński , Grzegorz Piotrowski , Nitesh V. Chawla , Tomasz Kajdanowicz

Autoregressive (AR) models are highly effective for image generation, yet their standard maximum-likelihood estimation training lacks direct optimization for sample quality and diversity. While reinforcement learning (RL) has been used to…

Machine Learning · Computer Science 2026-03-25 Orhun Buğra Baran , Melih Kandemir , Ramazan Gokberk Cinbis