Prompt Optimization for T2V Generation

T2V: Text-to-Video

Follow this topic Ask about this topic

Latest papers

12 papers3 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

FlowCred: Hierarchical Credit Assignment and Functional Coordination for Joint Text-to-Video Post-Training
Oct 13, 2026Mingxuan Zhu, Yanwei Huang, Shiyuan Liu +4T2V Generation Prompt Optimization for T2V Generation
Shanghai Jiao Tong University · KlingAI · The Hong Kong University of Science and Technology +2
TIDE: Trajectory-Informed Skill Distillation for Efficient Text-to-Video Prompt Optimization
Oct 10, 2026Chengxing Zhou, Yuliang Huang, Jingwei SongPrompt Optimization for T2V Generation Skill Distillation
Sun Yat-sen University, China · The University of Hong Kong, China
SkillPE: Creativity-Oriented Cinematic Skill Evolution for Text-to-Video Prompt Engineering
Sep 28, 2026Yanwei Huang, Mingxuan Zhu, Shujie Li +3T2V Generation Video Generation
HKUST · KlingAI · Shanghai Jiaotong University +1
WanPE: Towards Cinematic Prompt Enhancement for Modern Text-to-Video Generation
Sep 24, 2026Yubo Zhu, Yawen Shao, Ziyun Dai +27Prompt Optimization for T2V Generation T2V Generation
Nanjing University · Wan Team, Alibaba Group · University of Science and Technology of China +2
From Evaluation to Enhancement: Benchmarking and Improving Think-with-Video Reasoning for Video Generative Models
Sep 10, 2026Meng Luo, Yicheng Liu, Jiahao Wang +5Prompt Optimization for T2V Generation Video Generation
School of Computing, National University of Singapore, Singapore, Singapore · Kling Team, Kuaishou Technology, Beijing, China · Department of Computer Science and Technology, Nanjing University, Nanjing, China +1
Identity-Preserving Text-to-Video Generation via Agentic Enhancement and Semantic Repair
Aug 21, 2026Jiayi Gao, Changcheng Hua, Jiaqi Tang +2Prompt Optimization for T2V Generation Identity-Preserving Video Generation
Wangxuan Institute of Computer Technology, Peking University Beijing, China
CAPE-T2V: Captioner-Anchored Prompt Enhancement toward Two-Sided Conditioning Alignment in Text-to-Video Generation
Aug 4, 2026Yizhuo Jia, Jingyun Hua, Yuanxing ZhangDiffusion Transformer Prompt Optimization for T2V Generation
1Fudan University · 2Kling Team
MagicPrompt: Ultra-Lightweight Prompt Tuning for Video Generation
Jul 16, 2026Yinhan Zhang, Dinwei Tan, Xianghao Kong +3Video Diffusion Models Diffusion Model Fine-Tuning
HKUST · Tencent · HKUST(GZ)
SCMAPR: Self-Correcting Multi-Agent Prompt Refinement for Complex-Scenario Text-to-Video Generation
Apr 7, 2026Chengyi Yang, Pengzhen Li, Jiayin Qi +3Prompt Optimization for T2V Generation T2V Generation
HiThink Research · East China Normal University · Guangzhou University +1
VQQA: An Agentic Approach for Video Evaluation and Quality Improvement
Mar 12, 2026Yiwen Song, Tomas Pfister, Yale SongPrompt Optimization for T2V Generation Video Generation
Google
PhyPrompt: RL-based Prompt Refinement for Physically Plausible Text-to-Video Generation
Mar 3, 2026Shang Wu, Chenwei Xu, Zhuofan Xia +6Prompt Optimization for T2V Generation Physical Consistency in Video Generation
Northwestern University · Dolby Laboratories
Retrieval, Refinement, and Ranking for Text-to-Video Generation via Prompt Optimization and Test-Time Scaling
Mar 2, 2026Zillur Rahman, Alex Sheng, Cristian MeoPrompt Optimization for T2V Generation Retrieval-Augmented Video Generation
Algoverse AI

Oct 13, 2026J/K move · Enter open · S save

FlowCred: Hierarchical Credit Assignment and Functional Coordination for Joint Text-to-Video Post-Training

Mingxuan Zhu, Yanwei Huang, Shiyuan Liu, Xinzhi Zhang+3

Shanghai Jiao Tong University · KlingAI · The Hong Kong University of Science and Technology+2

T2V Generation Prompt Optimization for T2V Generation Prompt Optimization RL for Video Generation Credit Assignment in RL

Open paper AskPDF arXiv

Prompt optimization and generator post-training are two complementary ways to improve text-to-video (T2V) generation, and recent systems increasingly train both modules jointly. However, optimizing a prompt policy and a video generator from the same terminal reward creates two ambiguities: prompt quality is confounded with stochastic generation, and the two modules may realize overlapping local improvements. We introduce FlowCred, a two-level framework for joint T2V post-training. First, hierarchical credit assignment uses matched prompt-seed rollout grids to separate prompt-level credit from prompt-conditioned generator residuals under shared randomness. Second, functional coordination probes alternative current-policy prompts at states from actual generation trajectories, providing generator-aware evidence for prompt optimization while selectively attenuating generator updates already supported by conditioning changes. Across multiple T2V benchmarks, FlowCred consistently improves matched joint-training baselines. On LTX-2.5, FlowCred improves a strictly matched joint-training control from 61.47 to 64.46 on T2V-CompBench and from 55.58 to 58.08 on StoryEval, without increasing decoded-video or reward-model-call budgets. Factorial and realized-update analyses show complementary contributions from prompt shaping and generator routing, while human evaluation and transfer across backbones and updater families provide further supporting evidence.