Frank Wang

  ![](/sites/default/files/person/FrankWang.JPG)

 ### Publications

### 2026

[Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents](/index.php/publication/2026-12_mid-harness-scaling-actions-between-model-and-harness-terminal-agents)

Minki Kang, [Ryo Hachiuma](/index.php/person/ryo-hachiuma), [Shaokun Zhang](/index.php/person/shaokun-zhang), Subhashree Radhakrishnan, [Yonggan Fu](/index.php/person/yonggan-fu), [Jindong Jiang](/index.php/person/jindong-jiang), [Mingjie Liu](/index.php/person/mingjie-liu), Ehsan Hosseini-Asl, [Yi Dong](/index.php/person/yi-dong), [Yu-Chiang Frank Wang](/index.php/person/frank-wang), [Byung-Kwan Lee](/index.php/person/byung-kwan-lee)

[ArXiv](https://arxiv.org/abs/2609.39982)

[Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients](/publication/2026-12_zone-proximal-policy-optimization-teacher-prompts-not-gradients)

[Byung-Kwan Lee](/person/byung-kwan-lee), Ximing Lu, Shizhe Diao, Minki Kang, [Saurav Muralidharan](/person/saurav-muralidharan), Karan Sapra, Andrew Tao, [Frank Wang](/person/frank-wang), [Ryo Hachiuma](/person/ryo-hachiuma)

[ArXiv](https://arxiv.org/abs/2606.18216)

[Agent Explorative Policy Optimization for Multimodal Agentic Reasoning](/publication/2026-12_agent-explorative-policy-optimization-multimodal-agentic-reasoning)

Minki Kang, Shizhe Diao, [Ryo Hachiuma](/person/ryo-hachiuma), Sung Ju Hwang, [Pavlo Molchanov](/person/pavlo-molchanov), [Yu-Chiang Frank Wang](/person/frank-wang), [Byung-Kwan Lee](/person/byung-kwan-lee)

[NeurIPS 2026](https://arxiv.org/abs/2605.28774)

[SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning](/publication/2026-12_spatialclaw-rethinking-action-interface-agentic-spatial-reasoning)

Seokju Cho, [Ryo Hachiuma](/person/ryo-hachiuma), [Abhishek Badki](/person/abhishek-badki), [Hang Su](/person/hang-su), [Byung-Kwan Lee](/person/byung-kwan-lee), Chan Hee Song, [Sifei Liu](/person/sifei-liu), Subhashree Radhakrishnan, Seungryong Kim, [Yu-Chiang Frank Wang](/person/frank-wang), [Min-Hung Chen](/person/min-hung-chen)

[NeurIPS 2026](https://arxiv.org/abs/2606.13673)

[GenRecal: Generation after Recalibration from Large to Small Vision-Language Models](/publication/2026-09_genrecal-generation-after-recalibration-large-small-vision-language-models)

[Byung-Kwan Lee](/person/byung-kwan-lee), [Ryo Hachiuma](/person/ryo-hachiuma), Yong Man Ro, [Yu-Chiang Frank Wang](/person/frank-wang), Yueh-Hua Wu

[ECCV 2026](https://arxiv.org/abs/2506.15681)

[Masking Teacher and Reinforcing Student for Distilling Vision-Language Models](/publication/2026-06_masking-teacher-and-reinforcing-student-distilling-vision-language-models)

[Byung-Kwan Lee](/person/byung-kwan-lee), [Yu-Chiang Frank Wang](/person/frank-wang), [Ryo Hachiuma](/person/ryo-hachiuma)

[CVPR 2026](https://arxiv.org/abs/2512.22238)

[Test-Time Alignment for Large Language Models via Textual Model Predictive Control](/publication/2026-04_test-time-alignment-large-language-models-textual-model-predictive-control)

Kuang-Da Wang, Teng-Ruei Chen, Yu Heng Hung, Guo-Xun Ko, Shuoyang Ding, [Frank Wang](/person/frank-wang), [Huck Yang](/person/huck-yang), Wen-Chih Peng, Ping-Chun Hsieh

[ICLR](https://openreview.net/forum?id=DsS3xRPSs5)

### 2025

[ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning](/index.php/publication/2025-12_thinkact-vision-language-action-reasoning-reinforced-visual-latent-planning)

[Chi-Pin Huang](/index.php/person/chi-pin-huang), Yueh-Hua Wu, [Min-Hung Chen](/index.php/person/min-hung-chen), [Frank Wang](/index.php/person/frank-wang), [Fred Yang](/index.php/person/fred-yang)

[Neural Information Processing Systems (NeurIPS) 2025](https://arxiv.org/pdf/2507.16815)

[Unified Reinforcement and Imitation Learning for Vision-Language Models](/publication/2025-12_unified-reinforcement-and-imitation-learning-vision-language-models)

[Byung-Kwan Lee](/person/byung-kwan-lee), [Ryo Hachiuma](/person/ryo-hachiuma), Yong Man Ro, [Yu-Chiang Frank Wang](/person/frank-wang), Yueh-Hua Wu

[NeurIPS 2025](https://arxiv.org/abs/2510.19307)

[VoiceNoNG: Robust High-Quality Speech Editing Model without Hallucinations](/publication/2025-08_voicenong-robust-high-quality-speech-editing-model-without-hallucinations)

[Sung-Feng Huang](/person/sung-feng-huang), Heng-Cheng Kuo, Zhehuai Chen, Xuesong Yang, Pin-Jui Ku, Ante Jukić, [Huck Yang](/person/huck-yang), Yu Tsao, [Frank Wang](/person/frank-wang), Hung-yi Lee, [Szu-Wei Fu](/person/szu-wei-fu)

[Interspeech 2025](https://www.interspeech2025.org/home)

[VLsI: Verbalized Layers-to-Interactions from Large to Small Vision Language Models](/publication/2025-06_vlsi-verbalized-layers-interactions-large-small-vision-language-models)

[Byung-Kwan Lee](/person/byung-kwan-lee), [Ryo Hachiuma](/person/ryo-hachiuma), Yong Man Ro, [Yu-Chiang Frank Wang](/person/frank-wang), Yueh-Hua Wu

[CVPR 2025](https://arxiv.org/abs/2412.01822)

[UniWav: Towards Unified Pre-training for Speech Representation Learning and Generation](/publication/2025-04_uniwav-towards-unified-pre-training-speech-representation-learning-and)

Alexander H. Liu, Sang-gil Lee, [Huck Yang](/person/huck-yang), Yuan Gong, [Frank Wang](/person/frank-wang), James R. Glas, Rafael Valle

[ICLR 2025](https://openreview.net/forum?id=yj9lLwMjnE)

[Semantic Prompt Learning for Weakly-Supervised Semantic Segmentation](/index.php/publication/2025-02_semantic-prompt-learning-weakly-supervised-semantic-segmentation)

Ci-Siang Lin, Chien-Yi Wang, [Frank Wang](/index.php/person/frank-wang), [Min-Hung Chen](/index.php/person/min-hung-chen)

[Winter Conference on Applications of Computer Vision (WACV)](https://wacv2025.thecvf.com/)

### 2024

[Diffusion-Reward Adversarial Imitation Learning](/publication/2024-12_diffusion-reward-adversarial-imitation-learning)

Chun-Mao Lai, Hsiang-Chun Wang, Ping-Chun Hsieh, [Frank Wang](/person/frank-wang), [Min-Hung Chen](/person/min-hung-chen), Shao-Hua Sun

[Neural Information Processing Systems (NeurIPS)](https://neurips.cc/Conferences/2024)

[Detecting the Undetectable: Assessing the Efficacy of Current Spoof Detection Methods Against Seamless Speech Edits](/publication/2024-12_detecting-undetectable-assessing-efficacy-current-spoof-detection-methods)

[Sung-Feng Huang](/person/sung-feng-huang), Heng-Cheng Kuo, Zhehuai Chen, Xuesong Yang, [Huck Yang](/person/huck-yang), Yu Tsao, [Frank Wang](/person/frank-wang), Hung-yi Lee, [Szu-Wei Fu](/person/szu-wei-fu)

[IEEE SLT 2024](https://2024.ieeeslt.org/)

[DoRA: Weight-Decomposed Low-Rank Adaptation](/publication/2024-07_dora-weight-decomposed-low-rank-adaptation)

Shih-Yang Liu, Chien-Yi Wang, Hongxu Danny Yin, [Pavlo Molchanov](/person/pavlo-molchanov), [Frank Wang](/person/frank-wang), Kwang-Ting Cheng, [Min-Hung Chen](/person/min-hung-chen)

[International Conference on Machine Learning (ICML) 2024](https://icml.cc/Conferences/2024)

### 2023

[Target-free Text-guided Image Manipulation](/publication/2023-02_target-free-text-guided-image-manipulation)

Wan-Cyuan Fan, Cheng-Fu Yang, Chiao-An Yang, [Frank Wang](/person/frank-wang)

[AAAI 2023](https://aaai.org/Conferences/AAAI-23/)

[Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesis](/index.php/publication/2023-02_frido-feature-pyramid-diffusion-complex-scene-image-synthesis)

Wan-Cyuan Fan, Yen-Chun Chen, Dongdong Chen, Yu Cheng, Lu Yuan, [Frank Wang](/index.php/person/frank-wang)

[AAAI 2023](https://aaai.org/Conferences/AAAI-23/)

[Self-Supervised Pyramid Representation Learning for Multi-Label Visual Analysis and Beyond](/index.php/publication/2023-01_self-supervised-pyramid-representation-learning-multi-label-visual-analysis-and)

Cheng-Yen Hsieh, Chih-Jung Chang, Fu-En Yang, [Frank Wang](/index.php/person/frank-wang)

[WACV 2023](https://wacv2023.thecvf.com/home)

### 2022

[Paraphrasing Is All You Need for Novel Object Captioning](/publication/2022-11_paraphrasing-all-you-need-novel-object-captioning)

Cheng-Fu Yang, Yao-Hung Hubert Tsai, Wan-Cyuan Fan, Ruslan Salakhutdinov, Louis-Philippe Morency, [Frank Wang](/person/frank-wang)

[NeurIPS 2022](https://nips.cc/)

[SPoVT: Semantic-Prototype Variational Transformer for Dense Point Cloud Semantic Completion](/publication/2022-11_spovt-semantic-prototype-variational-transformer-dense-point-cloud-semantic)

Sheng-Yu Huang, Hao-Yu Hsu, [Yu-Chiang Frank Wang](/person/frank-wang)

[NeurIPS 2022](https://nips.cc/)
