Author name cluster

Frank Wang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

6 papers

1 author row

NeurIPS Conference 2025 Conference Paper

EMLoC: Emulator-based Memory-efficient Fine-tuning with LoRA Correction

Hsi-Che Lin
Yu-Chu Yu
Kai-Po Chang
Frank Wang

Open-source foundation models have seen rapid adoption and development, enabling powerful general-purpose capabilities across diverse domains. However, fine-tuning large foundation models for domain-specific or personalized tasks remains prohibitively expensive for most users due to the significant memory overhead beyond that of inference. We introduce EMLoC, an Emulator-based Memory-efficient fine-tuning framework with LoRA Correction, which enables model fine-tuning within the same memory budget required for inference. EMLoC constructs a task-specific light-weight emulator using activation-aware singular value decomposition (SVD) on a small downstream calibration set. Fine-tuning then is performed on this lightweight emulator via LoRA. To tackle the misalignment between the original model and the compressed emulator, we propose a novel compensation algorithm to correct the fine-tuned LoRA module, which thus can be merged into the original model for inference. EMLoC supports flexible compression ratios and standard training pipelines, making it adaptable to a wide range of applications. Extensive experiments demonstrate that EMLoC outperforms other baselines across multiple datasets and modalities. Moreover, without quantization, EMLoC enables fine-tuning of a 38B model, which originally required 95GB of memory, on a single 24GB consumer GPU—bringing efficient and practical model adaptation to individual users.

PDF Details

NeurIPS Conference 2025 Conference Paper

ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning

Chi-Pin Huang
Yueh-Hua Wu
Min-Hung Chen
Frank Wang
Fu-En Yang

Vision-language-action (VLA) reasoning tasks require agents to interpret multimodal instructions, perform long-horizon planning, and act adaptively in dynamic environments. Existing approaches typically train VLA models in an end-to-end fashion, directly mapping inputs to actions without explicit reasoning, which hinders their ability to plan over multiple steps or adapt to complex task variations. In this paper, we propose ThinkAct, a dual-system framework that bridges high-level reasoning with low-level action execution via reinforced visual latent planning. ThinkAct trains a multimodal LLM to generate embodied reasoning plans guided by reinforcing action-aligned visual rewards based on goal completion and trajectory consistency. These reasoning plans are compressed into a visual plan latent that conditions a downstream action model for robust action execution on target environments. Extensive experiments on embodied reasoning and robot manipulation benchmarks demonstrate that ThinkAct enables few-shot adaptation, long-horizon planning, and self-correction behaviors in complex embodied AI tasks.

PDF Details

NeurIPS Conference 2025 Conference Paper

Unified Reinforcement and Imitation Learning for Vision-Language Models

Byung-Kwan Lee
Ryo Hachiuma
Yong Man Ro
Frank Wang
Yueh-Hua Wu

Vision-Language Models (VLMs) have achieved remarkable progress, yet their large scale often renders them impractical for resource-constrained environments. This paper introduces Unified Reinforcement and Imitation Learning (RIL), a novel and efficient training algorithm designed to create powerful, lightweight VLMs. RIL distinctively combines the strengths of reinforcement learning with adversarial imitation learning. This enables smaller student VLMs not only to mimic the sophisticated text generation of large teacher models but also to systematically improve their generative capabilities through reinforcement signals. Key to our imitation framework is a LLM-based discriminator that adeptly distinguishes between student and teacher outputs, complemented by guidance from multiple large teacher VLMs to ensure diverse learning. This unified learning strategy, leveraging both reinforcement and imitation, empowers student models to achieve significant performance gains, making them competitive with leading closed-source VLMs. Extensive experiments on diverse vision-language benchmarks demonstrate that RIL significantly narrows the performance gap with state-of-the-art open- and closed-source VLMs and, in several instances, surpasses them.

PDF Details

NeurIPS Conference 2023 Conference Paper

Modality-Independent Teachers Meet Weakly-Supervised Audio-Visual Event Parser

Yung-Hsuan Lai
Yen-Chun Chen
Frank Wang

Audio-visual learning has been a major pillar of multi-modal machine learning, where the community mostly focused on its $\textit{modality-aligned}$ setting, $\textit{i. e. }$, the audio and visual modality are $\textit{both}$ assumed to signal the prediction target. With the Look, Listen, and Parse dataset (LLP), we investigate the under-explored $\textit{unaligned}$ setting, where the goal is to recognize audio and visual events in a video with only weak labels observed. Such weak video-level labels only tell what events happen without knowing the modality they are perceived (audio, visual, or both). To enhance learning in this challenging setting, we incorporate large-scale contrastively pre-trained models as the modality teachers. A simple, effective, and generic method, termed $\textbf{V}$isual-$\textbf{A}$udio $\textbf{L}$abel Elab$\textbf{or}$ation (VALOR), is innovated to harvest modality labels for the training events. Empirical studies show that the harvested labels significantly improve an attentional baseline by $\textbf{8. 0}$ in average F-score (Type@AV). Surprisingly, we found that modality-independent teachers outperform their modality-fused counterparts since they are noise-proof from the other potentially unaligned modality. Moreover, our best model achieves the new state-of-the-art on all metrics of LLP by a substantial margin ($\textbf{+5. 4}$ F-score for Type@AV). VALOR is further generalized to Audio-Visual Event Localization and achieves the new state-of-the-art as well.

PDF Details

NeurIPS Conference 2022 Conference Paper

Paraphrasing Is All You Need for Novel Object Captioning

Cheng-Fu Yang
Yao-Hung Hubert Tsai
Wan-Cyuan Fan
Russ R. Salakhutdinov
Louis-Philippe Morency
Frank Wang

Novel object captioning (NOC) aims to describe images containing objects without observing their ground truth captions during training. Due to the absence of caption annotation, captioning models cannot be directly optimized via sequence-to-sequence training or CIDEr optimization. As a result, we present Paraphrasing-to-Captioning (P2C), a two-stage learning framework for NOC, which would heuristically optimize the output captions via paraphrasing. With P2C, the captioning model first learns paraphrasing from a language model pre-trained on text-only corpus, allowing expansion of the word bank for improving linguistic fluency. To further enforce the output caption sufficiently describing the visual content of the input image, we perform self-paraphrasing for the captioning model with fidelity and adequacy objectives introduced. Since no ground truth captions are available for novel object images during training, our P2C leverages cross-modality (image-text) association modules to ensure the above caption characteristics can be properly preserved. In the experiments, we not only show that our P2C achieves state-of-the-art performances on nocaps and COCO Caption datasets, we also verify the effectiveness and flexibility of our learning framework by replacing language and cross-modality association models for NOC. Implementation details and code are available in the supplementary materials.

PDF Details

NeurIPS Conference 2022 Conference Paper

SPoVT: Semantic-Prototype Variational Transformer for Dense Point Cloud Semantic Completion

Sheng Yu Huang
Hao-Yu Hsu
Frank Wang

Point cloud completion is an active research topic for 3D vision and has been widelystudied in recent years. Instead of directly predicting missing point cloud fromthe partial input, we introduce a Semantic-Prototype Variational Transformer(SPoVT) in this work, which takes both partial point cloud and their semanticlabels as the inputs for semantic point cloud object completion. By observingand attending at geometry and semantic information as input features, our SPoVTwould derive point cloud features and their semantic prototypes for completionpurposes. As a result, our SPoVT not only performs point cloud completion withvarying resolution, it also allows manipulation of different semantic parts of anobject. Experiments on benchmark datasets would quantitatively and qualitativelyverify the effectiveness and practicality of our proposed model.

PDF Details