Yu-Chiang Frank Wang

Hsi-Che Lin, Chien-Yi Wang, Min-Hung Chen et al. · microsoft-research, nvidia

This technical report describes our QuAVF@NTU-NVIDIA submission to the Ego4D Talking to Me (TTM) Challenge 2023. Based on the observation from the TTM task and the provided dataset, we propose to use two separate models to process the input videos and audio. By doing so, we can utilize all the labeled training data, including those without bounding box labels. Furthermore, we leverage the face quality score from a facial landmark prediction model for filtering noisy face input data. The face quality score is also employed in our proposed quality-aware fusion for integrating the results from two branches. With the simple architecture design, our model achieves 67.4% mean average precision (mAP) on the test set, which ranks first on the leaderboard and outperforms the baseline method by a large margin. Code is available at: https://github.com/hsi-che-lin/Ego4D-QuAVF-TTM-CVPR23

Wan-Cyuan Fan, Yen-Chun Chen, Dongdong Chen et al.

Diffusion models (DMs) have shown great potential for high-quality image synthesis. However, when it comes to producing images with complex scenes, how to properly describe both image global structures and object details remains a challenging task. In this paper, we present Frido, a Feature Pyramid Diffusion model performing a multi-scale coarse-to-fine denoising process for image synthesis. Our model decomposes an input image into scale-dependent vector quantized features, followed by a coarse-to-fine gating for producing image output. During the above multi-scale representation learning stage, additional input conditions like text, scene graph, or image layout can be further exploited. Thus, Frido can be also applied for conditional or cross-modality image synthesis. We conduct extensive experiments over various unconditioned and conditional image generation tasks, ranging from text-to-image synthesis, layout-to-image, scene-graph-to-image, to label-to-image. More specifically, we achieved state-of-the-art FID scores on five benchmarks, namely layout-to-image on COCO and OpenImages, scene-graph-to-image on COCO and Visual Genome, and label-to-image on COCO. Code is available at https://github.com/davidhalladay/Frido.

Cheng-Fu Yang, Yen-Chun Chen, Jianwei Yang et al.

End-to-end Transformers have demonstrated an impressive success rate for Embodied Instruction Following when the environment has been seen in training. However, they tend to struggle when deployed in an unseen environment. This lack of generalizability is due to the agent's insensitivity to subtle changes in natural language instructions. To mitigate this issue, we propose explicitly aligning the agent's hidden states with the instructions via contrastive learning. Nevertheless, the semantic gap between high-level language instructions and the agent's low-level action space remains an obstacle. Therefore, we further introduce a novel concept of meta-actions to bridge the gap. Meta-actions are ubiquitous action patterns that can be parsed from the original action sequence. These patterns represent higher-level semantics that are intuitively aligned closer to the instructions. When meta-actions are applied as additional training signals, the agent generalizes better to unseen environments. Compared to a strong multi-modal Transformer baseline, we achieve a significant 4.5% absolute gain in success rate in unseen environments of ALFRED Embodied Instruction Following. Additional analysis shows that the contrastive objective and meta-actions are complementary in achieving the best results, and the resulting agent better aligns its states with corresponding instructions, making it more suitable for real-world embodied agents. The code is available at: https://github.com/joeyy5588/LACMA.

Fu-En Yang, Chien-Yi Wang, Yu-Chiang Frank Wang · microsoft-research

Federated learning (FL) emerges as a decentralized learning framework which trains models from multiple distributed clients without sharing their data to preserve privacy. Recently, large-scale pre-trained models (e.g., Vision Transformer) have shown a strong capability of deriving robust representations. However, the data heterogeneity among clients, the limited computation resources, and the communication bandwidth restrict the deployment of large-scale models in FL frameworks. To leverage robust representations from large-scale models while enabling efficient model personalization for heterogeneous clients, we propose a novel personalized FL framework of client-specific Prompt Generation (pFedPG), which learns to deploy a personalized prompt generator at the server for producing client-specific visual prompts that efficiently adapts frozen backbones to local data distributions. Our proposed framework jointly optimizes the stages of personalized prompt adaptation locally and personalized prompt generation globally. The former aims to train visual prompts that adapt foundation models to each client, while the latter observes local optimization directions to generate personalized prompts for all clients. Through extensive experiments on benchmark datasets, we show that our pFedPG is favorable against state-of-the-art personalized FL methods under various types of data heterogeneity, allowing computation and communication efficient model personalization.

Cheng-Fu Yang, Yao-Hung Hubert Tsai, Wan-Cyuan Fan et al.

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.

Shang-Fu Chen, Yu-Min Liu, Chia-Ching Lin et al. · microsoft-research

Anomaly detection aims to identify abnormal data that deviates from the normal ones, while typically requiring a sufficient amount of normal data to train the model for performing this task. Despite the success of recent anomaly detection methods, performing anomaly detection in an unseen domain remain a challenging task. In this paper, we address the task of domain-generalized textured surface anomaly detection. By observing normal and abnormal surface data across multiple source domains, our model is expected to be generalized to an unseen textured surface of interest, in which only a small number of normal data can be observed during testing. Although with only image-level labels observed in the training data, our patch-based meta-learning model exhibits promising generalization ability: not only can it generalize to unseen image domains, but it can also localize abnormal regions in the query image. Our experiments verify that our model performs favorably against state-of-the-art anomaly detection and domain generalization approaches in various settings.

Cheng Sun, Wei-En Tai, Yu-Lin Shih et al. · nvidia

State-of-the-art single-view 360-degree room layout reconstruction methods formulate the problem as a high-level 1D (per-column) regression task. On the other hand, traditional low-level 2D layout segmentation is simpler to learn and can represent occluded regions, but it requires complex post-processing for the targeting layout polygon and sacrifices accuracy. We present Seg2Reg to render 1D layout depth regression from the 2D segmentation map in a differentiable and occlusion-aware way, marrying the merits of both sides. Specifically, our model predicts floor-plan density for the input equirectangular 360-degree image. Formulating the 2D layout representation as a density field enables us to employ `flattened' volume rendering to form 1D layout depth regression. In addition, we propose a novel 3D warping augmentation on layout to improve generalization. Finally, we re-implement recent room layout reconstruction methods into our codebase for benchmarking and explore modern backbones and training techniques to serve as the strong baseline. Our model significantly outperforms previous arts. The code will be made available upon publication.

Zhi-Hao Lin, Wei-Chiu Ma, Hao-Yu Hsu et al.

We present Neural Mixtures of Planar Experts (NeurMiPs), a novel planar-based scene representation for modeling geometry and appearance. NeurMiPs leverages a collection of local planar experts in 3D space as the scene representation. Each planar expert consists of the parameters of the local rectangular shape representing geometry and a neural radiance field modeling the color and opacity. We render novel views by calculating ray-plane intersections and composite output colors and densities at intersected points to the image. NeurMiPs blends the efficiency of explicit mesh rendering and flexibility of the neural radiance field. Experiments demonstrate superior performance and speed of our proposed method, compared to other 3D representations in novel view synthesis.

Ci-Siang Lin, Min-Hung Chen, Yu-Chiang Frank Wang

Data collected from the real world typically exhibit long-tailed distributions, where frequent classes contain abundant data while rare ones have only a limited number of samples. While existing supervised learning approaches have been proposed to tackle such data imbalance, the requirement of label supervision would limit their applicability to real-world scenarios in which label annotation might not be available. Without the access to class labels nor the associated class frequencies, we propose Frequency-Aware Self-Supervised Learning (FASSL) in this paper. Targeting at learning from unlabeled data with inherent long-tailed distributions, the goal of FASSL is to produce discriminative feature representations for downstream classification tasks. In FASSL, we first learn frequency-aware prototypes, reflecting the associated long-tailed distribution. Particularly focusing on rare-class samples, the relationships between image data and the derived prototypes are further exploited with the introduced self-supervised learning scheme. Experiments on long-tailed image datasets quantitatively and qualitatively verify the effectiveness of our learning scheme.

Shih-Yang Liu, Chien-Yi Wang, Hongxu Yin et al.

Among the widely used parameter-efficient fine-tuning (PEFT) methods, LoRA and its variants have gained considerable popularity because of avoiding additional inference costs. However, there still often exists an accuracy gap between these methods and full fine-tuning (FT). In this work, we first introduce a novel weight decomposition analysis to investigate the inherent differences between FT and LoRA. Aiming to resemble the learning capacity of FT from the findings, we propose Weight-Decomposed Low-Rank Adaptation (DoRA). DoRA decomposes the pre-trained weight into two components, magnitude and direction, for fine-tuning, specifically employing LoRA for directional updates to efficiently minimize the number of trainable parameters. By employing \ours, we enhance both the learning capacity and training stability of LoRA while avoiding any additional inference overhead. \ours~consistently outperforms LoRA on fine-tuning LLaMA, LLaVA, and VL-BART on various downstream tasks, such as commonsense reasoning, visual instruction tuning, and image/video-text understanding. Code is available at https://github.com/NVlabs/DoRA.

Ke-Han Lu, Zhehuai Chen, Szu-Wei Fu et al.

Recent end-to-end speech language models (SLMs) have expanded upon the capabilities of large language models (LLMs) by incorporating pre-trained speech models. However, these SLMs often undergo extensive speech instruction-tuning to bridge the gap between speech and text modalities. This requires significant annotation efforts and risks catastrophic forgetting of the original language capabilities. In this work, we present a simple yet effective automatic process for creating speech-text pair data that carefully injects speech paralinguistic understanding abilities into SLMs while preserving the inherent language capabilities of the text-based LLM. Our model demonstrates general capabilities for speech-related tasks without the need for speech instruction-tuning data, achieving impressive performance on Dynamic-SUPERB and AIR-Bench-Chat benchmarks. Furthermore, our model exhibits the ability to follow complex instructions derived from LLMs, such as specific output formatting and chain-of-thought reasoning. Our approach not only enhances the versatility and effectiveness of SLMs but also reduces reliance on extensive annotated datasets, paving the way for more efficient and capable speech understanding systems.

Chiao-An Yang, Cheng-Yo Tan, Wan-Cyuan Fan et al.

In this paper, we address the task of semantics-guided image outpainting, which is to complete an image by generating semantically practical content. Different from most existing image outpainting works, we approach the above task by understanding and completing image semantics at the scene graph level. In particular, we propose a novel network of Scene Graph Transformer (SGT), which is designed to take node and edge features as inputs for modeling the associated structural information. To better understand and process graph-based inputs, our SGT uniquely performs feature attention at both node and edge levels. While the former views edges as relationship regularization, the latter observes the co-occurrence of nodes for guiding the attention process. We demonstrate that, given a partial input image with its layout and scene graph, our SGT can be applied for scene graph expansion and its conversion to a complete layout. Following state-of-the-art layout-to-image conversions works, the task of image outpainting can be completed with sufficient and practical semantics introduced. Extensive experiments are conducted on the datasets of MS-COCO and Visual Genome, which quantitatively and qualitatively confirm the effectiveness of our proposed SGT and outpainting frameworks.

Cheng-Yen Hsieh, Chih-Jung Chang, Fu-En Yang et al.

While self-supervised learning has been shown to benefit a number of vision tasks, existing techniques mainly focus on image-level manipulation, which may not generalize well to downstream tasks at patch or pixel levels. Moreover, existing SSL methods might not sufficiently describe and associate the above representations within and across image scales. In this paper, we propose a Self-Supervised Pyramid Representation Learning (SS-PRL) framework. The proposed SS-PRL is designed to derive pyramid representations at patch levels via learning proper prototypes, with additional learners to observe and relate inherent semantic information within an image. In particular, we present a cross-scale patch-level correlation learning in SS-PRL, which allows the model to aggregate and associate information learned across patch scales. We show that, with our proposed SS-PRL for model pre-training, one can easily adapt and fine-tune the models for a variety of applications including multi-label classification, object detection, and instance segmentation.

Yuan-Chia Cheng, Zu-Yun Shiau, Fu-En Yang et al.

To understand how deep neural networks perform classification predictions, recent research attention has been focusing on developing techniques to offer desirable explanations. However, most existing methods cannot be easily applied for semantic segmentation; moreover, they are not designed to offer interpretability under the multi-annotator setting. Instead of viewing ground-truth pixel-level labels annotated by a single annotator with consistent labeling tendency, we aim at providing interpretable semantic segmentation and answer two critical yet practical questions: "who" contributes to the resulting segmentation, and "why" such an assignment is determined. In this paper, we present a learning framework of Tendency-and-Assignment Explainer (TAX), designed to offer interpretability at the annotator and assignment levels. More specifically, we learn convolution kernel subsets for modeling labeling tendencies of each type of annotation, while a prototype bank is jointly observed to offer visual guidance for learning the above kernels. For evaluation, we consider both synthetic and real-world datasets with multi-annotators. We show that our TAX can be applied to state-of-the-art network architectures with comparable performances, while segmentation interpretability at both levels can be offered accordingly.

Xiaoqian Shen, Min-Hung Chen, Yu-Chiang Frank Wang et al.

Grounded video question answering (GVQA) aims to localize relevant temporal segments in videos and generate accurate answers to a given question; however, large video-language models (LVLMs) exhibit limited temporal awareness. Although existing approaches based on Group Relative Policy Optimization (GRPO) attempt to improve temporal grounding, they still struggle to faithfully ground their answers in the relevant video evidence, leading to temporal mislocalization and hallucinations. In this work, we present Zoom-Zero, a coarse-to-fine framework that first localizes query-relevant segments and then temporally zooms into the most salient frames for finer-grained visual verification. Our method addresses the limits of GRPO for the GVQA task with two key innovations: (i) a zoom-in accuracy reward that validates the fidelity of temporal grounding prediction and facilitates fine-grained visual verification on grounded frames; (ii) token-selective credit assignment, which attributes rewards to the tokens responsible for temporal localization or answer generation, mitigating GRPO's issue in handling multi-faceted reward signals. Our proposed method advances grounded video question answering, improving temporal grounding by 5.2\% on NExT-GQA and 4.6\% on ReXTime, while also enhancing average answer accuracy by 2.4\%. Additionally, the coarse-to-fine zoom-in during inference further benefits long-form video understanding by preserving critical visual details without compromising global context, yielding an average improvement of 6.4\% on long-video benchmarks.

Zih-Ching Chen, Lin-Hsi Tsao, Chin-Lun Fu et al.

Face anti-spoofing (FAS) aims at distinguishing face spoof attacks from the authentic ones, which is typically approached by learning proper models for performing the associated classification task. In practice, one would expect such models to be generalized to FAS in different image domains. Moreover, it is not practical to assume that the type of spoof attacks would be known in advance. In this paper, we propose a deep learning model for addressing the aforementioned domain-generalized face anti-spoofing task. In particular, our proposed network is able to disentangle facial liveness representation from the irrelevant ones (i.e., facial content and image domain features). The resulting liveness representation exhibits sufficient domain invariant properties, and thus it can be applied for performing domain-generalized FAS. In our experiments, we conduct experiments on five benchmark datasets with various settings, and we verify that our model performs favorably against state-of-the-art approaches in identifying novel types of spoof attacks in unseen image domains.

Yusuke Hirota, Min-Hung Chen, Chien-Yi Wang et al.

Large-scale vision-language models, such as CLIP, are known to contain societal bias regarding protected attributes (e.g., gender, age). This paper aims to address the problems of societal bias in CLIP. Although previous studies have proposed to debias societal bias through adversarial learning or test-time projecting, our comprehensive study of these works identifies two critical limitations: 1) loss of attribute information when it is explicitly disclosed in the input and 2) use of the attribute annotations during debiasing process. To mitigate societal bias in CLIP and overcome these limitations simultaneously, we introduce a simple-yet-effective debiasing method called SANER (societal attribute neutralizer) that eliminates attribute information from CLIP text features only of attribute-neutral descriptions. Experimental results show that SANER, which does not require attribute annotations and preserves original information for attribute-specific descriptions, demonstrates superior debiasing ability than the existing methods.

Hsu-kuang Chiu, Ryo Hachiuma, Chien-Yi Wang et al.

Current autonomous driving vehicles rely mainly on their individual sensors to understand surrounding scenes and plan for future trajectories, which can be unreliable when the sensors are malfunctioning or occluded. To address this problem, cooperative perception methods via vehicle-to-vehicle (V2V) communication have been proposed, but they have tended to focus on perception tasks like detection or tracking. How those approaches contribute to overall cooperative planning performance is still under-explored. Inspired by recent progress using Large Language Models (LLMs) to build autonomous driving systems, we propose a novel problem setting that integrates a Multi-Modal LLM into cooperative autonomous driving, with the proposed Vehicle-to-Vehicle Question-Answering (V2V-QA) dataset and benchmark. We also propose our baseline method Vehicle-to-Vehicle Multi-Modal Large Language Model (V2V-LLM), which uses an LLM to fuse perception information from multiple connected autonomous vehicles (CAVs) and answer various types of driving-related questions: grounding, notable object identification, and planning. Experimental results show that our proposed V2V-LLM can be a promising unified model architecture for performing various tasks in cooperative autonomous driving, and outperforms other baseline methods that use different fusion approaches. Our work also creates a new research direction that can improve the safety of future autonomous driving systems. The code and data will be released to the public to facilitate open-source research in this field. Our project website: https://eddyhkchiu.github.io/v2vllm.github.io/ .

Wan-Cyuan Fan, Cheng-Fu Yang, Chiao-An Yang et al.

We tackle the problem of target-free text-guided image manipulation, which requires one to modify the input reference image based on the given text instruction, while no ground truth target image is observed during training. To address this challenging task, we propose a Cyclic-Manipulation GAN (cManiGAN) in this paper, which is able to realize where and how to edit the image regions of interest. Specifically, the image editor in cManiGAN learns to identify and complete the input image, while cross-modal interpreter and reasoner are deployed to verify the semantic correctness of the output image based on the input instruction. While the former utilizes factual/counterfactual description learning for authenticating the image semantics, the latter predicts the "undo" instruction and provides pixel-level supervision for the training of cManiGAN. With such operational cycle-consistency, our cManiGAN can be trained in the above weakly supervised setting. We conduct extensive experiments on the datasets of CLEVR and COCO, and the effectiveness and generalizability of our proposed method can be successfully verified. Project page: https://sites.google.com/view/wancyuanfan/projects/cmanigan.

I-Jieh Liu, Ci-Siang Lin, Fu-En Yang et al.

Federated Learning (FL) is an emerging paradigm that enables multiple users to collaboratively train a robust model in a privacy-preserving manner without sharing their private data. Most existing approaches of FL only consider traditional single-label image classification, ignoring the impact when transferring the task to multi-label image classification. Nevertheless, it is still challenging for FL to deal with user heterogeneity in their local data distribution in the real-world FL scenario, and this issue becomes even more severe in multi-label image classification. Inspired by the recent success of Transformers in centralized settings, we propose a novel FL framework for multi-label classification. Since partial label correlation may be observed by local clients during training, direct aggregation of locally updated models would not produce satisfactory performances. Thus, we propose a novel FL framework of Language-Guided Transformer (FedLGT) to tackle this challenging task, which aims to exploit and transfer knowledge across different clients for learning a robust global model. Through extensive experiments on various multi-label datasets (e.g., FLAIR, MS-COCO, etc.), we show that our FedLGT is able to achieve satisfactory performance and outperforms standard FL techniques under multi-label FL scenarios. Code is available at https://github.com/Jack24658735/FedLGT.

Kai-Po Chang, Wei-Yuan Cheng, Chi-Pin Huang et al.

Recent advancement in multimodal LLMs (MLLMs) has demonstrated their remarkable capability to generate descriptive captions for input videos. However, these models suffer from factual inaccuracies in the generated descriptions, causing severe hallucination issues. While prior works have explored alleviating hallucinations for static images, jointly mitigating visual object and temporal action hallucinations for dynamic videos remains a challenging and unsolved task. To tackle this challenge, we propose a Self-Augmented Contrastive Alignment (SANTA) framework for enabling object and action faithfulness by exempting the spurious correlations and enforcing the emphasis on visual facts. SANTA employs a hallucinative self-augmentation scheme to identify the potential hallucinations that lie in the MLLM and transform the original captions to the contrasted negatives. Furthermore, we develop a tracklet-phrase contrastive alignment to match the regional objects and relation-guided actions with their corresponding visual and temporal phrases. Extensive experiments demonstrate that SANTA outperforms existing methods in alleviating object and action hallucinations, yielding superior performance on the hallucination examination benchmarks.

Byung-Kwan Lee, Ryo Hachiuma, Yu-Chiang Frank Wang et al.

The recent surge in high-quality visual instruction tuning samples from closed-source vision-language models (VLMs) such as GPT-4V has accelerated the release of open-source VLMs across various model sizes. However, scaling VLMs to improve performance using larger models brings significant computational challenges, especially for deployment on resource-constrained devices like mobile platforms and robots. To address this, we propose VLsI: Verbalized Layers-to-Interactions, a new VLM family in 2B and 7B model sizes, which prioritizes efficiency without compromising accuracy. VLsI leverages a unique, layer-wise distillation process, introducing intermediate "verbalizers" that map features from each layer to natural language space, allowing smaller VLMs to flexibly align with the reasoning processes of larger VLMs. This approach mitigates the training instability often encountered in output imitation and goes beyond typical final-layer tuning by aligning the small VLMs' layer-wise progression with that of the large ones. We validate VLsI across ten challenging vision-language benchmarks, achieving notable performance gains (11.0% for 2B and 17.4% for 7B) over GPT-4V without the need for model scaling, merging, or architectural changes.

Chia-Ming Lee, Ching-Heng Cheng, Yu-Fan Lin et al.

Recent advances in All-in-One (AiO) RGB image restoration have demonstrated the effectiveness of prompt learning in handling multiple degradations within a single model. However, extending these approaches to hyperspectral image (HSI) restoration is challenging due to the domain gap between RGB and HSI features, information loss in visual prompts under severe composite degradations, and difficulties in capturing HSI-specific degradation patterns via text prompts. In this paper, we propose PromptHSI, the first universal AiO HSI restoration framework that addresses these challenges. By incorporating frequency-aware feature modulation, which utilizes frequency analysis to narrow down the restoration search space and employing vision-language model (VLM)-guided prompt learning, our approach decomposes text prompts into intensity and bias controllers that effectively guide the restoration process while mitigating domain discrepancies. Extensive experiments demonstrate that our unified architecture excels at both fine-grained recovery and global information restoration across diverse degradation scenarios, highlighting its significant potential for practical remote sensing applications. The source code is available at https://github.com/chingheng0808/PromptHSI.

Tung-Yu Wu, Sheng-Yu Huang, Yu-Chiang Frank Wang

3D visual grounding aims to identify the target object within a 3D point cloud scene referred to by a natural language description. Previous works usually require significant data relating to point color and their descriptions to exploit the corresponding complicated verbo-visual relations. In our work, we introduce Vigor, a novel Data-Efficient 3D Visual Grounding framework via Order-aware Referring. Vigor leverages LLM to produce a desirable referential order from the input description for 3D visual grounding. With the proposed stacked object-referring blocks, the predicted anchor objects in the above order allow one to locate the target object progressively without supervision on the identities of anchor objects or exact relations between anchor/target objects. In addition, we present an order-aware warm-up training strategy, which augments referential orders for pre-training the visual grounding framework. This allows us to better capture the complex verbo-visual relations and benefit the desirable data-efficient learning scheme. Experimental results on the NR3D and ScanRefer datasets demonstrate our superiority in low-resource scenarios. In particular, Vigor surpasses current state-of-the-art frameworks by 9.3% and 7.6% grounding accuracy under 1% data and 10% data settings on the NR3D dataset, respectively. Our code is publicly available at https://github.com/tony10101105/Vigor.

Shih-Yang Liu, Maksim Khadkevich, Nai Chit Fung et al.

While post-training compression techniques effectively reduce the memory footprint, latency, and power consumption of Large Language Models (LLMs), they often result in noticeable accuracy degradation and remain limited by hardware and kernel constraints that restrict supported compression formats ultimately reducing flexibility across a wide range of deployment scenarios. In this work, we propose EoRA, a novel fine-tuning-free method that augments compressed LLMs with low-rank matrices, allowing users to rapidly enhance task-specific performance and freely balance the trade-off between accuracy and computational overhead beyond the constraints of compression formats. EoRA consistently outperforms prior training-free low rank methods in recovering the accuracy of compressed LLMs, achieving notable accuracy improvements (e.g., $\mathbf{10.84\%}$ on ARC-Challenge, $\mathbf{6.74\%}$ on MathQA, and $\mathbf{6.74\%}$ on GSM8K) for LLaMA3-8B compressed to 3-bit. We also introduce an optimized CUDA kernel, accelerating inference by up to 1.4x and reducing memory overhead through quantizing EoRA. Overall, EoRA offers a prompt solution for improving the accuracy of compressed models under varying user requirements, enabling more efficient and flexible deployment of LLMs. Code is available at https://github.com/NVlabs/EoRA.

Ci-Siang Lin, Chien-Yi Wang, Yu-Chiang Frank Wang et al.

Weakly-Supervised Semantic Segmentation (WSSS) aims to train segmentation models using image data with only image-level supervision. Since precise pixel-level annotations are not accessible, existing methods typically focus on producing pseudo masks for training segmentation models by refining CAM-like heatmaps. However, the produced heatmaps may capture only the discriminative image regions of object categories or the associated co-occurring backgrounds. To address the issues, we propose a Semantic Prompt Learning for WSSS (SemPLeS) framework, which learns to effectively prompt the CLIP latent space to enhance the semantic alignment between the segmented regions and the target object categories. More specifically, we propose Contrastive Prompt Learning and Prompt-guided Semantic Refinement to learn the prompts that adequately describe and suppress the co-occurring backgrounds associated with each object category. In this way, SemPLeS can perform better semantic alignment between object regions and class labels, resulting in desired pseudo masks for training segmentation models. The proposed SemPLeS framework achieves competitive performance on standard WSSS benchmarks, PASCAL VOC 2012 and MS COCO 2014, and shows compatibility with other WSSS methods. Code: https://github.com/NVlabs/SemPLeS.

Chia-Hsiang Kao, Yu-Chiang Frank Wang

Federated Learning (FL) offers a collaborative training framework, allowing multiple clients to contribute to a shared model without compromising data privacy. Due to the heterogeneous nature of local datasets, updated client models may overfit and diverge from one another, commonly known as the problem of client drift. In this paper, we propose FedBug (Federated Learning with Bottom-Up Gradual Unfreezing), a novel FL framework designed to effectively mitigate client drift. FedBug adaptively leverages the client model parameters, distributed by the server at each global round, as the reference points for cross-client alignment. Specifically, on the client side, FedBug begins by freezing the entire model, then gradually unfreezes the layers, from the input layer to the output layer. This bottom-up approach allows models to train the newly thawed layers to project data into a latent space, wherein the separating hyperplanes remain consistent across all clients. We theoretically analyze FedBug in a novel over-parameterization FL setup, revealing its superior convergence rate compared to FedAvg. Through comprehensive experiments, spanning various datasets, training conditions, and network architectures, we validate the efficacy of FedBug. Our contributions encompass a novel FL framework, theoretical analysis, and empirical validation, demonstrating the wide potential and applicability of FedBug.

Hsi-Che Lin, Yu-Chu Yu, Kai-Po Chang et al.

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 on a single 24GB consumer GPU-bringing efficient and practical model adaptation to individual users.

Yung-Hsuan Lai, Yen-Chun Chen, Yu-Chiang Frank Wang

Audio-visual learning has been a major pillar of multi-modal machine learning, where the community mostly focused on its modality-aligned setting, i.e., the audio and visual modality are both assumed to signal the prediction target. With the Look, Listen, and Parse dataset (LLP), we investigate the under-explored 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 Visual-Audio Label Elaboration (VALOR), is innovated to harvest modality labels for the training events. Empirical studies show that the harvested labels significantly improve an attentional baseline by 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 (+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. Code is available at: https://github.com/Franklin905/VALOR.

Chang-Hsun Wu, Kai-Po Chang, Yu-Yang Sheng et al.

Video Large Language Models (VideoLLMs) have shown remarkable progress in video understanding. However, these models still struggle to effectively perceive and exploit rich temporal information in videos when responding to user queries. Therefore, they often generate descriptions of events that are temporal inconsistent or causally implausible, causing severe hallucination issues. While most prior studies have focused on spatial hallucinations (e.g. object mismatches), temporal reasoning in video understanding remains relatively underexplored. To address this issue, we propose Self-Diagnostic Contrastive Decoding (SEASON), a training-free method that adaptively enhances temporal and spatial faithfulness for each output token. It achieves this by dynamically diagnosing each token's hallucination tendency and applying adaptive contrastive decoding against its corresponding temporal and spatial negatives. Extensive experiments demonstrate that SEASON outperforms all existing training-free hallucination mitigation approaches on three hallucination examination benchmarks, while further improves VideoLLMs across four general video understanding benchmarks. The code will be released upon acceptance.

Chi-Pin Huang, Yueh-Hua Wu, Min-Hung Chen et al.

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.

Szu-Wei Fu, Kuo-Hsuan Hung, Yu Tsao et al.

Speech quality estimation has recently undergone a paradigm shift from human-hearing expert designs to machine-learning models. However, current models rely mainly on supervised learning, which is time-consuming and expensive for label collection. To solve this problem, we propose VQScore, a self-supervised metric for evaluating speech based on the quantization error of a vector-quantized-variational autoencoder (VQ-VAE). The training of VQ-VAE relies on clean speech; hence, large quantization errors can be expected when the speech is distorted. To further improve correlation with real quality scores, domain knowledge of speech processing is incorporated into the model design. We found that the vector quantization mechanism could also be used for self-supervised speech enhancement (SE) model training. To improve the robustness of the encoder for SE, a novel self-distillation mechanism combined with adversarial training is introduced. In summary, the proposed speech quality estimation method and enhancement models require only clean speech for training without any label requirements. Experimental results show that the proposed VQScore and enhancement model are competitive with supervised baselines. The code will be released after publication.

Cheng Sun, Jaesung Choe, Charles Loop et al. · nvidia

We propose an efficient radiance field rendering algorithm that incorporates a rasterization process on adaptive sparse voxels without neural networks or 3D Gaussians. There are two key contributions coupled with the proposed system. The first is to adaptively and explicitly allocate sparse voxels to different levels of detail within scenes, faithfully reproducing scene details with $65536^3$ grid resolution while achieving high rendering frame rates. Second, we customize a rasterizer for efficient adaptive sparse voxels rendering. We render voxels in the correct depth order by using ray direction-dependent Morton ordering, which avoids the well-known popping artifact found in Gaussian splatting. Our method improves the previous neural-free voxel model by over 4db PSNR and more than 10x FPS speedup, achieving state-of-the-art comparable novel-view synthesis results. Additionally, our voxel representation is seamlessly compatible with grid-based 3D processing techniques such as Volume Fusion, Voxel Pooling, and Marching Cubes, enabling a wide range of future extensions and applications.

Zi-Ting Chou, Sheng-Yu Huang, I-Jieh Liu et al.

Utilizing multi-view inputs to synthesize novel-view images, Neural Radiance Fields (NeRF) have emerged as a popular research topic in 3D vision. In this work, we introduce a Generalizable Semantic Neural Radiance Field (GSNeRF), which uniquely takes image semantics into the synthesis process so that both novel view images and the associated semantic maps can be produced for unseen scenes. Our GSNeRF is composed of two stages: Semantic Geo-Reasoning and Depth-Guided Visual rendering. The former is able to observe multi-view image inputs to extract semantic and geometry features from a scene. Guided by the resulting image geometry information, the latter performs both image and semantic rendering with improved performances. Our experiments not only confirm that GSNeRF performs favorably against prior works on both novel-view image and semantic segmentation synthesis but the effectiveness of our sampling strategy for visual rendering is further verified.

Kim Jun-Seong, GeonU Kim, Kim Yu-Ji et al.

We introduce Dr. Splat, a novel approach for open-vocabulary 3D scene understanding leveraging 3D Gaussian Splatting. Unlike existing language-embedded 3DGS methods, which rely on a rendering process, our method directly associates language-aligned CLIP embeddings with 3D Gaussians for holistic 3D scene understanding. The key of our method is a language feature registration technique where CLIP embeddings are assigned to the dominant Gaussians intersected by each pixel-ray. Moreover, we integrate Product Quantization (PQ) trained on general large-scale image data to compactly represent embeddings without per-scene optimization. Experiments demonstrate that our approach significantly outperforms existing approaches in 3D perception benchmarks, such as open-vocabulary 3D semantic segmentation, 3D object localization, and 3D object selection tasks. For video results, please visit : https://drsplat.github.io/

Chi-Pin Huang, Yen-Siang Wu, Hung-Kai Chung et al.

Customized text-to-video generation aims to produce high-quality videos that incorporate user-specified subject identities or motion patterns. However, existing methods mainly focus on personalizing a single concept, either subject identity or motion pattern, limiting their effectiveness for multiple subjects with the desired motion patterns. To tackle this challenge, we propose a unified framework VideoMage for video customization over both multiple subjects and their interactive motions. VideoMage employs subject and motion LoRAs to capture personalized content from user-provided images and videos, along with an appearance-agnostic motion learning approach to disentangle motion patterns from visual appearance. Furthermore, we develop a spatial-temporal composition scheme to guide interactions among subjects within the desired motion patterns. Extensive experiments demonstrate that VideoMage outperforms existing methods, generating coherent, user-controlled videos with consistent subject identities and interactions.

Sheng-Yu Huang, Zi-Ting Chou, Yu-Chiang Frank Wang

When performing 3D inpainting using novel-view rendering methods like Neural Radiance Field (NeRF) or 3D Gaussian Splatting (3DGS), how to achieve texture and geometry consistency across camera views has been a challenge. In this paper, we propose a framework of 3D Gaussian Inpainting with Depth-Guided Cross-View Consistency (3DGIC) for cross-view consistent 3D inpainting. Guided by the rendered depth information from each training view, our 3DGIC exploits background pixels visible across different views for updating the inpainting mask, allowing us to refine the 3DGS for inpainting purposes.Through extensive experiments on benchmark datasets, we confirm that our 3DGIC outperforms current state-of-the-art 3D inpainting methods quantitatively and qualitatively.

Miran Heo, Min-Hung Chen, De-An Huang et al.

We present Omni-RGPT, a multimodal large language model designed to facilitate region-level comprehension for both images and videos. To achieve consistent region representation across spatio-temporal dimensions, we introduce Token Mark, a set of tokens highlighting the target regions within the visual feature space. These tokens are directly embedded into spatial regions using region prompts (e.g., boxes or masks) and simultaneously incorporated into the text prompt to specify the target, establishing a direct connection between visual and text tokens. To further support robust video understanding without requiring tracklets, we introduce an auxiliary task that guides Token Mark by leveraging the consistency of the tokens, enabling stable region interpretation across the video. Additionally, we introduce a large-scale region-level video instruction dataset (RegVID-300k). Omni-RGPT achieves state-of-the-art results on image and video-based commonsense reasoning benchmarks while showing strong performance in captioning and referring expression comprehension tasks.

Bin-Shih Wu, Hong-En Chen, Sheng-Yu Huang et al.

Due to the lack of large-scale text-3D correspondence data, recent text-to-3D generation works mainly rely on utilizing 2D diffusion models for synthesizing 3D data. Since diffusion-based methods typically require significant optimization time for both training and inference, the use of GAN-based models would still be desirable for fast 3D generation. In this work, we propose Triplane Attention for text-guided 3D generation (TPA3D), an end-to-end trainable GAN-based deep learning model for fast text-to-3D generation. With only 3D shape data and their rendered 2D images observed during training, our TPA3D is designed to retrieve detailed visual descriptions for synthesizing the corresponding 3D mesh data. This is achieved by the proposed attention mechanisms on the extracted sentence and word-level text features. In our experiments, we show that TPA3D generates high-quality 3D textured shapes aligned with fine-grained descriptions, while impressive computation efficiency can be observed.

Junha Lee, Chunghyun Park, Jaesung Choe et al.

We tackle open-vocabulary 3D scene understanding by introducing a novel data generation pipeline and training framework. Our method addresses three critical requirements for effective training: precise 3D region segmentation, comprehensive textual descriptions, and sufficient dataset scale. By leveraging state-of-the-art open-vocabulary image segmentation models and region-aware Vision-Language Models, we develop an automatic pipeline that generates high-quality 3D mask-text pairs. Applying this pipeline to multiple 3D scene datasets, we create Mosaic3D-5.6M, a dataset of over 30K annotated scenes with 5.6M mask-text pairs, significantly larger than existing datasets. Building upon this data, we propose Mosaic3D, a foundation model combining a 3D encoder trained with contrastive learning and a lightweight mask decoder for open-vocabulary 3D semantic and instance segmentation. Our approach achieves state-of-the-art results on open-vocabulary 3D semantic and instance segmentation tasks including ScanNet200, Matterport3D, and ScanNet++, with ablation studies validating the effectiveness of our large-scale training data.

Yen-Ting Lin, Chao-Han Huck Yang, Zhehuai Chen et al.

Construction of a general-purpose post-recognition error corrector poses a crucial question: how can we most effectively train a model on a large mixture of domain datasets? The answer would lie in learning dataset-specific features and digesting their knowledge in a single model. Previous methods achieve this by having separate correction language models, resulting in a significant increase in parameters. In this work, we present Mixture-of-Experts as a solution, highlighting that MoEs are much more than a scalability tool. We propose a Multi-Task Correction MoE, where we train the experts to become an ``expert'' of speech-to-text, language-to-text and vision-to-text datasets by learning to route each dataset's tokens to its mapped expert. Experiments on the Open ASR Leaderboard show that we explore a new state-of-the-art performance by achieving an average relative $5.0$% WER reduction and substantial improvements in BLEU scores for speech and translation tasks. On zero-shot evaluation, NeKo outperforms GPT-3.5 and Claude-Opus with $15.5$% to $27.6$% relative WER reduction in the Hyporadise benchmark. NeKo performs competitively on grammar and post-OCR correction as a multi-task model.

Yen-Siang Wu, Chi-Pin Huang, Fu-En Yang et al.

Text-to-video (T2V) diffusion models have shown promising capabilities in synthesizing realistic videos from input text prompts. However, the input text description alone provides limited control over the precise objects movements and camera framing. In this work, we tackle the motion customization problem, where a reference video is provided as motion guidance. While most existing methods choose to fine-tune pre-trained diffusion models to reconstruct the frame differences of the reference video, we observe that such strategy suffer from content leakage from the reference video, and they cannot capture complex motion accurately. To address this issue, we propose MotionMatcher, a motion customization framework that fine-tunes the pre-trained T2V diffusion model at the feature level. Instead of using pixel-level objectives, MotionMatcher compares high-level, spatio-temporal motion features to fine-tune diffusion models, ensuring precise motion learning. For the sake of memory efficiency and accessibility, we utilize a pre-trained T2V diffusion model, which contains considerable prior knowledge about video motion, to compute these motion features. In our experiments, we demonstrate state-of-the-art motion customization performances, validating the design of our framework.

Chung-Ting Tsai, Ching-Yun Ko, I-Hsin Chung et al.

The rapid advancement of generative models has introduced serious risks, including deepfake techniques for facial synthesis and editing. Traditional approaches rely on training classifiers and enhancing generalizability through various feature extraction techniques. Meanwhile, training-free detection methods address issues like limited data and overfitting by directly leveraging statistical properties from vision foundation models to distinguish between real and fake images. The current leading training-free approach, RIGID, utilizes DINOv2 sensitivity to perturbations in image space for detecting fake images, with fake image embeddings exhibiting greater sensitivity than those of real images. This observation prompts us to investigate how detection performance varies across model backbones, perturbation types, and datasets. Our experiments reveal that detection performance is closely linked to model robustness, with self-supervised (SSL) models providing more reliable representations. While Gaussian noise effectively detects general objects, it performs worse on facial images, whereas Gaussian blur is more effective due to potential frequency artifacts. To further improve detection, we introduce Contrastive Blur, which enhances performance on facial images, and MINDER (MINimum distance DetEctoR), which addresses noise type bias, balancing performance across domains. Beyond performance gains, our work offers valuable insights for both the generative and detection communities, contributing to a deeper understanding of model robustness property utilized for deepfake detection.

Shih-Yang Liu, Xin Dong, Ximing Lu et al. · uw

Reasoning language models such as OpenAI-o1, DeepSeek-R1, and Qwen achieve strong performance via extended chains of thought but often generate unnecessarily long outputs. Maximizing intelligence per token--accuracy relative to response length--remains an open problem. We revisit reinforcement learning (RL) with the simplest length penalty--truncation--and show that accuracy degradation arises not from the lack of sophisticated penalties but from inadequate RL optimization. We identify three key challenges: (i) large bias in advantage estimation, (ii) entropy collapse, and (iii) sparse reward signal. We address them with Doing Length pEnalty Right (DLER), a training recipe combining batch-wise reward normalization, higher clipping, dynamic sampling, and a simple truncation length penalty. DLER achieves state-of-the-art accuracy--efficiency trade-offs, cutting output length by over 70 percent while surpassing all previous baseline accuracy. It also improves test-time scaling: compared to DeepSeek-R1-7B, DLER-7B generates multiple concise responses in parallel with 28 percent higher accuracy and lower latency. We further introduce Difficulty-Aware DLER, which adaptively tightens truncation on easier questions for additional efficiency gains. We also propose an update-selective merging method that preserves baseline accuracy while retaining the concise reasoning ability of the DLER model, which is useful for scenarios where RL training data is scarce.

Byung-Kwan Lee, Ryo Hachiuma, Yong Man Ro et al.

Recent advancements in vision-language models (VLMs) have leveraged large language models (LLMs) to achieve performance on par with closed-source systems like GPT-4V. However, deploying these models in real-world scenarios, particularly on resource-constrained devices, remains challenging due to their substantial computational demands. This has spurred interest in distilling knowledge from large VLMs into smaller, more efficient counterparts. A key challenge arises here from the diversity of VLM architectures, which are built on different LLMs and employ varying token types-differing in vocabulary size, token splits, and token index ordering. To address this challenge of limitation to a specific VLM type, we present Generation after Recalibration (GenRecal), a general-purpose distillation framework for VLMs. GenRecal incorporates a Recalibrator that aligns and adapts feature representations between heterogeneous VLMs, enabling effective knowledge transfer across different types of VLMs. Through extensive experiments on multiple challenging benchmarks, we demonstrate that GenRecal significantly improves baseline performances, eventually outperforming large-scale open- and closed-source VLMs.

Yu-Hsiang Huang, Wei Wang, Sheng-Yu Huang et al.

Recent advancements in object-centric text-to-3D generation have shown impressive results. However, generating complex 3D scenes remains an open challenge due to the intricate relations between objects. Moreover, existing methods are largely based on score distillation sampling (SDS), which constrains the ability to manipulate multiobjects with specific interactions. Addressing these critical yet underexplored issues, we present a novel framework of Scene Graph and Layout Guided 3D Scene Generation (GraLa3D). Given a text prompt describing a complex 3D scene, GraLa3D utilizes LLM to model the scene using a scene graph representation with layout bounding box information. GraLa3D uniquely constructs the scene graph with single-object nodes and composite super-nodes. In addition to constraining 3D generation within the desirable layout, a major contribution lies in the modeling of interactions between objects in a super-node, while alleviating appearance leakage across objects within such nodes. Our experiments confirm that GraLa3D overcomes the above limitations and generates complex 3D scenes closely aligned with text prompts.

Byung-Kwan Lee, Ryo Hachiuma, Yong Man Ro et al.

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 an 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.

Chih-Kai Yang, Yen-Ting Piao, Tzu-Wen Hsu et al.

Knowledge editing offers an efficient way to update model knowledge without full retraining, but prior work has concentrated almost exclusively on textual or visual modalities. We introduce SAKE, the first benchmark specifically designed for editing auditory attribute knowledge in Large Audio-Language Models (LALMs). Unlike factual updates, SAKE targets several abstract auditory attributes, capturing knowledge types that go beyond conventional textual and visual domains. We benchmark seven editing methods on two LALMs along four dimensions: reliability, generality, audio/text locality, and portability. Results highlight challenges such as preserving intra-attribute knowledge unrelated to the edit, generalizing edits to multimodal reasoning, and maintaining edits under sequential updates. SAKE provides a principled framework to study how knowledge editing extends to the auditory modalities, opening new directions for maintaining and adapting LALMs in more diverse real-world scenarios.

Bo-Han Feng, Chien-Feng Liu, Yu-Hsuan Li Liang et al.

Large audio-language models (LALMs) extend text-based LLMs with auditory understanding, offering new opportunities for multimodal applications. While their perception, reasoning, and task performance have been widely studied, their safety alignment under paralinguistic variation remains underexplored. This work systematically investigates the role of speaker emotion. We construct a dataset of malicious speech instructions expressed across multiple emotions and intensities, and evaluate several state-of-the-art LALMs. Our results reveal substantial safety inconsistencies: different emotions elicit varying levels of unsafe responses, and the effect of intensity is non-monotonic, with medium expressions often posing the greatest risk. These findings highlight an overlooked vulnerability in LALMs and call for alignment strategies explicitly designed to ensure robustness under emotional variation, a prerequisite for trustworthy deployment in real-world settings.

Ci-Siang Lin, Min-Hung Chen, Yu-Yang Sheng et al.

Multimodal Large Language Models (MLLMs) have achieved strong performance on general visual benchmarks but struggle with out-of-distribution (OOD) tasks in specialized domains such as medical imaging, where labeled data is limited and expensive. We introduce LEAML, a label-efficient adaptation framework that leverages both scarce labeled VQA samples and abundant unlabeled images. Our approach generates domain-relevant pseudo question-answer pairs for unlabeled data using a QA generator regularized by caption distillation. Importantly, we selectively update only those neurons most relevant to question-answering, enabling the QA Generator to efficiently acquire domain-specific knowledge during distillation. Experiments on gastrointestinal endoscopy and sports VQA demonstrate that LEAML consistently outperforms standard fine-tuning under minimal supervision, highlighting the effectiveness of our proposed LEAML framework.