arXiv subjects

Taesup Kim

Publications and source records attributed to Taesup Kim.

At least 55 records · Page 3Linked to original sources

arXiv2025

From Threat to Tool: Leveraging Refusal-Aware Injection Attacks for Safety Alignment

Safely aligning large language models (LLMs) often demands extensive human-labeled preference data, a process that's both costly and time-consuming. While synthetic data offers a promising alternative, current methods frequently rely on complex iterative prompting or auxiliary models. To address this, we introduce Refusal-Aware Adaptive Injection (RAAI), a straightforward, training-free, and model-agnostic framework that repurposes LLM attack techniques. RAAI works by detecting internal refusal signals and adaptively injecting predefined phrases to elicit harmful, yet fluent, completions. Our experiments show RAAI effectively jailbreaks LLMs, increasing the harmful response rate from a baseline of 2.15% to up to 61.04% on average across four benchmarks. Crucially, fine-tuning LLMs with the synthetic data generated by RAAI improves model robustness against harmful prompts while preserving general capabilities on standard tasks like MMLU and ARC. This work highlights how LLM attack methodologies can be reframed as practical tools for scalable and controllable safety alignment.

cs.CR↗

arXiv2025

"Well, Keep Thinking": Enhancing LLM Reasoning with Adaptive Injection Decoding

Large language models (LLMs) exhibit strong reasoning abilities, often attributed to few-shot or zero-shot chain-of-thought (CoT) prompting. While effective, these methods require labor-intensive prompt engineering, raising the question of whether reasoning can be induced without reliance on explicit prompts. In this work, we unlock the reasoning capabilities of LLMs without explicit prompting. Inspired by zero-shot CoT and CoT-decoding, we propose a novel decoding strategy that systematically nudges LLMs to continue reasoning, thereby preventing immature reasoning processes. Specifically, we monitor the model's generation and inject a designated phrase whenever it is likely to conclude its response prematurely, before completing the reasoning process. Our experimental evaluations on diverse reasoning benchmarks demonstrate that our proposed strategy substantially improves LLM reasoning capabilities, highlighting the potential of decoding-based interventions as an alternative to traditional prompting techniques.

cs.CL↗

arXiv2025

Object-Centric World Model for Language-Guided Manipulation

A world model is essential for an agent to predict the future and plan in domains such as autonomous driving and robotics. To achieve this, recent advancements have focused on video generation, which has gained significant attention due to the impressive success of diffusion models. However, these models require substantial computational resources. To address these challenges, we propose a world model leveraging object-centric representation space using slot attention, guided by language instructions. Our model perceives the current state as an object-centric representation and predicts future states in this representation space conditioned on natural language instructions. This approach results in a more compact and computationally efficient model compared to diffusion-based generative alternatives. Furthermore, it flexibly predicts future states based on language instructions, and offers a significant advantage in manipulation tasks where object recognition is crucial. In this paper, we demonstrate that our latent predictive world model surpasses generative world models in visuo-linguo-motor control tasks, achieving superior sample and computation efficiency. We also investigate the generalization performance of the proposed method and explore various strategies for predicting actions using object-centric representations.

cs.AI↗

arXiv2024

Retaining and Enhancing Pre-trained Knowledge in Vision-Language Models with Prompt Ensembling

The advancement of vision-language models, particularly the Contrastive Language-Image Pre-training (CLIP) model, has revolutionized the field of machine learning by enabling robust zero-shot learning capabilities. These capabilities allow models to understand and respond to previously unseen data without task-specific training. However, adapting CLIP to integrate specialized knowledge from various domains while retaining its zero-shot capabilities remains a significant challenge. To address this, we introduce a novel prompt ensemble learning approach called Group-wise Prompt Ensemble (GPE). This method aims to enhance CLIP's zero-shot capabilities by incorporating new domain knowledge while improving its adaptability and robustness against data distribution shifts. Our approach hinges on three main strategies: prompt grouping with masked attention to optimize CLIP's adaptability while safeguarding its zero-shot capabilities; the incorporation of auxiliary prompts for the seamless integration of new domain insights without disrupting the original model's representation; and an ensemble learning strategy that effectively merges original and new knowledge. Through rigorous experimentation, including more challenging cross-dataset transfer evaluations, our GPE method redefines the benchmarks for the adaptability and efficiency of vision-language models, surpassing existing models across various scenarios.

cs.CV↗

arXiv2024

When Vision Models Meet Parameter Efficient Look-Aside Adapters Without Large-Scale Audio Pretraining

Recent studies show that pretrained vision models can boost performance in audio downstream tasks. To enhance the performance further, an additional pretraining stage with large scale audio data is typically required to infuse audio specific knowledge into the vision model. However, such approaches require extensive audio data and a carefully designed objective function. In this work, we propose bypassing the pretraining stage by directly fine-tuning the vision model with our Look Aside Adapter (LoAA) designed for efficient audio understanding. Audio spectrum data is represented across two heterogeneous dimensions time and frequency and we refine adapters to facilitate interactions between tokens across these dimensions. Our experiments demonstrate that our adapters allow vision models to reach or surpass the performance of pretrained audio models in various audio and speech tasks, offering a resource efficient and effective solution for leveraging vision models in audio applications.

cs.SD↗

arXiv2024

Hollowed Net for On-Device Personalization of Text-to-Image Diffusion Models

Recent advancements in text-to-image diffusion models have enabled the personalization of these models to generate custom images from textual prompts. This paper presents an efficient LoRA-based personalization approach for on-device subject-driven generation, where pre-trained diffusion models are fine-tuned with user-specific data on resource-constrained devices. Our method, termed Hollowed Net, enhances memory efficiency during fine-tuning by modifying the architecture of a diffusion U-Net to temporarily remove a fraction of its deep layers, creating a hollowed structure. This approach directly addresses on-device memory constraints and substantially reduces GPU memory requirements for training, in contrast to previous methods that primarily focus on minimizing training steps and reducing the number of parameters to update. Additionally, the personalized Hollowed Net can be transferred back into the original U-Net, enabling inference without additional memory overhead. Quantitative and qualitative analyses demonstrate that our approach not only reduces training memory to levels as low as those required for inference but also maintains or improves personalization performance compared to existing methods.

cs.CV↗

arXiv2024

Model-based Preference Optimization in Abstractive Summarization without Human Feedback

In abstractive summarization, the challenge of producing concise and accurate summaries arises from the vast amount of information contained in the source document. Consequently, although Large Language Models (LLMs) can generate fluent text, they often introduce inaccuracies by hallucinating content not found in the original source. While supervised fine-tuning methods that maximize likelihood contribute to this issue, they do not consistently enhance the faithfulness of the summaries. Preference-based optimization methods, such as Direct Preference Optimization (DPO), can further refine the model to align with human preferences. However, these methods still heavily depend on costly human feedback. In this work, we introduce a novel and straightforward approach called Model-based Preference Optimization (MPO) to fine-tune LLMs for improved summarization abilities without any human feedback. By leveraging the model's inherent summarization capabilities, we create a preference dataset that is fully generated by the model using different decoding strategies. Our experiments on standard summarization datasets and various metrics demonstrate that our proposed MPO significantly enhances the quality of generated summaries without relying on human feedback.

cs.CL↗

arXiv2024

Missing Modality Prediction for Unpaired Multimodal Learning via Joint Embedding of Unimodal Models

Multimodal learning typically relies on the assumption that all modalities are fully available during both the training and inference phases. However, in real-world scenarios, consistently acquiring complete multimodal data presents significant challenges due to various factors. This often leads to the issue of missing modalities, where data for certain modalities are absent, posing considerable obstacles not only for the availability of multimodal pretrained models but also for their fine-tuning and the preservation of robustness in downstream tasks. To address these challenges, we propose a novel framework integrating parameter-efficient fine-tuning of unimodal pretrained models with a self-supervised joint-embedding learning method. This framework enables the model to predict the embedding of a missing modality in the representation space during inference. Our method effectively predicts the missing embedding through prompt tuning, leveraging information from available modalities. We evaluate our approach on several multimodal benchmark datasets and demonstrate its effectiveness and robustness across various scenarios of missing modalities.

cs.CV↗

arXiv2024

Mitigating Hallucination in Abstractive Summarization with Domain-Conditional Mutual Information

A primary challenge in abstractive summarization is hallucination -- the phenomenon where a model generates plausible text that is absent in the source text. We hypothesize that the domain (or topic) of the source text triggers the model to generate text that is highly probable in the domain, neglecting the details of the source text. To alleviate this model bias, we introduce a decoding strategy based on domain-conditional pointwise mutual information. This strategy adjusts the generation probability of each token by comparing it with the token's marginal probability within the domain of the source text. According to evaluation on the XSUM dataset, our method demonstrates improvement in terms of faithfulness and source relevance. The code is publicly available at \url{https://github.com/qqplot/dcpmi}.

cs.CL↗

arXiv2024

Overcoming Data Inequality across Domains with Semi-Supervised Domain Generalization

While there have been considerable advancements in machine learning driven by extensive datasets, a significant disparity still persists in the availability of data across various sources and populations. This inequality across domains poses challenges in modeling for those with limited data, which can lead to profound practical and ethical concerns. In this paper, we address a representative case of data inequality problem across domains termed Semi-Supervised Domain Generalization (SSDG), in which only one domain is labeled while the rest are unlabeled. We propose a novel algorithm, ProUD, which can effectively learn domain-invariant features via domain-aware prototypes along with progressive generalization via uncertainty-adaptive mixing of labeled and unlabeled domains. Our experiments on three different benchmark datasets demonstrate the effectiveness of ProUD, outperforming all baseline models including single domain generalization and semi-supervised learning. Source code will be released upon acceptance of the paper.

cs.LG↗

arXiv2024

X-PEFT: eXtremely Parameter-Efficient Fine-Tuning for Extreme Multi-Profile Scenarios

Parameter-efficient fine-tuning (PEFT) techniques, such as adapter tuning, aim to fine-tune a pre-trained language model (PLM) using a minimal number of parameters for a specific task or profile. Although adapter tuning provides increased parameter efficiency compared to full-model fine-tuning, it introduces a small set of additional parameters attached to a PLM for each profile. This can become problematic in practical applications with multiple profiles, particularly when a significant increase in the number of profiles linearly boosts the total number of additional parameters. To mitigate this issue, we introduce X-PEFT, a novel PEFT method that leverages a multitude of given adapters by fine-tuning an extremely small set of compact tensors for a new profile, which serve as binary masks to adaptively select the given adapters. To efficiently validate our proposed method, we implement it using a large number of trained or untrained (random) adapters. We evaluate the performance of X-PEFT through LaMP and GLUE tasks and demonstrate that it either matches or surpasses the effectiveness of conventional adapter tuning, despite reducing the memory requirements per profile by a factor of 10,000 compared to it.

cs.LG↗

arXiv2023

Meta-Learning with a Geometry-Adaptive Preconditioner

Model-agnostic meta-learning (MAML) is one of the most successful meta-learning algorithms. It has a bi-level optimization structure where the outer-loop process learns a shared initialization and the inner-loop process optimizes task-specific weights. Although MAML relies on the standard gradient descent in the inner-loop, recent studies have shown that controlling the inner-loop's gradient descent with a meta-learned preconditioner can be beneficial. Existing preconditioners, however, cannot simultaneously adapt in a task-specific and path-dependent way. Additionally, they do not satisfy the Riemannian metric condition, which can enable the steepest descent learning with preconditioned gradient. In this study, we propose Geometry-Adaptive Preconditioned gradient descent (GAP) that can overcome the limitations in MAML; GAP can efficiently meta-learn a preconditioner that is dependent on task-specific parameters, and its preconditioner can be shown to be a Riemannian metric. Thanks to the two properties, the geometry-adaptive preconditioner is effective for improving the inner-loop optimization. Experiment results show that GAP outperforms the state-of-the-art MAML family and preconditioned gradient descent-MAML (PGD-MAML) family in a variety of few-shot learning tasks. Code is available at: https://github.com/Suhyun777/CVPR23-GAP.

cs.CV↗

arXiv2023

Complementary Domain Adaptation and Generalization for Unsupervised Continual Domain Shift Learning

Continual domain shift poses a significant challenge in real-world applications, particularly in situations where labeled data is not available for new domains. The challenge of acquiring knowledge in this problem setting is referred to as unsupervised continual domain shift learning. Existing methods for domain adaptation and generalization have limitations in addressing this issue, as they focus either on adapting to a specific domain or generalizing to unseen domains, but not both. In this paper, we propose Complementary Domain Adaptation and Generalization (CoDAG), a simple yet effective learning framework that combines domain adaptation and generalization in a complementary manner to achieve three major goals of unsupervised continual domain shift learning: adapting to a current domain, generalizing to unseen domains, and preventing forgetting of previously seen domains. Our approach is model-agnostic, meaning that it is compatible with any existing domain adaptation and generalization algorithms. We evaluate CoDAG on several benchmark datasets and demonstrate that our model outperforms state-of-the-art models in all datasets and evaluation metrics, highlighting its effectiveness and robustness in handling unsupervised continual domain shift learning.

cs.LG↗

arXiv2023

Meta-Learning with Adaptive Weighted Loss for Imbalanced Cold-Start Recommendation

Sequential recommenders have made great strides in capturing a user's preferences. Nevertheless, the cold-start recommendation remains a fundamental challenge as they typically involve limited user-item interactions for personalization. Recently, gradient-based meta-learning approaches have emerged in the sequential recommendation field due to their fast adaptation and easy-to-integrate abilities. The meta-learning algorithms formulate the cold-start recommendation as a few-shot learning problem, where each user is represented as a task to be adapted. While meta-learning algorithms generally assume that task-wise samples are evenly distributed over classes or values, user-item interactions in real-world applications do not conform to such a distribution (e.g., watching favorite videos multiple times, leaving only positive ratings without any negative ones). Consequently, imbalanced user feedback, which accounts for the majority of task training data, may dominate the user adaptation process and prevent meta-learning algorithms from learning meaningful meta-knowledge for personalized recommendations. To alleviate this limitation, we propose a novel sequential recommendation framework based on gradient-based meta-learning that captures the imbalanced rating distribution of each user and computes adaptive loss for user-specific learning. Our work is the first to tackle the impact of imbalanced ratings in cold-start sequential recommendation scenarios. Through extensive experiments conducted on real-world datasets, we demonstrate the effectiveness of our framework.

cs.IR↗

arXiv2023

Task-Agnostic Continual Reinforcement Learning: Gaining Insights and Overcoming Challenges

Continual learning (CL) enables the development of models and agents that learn from a sequence of tasks while addressing the limitations of standard deep learning approaches, such as catastrophic forgetting. In this work, we investigate the factors that contribute to the performance differences between task-agnostic CL and multi-task (MTL) agents. We pose two hypotheses: (1) task-agnostic methods might provide advantages in settings with limited data, computation, or high dimensionality, and (2) faster adaptation may be particularly beneficial in continual learning settings, helping to mitigate the effects of catastrophic forgetting. To investigate these hypotheses, we introduce a replay-based recurrent reinforcement learning (3RL) methodology for task-agnostic CL agents. We assess 3RL on a synthetic task and the Meta-World benchmark, which includes 50 unique manipulation tasks. Our results demonstrate that 3RL outperforms baseline methods and can even surpass its multi-task equivalent in challenging settings with high dimensionality. We also show that the recurrent task-agnostic agent consistently outperforms or matches the performance of its transformer-based counterpart. These findings provide insights into the advantages of task-agnostic CL over task-aware MTL approaches and highlight the potential of task-agnostic methods in resource-constrained, high-dimensional, and multi-task environments.

cs.LG↗

arXiv2023

Faster Deep Reinforcement Learning with Slower Online Network

Deep reinforcement learning algorithms often use two networks for value function optimization: an online network, and a target network that tracks the online network with some delay. Using two separate networks enables the agent to hedge against issues that arise when performing bootstrapping. In this paper we endow two popular deep reinforcement learning algorithms, namely DQN and Rainbow, with updates that incentivize the online network to remain in the proximity of the target network. This improves the robustness of deep reinforcement learning in presence of noisy updates. The resultant agents, called DQN Pro and Rainbow Pro, exhibit significant performance improvements over their original counterparts on the Atari benchmark demonstrating the effectiveness of this simple idea in deep reinforcement learning. The code for our paper is available here: Github.com/amazon-research/fast-rl-with-slow-updates.

cs.LG↗

arXiv2023

Flexible Model Aggregation for Quantile Regression

Quantile regression is a fundamental problem in statistical learning motivated by a need to quantify uncertainty in predictions, or to model a diverse population without being overly reductive. For instance, epidemiological forecasts, cost estimates, and revenue predictions all benefit from being able to quantify the range of possible values accurately. As such, many models have been developed for this problem over many years of research in statistics, machine learning, and related fields. Rather than proposing yet another (new) algorithm for quantile regression we adopt a meta viewpoint: we investigate methods for aggregating any number of conditional quantile models, in order to improve accuracy and robustness. We consider weighted ensembles where weights may vary over not only individual models, but also over quantile levels, and feature values. All of the models we consider in this paper can be fit using modern deep learning toolkits, and hence are widely accessible (from an implementation point of view) and scalable. To improve the accuracy of the predicted quantiles (or equivalently, prediction intervals), we develop tools for ensuring that quantiles remain monotonically ordered, and apply conformal calibration methods. These can be used without any modification of the original library of base models. We also review some basic theory surrounding quantile aggregation and related scoring rules, and contribute a few new results to this literature (for example, the fact that post sorting or post isotonic regression can only improve the weighted interval score). Finally, we provide an extensive suite of empirical comparisons across 34 data sets from two different benchmark repositories.

stat.ML↗

arXiv2020

Visual Concept Reasoning Networks

A split-transform-merge strategy has been broadly used as an architectural constraint in convolutional neural networks for visual recognition tasks. It approximates sparsely connected networks by explicitly defining multiple branches to simultaneously learn representations with different visual concepts or properties. Dependencies or interactions between these representations are typically defined by dense and local operations, however, without any adaptiveness or high-level reasoning. In this work, we propose to exploit this strategy and combine it with our Visual Concept Reasoning Networks (VCRNet) to enable reasoning between high-level visual concepts. We associate each branch with a visual concept and derive a compact concept state by selecting a few local descriptors through an attention module. These concept states are then updated by graph-based interaction and used to adaptively modulate the local descriptors. We describe our proposed model by split-transform-attend-interact-modulate-merge stages, which are implemented by opting for a highly modularized architecture. Extensive experiments on visual recognition tasks such as image classification, semantic segmentation, object detection, scene recognition, and action recognition show that our proposed model, VCRNet, consistently improves the performance by increasing the number of parameters by less than 1%.

cs.CV↗