Minchan Kwon

Hoyong Kim, Minchan Kwon, Kangil Kim

In replay-based methods for continual learning, replaying input samples in episodic memory has shown its effectiveness in alleviating catastrophic forgetting. However, the potential key factor of cross-entropy loss with softmax in causing catastrophic forgetting has been underexplored. In this paper, we analyze the effect of softmax and revisit softmax masking with negative infinity to shed light on its ability to mitigate catastrophic forgetting. Based on the analyses, it is found that negative infinity masked softmax is not always compatible with dark knowledge. To improve the compatibility, we propose a general masked softmax that controls the stability by adjusting the gradient scale to old and new classes. We demonstrate that utilizing our method on other replay-based methods results in better performance, primarily by enhancing model stability in continual learning benchmarks, even when the buffer size is set to an extremely small value.

Minchan Kwon, Hyounguk Shon, Junmo Kim

Large multimodal models (LMMs) have recently demonstrated remarkable performance in video question answering (VideoQA), yet reasoning over video remains challenging due to high inference cost and diluted information. Keyframe selection offers efficiency and sharper reasoning but suffers from sparse supervision and redundant frame choices when relying only on image-text similarity. We present a question-aware keyframe selection framework with two components: pseudo keyframe labels derived from LMMs that provide informative supervision and a coverage regularization that promotes diverse, complementary evidence across time. Experiments on NExT-QA show that our method significantly improves accuracy, especially for temporal and causal question types, establishing keyframe selection as an effective and learnable module for VideoQA.

Minseo Kim, Minchan Kwon, Dongyeun Lee et al.

Personalized text-to-image generation suffers from concept entanglement, where irrelevant residual information from reference images is captured, leading to a trade-off between concept fidelity and text alignment. Recent disentanglement approaches attempt to solve this utilizing manual guidance, such as linguistic cues or segmentation masks, which limits their applicability and fails to fully articulate the target concept. In this paper, we propose ConceptPrism, a novel framework that automatically disentangles the shared visual concept from image-specific residuals by comparing images within a set. Our method jointly optimizes a target token and image-wise residual tokens using two complementary objectives: a reconstruction loss to ensure fidelity, and a novel exclusion loss that compels residual tokens to discard the shared concept. This process allows the target token to capture the pure concept without direct supervision. Extensive experiments demonstrate that ConceptPrism effectively resolves concept entanglement, achieving a significantly improved trade-off between fidelity and alignment.

Minchan Kwon, Sunghyun Baek, Minseo Kim et al.

Large Language Model (LLM) Red-Teaming, which proactively identifies vulnerabilities of LLMs, is an essential process for ensuring safety. Finding effective and diverse attacks in red-teaming is important, but achieving both is challenging. Generative Flow Networks (GFNs) that perform distribution matching are a promising methods, but they are notorious for training instability and mode collapse. In particular, unstable rewards in red-teaming accelerate mode collapse. We propose Stable-GFN (S-GFN), which eliminates partition function $Z$ estimation in GFN and reduces training instability. S-GFN avoids Z-estimation through pairwise comparisons and employs a robust masking methodology against noisy rewards. Additionally, we propose a fluency stabilizer to prevent the model from getting stuck in local optima that produce gibberish. S-GFN provides more stable training while maintaining the optimal policy of GFN. We demonstrate the overwhelming attack performance and diversity of S-GFN across various settings.

Seoyeon Gye, Junwon Ko, Hyounguk Shon et al.

Identifying AI-generated content is critical for the safe and ethical use of generative AI. Recent research has focused on developing detectors that generalize to unknown generators, with popular methods relying either on high-level features or low-level fingerprints. However, these methods have clear limitations: biased towards unseen content, or vulnerable to common image degradations, such as JPEG compression. To address these issues, we propose a novel approach, SFLD, which incorporates PatchShuffle to integrate high-level semantic and low-level textural information. SFLD applies PatchShuffle at multiple levels, improving robustness and generalization across various generative models. Additionally, current benchmarks face challenges such as low image quality, insufficient content preservation, and limited class diversity. In response, we introduce TwinSynths, a new benchmark generation methodology that constructs visually near-identical pairs of real and synthetic images to ensure high quality and content preservation. Our extensive experiments and analysis show that SFLD outperforms existing methods on detecting a wide variety of fake images sourced from GANs, diffusion models, and TwinSynths, demonstrating the state-of-the-art performance and generalization capabilities to novel generative models.

Minchan Kwon, Junwon Ko, Kangil Kim et al.

Direct Preference Optimization (DPO) is a powerful paradigm to align language models with human preferences using pairwise comparisons. However, its binary win-or-loss supervision often proves insufficient for training small models with limited capacity. Prior works attempt to distill information from large teacher models using behavior cloning or KL divergence. These methods often focus on mimicking current behavior and overlook distilling reward modeling. To address this issue, we propose \textit{Teacher Value-based Knowledge Distillation} (TVKD), which introduces an auxiliary reward from the value function of the teacher model to provide a soft guide. This auxiliary reward is formulated to satisfy potential-based reward shaping, ensuring that the global reward structure and optimal policy of DPO are preserved. TVKD can be integrated into the standard DPO training framework and does not require additional rollouts. Our experimental results show that TVKD consistently improves performance across various benchmarks and model sizes.

Minseo Kim, Minchan Kwon, Dongyeun Lee et al.

The recent demand for customized image generation raises a need for techniques that effectively extract the common concept from small sets of images. Existing methods typically rely on additional guidance, such as text prompts or spatial masks, to capture the common target concept. Unfortunately, relying on manually provided guidance can lead to incomplete separation of auxiliary features, which degrades generation quality.In this paper, we propose Contrastive Inversion, a novel approach that identifies the common concept by comparing the input images without relying on additional information. We train the target token along with the image-wise auxiliary text tokens via contrastive learning, which extracts the well-disentangled true semantics of the target. Then we apply disentangled cross-attention fine-tuning to improve concept fidelity without overfitting. Experimental results and analysis demonstrate that our method achieves a balanced, high-level performance in both concept representation and editing, outperforming existing techniques.

Minchan Kwon, Kangil Kim

In real life, adversarial attack to deep learning models is a fatal security issue. However, the issue has been rarely discussed in a widely used class-incremental continual learning (CICL). In this paper, we address problems of applying adversarial training to CICL, which is well-known defense method against adversarial attack. A well-known problem of CICL is class-imbalance that biases a model to the current task by a few samples of previous tasks. Meeting with the adversarial training, the imbalance causes another imbalance of attack trials over tasks. Lacking clean data of a minority class by the class-imbalance and increasing of attack trials from a majority class by the secondary imbalance, adversarial training distorts optimal decision boundaries. The distortion eventually decreases both accuracy and robustness than adversarial training. To exclude the effects, we propose a straightforward but significantly effective method, External Adversarial Training (EAT) which can be applied to methods using experience replay. This method conduct adversarial training to an auxiliary external model for the current task data at each time step, and applies generated adversarial examples to train the target model. We verify the effects on a toy problem and show significance on CICL benchmarks of image classification. We expect that the results will be used as the first baseline for robustness research of CICL.