arXiv subjects

Junho Kim

Publications and source records attributed to Junho Kim.

At least 55 records · Page 3Linked to original sources

arXiv2025

StyleKeeper: Prevent Content Leakage using Negative Visual Query Guidance

In the domain of text-to-image generation, diffusion models have emerged as powerful tools. Recently, studies on visual prompting, where images are used as prompts, have enabled more precise control over style and content. However, existing methods often suffer from content leakage, where undesired elements of the visual style prompt are transferred along with the intended style. To address this issue, we 1) extend classifier-free guidance (CFG) to utilize swapping self-attention and propose 2) negative visual query guidance (NVQG) to reduce the transfer of unwanted contents. NVQG employs negative score by intentionally simulating content leakage scenarios that swap queries instead of key and values of self-attention layers from visual style prompts. This simple yet effective method significantly reduces content leakage. Furthermore, we provide careful solutions for using a real image as visual style prompts. Through extensive evaluation across various styles and text prompts, our method demonstrates superiority over existing approaches, reflecting the style of the references, and ensuring that resulting images match the text prompts. Our code is available \href{https://github.com/naver-ai/StyleKeeper}{here}.

cs.CV↗

arXiv2025

CapeLLM: Support-Free Category-Agnostic Pose Estimation with Multimodal Large Language Models

Category-agnostic pose estimation (CAPE) has traditionally relied on support images with annotated keypoints, a process that is often cumbersome and may fail to fully capture the necessary correspondences across diverse object categories. Recent efforts have explored the use of text queries, leveraging their enhanced stability and generalization capabilities. However, existing approaches often remain constrained by their reliance on support queries, their failure to fully utilize the rich priors embedded in pre-trained large language models, and the limitations imposed by their parametric distribution assumptions. To address these challenges, we introduce CapeLLM, the first multimodal large language model (MLLM) designed for CAPE. Our method only employs query image and detailed text descriptions as an input to estimate category-agnostic keypoints. Our method encompasses effective training strategies and carefully designed instructions for applying the MLLM to CAPE. Moreover, we propose an inference mechanism that further enhances the reasoning process for unseen keypoints. while flexibly modeling their underlying spatial distribution and uncertainty, allowing for adaptive refinement based on contextual cues. We conducted extensive experiments to apply the MLLM to CAPE effectively, focusing not only on the model architecture and prompt design but also on ensuring robustness across input variations. Our approach sets a new state-of-the-art on the MP-100 benchmark in the 1-shot and even 5-shot setting, marking a significant advancement in the field of category-agnostic pose estimation. Code is available at https://github.com/Junhojuno/CapeLLM.

cs.CV↗

arXiv2025

Learning 3D Scene Analogies with Neural Contextual Scene Maps

Understanding scene contexts is crucial for machines to perform tasks and adapt prior knowledge in unseen or noisy 3D environments. As data-driven learning is intractable to comprehensively encapsulate diverse ranges of layouts and open spaces, we propose teaching machines to identify relational commonalities in 3D spaces. Instead of focusing on point-wise or object-wise representations, we introduce 3D scene analogies, which are smooth maps between 3D scene regions that align spatial relationships. Unlike well-studied single instance-level maps, these scene-level maps smoothly link large scene regions, potentially enabling unique applications in trajectory transfer in AR/VR, long demonstration transfer for imitation learning, and context-aware object rearrangement. To find 3D scene analogies, we propose neural contextual scene maps, which extract descriptor fields summarizing semantic and geometric contexts, and holistically align them in a coarse-to-fine manner for map estimation. This approach reduces reliance on individual feature points, making it robust to input noise or shape variations. Experiments demonstrate the effectiveness of our approach in identifying scene analogies and transferring trajectories or object placements in diverse indoor scenes, indicating its potential for robotics and AR/VR applications. Project page including the code is available through this link: https://82magnolia.github.io/3d_scene_analogies/.

cs.CV↗

arXiv2025

Incorporating Domain Knowledge into Materials Tokenization

While language models are increasingly utilized in materials science, typical models rely on frequency-centric tokenization methods originally developed for natural language processing. However, these methods frequently produce excessive fragmentation and semantic loss, failing to maintain the structural and semantic integrity of material concepts. To address this issue, we propose MATTER, a novel tokenization approach that integrates material knowledge into tokenization. Based on MatDetector trained on our materials knowledge base and a re-ranking method prioritizing material concepts in token merging, MATTER maintains the structural integrity of identified material concepts and prevents fragmentation during tokenization, ensuring their semantic meaning remains intact. The experimental results demonstrate that MATTER outperforms existing tokenization methods, achieving an average performance gain of $4\%$ and $2\%$ in the generation and classification tasks, respectively. These results underscore the importance of domain knowledge for tokenization strategies in scientific text processing. Our code is available at https://github.com/yerimoh/MATTER

cs.CL↗

arXiv2025

Enhancing Creative Generation on Stable Diffusion-based Models

Recent text-to-image generative models, particularly Stable Diffusion and its distilled variants, have achieved impressive fidelity and strong text-image alignment. However, their creative capability remains constrained, as including `creative' in prompts seldom yields the desired results. This paper introduces C3 (Creative Concept Catalyst), a training-free approach designed to enhance creativity in Stable Diffusion-based models. C3 selectively amplifies features during the denoising process to foster more creative outputs. We offer practical guidelines for choosing amplification factors based on two main aspects of creativity. C3 is the first study to enhance creativity in diffusion models without extensive computational costs. We demonstrate its effectiveness across various Stable Diffusion-based models.

cs.CV↗

arXiv2025

Design of Seamless Multi-modal Interaction Framework for Intelligent Virtual Agents in Wearable Mixed Reality Environment

In this paper, we present the design of a multimodal interaction framework for intelligent virtual agents in wearable mixed reality environments, especially for interactive applications at museums, botanical gardens, and similar places. These places need engaging and no-repetitive digital content delivery to maximize user involvement. An intelligent virtual agent is a promising mode for both purposes. Premises of framework is wearable mixed reality provided by MR devices supporting spatial mapping. We envisioned a seamless interaction framework by integrating potential features of spatial mapping, virtual character animations, speech recognition, gazing, domain-specific chatbot and object recognition to enhance virtual experiences and communication between users and virtual agents. By applying a modular approach and deploying computationally intensive modules on cloud-platform, we achieved a seamless virtual experience in a device with limited resources. Human-like gaze and speech interaction with a virtual agent made it more interactive. Automated mapping of body animations with the content of a speech made it more engaging. In our tests, the virtual agents responded within 2-4 seconds after the user query. The strength of the framework is flexibility and adaptability. It can be adapted to any wearable MR device supporting spatial mapping.

cs.HC↗

arXiv2025

SALOVA: Segment-Augmented Long Video Assistant for Targeted Retrieval and Routing in Long-Form Video Analysis

Despite advances in Large Multi-modal Models, applying them to long and untrimmed video content remains challenging due to limitations in context length and substantial memory overhead. These constraints often lead to significant information loss and reduced relevance in the model responses. With the exponential growth of video data across web platforms, understanding long-form video is crucial for advancing generalized intelligence. In this paper, we introduce SALOVA: Segment-Augmented LOng Video Assistant, a novel video-LLM framework designed to enhance the comprehension of lengthy video content through targeted retrieval process. We address two main challenges to achieve it: (i) We present the SceneWalk dataset, a high-quality collection of 87.8K long videos, each densely captioned at the segment level to enable models to capture scene continuity and maintain rich descriptive context. (ii) We develop robust architectural designs integrating dynamic routing mechanism and spatio-temporal projector to efficiently retrieve and process relevant video segments based on user queries. Our framework mitigates the limitations of current video-LMMs by allowing for precise identification and retrieval of relevant video segments in response to queries, thereby improving the contextual relevance of the generated responses. Through extensive experiments, SALOVA demonstrates enhanced capability in processing complex long-form videos, showing significant capability to maintain contextual integrity across extended sequences.

cs.CV↗

arXiv2025

Direct Unlearning Optimization for Robust and Safe Text-to-Image Models

Recent advancements in text-to-image (T2I) models have unlocked a wide range of applications but also present significant risks, particularly in their potential to generate unsafe content. To mitigate this issue, researchers have developed unlearning techniques to remove the model's ability to generate potentially harmful content. However, these methods are easily bypassed by adversarial attacks, making them unreliable for ensuring the safety of generated images. In this paper, we propose Direct Unlearning Optimization (DUO), a novel framework for removing Not Safe For Work (NSFW) content from T2I models while preserving their performance on unrelated topics. DUO employs a preference optimization approach using curated paired image data, ensuring that the model learns to remove unsafe visual concepts while retaining unrelated features. Furthermore, we introduce an output-preserving regularization term to maintain the model's generative capabilities on safe content. Extensive experiments demonstrate that DUO can robustly defend against various state-of-the-art red teaming methods without significant performance degradation on unrelated topics, as measured by FID and CLIP scores. Our work contributes to the development of safer and more reliable T2I models, paving the way for their responsible deployment in both closed-source and open-source scenarios.

cs.CV↗

arXiv2024

DECOR:Decomposition and Projection of Text Embeddings for Text-to-Image Customization

Text-to-image (T2I) models can effectively capture the content or style of reference images to perform high-quality customization. A representative technique for this is fine-tuning using low-rank adaptations (LoRA), which enables efficient model customization with reference images. However, fine-tuning with a limited number of reference images often leads to overfitting, resulting in issues such as prompt misalignment or content leakage. These issues prevent the model from accurately following the input prompt or generating undesired objects during inference. To address this problem, we examine the text embeddings that guide the diffusion model during inference. This study decomposes the text embedding matrix and conducts a component analysis to understand the embedding space geometry and identify the cause of overfitting. Based on this, we propose DECOR, which projects text embeddings onto a vector space orthogonal to undesired token vectors, thereby reducing the influence of unwanted semantics in the text embeddings. Experimental results demonstrate that DECOR outperforms state-of-the-art customization models and achieves Pareto frontier performance across text and visual alignment evaluation metrics. Furthermore, it generates images more faithful to the input prompts, showcasing its effectiveness in addressing overfitting and enhancing text-to-image customization.

cs.CV↗

arXiv2024

Look Every Frame All at Once: Video-Ma$^2$mba for Efficient Long-form Video Understanding with Multi-Axis Gradient Checkpointing

With the growing scale and complexity of video data, efficiently processing long video sequences poses significant challenges due to the quadratic increase in memory and computational demands associated with existing transformer-based Large Multi-modal Models (LMMs). To address these issues, we introduce Video-Ma$^2$mba, a novel architecture that incorporates State Space Models (SSMs) within the Mamba-2 framework, replacing the attention mechanisms. This allows the LMMs to scale linearly in terms of time and memory requirements, making it feasible to handle long-duration video content. Furthermore, we enhance the memory efficiency introducing the Multi-Axis Gradient Checkpointing (MA-GC) method, which strategically manages memory by retaining only essential activations across multiple computational axes. Our approach significantly reduces the memory footprint compared to standard gradient checkpointing. Empirical analyses show that Video-Ma$^2$mba can process extensive video sequences-equivalent to millions of tokens or over two hours of continuous sequences at 1 FPS-on a single GPU. By maintaining a detailed capture of temporal dynamics, our model improves the accuracy and relevance of responses in long video understanding tasks, demonstrating substantial advantages over existing frameworks.

cs.CV↗

arXiv2024

D-Cube: Exploiting Hyper-Features of Diffusion Model for Robust Medical Classification

The integration of deep learning technologies in medical imaging aims to enhance the efficiency and accuracy of cancer diagnosis, particularly for pancreatic and breast cancers, which present significant diagnostic challenges due to their high mortality rates and complex imaging characteristics. This paper introduces Diffusion-Driven Diagnosis (D-Cube), a novel approach that leverages hyper-features from a diffusion model combined with contrastive learning to improve cancer diagnosis. D-Cube employs advanced feature selection techniques that utilize the robust representational capabilities of diffusion models, enhancing classification performance on medical datasets under challenging conditions such as data imbalance and limited sample availability. The feature selection process optimizes the extraction of clinically relevant features, significantly improving classification accuracy and demonstrating resilience in imbalanced and limited data scenarios. Experimental results validate the effectiveness of D-Cube across multiple medical imaging modalities, including CT, MRI, and X-ray, showing superior performance compared to existing baseline models. D-Cube represents a new strategy in cancer detection, employing advanced deep learning techniques to achieve state-of-the-art diagnostic accuracy and efficiency.

cs.CV↗

arXiv2024

C2A: Client-Customized Adaptation for Parameter-Efficient Federated Learning

Despite the versatility of pre-trained language models (PLMs) across domains, their large memory footprints pose significant challenges in federated learning (FL), where the training model has to be distributed between a server and clients. One potential solution to bypass such constraints might be the use of parameter-efficient fine-tuning (PEFT) in the context of FL. However, we have observed that typical PEFT tends to severely suffer from heterogeneity among clients in FL scenarios, resulting in unstable and slow convergence. In this paper, we propose Client-Customized Adaptation (C2A), a novel hypernetwork-based FL framework that generates client-specific adapters by conditioning the client information. With the effectiveness of the hypernetworks in generating customized weights through learning to adopt the different characteristics of inputs, C2A can maximize the utility of shared model parameters while minimizing the divergence caused by client heterogeneity. To verify the efficacy of C2A, we perform extensive evaluations on FL scenarios involving heterogeneity in label and language distributions. Comprehensive evaluation results clearly support the superiority of C2A in terms of both efficiency and effectiveness in FL scenarios.

cs.LG↗

arXiv2024

CleaR: Towards Robust and Generalized Parameter-Efficient Fine-Tuning for Noisy Label Learning

Parameter-efficient fine-tuning (PEFT) has enabled the efficient optimization of cumbersome language models in real-world settings. However, as datasets in such environments often contain noisy labels that adversely affect performance, PEFT methods are inevitably exposed to noisy labels. Despite this challenge, the adaptability of PEFT to noisy environments remains underexplored. To bridge this gap, we investigate various PEFT methods under noisy labels. Interestingly, our findings reveal that PEFT has difficulty in memorizing noisy labels due to its inherently limited capacity, resulting in robustness. However, we also find that such limited capacity simultaneously makes PEFT more vulnerable to interference of noisy labels, impeding the learning of clean samples. To address this issue, we propose Clean Routing (CleaR), a novel routing-based PEFT approach that adaptively activates PEFT modules. In CleaR, PEFT modules are preferentially exposed to clean data while bypassing the noisy ones, thereby minimizing the noisy influence. To verify the efficacy of CleaR, we perform extensive experiments on diverse configurations of noisy labels. The results convincingly demonstrate that CleaR leads to substantially improved performance in noisy environments.

cs.LG↗

arXiv2024

MELT: Materials-aware Continued Pre-training for Language Model Adaptation to Materials Science

We introduce a novel continued pre-training method, MELT (MatEriaLs-aware continued pre-Training), specifically designed to efficiently adapt the pre-trained language models (PLMs) for materials science. Unlike previous adaptation strategies that solely focus on constructing domain-specific corpus, MELT comprehensively considers both the corpus and the training strategy, given that materials science corpus has distinct characteristics from other domains. To this end, we first construct a comprehensive materials knowledge base from the scientific corpus by building semantic graphs. Leveraging this extracted knowledge, we integrate a curriculum into the adaptation process that begins with familiar and generalized concepts and progressively moves toward more specialized terms. We conduct extensive experiments across diverse benchmarks to verify the effectiveness and generality of MELT. A comprehensive evaluation convincingly supports the strength of MELT, demonstrating superior performance compared to existing continued pre-training methods. The in-depth analysis also shows that MELT enables PLMs to effectively represent materials entities compared to the existing adaptation methods, thereby highlighting its broad applicability across a wide spectrum of materials science.

cs.CL↗

arXiv2024

Mentor-KD: Making Small Language Models Better Multi-step Reasoners

Large Language Models (LLMs) have displayed remarkable performances across various complex tasks by leveraging Chain-of-Thought (CoT) prompting. Recently, studies have proposed a Knowledge Distillation (KD) approach, reasoning distillation, which transfers such reasoning ability of LLMs through fine-tuning language models of multi-step rationales generated by LLM teachers. However, they have inadequately considered two challenges regarding insufficient distillation sets from the LLM teacher model, in terms of 1) data quality and 2) soft label provision. In this paper, we propose Mentor-KD, which effectively distills the multi-step reasoning capability of LLMs to smaller LMs while addressing the aforementioned challenges. Specifically, we exploit a mentor, intermediate-sized task-specific fine-tuned model, to augment additional CoT annotations and provide soft labels for the student model during reasoning distillation. We conduct extensive experiments and confirm Mentor-KD's effectiveness across various models and complex reasoning tasks.

cs.CL↗

arXiv2024

What if...?: Thinking Counterfactual Keywords Helps to Mitigate Hallucination in Large Multi-modal Models

This paper presents a way of enhancing the reliability of Large Multi-modal Models (LMMs) in addressing hallucination, where the models generate cross-modal inconsistent responses. Without additional training, we propose Counterfactual Inception, a novel method that implants counterfactual thinking into LMMs using self-generated counterfactual keywords. Our method is grounded in the concept of counterfactual thinking, a cognitive process where human considers alternative realities, enabling more extensive context exploration. Bridging the human cognition mechanism into LMMs, we aim for the models to engage with and generate responses that span a wider contextual scene understanding, mitigating hallucinatory outputs. We further introduce Plausibility Verification Process (PVP), a simple yet robust keyword constraint that effectively filters out sub-optimal keywords to enable the consistent triggering of counterfactual thinking in the model responses. Comprehensive analyses across various LMMs, including both open-source and proprietary models, corroborate that counterfactual thinking significantly reduces hallucination and helps to broaden contextual understanding based on true visual clues.

cs.CV↗

arXiv2024

CODE: Contrasting Self-generated Description to Combat Hallucination in Large Multi-modal Models

Large Multi-modal Models (LMMs) have recently demonstrated remarkable abilities in visual context understanding and coherent response generation. However, alongside these advancements, the issue of hallucinations has emerged as a significant challenge, producing erroneous responses that are unrelated to the visual contents. In this paper, we introduce a novel contrastive-based decoding method, COuntering DEscription Contrastive Decoding (CODE), which leverages self-generated descriptions as contrasting references during the decoding phase of LMMs to address hallucination issues. CODE utilizes the comprehensive descriptions from model itself as visual counterpart to correct and improve response alignment with actual visual content. By dynamically adjusting the information flow and distribution of next-token predictions in the LMM's vocabulary, CODE enhances the coherence and informativeness of generated responses. Extensive experiments demonstrate that our method significantly reduces hallucinations and improves cross-modal consistency across various benchmarks and cutting-edge LMMs. Our method provides a simple yet effective decoding strategy that can be integrated to existing LMM frameworks without additional training.

cs.CV↗

arXiv2024

Fully Geometric Panoramic Localization

We introduce a lightweight and accurate localization method that only utilizes the geometry of 2D-3D lines. Given a pre-captured 3D map, our approach localizes a panorama image, taking advantage of the holistic 360 view. The system mitigates potential privacy breaches or domain discrepancies by avoiding trained or hand-crafted visual descriptors. However, as lines alone can be ambiguous, we express distinctive yet compact spatial contexts from relationships between lines, namely the dominant directions of parallel lines and the intersection between non-parallel lines. The resulting representations are efficient in processing time and memory compared to conventional visual descriptor-based methods. Given the groups of dominant line directions and their intersections, we accelerate the search process to test thousands of pose candidates in less than a millisecond without sacrificing accuracy. We empirically show that the proposed 2D-3D matching can localize panoramas for challenging scenes with similar structures, dramatic domain shifts or illumination changes. Our fully geometric approach does not involve extensive parameter tuning or neural network training, making it a practical algorithm that can be readily deployed in the real world. Project page including the code is available through this link: https://82magnolia.github.io/fgpl/.

cs.CV↗