Jungwon Park

Jungmin Ko, Jungwon Park, Jimyeong Kim et al.

Text-to-image (T2I) models have become increasingly capable of generating high-quality images. Yet, enforcing the explicit absence of a specified object or attribute remains a fundamentally challenging problem. Existing approaches, including prompt negation, post-hoc editing, and negative guidance, remain insufficient for explicit concept suppression, often failing to remove the target concept or degrading overall image quality. To this end, we propose Orthogonal Negative Guidance in attention feature space, a training-free method that operates in the attention output space of MM-DiT-based T2I transformers. Our method orthogonalizes negative-prompt attention features with respect to positive-prompt features and subtracts only the orthogonal component, suppressing unwanted concepts while preserving desired semantics. Experiments on FLUX-dev and FLUX-schnell show that our method achieves favorable trade-offs between concept suppression, prompt alignment, and image quality. In human evaluation, our method outperforms the second-best baseline by 18.78%. We further show that our method supports multi-concept suppression and adjustable concept suppression.

Jungwon Park, Jimyeong Kim, Jungmin Ko et al.

Diffusion language models decode text by iteratively denoising masked token sequences, making the choice of which positions to decode a central inference-time decision. Most training-free decoding strategies use model confidence for position selection, assuming that high-confidence positions are ready to be decoded. In this work, we revisit this assumption by studying when confidence misleads fully non-autoregressive (fully non-AR) decoding. EOT tokens can receive high confidence and cause incomplete generation; inserting a suffix anchor can mitigate this issue but introduces local overconfidence near the anchor, causing anchor-adjacent tokens to be decoded too early. To address these issues, we propose Suffix-Anchored Confidence Modulation, a simple training-free method that inserts a short suffix anchor to encourage response completion and modulates confidence near the anchor according to decoding progress. This preserves the response-completion benefit of suffix anchoring while reducing premature decoding of anchor-adjacent tokens. Across text-only reasoning, vision-language reasoning, and code-generation benchmarks, our method consistently improves confidence-based fully non-AR decoding, outperforms explicit EOT suppression, and preserves the parallel decoding advantage of fully non-AR generation.

Euna Jung, Jungwon Park, Jaekeol Choi et al.

The recent advancement in language representation modeling has broadly affected the design of dense retrieval models. In particular, many of the high-performing dense retrieval models evaluate representations of query and document using BERT, and subsequently apply a cosine-similarity based scoring to determine the relevance. BERT representations, however, are known to follow an anisotropic distribution of a narrow cone shape and such an anisotropic distribution can be undesirable for the cosine-similarity based scoring. In this work, we first show that BERT-based DR also follows an anisotropic distribution. To cope with the problem, we introduce unsupervised post-processing methods of Normalizing Flow and whitening, and develop token-wise method in addition to the sequence-wise method for applying the post-processing methods to the representations of dense retrieval models. We show that the proposed methods can effectively enhance the representations to be isotropic, then we perform experiments with ColBERT and RepBERT to show that the performance (NDCG at 10) of document re-ranking can be improved by 5.17\%$\sim$8.09\% for ColBERT and 6.88\%$\sim$22.81\% for RepBERT. To examine the potential of isotropic representation for improving the robustness of DR models, we investigate out-of-distribution tasks where the test dataset differs from the training dataset. The results show that isotropic representation can achieve a generally improved performance. For instance, when training dataset is MS-MARCO and test dataset is Robust04, isotropy post-processing can improve the baseline performance by up to 24.98\%. Furthermore, we show that an isotropic model trained with an out-of-distribution dataset can even outperform a baseline model trained with the in-distribution dataset.

Jimyeong Kim, Jungwon Park, Wonjong Rhee

In text-to-image personalization, a timely and crucial challenge is the tendency of generated images overfitting to the biases present in the reference images. We initiate our study with a comprehensive categorization of the biases into background, nearby-object, tied-object, substance (in style re-contextualization), and pose biases. These biases manifest in the generated images due to their entanglement into the subject embedding. This undesired embedding entanglement not only results in the reflection of biases from the reference images into the generated images but also notably diminishes the alignment of the generated images with the given generation prompt. To address this challenge, we propose SID~(Selectively Informative Description), a text description strategy that deviates from the prevalent approach of only characterizing the subject's class identification. SID is generated utilizing multimodal GPT-4 and can be seamlessly integrated into optimization-based models. We present comprehensive experimental results along with analyses of cross-attention maps, subject-alignment, non-subject-disentanglement, and text-alignment.

Jungwon Park, Jungmin Ko, Dongnam Byun et al.

Numerous studies on text-to-image (T2I) generative models have utilized cross-attention maps to boost application performance and interpret model behavior. However, the distinct characteristics of attention maps from different attention heads remain relatively underexplored. In this study, we show that selectively aggregating cross-attention maps from heads most relevant to a target concept can improve visual interpretability. Compared to the diffusion-based segmentation method DAAM, our approach achieves higher mean IoU scores. We also find that the most relevant heads capture concept-specific features more accurately than the least relevant ones, and that selective aggregation helps diagnose prompt misinterpretations. These findings suggest that attention head selection offers a promising direction for improving the interpretability and controllability of T2I generation.

Jimyeong Kim, Jungwon Park, Yeji Song et al.

Rectified Flow text-to-image models surpass diffusion models in image quality and text alignment, but adapting ReFlow for real-image editing remains challenging. We propose a new real-image editing method for ReFlow by analyzing the intermediate representations of multimodal transformer blocks and identifying three key features. To extract these features from real images with sufficient structural preservation, we leverage mid-step latent, which is inverted only up to the mid-step. We then adapt attention during injection to improve editability and enhance alignment to the target text. Our method is training-free, requires no user-provided mask, and can be applied even without a source prompt. Extensive experiments on two benchmarks with nine baselines demonstrate its superior performance over prior methods, further validated by human evaluations confirming a strong user preference for our approach.

Jungwon Park, Jungmin Ko, Dongnam Byun et al.

Recent text-to-image diffusion models leverage cross-attention layers, which have been effectively utilized to enhance a range of visual generative tasks. However, our understanding of cross-attention layers remains somewhat limited. In this study, we introduce a mechanistic interpretability approach for diffusion models by constructing Head Relevance Vectors (HRVs) that align with human-specified visual concepts. An HRV for a given visual concept has a length equal to the total number of cross-attention heads, with each element representing the importance of the corresponding head for the given visual concept. To validate HRVs as interpretable features, we develop an ordered weakening analysis that demonstrates their effectiveness. Furthermore, we propose concept strengthening and concept adjusting methods and apply them to enhance three visual generative tasks. Our results show that HRVs can reduce misinterpretations of polysemous words in image generation, successfully modify five challenging attributes in image editing, and mitigate catastrophic neglect in multi-concept generation. Overall, our work provides an advancement in understanding cross-attention layers and introduces new approaches for fine-controlling these layers at the head level.

Dongnam Byun, Jungwon Park, Jungmin Ko et al.

Recent progress in text-to-image (T2I) generative models has led to significant improvements in generating high-quality images aligned with text prompts. However, these models still struggle with prompts involving multiple objects, often resulting in object neglect or object mixing. Through extensive studies, we identify four problematic scenarios, Similar Shapes, Similar Textures, Dissimilar Background Biases, and Many Objects, where inter-object relationships frequently lead to such failures. Motivated by two key observations about CLIP embeddings, we propose DOS (Directional Object Separation), a method that modifies three types of CLIP text embeddings before passing them into text-to-image models. Experimental results show that DOS consistently improves the success rate of multi-object image generation and reduces object mixing. In human evaluations, DOS significantly outperforms four competing methods, receiving 26.24%-43.04% more votes across four benchmarks. These results highlight DOS as a practical and effective solution for improving multi-object image generation.

Jungwon Park, Wonjong Rhee

In-Context Learning (ICL) enables Large Language Models (LLMs) to perform tasks by conditioning on input-output examples in the prompt, without requiring any update in model parameters. While widely adopted, it remains unclear whether prompting with multiple examples is the most effective and efficient way to convey task information. In this work, we propose Soft Injection of task embeddings. The task embeddings are constructed only once using few-shot ICL prompts and repeatedly used during inference. Soft injection is performed by softly mixing task embeddings with attention head activations using pre-optimized mixing parameters, referred to as soft head-selection parameters. This method not only allows a desired task to be performed without in-prompt demonstrations but also significantly outperforms existing ICL approaches while reducing memory usage and compute cost at inference time. An extensive evaluation is performed across 57 tasks and 12 LLMs, spanning four model families of sizes from 4B to 70B. Averaged across 57 tasks, our method outperforms 10-shot ICL by 10.2%-14.3% across 12 LLMs. Additional analyses show that our method also serves as an insightful tool for analyzing task-relevant roles of attention heads, revealing that task-relevant head positions selected by our method transfer across similar tasks but not across dissimilar ones -- underscoring the task-specific nature of head functionality. Our soft injection method opens a new paradigm for reducing prompt length and improving task performance by shifting task conditioning from the prompt space to the activation space.

Suhyun Kang, Jungwon Park, Wonseok Lee et al.

Cross-Domain Few-Shot Learning~(CDFSL) methods typically parameterize models with task-agnostic and task-specific parameters. To adapt task-specific parameters, recent approaches have utilized fixed optimization strategies, despite their potential sub-optimality across varying domains or target tasks. To address this issue, we propose a novel adaptation mechanism called Task-Specific Preconditioned gradient descent~(TSP). Our method first meta-learns Domain-Specific Preconditioners~(DSPs) that capture the characteristics of each meta-training domain, which are then linearly combined using task-coefficients to form the Task-Specific Preconditioner. The preconditioner is applied to gradient descent, making the optimization adaptive to the target task. We constrain our preconditioners to be positive definite, guiding the preconditioned gradient toward the direction of steepest descent. Empirical evaluations on the Meta-Dataset show that TSP achieves state-of-the-art performance across diverse experimental scenarios.

Jungwon Park, Dabin Kim, Gyeong Chan Kim et al.

This paper presents a new online multi-agent trajectory planning algorithm that guarantees to generate safe, dynamically feasible trajectories in a cluttered environment. The proposed algorithm utilizes a linear safe corridor (LSC) to formulate the distributed trajectory optimization problem with only feasible constraints, so it does not resort to slack variables or soft constraints to avoid optimization failure. We adopt a priority-based goal planning method to prevent the deadlock without an additional procedure to decide which robot to yield. The proposed algorithm can compute the trajectories for 60 agents on average 15.5 ms per agent with an Intel i7 laptop and shows a similar flight distance and distance compared to the baselines based on soft constraints. We verified that the proposed method can reach the goal without deadlock in both the random forest and the indoor space, and we validated the safety and operability of the proposed algorithm through a real flight test with ten quadrotors in a maze-like environment.

Jungwon Park, H. Jin Kim

This paper presents a new trajectory planning method for multiple quadrotors in obstacle-dense environments. We suggest a relative safe flight corridor (RSFC) to model safe region between a pair of agents, and it is used to generate linear constraints for inter-collision avoidance by utilizing the convex hull property of relative Bernstein polynomial. Our approach employs a graph-based multi-agent pathfinding algorithm to generate an initial trajectory, which is used to construct a safe flight corridor (SFC) and RSFC. We express the trajectory as a piecewise Bernstein polynomial and formulate the trajectory planning problem into one quadratic programming problem using linear constraints from SFC and RSFC. The proposed method can compute collision-free trajectory for 16 agents within a second and for 64 agents less than a minute, and it is validated both through simulation and indoor flight test.