Junyoung Koh

Jaeyun Lee, Junyoung Koh, Zeynel Tok et al.

Multi-constraint instruction following requires verifying whether a response satisfies multiple individual requirements, yet LLM judges are often assessed only through overall-response judgments. We introduce MCJudgeBench, a benchmark for constraint-level judge evaluation in multi-constraint instruction following. Each instance includes an instruction, a candidate response, an explicit constraint list, per-constraint gold labels in {yes, partial, no}, and controlled response-side perturbations. The evaluation protocol further includes evaluation prompt variants to test judge stability. We evaluate proprietary and open-source LLM judges using both correctness and inconsistency metrics, distinguishing intrinsic inconsistency under stochastic decoding from procedural inconsistency under prompt and response perturbations. Our results show that judge reliability has multiple dimensions: strong overall performance does not guarantee equally reliable detection across label categories, especially for rarer partial and no cases. Judges with higher correctness do not always have lower inconsistency. Evaluation with reasoning improves correctness but does not uniformly improve stability. These findings motivate evaluating LLM judges at the constraint level to study these failure modes.

Junyoung Koh

Text-to-music generation has advanced rapidly, with modern autoregressive and diffusion-based models producing convincing music from natural-language prompts. However, much of this progress relies on large-scale training data and external pretraining, making it difficult to isolate which design choices remain effective when data and pretraining are controlled. We study this setting using a Diffusion Transformer backbone with lyric and timbre conditioning, adapted to an instrumental-only text-to-music task in which the auxiliary lyric and timbre branches receive only degenerate conditioning signals. Through controlled ablations, we find that models retrained without these branches score lower across AudioBox aesthetics, LLM-as-judge, and human MOS, and that reinvesting the saved parameters as additional DiT depth recovers only marginally. This suggests the auxiliary branches may act as training-time architectural anchors whose contribution goes beyond their explicit conditioning content. We validate the same model through comparisons with external instrumental baselines and through our submission to the ICME 2026 Academic Text-to-Music (ATTM) Grand Challenge, where our Performance submission ranked first under both the objective metrics and the subsequent organizer-administered MOS over 35 raters, attaining the highest overall MOS across all challenge submissions, while our Efficiency submission was a finalist that tied for second under the objective metrics.

Junyoung Koh, Jaeyun Lee, Soo Yong Kim et al.

Recent work on music question answering (Music-QA) has primarily focused on single-track understanding, where models answer questions about an individual audio clip using its tags, captions, or metadata. However, listeners often describe music in comparative terms, and existing benchmarks do not systematically evaluate reasoning across multiple tracks. Building on the Jamendo-QA dataset, we introduce Jamendo-MT-QA, a dataset and benchmark for multi-track comparative question answering. From Creative Commons-licensed tracks on Jamendo, we construct 36,519 comparative QA items over 12,173 track pairs, with each pair yielding three question types: yes/no, short-answer, and sentence-level questions. We describe an LLM-assisted pipeline for generating and filtering comparative questions, and benchmark representative audio-language models using both automatic metrics and LLM-as-a-Judge evaluation.

Junyoung Koh, Hoyeon Moon, Dongha Kim et al.

Text-to-image models such as Stable Diffusion have achieved unprecedented levels of high-fidelity visual synthesis. As these models advance, personalization of generative models -- commonly facilitated through Low-Rank Adaptation (LoRA) with a dedicated trigger token -- has become a significant area of research. Previous works have naively assumed that fine-tuning with a single trigger token to represent new concepts. However, this often results in poor controllability, where the trigger token alone fails to reliably evoke the intended concept. We attribute this issue to the frequent co-occurrence of the trigger token with the surrounding context during fine-tuning, which entangles their representations and compromises the token's semantic distinctiveness. To disentangle this, we propose Frequency-Aware Dropout (FAD) -- a novel regularization technique that improves prompt controllability without adding new parameters. FAD consists of two key components: co-occurrence analysis and curriculum-inspired scheduling. Qualitative and quantitative analyses across token-based diffusion models (SD~1.5 and SDXL) and natural language--driven backbones (FLUX and Qwen-Image) demonstrate consistent gains in prompt fidelity, stylistic precision, and user-perceived quality. Our method provides a simple yet effective dropout strategy that enhances controllability and personalization in text-to-image generation. Notably, it achieves these improvements without introducing additional parameters or architectural modifications, making it readily applicable to existing models with minimal computational overhead.

Seungmin Lee, Dongha Kim, Yuni Jeon et al.

Existing automatic scientific question generation studies mainly focus on single-document factoid QA, overlooking the inter-document reasoning crucial for scientific understanding. We present AIM-SciQA, an automated framework for generating multi-document, multi-hop scientific QA datasets. AIM-SciQA extracts single-hop QAs using large language models (LLMs) with machine reading comprehension and constructs cross-document relations based on embedding-based semantic alignment while selectively leveraging citation information. Applied to 8,211 PubMed Central papers, it produced 411,409 single-hop and 13,672 multi-hop QAs, forming the IM-SciQA dataset. Human and automatic validation confirmed high factual consistency, and experimental results demonstrate that IM-SciQA effectively differentiates reasoning capabilities across retrieval and QA stages, providing a realistic and interpretable benchmark for retrieval-augmented scientific reasoning. We further extend this framework to construct CIM-SciQA, a citation-guided variant achieving comparable performance to the Oracle setting, reinforcing the dataset's validity and generality.