Diffusion Language Models (DLMs) have emerged as a promising alternative to Autoregressive Language Models, yet their inference strategies largely rely on prefix-based prompting inherited from the autoregressive paradigm.In this paper, we propose Template Infilling (TI), a conditioning methodology tailored for DLMs.Unlike conventional prefix prompting, TI distributes structural anchors across the target response, establishing a global template before infilling masked segments.This enables structured conditioning that leverages the bidirectional generation process of DLMs.We evaluate TI on diverse benchmarks, including mathematical reasoning, code generation, and trip planning, achieving consistent improvements of 9.40%p over baseline prompting strategies.Furthermore, TI naturally supports multi-token generation settings, providing practical speed advantages while maintaining generation quality and robustness.Overall, our results highlight a DLM-specific conditioning paradigm for structured generation, suggesting a promising direction for inference methods tailored to diffusion-based language models.

ABSTRACT Recent advancements in text‐to‐image (T2I) models have enabled the synthesis of personalized images that align closely with user‐specified prompts, especially through the use of modifiers. However, generating multiple detailed objects with distinct modifiers in a single image remains challenging due to concept‐mixing, resulting from the difficulty of capturing interactions among text tokens. This paper proposes a modifier‐based approach to mitigate concept‐mixing by addressing the interaction among text tokens. Our method enables practical multi‐personalization while preserving the original T2I model's straightforward inference pipeline. Without structural guidance, it ensures seamless object interaction with enhanced consistency. Through a loss‐based finetuning approach, our method is adaptable to various concept‐learning algorithms, enabling plug‐and‐play functionality. Through both qualitative and quantitative evaluations, we demonstrate that our method effectively resolves concept‐mixing issues to better preserve concepts' identities and outperforms recent baselines in both quantitative and qualitative results. Our code will be publicly available.

Audio-Visual Localization (AVL) aims to identify sound-emitting sources within a visual scene. However, existing studies focus on image-level audio-visual associations, failing to capture temporal dynamics. Moreover, they assume simplified scenarios where sound sources are always visible and involve only a single object. To address these limitations, we propose AVATAR, a video-centric AVL benchmark that incorporates high-resolution temporal information. AVATAR introduces four distinct scenarios -- Single-sound, Mixed-sound, Multi-entity, and Off-screen -- enabling a more comprehensive evaluation of AVL models. Additionally, we present TAVLO, a novel video-centric AVL model that explicitly integrates temporal information. Experimental results show that conventional methods struggle to track temporal variations due to their reliance on global audio features and frame-level mappings. In contrast, TAVLO achieves robust and precise audio-visual alignment by leveraging high-resolution temporal modeling. Our work empirically demonstrates the importance of temporal dynamics in AVL and establishes a new standard for video-centric audio-visual localization.

Although meta-learning seems promising performance in the realm of rapid adaptability, it is constrained by fixed cardinality. When faced with tasks of varying cardinalities that were unseen during training, the model lacks its ability. In this paper, we address and resolve this challenge by harnessing `label equivalence' emerged from stochastic numeric label assignments during episodic task sampling. Questioning what defines ``true" meta-learning, we introduce the ``any-way" learning paradigm, an innovative model training approach that liberates model from fixed cardinality constraints. Surprisingly, this model not only matches but often outperforms traditional fixed-way models in terms of performance, convergence speed, and stability. This disrupts established notions about domain generalization. Furthermore, we argue that the inherent label equivalence naturally lacks semantic information. To bridge this semantic information gap arising from label equivalence, we further propose a mechanism for infusing semantic class information into the model. This would enhance the model's comprehension and functionality. Experiments conducted on renowned architectures like MAML and ProtoNet affirm the effectiveness of our method.

In this paper, we hypothesize that gradient-based meta-learning (GBML) implicitly suppresses the Hessian along the optimization trajectory in the inner loop. Based on this hypothesis, we introduce an algorithm called SHOT (Suppressing the Hessian along the Optimization Trajectory) that minimizes the distance between the parameters of the target and reference models to suppress the Hessian in the inner loop. Despite dealing with high-order terms, SHOT does not increase the computational complexity of the baseline model much. It is agnostic to both the algorithm and architecture used in GBML, making it highly versatile and applicable to any GBML baseline. To validate the effectiveness of SHOT, we conduct empirical tests on standard few-shot learning tasks and qualitatively analyze its dynamics. We confirm our hypothesis empirically and demonstrate that SHOT outperforms the corresponding baseline.