Masked diffusion models (MDMs) offer a promising non-autoregressive alternative for large language modeling.Standard decoding methods for MDMs, such as confidence-based sampling, select tokens independently based on individual token confidences at each diffusion step.However, we observe that this independent token selection often results in generation orders resembling sequential autoregressive processes, limiting the advantages of non-autoregressive modeling.To mitigate this pheonomenon, we propose Reward-Weighted Sampling (RWS), a novel decoding strategy that leverages an external reward model to provide a principled global signal during the iterative diffusion process.Specifically, at each diffusion step, RWS evaluates the quality of the entire intermediate sequence and scales token logits accordingly, guiding token selection by integrating global sequence-level coherence.This method selectively increases the confidence of tokens that initially have lower scores, thereby promoting a more non-autoregressive generation order.Furthermore, we provide theoretical justification showing that rewardweighted logit scaling induces beneficial rank reversals in token selection and consistently improves expected reward.Experiments demonstrate that RWS significantly promotes nonautoregressive generation orders, leading to improvements across multiple evaluation metrics.These results highlight the effectiveness of integrating global signals in enhancing both the non-autoregressive properties and overall performance of MDMs.

Recent efforts to apply Large Language Models (LLMs) to time-series anomaly detection (TSAD) have yielded limited success, often performing worse than even simple methods. While prior work has focused solely on downstream performance evaluation, the fundamental question—why do LLMs struggle with TSAD?—has remained largely unexplored. In this paper, we present an in-depth analysis that identifies two core challenges in understanding complex temporal dynamics and accurately localizing anomalies. To address these challenges, we propose a simple yet effective method that combines statistical decomposition with index-aware prompting. Our method outperforms 21 existing prompting strategies on the AnomLLM benchmark, achieving up to a 66.6\% improvement in F1 score. We further compare LLMs with 16 non-LLM baselines on the TSB-AD benchmark, highlighting scenarios where LLMs offer unique advantages via contextual reasoning. Our findings provide empirical insights into how and when LLMs can be effective for TSAD. The code is publicly available at: https://github.com/junwoopark92/LLM-TSAD

Long-term forecasting presents unique challenges due to the time and memory complexity of handling long sequences. Existing methods, which rely on sliding windows to process long sequences, struggle to effectively capture long-term variations that are partially caught within the short window (i.e., outer-window variations). In this paper, we introduce a novel approach that overcomes this limitation by employing contrastive learning and enhanced decomposition architecture, specifically designed to focus on long-term variations. To this end, our contrastive loss incorporates global autocorrelation held in the whole time series, which facilitates the construction of positive and negative pairs in a self-supervised manner. When combined with our decomposition networks, our constrative learning significantly improves long-term forecasting performance. Extensive experiments demonstrate that our approach outperforms 14 baseline models on well-established nine long-term benchmarks, especially in challenging scenarios that require a significantly long output for forecasting. This paper not only presents a novel direction for long-term forecasting but also offers a more reliable method for effectively integrating long-term variations into time-series representation learning.

In Reinforcement Learning (RL), enhancing sample efficiency is crucial, particularly in scenarios when data acquisition is costly and risky. In principle, off-policy RL algorithms can improve sample efficiency by allowing multiple updates per environment interaction. However, these multiple updates often lead the model to overfit to earlier interactions, which is referred to as the loss of plasticity. Our study investigates the underlying causes of this phenomenon by dividing plasticity into two aspects. Input plasticity, which denotes the model's adaptability to changing input data, and label plasticity, which denotes the model's adaptability to evolving input-output relationships. Synthetic experiments on the CIFAR-10 dataset reveal that finding smoother minima of loss landscape enhances input plasticity, whereas refined gradient propagation improves label plasticity. Leveraging these findings, we introduce the **PLASTIC** algorithm, which harmoniously combines techniques to address both concerns. With minimal architectural modifications, PLASTIC achieves competitive performance on benchmarks including Atari-100k and Deepmind Control Suite. This result emphasizes the importance of preserving the model's plasticity to elevate the sample efficiency in RL. The code is available at https://github.com/dojeon-ai/plastic.

Identifying unexpected objects on roads in semantic segmentation (e.g., identifying dogs on roads) is crucial in safetycritical applications. Existing approaches use images of unexpected objects from external datasets or require additional training (e.g., retraining segmentation networks or training an extra network), which necessitate a non-trivial amount of labor intensity or lengthy inference time. One possible alternative is to use prediction scores of a pretrained network such as the max logits (i.e., maximum values among classes before the final softmax layer) for detecting such objects. However, the distribution of max logits of each predicted class is significantly different from each other, which degrades the performance of identifying unexpected objects in urban-scene segmentation. To address this issue, we propose a simple yet effective approach that standardizes the max logits in order to align the different distributions and reflect the relative meanings of max logits within each predicted class. Moreover, we consider the local regions from two different perspectives based on the intuition that neighboring pixels share similar semantic information. In contrast to previous approaches, our method does not utilize any external datasets or require additional training, which makes our method widely applicable to existing pretrained segmentation models. Such a straightforward approach achieves a new state-of-the-art performance on the publicly available Fishyscapes Lost & Found leader-board with a large margin. Our code is publicly available at this link1.