Social media data has been of interest to Natural Language Processing (NLP) practitioners for over a decade, because of its richness in information, but also challenges for automatic processing. Since language use is more informal, spontaneous, and adheres to many different sociolects, the performance of NLP models often deteriorates. One solution to this problem is to transform data to a standard variant before processing it, which is also called lexical normalization. There has been a wide variety of benchmarks and models proposed for this task. The MultiLexNorm benchmark proposed to unify these efforts, but it consists almost solely of languages from the Indo-European language family in the Latin script. Hence, we propose an extension to MultiLexNorm, which covers five Asian languages from different language families in four different scripts. We show that the previous state-of-the-art model performs worse on the new languages and propose a new architecture based on Large Language Models (LLMs), which shows more robust performance. Finally, we analyze remaining errors, revealing future directions for this task.

3D point clouds are increasingly vital for applications like autonomous driving and robotics, yet the raw data captured by sensors often suffer from noise and sparsity, creating challenges for downstream tasks. Consequently, point cloud upsampling becomes essential for improving density and uniformity, with recent approaches showing promise by projecting randomly generated query points onto the underlying surface of sparse point clouds. However, these methods often result in outliers, non-uniformity, and difficulties in handling regions with high curvature and intricate structures. In this work, we address these challenges by introducing the Progressive Local Surface Estimator (PLSE), which more effectively captures local features in complex regions through a curvature-based sampling technique that selectively targets high-curvature areas. Additionally, we incorporate a curriculum learning strategy that leverages the curvature distribution within the point cloud to naturally assess the sample difficulty, enabling curriculum learning on point cloud data for the first time. The experimental results demonstrate that our approach significantly outperforms existing methods, achieving high-quality, dense point clouds with superior accuracy and detail.

As Large Language Models (LLMs) are increasingly deployed in sensitive domains such as enterprise and government, ensuring that they adhere to user-defined security policies within context is critical-especially with respect to information non-disclosure.While prior LLM studies have focused on general safety and socially sensitive data, large-scale benchmarks for contextual security preservation against attacks remain lacking.To address this, we introduce a novel large-scale benchmark dataset, CoPriva, evaluating LLM adherence to contextual non-disclosure policies in question answering.Derived from realistic contexts, our dataset includes explicit policies and queries designed as direct and challenging indirect attacks seeking prohibited information.We evaluate 10 LLMs on our benchmark and reveal a significant vulnerability: many models violate user-defined policies and leak sensitive information.This failure is particularly severe against indirect attacks, highlighting a critical gap in current LLM safety alignment for sensitive applications.Our analysis reveals that while models can often identify the correct answer to a query, they struggle to incorporate policy constraints during generation.In contrast, they exhibit a partial ability to revise outputs when explicitly prompted.Our findings underscore the urgent need for more robust methods to guarantee contextual security.1

Sarcasm is a way of verbal irony where someone says the opposite of what they mean, often to ridicule a person, situation, or idea. It is often difficult to detect sarcasm in the dialogue since detecting sarcasm should reflect the context (i.e., dialogue history). In this paper, we introduce a new dataset for the Korean dialogue sarcasm detection task, KoCoSa (Korean Context-aware Sarcasm Detection Dataset), which consists of 12.8K daily Korean dialogues and the labels for this task on the last response. To build the dataset, we propose an efficient sarcasm detection dataset generation pipeline: 1) generating new sarcastic dialogues from source dialogues with large language models, 2) automatic and manual filtering of abnormal and toxic dialogues, and 3) human annotation for the sarcasm detection task. We also provide a simple but effective baseline for the Korean sarcasm detection task trained on our dataset. Experimental results on the dataset show that our baseline system outperforms strong baselines like large language models, such as GPT-3.5, in the Korean sarcasm detection task. We show that the sarcasm detection task relies deeply on the existence of sufficient context. We will release the dataset at https://github.com/Yu-billie/KoCoSa_sarcasm_detection.

In this paper, we propose OBFUS, a web-based tool that can easily apply obfuscation techniques to high-level and low-level programming languages. OBFUS's high-level obfuscator parses and obfuscates the source code, overlaying the obfuscation to produce more complex results. OBFUS's low-level obfuscator decompiles binary programs into LLVM IR. This LLVM IR pro-gram is obfuscated and the LLVM IR program is recompiled to become an obfuscated binary program.

We propose an energy-efficient analog implementation of binarized neural network with a novel technique called VCAM, variation compensation through activation matching. The architecture consists of 1T1R ReRAM arrays and differential amplifiers for implementing synapses and neurons, respectively. To restore classification test accuracy degraded by process variation, we adjust the biases of the neurons to match their average output activations with those of ideal neurons. Experimental results show that the proposed approach recovers the accuracy to 98.55% on MNIST and 89.63% on CIFAR-10 even in the presence of 50% threshold voltage and 15% resistance variations at 3-sigma point. This result corresponds to the accuracy degradation of only 0.05% and 1.35%, respectively, compared to the ideal case.