This work investigates distillation methods for large language models (LLMs) with the goal of developing compact models that preserve high performance. Several existing approaches are reviewed, with a discussion of their respective strengths and limitations. An improved method based on the ShortGPT approach has been developed, building upon the idea of incorporating iterative evaluation of layer importance. At each step, importance is assessed by measuring performance degradation when individual layers are removed, using a set of representative datasets. This process is combined with further training using a joint loss function based on KL divergence and mean squared error. Experiments on the Qwen2.5-3B model show that the number of layers can be reduced from 36 to 28 (resulting in a 2.47 billion parameter model) with only a 9.7% quality loss, and to 24 layers with an 18% loss. The findings suggest that the middle transformer layers contribute less to inference, underscoring the potential of the proposed method for creating efficient models. The results demonstrate the effectiveness of iterative distillation and fine-tuning, making the approach suitable for deployment in resource-limited settings.

We address claim normalization for multilingual misinformation detection - transforming noisy social media posts into clear, verifiable statements across 20 languages. The key contribution demonstrates how systematic decomposition of posts using Who, What, Where, When, Why and How questions enables robust cross-lingual transfer despite training exclusively on English data. Our methodology incorporates finetuning Qwen3-14B using LoRA with the provided dataset after intra-post deduplication, token-level recall filtering for semantic alignment and retrieval-augmented few-shot learning with contextual examples during inference. Our system achieves METEOR scores ranging from 41.16 (English) to 15.21 (Marathi), securing third rank on the English leaderboard and fourth rank for Dutch and Punjabi. The approach shows 41.3% relative improvement in METEOR over baseline configurations and substantial gains over existing methods. Results demonstrate effective cross-lingual generalization for Romance and Germanic languages while maintaining semantic coherence across diverse linguistic structures.

Understanding intrinsic differences between adversarial examples and clean samples is key to enhancing DNN robustness and detection against adversarial attacks. This study first empirically finds that image-based adversarial examples are notably sensitive to occlusion. Controlled experiments on CIFAR-10 used nine canonical attacks (e.g., FGSM, PGD) to generate adversarial examples, paired with original samples for evaluation. We introduce Sliding Mask Confidence Entropy (SMCE) to quantify model confidence fluctuation under occlusion. Using 1800+ test images, SMCE calculations supported by Mask Entropy Field Maps and statistical distributions show adversarial examples have significantly higher confidence volatility under occlusion than originals. Based on this, we propose Sliding Window Mask-based Adversarial Example Detection (SWM-AED), which avoids catastrophic overfitting of conventional adversarial training. Evaluations across classifiers and attacks on CIFAR-10 demonstrate robust performance, with accuracy over 62% in most cases and up to 96.5%.

Machine learning based on neural networks has advanced rapidly, but the high energy consumption required for training and inference remains a major challenge. Hyperdimensional Computing (HDC) offers a lightweight, brain-inspired alternative that enables high parallelism but often suffers from lower accuracy on complex visual tasks. To overcome this, hybrid accelerators combining HDC and Convolutional Neural Networks (CNNs) have been proposed, though their adoption is limited by poor generalizability and programmability. The rise of open-source RISC-V architectures has created new opportunities for domain-specific GPU design. Unlike traditional proprietary GPUs, emerging RISC-V-based GPUs provide flexible, programmable platforms suitable for custom computation models such as HDC. In this study, we design and implement custom GPU instructions optimized for HDC operations, enabling efficient processing for hybrid HDC-CNN workloads. Experimental results using four types of custom HDC instructions show a performance improvement of up to 56.2 times in microbenchmark tests, demonstrating the potential of RISC-V GPUs for energy-efficient, high-performance computing.

Abstract--Radar systems are increasingly favored for medical applications because they provide non-intrusive monitoring with high privacy and robustness to lighting conditions. However, existing research typically relies on single-domain radar signals and overlooks the temporal dependencies inherent in human activity, which complicates the classification of similar actions. PECL combines a channel-spatial attention module and temporal units to capture more features and dynamic dependencies during action sequences, improving both accuracy and robustness. The experimental results show that PECL achieves an accuracy of 96.16% on the same dataset, outperforming existing methods by at least 4.78%. PECL also performs best in distinguishing between easily confused actions. Despite its strong performance, PECL maintains moderate model complexity, with 23.42M parameters and 1324.82M Its parameter-efficient design further reduces computational cost. Human activity recognition (HAR) has long been an active research area. With the acceleration of population aging, demand for HAR technology is growing in both hospitals and households [1][2][3].

Whole Slide Image (WSI) representation is critical for cancer subtyping, cancer recognition and mutation prediction.Training an end-to-end WSI representation model poses significant challenges, as a standard gigapixel slide can contain tens of thousands of image tiles, making it difficult to compute gradients of all tiles in a single mini-batch due to current GPU limitations. To address this challenge, we propose a method of dynamic residual encoding with slide-level contrastive learning (DRE-SLCL) for end-to-end WSI representation. Our approach utilizes a memory bank to store the features of tiles across all WSIs in the dataset. During training, a mini-batch usually contains multiple WSIs. For each WSI in the batch, a subset of tiles is randomly sampled and their features are computed using a tile encoder. Then, additional tile features from the same WSI are selected from the memory bank. The representation of each individual WSI is generated using a residual encoding technique that incorporates both the sampled features and those retrieved from the memory bank. Finally, the slide-level contrastive loss is computed based on the representations and histopathology reports ofthe WSIs within the mini-batch. Experiments conducted over cancer subtyping, cancer recognition, and mutation prediction tasks proved the effectiveness of the proposed DRE-SLCL method.

Epically Powerful is an open-source robotics infrastructure that streamlines the underlying framework of wearable robotic systems - managing communication protocols, clocking, actuator commands, visualization, sensor data acquisition, data logging, and more - while also providing comprehensive guides for hardware selection, system assembly, and controller implementation. Epically Powerful contains a code base enabling simplified user implementation via Python that seamlessly interfaces with various commercial state-of-the-art quasi-direct drive (QDD) actuators, single-board computers, and common sensors, provides example controllers, and enables real-time visualization. To further support device development, the package also includes a recommended parts list and compatibility guide and detailed documentation on hardware and software implementation. The goal of Epically Powerful is to lower the barrier to developing and deploying custom wearable robotic systems without a pre-specified form factor, enabling researchers to go from raw hardware to modular, robust devices quickly and effectively. Though originally designed with wearable robotics in mind, Epically Powerful is broadly applicable to other robotic domains that utilize QDD actuators, single-board computers, and sensors for closed-loop control.

The proliferation of assistive chatbots offering efficient, personalized communication has driven widespread over-reliance on them for decision-making, information-seeking and everyday tasks. This dependence was found to have adverse consequences on information retention as well as lead to superficial emotional attachment. As such, this work introduces 8bit-GPT; a language model simulated on a legacy Macintosh Operating System, to evoke reflection on the nature of Human-AI interaction and the consequences of anthropomorphic rhetoric. Drawing on reflective design principles such as slow-technology and counterfunctionality, this work aims to foreground the presence of chatbots as a tool by defamiliarizing the interface and prioritizing inefficient interaction, creating a friction between the familiar and not.

Large language models (LLMs) are typically aligned to a universal set of safety and usage principles intended for broad public acceptability. Yet, real-world applications of LLMs often take place within organizational ecosystems shaped by distinctive corporate policies, regulatory requirements, use cases, brand guidelines, and ethical commitments. This reality highlights the need for rigorous and comprehensive evaluation of LLMs with pluralistic alignment goals, an alignment paradigm that emphasizes adaptability to diverse user values and needs. In this work, we present PLURALISTIC BEHAVIOR SUITE (PBSUITE), a dynamic evaluation suite designed to systematically assess LLMs' capacity to adhere to pluralistic alignment specifications in multi-turn, interactive conversations. PBSUITE consists of (1) a diverse dataset of 300 realistic LLM behavioral policies, grounded in 30 industries; and (2) a dynamic evaluation framework for stress-testing model compliance with custom behavioral specifications under adversarial conditions. Using PBSUITE, We find that leading open- and closed-source LLMs maintain robust adherence to behavioral policies in single-turn settings (less than 4% failure rates), but their compliance weakens substantially in multi-turn adversarial interactions (up to 84% failure rates). These findings highlight that existing model alignment and safety moderation methods fall short in coherently enforcing pluralistic behavioral policies in real-world LLM interactions. Our work contributes both the dataset and analytical framework to support future research toward robust and context-aware pluralistic alignment techniques.

As financial applications of large language models (LLMs) gain attention, accurate Information Retrieval (IR) remains crucial for reliable AI services. However, existing benchmarks fail to capture the complex and domain-specific information needs of real-world banking scenarios. Building domain-specific IR benchmarks is costly and constrained by legal restrictions on using real customer data. To address these challenges, we propose a systematic methodology for constructing domain-specific IR benchmarks through LLM-based query generation. As a concrete implementation of this methodology, our pipeline combines single and multi-document query generation with an enhanced and reasoning-augmented answerability assessment method, achieving stronger alignment with human judgments than prior approaches. Using this methodology, we construct KoBankIR, comprising 815 queries derived from 204 official banking documents. Our experiments show that existing retrieval models struggle with the complex multi-document queries in KoBankIR, demonstrating the value of our systematic approach for domain-specific benchmark construction and underscoring the need for improved retrieval techniques in financial domains.