arXiv:2603.10031v1 Announce Type: new Abstract: We present a cross-architecture evaluation of production LLM inference on AMD Instinct MI325X GPUs, benchmarking four models spanning 235B to 1 trillion parameters across three architectural families (MoE+MLA, Dense+GQA, MoE+GQA) on an 8-GPU cluster with 2TB aggregate HBM3e using vLLM v0.14.1. Our results demonstrate that architecture-aware optimization is essential: MLA models require block size 1 and cannot use KV cache offloading, while GQA models benefit from both. The AMD AITER runtime is required […]

Ver mais

arXiv:2604.04588v1 Announce Type: new Abstract: Pairwise comparisons are widely used in decision analysis, preference modeling, and evaluation problems. In many practical situations, the observed comparison matrix is not reciprocal. This lack of reciprocity is often treated as a defect to be corrected immediately. In this article, we adopt a different point of view: part of the nonreciprocity may reflect a genuine variation in the evaluation scale, while another part is due to random perturbations. We introduce an additive […]

Ver mais

Effervescent tablets are highly hygroscopic solid dosage forms in which even minor surface defects can compromise product stability, dose uniformity, and patient safety. Reliable, high-throughput defect detection is therefore essential, yet the existing literature overwhelmingly focuses on compressed or film-coated tablets and rarely offers a systematic comparison across recent YOLO families and scales. This study presents a multi-scale performance benchmarking of three recent YOLO families—YOLO11, YOLO12, and YOLO26—on a newly constructed effervescent tablet defect dataset. The dataset comprises […]

Ver mais

Alzheimer’s disease (AD), defined as an abnormal buildup of amyloid plaques and tau tangles in the brain can be diagnosed with high accuracy based on protein biomarkers via PET or CSF analysis. However, due to the invasive nature of biomarker collection, most AD diagnoses are made in memory clinics using cognitive tests and evaluation of hippocampal atrophy based on MRI. While clinical assessment and hippocampal volume show high diagnostic accuracy for amnestic or typical AD (tAD), a substantial […]

Ver mais

if you’ve ever built an elegant, complex ML pipeline to solve something a 10-line prompt could’ve handled… this is for you. i’ve been thinking about what separates people who do useful research from people who do impressive-looking research. it’s almost always the problems you choose rather than raw technical skill. here’s the mental model i’ve landed on. every problem kind of follows these steps: find a clear problem people actually care about try the dumbest solution first. can […]

Ver mais

Adapter-based methods have become a cost-effective approach to continual learning (CL) for Large Language Models (LLMs), by sequentially learning a low-rank update matrix for each task. To mitigate catastrophic forgetting, state-of-the-art approaches impose constraints on new adapters with respect to the previous ones, by targeting either subspace or coordinate-wise interference. In this paper, we propose JumpLoRA, a novel framework to adaptively induce sparsity in the Low-Rank Adaptation (LoRA) blocks through the use of JumpReLU gating. The method achieves […]

Ver mais

arXiv:2602.15897v1 Announce Type: new Abstract: Training and fine-tuning large-scale language models largely benefit from collaborative learning, but the approach has been proven vulnerable to gradient inversion attacks (GIAs), which allow adversaries to reconstruct private training data from shared gradients. Existing defenses mainly employ gradient perturbation techniques, e.g., noise injection or gradient pruning, to disrupt GIAs’ direct mapping from gradient space to token space. However, these methods often fall short due to the retention of semantics similarity across gradient, […]

Ver mais

I watch a lot of nature documentaries. I’m not very choosy about the animals covered, whether whales, moles, lions, ants, chameleons, blowfish, or mosquitoes. I’m even fascinated by footage of bacteria under a microscope. I’m usually immersed as I sit in front of my large-screen television, so long as I learn something about the intricacies of the species filmed in vibrant colors. What do they eat and how do they avoid being eaten? What are their life expectancies, […]

Ver mais

arXiv:2604.06231v1 Announce Type: new Abstract: Database systems incorporate an ever-growing number of functions in their kernels (a.k.a., database native functions) for scenarios like new application support and business migration. This growth causes an urgent demand for automatic database native function synthesis. While recent advances in LLM-based code generation (e.g., Claude Code) show promise, they are too generic for database-specific development. They often hallucinate or overlook critical context because database function synthesis is inherently complex and error-prone, where synthesizing […]

Ver mais

Batman made his first appearance in 1939. When you have a character who has been around for 80 years, they’re bound to change their appearance from time to time. So, it only makes sense for video games like Batman: Arkham Knight to take advantage of this and add different alternative costumes that players can pick and choose from. Some of these were hits, some of these were misses, and some were just okay. Let’s take a look at […]

Ver mais