Large Language Models (LLMs) have revolutionized a wide range of domains such as natural language processing, computer vision, and multi-modal tasks due to their ability to comprehend context and perform logical reasoning. However, the computational and memory demands of LLMs, particularly during inference, pose significant challenges when scaling them to real-world, long-context, and real-time applications. Key-Value (KV) cache management has emerged as a critical optimization technique for accelerating LLM inference by reducing redundant computations and improving memory utilization. This survey provides a comprehensive overview of KV cache management strategies for LLM acceleration, categorizing them into token-level, model-level, and system-level optimizations. Token-level strategies include KV cache selection, budget allocation, merging, quantization, and low-rank decomposition, while model-level optimizations focus on architectural innovations and attention mechanisms to enhance KV reuse. System-level approaches address memory management, scheduling, and hardware-aware designs to improve efficiency across diverse computing environments. Additionally, the survey provides an overview of both text and multimodal datasets and benchmarks used to evaluate these strategies. By presenting detailed taxonomies and comparative analyses, this work aims to offer useful insights for researchers and practitioners to support the development of efficient and scalable KV cache management techniques, contributing to the practical deployment of LLMs in real-world applications. The curated paper list for KV cache management is in: \href{https://github.com/TreeAI-Lab/Awesome-KV-Cache-Management}{https://github.com/TreeAI-Lab/Awesome-KV-Cache-Management}.

Augmented Reality assistance are increasingly popular for supporting users with tasks like assembly and cooking. However, current practice typically provide reactive responses initialized from user requests, lacking consideration of rich contextual and user-specific information. To address this limitation, we propose a novel AR assistance system, Satori, that models both user states and environmental contexts to deliver proactive guidance. Our system combines the Belief-Desire-Intention (BDI) model with a state-of-the-art multi-modal large language model (LLM) to infer contextually appropriate guidance. The design is informed by two formative studies involving twelve experts. A sixteen within-subject study find that Satori achieves performance comparable to an designer-created Wizard-of-Oz (WoZ) system without relying on manual configurations or heuristics, thereby enhancing generalizability, reusability and opening up new possibilities for AR assistance.

We analyze the training of a two-layer autoencoder used to parameterize a flow-based generative model for sampling from a high-dimensional Gaussian mixture. Previous work shows that the phase where the relative probability between the modes is learned disappears as the dimension goes to infinity without an appropriate time schedule. We introduce a time dilation that solves this problem. This enables us to characterize the learned velocity field, finding a first phase where the probability of each mode is learned and a second phase where the variance of each mode is learned. We find that the autoencoder representing the velocity field learns to simplify by estimating only the parameters relevant to each phase. Turning to real data, we propose a method that, for a given feature, finds intervals of time where training improves accuracy the most on that feature. Since practitioners take a uniform distribution over training times, our method enables more efficient training. We provide preliminary experiments validating this approach.

Large language models are increasingly being integrated into applications that shape the production and discovery of societal knowledge such as search, online education, and travel planning. As a result, language models will shape how people learn about, perceive and interact with global cultures making it important to consider whose knowledge systems and perspectives are represented in models. Recognizing this importance, increasingly work in Machine Learning and NLP has focused on evaluating gaps in global cultural representational distribution within outputs. However, more work is needed on developing benchmarks for cross-cultural impacts of language models that stem from a nuanced sociologically-aware conceptualization of cultural impact or harm. We join this line of work arguing for the need of metricizable evaluations of language technologies that interrogate and account for historical power inequities and differential impacts of representation on global cultures, particularly for cultures already under-represented in the digital corpora. We look at two concepts of erasure: omission: where cultures are not represented at all and simplification i.e. when cultural complexity is erased by presenting one-dimensional views of a rich culture. The former focuses on whether something is represented, and the latter on how it is represented. We focus our analysis on two task contexts with the potential to influence global cultural production. First, we probe representations that a language model produces about different places around the world when asked to describe these contexts. Second, we analyze the cultures represented in the travel recommendations produced by a set of language model applications. Our study shows ways in which the NLP community and application developers can begin to operationalize complex socio-cultural considerations into standard evaluations and benchmarks.

So much of this year felt like a fever dream: The attempted assassination of Donald Trump. Which is why, this year, I'm leaning into my nerdish tendencies and rounding up some good, interesting, or inspiring news stories from the science world--promising discoveries, exciting new data, historic events, and unsung heroes. In the hope of providing relief from the hell that has been 2024, here's a non-comprehensive list of the year's coolest science stories, both big and small: Wildlife filmmaker Carlos Gauna and University of California, Riverside, PhD student Phillip Sternes spotted what appears to be a baby great white shark off the coast of California last year. In January, the team published the photos in the journal Environmental Biology of Fishes. "Where white sharks give birth is one of the holy grails of shark science. No one has ever been able to pinpoint where they are born, nor has anyone seen a newborn baby shark alive," Gauna said in a UC Riverside press release.

On New Year's Eve 25 years ago, sane people worried that the modern world was about to melt down. The millennium bug seemed to be threatening to crash the world's computer systems, as technology struggled to distinguish between the years 1900 and 2000. The public, faced with daily predictions of potentially terrible outcomes, braced themselves nervously. Dark jokes prevailed about avoiding being on "a life-support system at midnight on 31 December 1999". In China, Zhao Be, then the head of the country's millennium bug coordination efforts, commanded airline executives to be on a flight on 1 January 2000 to demonstrate any problems had been sorted.

This research employs Universal Differential Equations (UDEs) alongside differentiable physics to model viscoelastic fluids, merging conventional differential equations, neural networks and numerical methods to reconstruct missing terms in constitutive models. This study focuses on analyzing four viscoelastic models: Upper Convected Maxwell (UCM), Johnson-Segalman, Giesekus, and Exponential Phan-Thien-Tanner (ePTT), through the use of synthetic datasets. The methodology was tested across different experimental conditions, including oscillatory and startup flows. While the UDE framework effectively predicts shear and normal stresses for most models, it demonstrates some limitations when applied to the ePTT model. The findings underscore the potential of UDEs in fluid mechanics while identifying critical areas for methodological improvement. Also, a model distillation approach was employed to extract simplified models from complex ones, emphasizing the versatility and robustness of UDEs in rheological modeling.

Scoring the Optical Character Recognition (OCR) capabilities of Large Multimodal Models (LMMs) has witnessed growing interest recently. Existing benchmarks have highlighted the impressive performance of LMMs in text recognition; however, their abilities on certain challenging tasks, such as text localization, handwritten content extraction, and logical reasoning, remain underexplored. To bridge this gap, we introduce OCRBench v2, a large-scale bilingual text-centric benchmark with currently the most comprehensive set of tasks (4x more tasks than the previous multi-scene benchmark OCRBench), the widest coverage of scenarios (31 diverse scenarios including street scene, receipt, formula, diagram, and so on), and thorough evaluation metrics, with a total of 10,000 human-verified question-answering pairs and a high proportion of difficult samples. After carefully benchmarking state-of-the-art LMMs on OCRBench v2, we find that 20 out of 22 LMMs score below 50 (100 in total) and suffer from five-type limitations, including less frequently encountered text recognition, fine-grained perception, layout perception, complex element parsing, and logical reasoning. The benchmark and evaluation scripts are available at https://github.com/Yuliang-liu/MultimodalOCR.

Approaching Speech-to-Text and Automatic Speech Recognition problems in low-resource languages is notoriously challenging due to the scarcity of validated datasets and the diversity of dialects. Arabic, Russian, and Portuguese exemplify these difficulties, being low-resource languages due to the many dialects of these languages across different continents worldwide. Moreover, the variety of accents and pronunciations of such languages complicate ASR models' success. With the increasing popularity of Deep Learning and Transformers, acoustic models like the renowned Wav2Vec2 have achieved superior performance in the Speech Recognition field compared to state-of-the-art approaches. However, despite Wav2Vec2's improved efficiency over traditional methods, its performance significantly declines for under-represented languages, even though it requires significantly less labeled data. This paper introduces an end-to-end framework that enhances ASR systems fine-tuned on Wav2Vec2 through data augmentation techniques. To validate our framework's effectiveness, we conducted a detailed experimental evaluation using three datasets from Mozilla's Common Voice project in Arabic, Russian, and Portuguese. Additionally, the framework presented in this paper demonstrates robustness to different diacritics. Ultimately, our approach outperforms two previous baseline models, which are the pre-trained Wav2Vec2 and the well-known Whisper ASR model, resulting in an average relative improvement of 33.9\% in Word Error Rate and a 53.2\% relative improvement in Character Error Rate.

In differential equation discovery algorithms, a priori expert knowledge is mainly used implicitly to constrain the form of the expected equation, making it impossible for the algorithm to truly discover equations. Instead, most differential equation discovery algorithms try to recover the coefficients for a known structure. In this paper, we describe an algorithm that allows the discovery of unknown equations using automatically or manually extracted background knowledge. Instead of imposing rigid constraints, we modify the structure space so that certain terms are likely to appear within the crossover and mutation operators. In this way, we mimic expertly chosen terms while preserving the possibility of obtaining any equation form. The paper shows that the extraction and use of knowledge allows it to outperform the SINDy algorithm in terms of search stability and robustness. Synthetic examples are given for Burgers, wave, and Korteweg--De Vries equations.