These female athletes need to speak up about keeping women's sports for women, like Sophie Cunningham did Jacksonville Jaguars set at 8.5 win total after surprising 13-4 season and Wild Card loss to Buffalo Riley Gaines calls USA Today reporter'insane' for invoking Emmett Till in column about Caitlin Clark WNBA All-Star Game betting preview: Team Coop's guards could give them the edge over Team Spoon Tony Romo's brutal golf score before getting arrested paints a nightmarish picture Dolphins cheerleaders reveal new uniforms as rivalry with Cowboys ramps up, Romo DUI memes & Vrabel's puppy Caitlin Clark calls out media's'false characterization' of her amid weeks of controversy Dan Le Batard claims ESPN is run by McAfee and'White people' after layoffs, slanders OutKick in unhinged rant One restaurant chain's special promo may not have been a great idea during Red Sox winning streak Convention or coronation?: Maine Democrats pick Platner replacement Department of War's proposed protocol fuels testosterone debate Convention or coronation?: Maine Democrats pick Platner replacement US intelligence says Iran's new leader more open to nukes than predecessor US intelligence says Iran's new leader more open to nukes than predecessor OutKick Sports Miami Marlins' collapse back to mediocrity is so predictable you could set your watch to it President Donald Trump could not help but poke fun at the New York Mets for losing all the time despite their sky-high payroll this season. I want to take you on a journey back to July 9 in Major League Baseball . The Miami Marlins are ten games above .500 Their pitching looks dominant, they are getting timely hits with great baserunning, and their version of home cooking at loanDepot Park is setting all sorts of team records. It seems like nothing can slow down this freight train from South Florida.

Multi-agent reinforcement learning is a key method for training multi-robot systems over a series of episodes in which robots are rewarded or punished according to their performance; only once the system is trained to a suitable standard is it deployed in the real world. If the system is not trained enough, the task will likely not be completed and could pose a risk to the surrounding environment. Therefore, reaching high performance in a shorter training period can lead to significant reductions in time and resource consumption. We introduce Multi-Agent Reinforcement Learning guided by Language-based Inter-Robot Negotiation (MARLIN), which makes the training process both faster and more transparent. We equip robots with large language models that negotiate and debate the task, producing a plan that is used to guide the policy during training. We dynamically switch between using reinforcement learning and the negotiation-based approach throughout training. This offers an increase in training speed when compared to standard multi-agent reinforcement learning and allows the system to be deployed to physical hardware earlier. As robots negotiate in natural language, we can better understand the behaviour of the robots individually and as a collective. We compare the performance of our approach to multi-agent reinforcement learning and a large language model to show that our hybrid method trains faster at little cost to performance.

As inference on Large Language Models (LLMs) emerges as an important workload in machine learning applications, weight quantization has become a standard technique for efficient GPU deployment. Quantization not only reduces model size, but has also been shown to yield substantial speedups for single-user inference, due to reduced memory movement, with low accuracy impact. Yet, it remains open whether speedups are achievable also in \emph{batched} settings with multiple parallel clients, which are highly relevant for practical serving. It is unclear whether GPU kernels can be designed to remain practically memory-bound, while supporting the substantially increased compute requirements of batched workloads. This paper resolves this question positively by describing the design of Mixed-precision Auto-Regressive LINear kernels, called MARLIN. Concretely, given a model whose weights are compressed via quantization to, e.g., 4 bits per element, MARLIN shows that batchsizes up to 16-32 can be supported with close to maximum ($4\times$) quantization speedup, and larger batchsizes up to 64-128 with gradually decreasing, but still significant, acceleration. MARLIN accomplishes this via a combination of techniques, such as asynchronous memory access, complex task scheduling and pipelining, and bespoke quantization support. Our experiments show that MARLIN's near-optimal performance on individual LLM layers across different scenarios can also lead to end-to-end LLM inference speedups (of up to $2.8\times$) when integrated with the popular vLLM serving engine. Finally, MARLIN is extensible to further compression techniques, like NVIDIA 2:4 sparsity, leading to additional speedups.

In this paper, we present the service robot MARLIN and its integration with the K4R platform, a cloud system for complex AI applications in retail. At its core, this platform contains so-called semantic digital twins, a semantically annotated representation of the retail store. MARLIN continuously exchanges data with the K4R platform, improving the robot's capabilities in perception, autonomous navigation, and task planning. We exploit these capabilities in a retail intralogistics scenario, specifically by assisting store employees in stocking shelves. We demonstrate that MARLIN is able to update the digital representation of the retail store by detecting and classifying obstacles, autonomously planning and executing replenishment missions, adapting to unforeseen changes in the environment, and interacting with store employees. Experiments are conducted in simulation, in a laboratory environment, and in a real store. We also describe and evaluate a novel algorithm for autonomous navigation of articulated tractor-trailer systems. The algorithm outperforms the manufacturer's proprietary navigation approach and improves MARLIN's navigation capabilities in confined spaces.

Quantization is a proven effective method for compressing large language models. Although popular techniques like W8A8 and W4A16 effectively maintain model performance, they often fail to concurrently speed up the prefill and decoding stages of inference. W4A8 is a promising strategy to accelerate both of them while usually leads to a significant performance degradation. To address these issues, we present QQQ, a Quality Quattuor-bit Quantization method with 4-bit weights and 8-bit activations. QQQ employs adaptive smoothing and Hessian-based compensation, significantly enhancing the performance of quantized models without extensive training. Furthermore, we meticulously engineer W4A8 GEMM kernels to increase inference speed. Our specialized per-channel W4A8 GEMM and per-group W4A8 GEMM achieve impressive speed increases of 3.67$\times$ and 3.29 $\times$ over FP16 GEMM. Our extensive experiments show that QQQ achieves performance on par with existing state-of-the-art LLM quantization methods while significantly accelerating inference, achieving speed boosts up to 2.24 $\times$, 2.10$\times$, and 1.25$\times$ compared to FP16, W8A8, and W4A16, respectively.

Irregular multivariate time series data is characterized by varying time intervals between consecutive observations of measured variables/signals (i.e., features) and varying sampling rates (i.e., recordings/measurement) across these features. Modeling time series while taking into account these irregularities is still a challenging task for machine learning methods. Here, we introduce TADA, a Two-stageAggregation process with Dynamic local Attention to harmonize time-wise and feature-wise irregularities in multivariate time series. In the first stage, the irregular time series undergoes temporal embedding (TE) using all available features at each time step. This process preserves the contribution of each available feature and generates a fixed-dimensional representation per time step. The second stage introduces a dynamic local attention (DLA) mechanism with adaptive window sizes. DLA aggregates time recordings using feature-specific windows to harmonize irregular time intervals capturing feature-specific sampling rates. Then hierarchical MLP mixer layers process the output of DLA through multiscale patching to leverage information at various scales for the downstream tasks. TADA outperforms state-of-the-art methods on three real-world datasets, including the latest MIMIC IV dataset, and highlights its effectiveness in handling irregular multivariate time series and its potential for various real-world applications.

Irregularly-sampled time series (ITS) are native to high-impact domains like healthcare, where measurements are collected over time at uneven intervals. However, for many classification problems, only small portions of long time series are often relevant to the class label. In this case, existing ITS models often fail to classify long series since they rely on careful imputation, which easily over- or under-samples the relevant regions. Using this insight, we then propose CAT, a model that classifies multivariate ITS by explicitly seeking highly-relevant portions of an input series' timeline. CAT achieves this by integrating three components: (1) A Moment Network learns to seek relevant moments in an ITS's continuous timeline using reinforcement learning. (2) A Receptor Network models the temporal dynamics of both observations and their timing localized around predicted moments. (3) A recurrent Transition Model models the sequence of transitions between these moments, cultivating a representation with which the series is classified. Using synthetic and real data, we find that CAT outperforms ten state-of-the-art methods by finding short signals in long irregular time series.

Fast and efficient transport protocols are the foundation of an increasingly distributed world. The burden of continuously delivering improved communication performance to support next-generation applications and services, combined with the increasing heterogeneity of systems and network technologies, has promoted the design of Congestion Control (CC) algorithms that perform well under specific environments. The challenge of designing a generic CC algorithm that can adapt to a broad range of scenarios is still an open research question. To tackle this challenge, we propose to apply a novel Reinforcement Learning (RL) approach. Our solution, MARLIN, uses the Soft Actor-Critic algorithm to maximize both entropy and return and models the learning process as an infinite-horizon task. We trained MARLIN on a real network with varying background traffic patterns to overcome the sim-to-real mismatch that researchers have encountered when applying RL to CC. We evaluated our solution on the task of file transfer and compared it to TCP Cubic. While further research is required, results have shown that MARLIN can achieve comparable results to TCP with little hyperparameter tuning, in a task significantly different from its training setting. Therefore, we believe that our work represents a promising first step toward building CC algorithms based on the maximum entropy RL framework.

In many domains, including healthcare, biology, and climate science, time series are irregularly sampled with variable time between successive observations and different subsets of variables (sensors) are observed at different time points, even after alignment to start events. These data create multiple challenges for prevailing models that assume fully observed and fixed-length feature representations. To address these challenges, it is essential to understand the relationships between sensors and how they evolve over time. It considers both inter-sensor relationships shared across samples and those unique to each sample that can vary with time, and it adaptively estimates misaligned observations based on nearby observations. Multivariate time series are prevalent in a variety of domains including healthcare, space science, cybersecurity, biology, and finance (Ravuri et al., 2021; Sousa et al., 2020; Sezer et al., 2020; Fawaz et al., 2019; Abanda et al., 2019; Tang et al., 2018). Practical issues often exist in collecting sensor measurements that lead to various types of irregularities caused by missing observations, such as cost saving, sensor failures, external forces in physical scenarios, medical interventions, to name a few (Choi et al., 2020). While temporal machine learning models usually assume fully observable and fixed-size input data, irregularly sampled time series raise considerable challenges. For example, the observations of multiple sensors are not well-aligned; the time intervals among adjacent observations are different across sensors; and different samples have different numbers of observations for different subsets of sensors recorded at different time points.

Robots today generally come in one of two varieties: rigid and soft. When most people imagine a robot, they think of the rigid variety, like Boston Dynamics' Spot or those found on auto assembly lines. Soft robots, on the other hand, tend to mimic biological organisms enabling them to more easily adapt to their surrounding environment, work more safely in the presence of humans and now, with a novel robotic spine design developed by North Carolina State University, move faster than ever before. Cheetahs can average 58 mph while sprinting (though in 2012, an 11 year old cat at the Cincinnati Zoo set a record of 61mph while completing a 100 meter sprint in 5.95 seconds -- three seconds faster than Usain Bolt). This speed is due to their uniquely evolved, super flexible spines which allow them to dramatically arch their backs as they run, enabling the fast felines to take longer and faster strides than their preferred antelope prey.