While colonization has sociohistorically impacted people's identities across various dimensions, those colonial values and biases continue to be perpetuated by sociotechnical systems. One category of sociotechnical systems--sentiment analysis tools--can also perpetuate colonial values and bias, yet less attention has been paid to how such tools may be complicit in perpetuating coloniality, although they are often used to guide various practices (e.g., content moderation). In this paper, we explore potential bias in sentiment analysis tools in the context of Bengali communities that have experienced and continue to experience the impacts of colonialism. Drawing on identity categories most impacted by colonialism amongst local Bengali communities, we focused our analytic attention on gender, religion, and nationality. We conducted an algorithmic audit of all sentiment analysis tools for Bengali, available on the Python package index (PyPI) and GitHub. Despite similar semantic content and structure, our analyses showed that in addition to inconsistencies in output from different tools, Bengali sentiment analysis tools exhibit bias between different identity categories and respond differently to different ways of identity expression. Connecting our findings with colonially shaped sociocultural structures of Bengali communities, we discuss the implications of downstream bias of sentiment analysis tools.

Pre-trained large language models (LLMs) have powerful capabilities for generating creative natural text. Evolutionary algorithms (EAs) can discover diverse solutions to complex real-world problems. Motivated by the common collective and directionality of text sequence generation and evolution, this paper illustrates the strong consistency of LLMs and EAs, which includes multiple one-to-one key characteristics: token embedding and genotype-phenotype mapping, position encoding and fitness shaping, position embedding and selection, attention and crossover, feed-forward neural network and mutation, model training and parameter update, and multi-task learning and multi-objective optimization. Based on this consistency perspective, existing coupling studies are analyzed, including evolutionary fine-tuning and LLM-enhanced EAs. Leveraging these insights, we outline a fundamental roadmap for future research in coupling LLMs and EAs, while highlighting key challenges along the way. The consistency not only reveals the evolution mechanism behind LLMs but also facilitates the development of evolved artificial agents that approach or surpass biological organisms.

In-context learning is a promising paradigm that utilizes in-context examples as prompts for the predictions of large language models. These prompts are crucial for achieving strong performance. However, since the prompts need to be sampled from a large volume of annotated examples, finding the right prompt may result in high annotation costs. To address this challenge, this paper introduces an influence-driven selective annotation method that aims to minimize annotation costs while improving the quality of in-context examples. The essence of our method is to select a pivotal subset from a large-scale unlabeled data pool to annotate for the subsequent sampling of prompts. Specifically, a directed graph is first constructed to represent unlabeled data. Afterward, the influence of candidate unlabeled subsets is quantified with a diffusion process. A simple yet effective greedy algorithm for unlabeled data selection is lastly introduced. It iteratively selects the data if it provides a maximum marginal gain with respect to quantified influence. Compared with previous efforts on selective annotations, our influencedriven method works in an end-to-end manner, avoids an intractable explicit balance between data diversity and representativeness, and enjoys theoretical support. Experiments confirm the superiority of the proposed method on various benchmarks, achieving better performance under lower time consumption during subset selection. The project page is available at https://skzhang1.github.io/IDEAL/. In-context learning (ICL) entails presenting a small set of examples with demonstrations as prompts (called in-context examples) to large language models (LLMs), before making predictions on test inputs (Wei et al., 2022a; Min et al., 2022; Akyürek et al., 2023). This emerging few-shot learning paradigm is an appealing alternative to supervised fine-tuning as it can avoid heavy parameter updates of language models while improving accuracy (Liu et al., 2021; Yoo et al., 2022). Recent studies indicate that obtaining prompts from a vast collection of annotated examples is crucial to achieving strong performance (Rubin et al., 2022). Notably, these studies have illuminated the substantial performance improvements when retrieving analogous examples (under specific embedding criteria) as in-context examples tailored for each individual test input.

Federated Learning (FL) addresses the need to create models based on proprietary data in such a way that multiple clients retain exclusive control over their data, while all benefit from improved model accuracy due to pooled resources. Recently proposed Neural Graphical Models (NGMs) and Neural Graph Revealers (NGRs) are Probabilistic Graphical Models that utilize the expressive power of neural networks to learn complex non-linear dependencies between the input features. They learn to capture the underlying data distribution and have efficient algorithms for inference and sampling. We develop a FL framework which maintains a global NGM/NGR model that learns the averaged information from the local NGM/NGR models while the training data is kept within the client's environment. Our design, FedNGM, avoids the pitfalls and shortcomings of neuron matching frameworks like Federated Matched Averaging that suffers from model parameter explosion. Our global model size doesn't grow with the number or diversity of clients. In the cases where clients have local variables that are not part of the combined global distribution, we propose a Stitching algorithm, which personalizes the global NGM/NGR model by merging additional variables using the client's data. FedNGM is robust to data heterogeneity, large number of participants, and limited communication bandwidth.

Energy consumption of memory accesses dominates the compute energy in energy-constrained robots which require a compact 3D map of the environment to achieve autonomy. Recent mapping frameworks only focused on reducing the map size while incurring significant memory usage during map construction due to multi-pass processing of each depth image. In this work, we present a memory-efficient continuous occupancy map, named GMMap, that accurately models the 3D environment using a Gaussian Mixture Model (GMM). Memory-efficient GMMap construction is enabled by the single-pass compression of depth images into local GMMs which are directly fused together into a globally-consistent map. By extending Gaussian Mixture Regression to model unexplored regions, occupancy probability is directly computed from Gaussians. Using a low-power ARM Cortex A57 CPU, GMMap can be constructed in real-time at up to 60 images per second. Compared with prior works, GMMap maintains high accuracy while reducing the map size by at least 56%, memory overhead by at least 88%, DRAM access by at least 78%, and energy consumption by at least 69%. Thus, GMMap enables real-time 3D mapping on energy-constrained robots.

We survey the current state of millimeterwave (mmWave) radar applications in robotics with a focus on unique capabilities, and discuss future opportunities based on the state of the art. Frequency Modulated Continuous Wave (FMCW) mmWave radars operating in the 76--81GHz range are an appealing alternative to lidars, cameras and other sensors operating in the near visual spectrum. Radar has been made more widely available in new packaging classes, more convenient for robotics and its longer wavelengths have the ability to bypass visual clutter such as fog, dust, and smoke. We begin by covering radar principles as they relate to robotics. We then review the relevant new research across a broad spectrum of robotics applications beginning with motion estimation, localization, and mapping. We then cover object detection and classification, and then close with an analysis of current datasets and calibration techniques that provide entry points into radar research.

The European Parliament is calling for new regulations to ensure streaming services pay artists fairly. The proposal also calls for more transparency around how algorithms generate suggestions for which artists to stream and what tracks get the most promotion. The proposed changes will be designed to ensure smaller artists are compensated fairly. Currently, royalty rates are set in a way that makes artists accept lower pay for the distribution of their content in exchange for visibility on streaming platforms like Spotify and Apple Music. The members of the European Parliament (MEPs) are primarily concerned with introducing new legal frameworks to help support artists.

Iran and Pakistan have carried out air attacks on each other's territories, targeting armed groups near their 900km-long (559-mile) volatile border, which they say were meant to ensure their respective national security. Iran's powerful Islamic Revolutionary Guard Corps (IRGC) targeted an armed group in Panjgur town of Pakistan's Balochistan province late on Tuesday, prompting Pakistan to bomb hideouts of armed groups in the Sistan-Baluchestan province of Iran early on Thursday. Let's take a look at why the neighbours have resorted to direct military strikes, who the targets were, and what the attacks tell us. The IRGC, an elite force which is a vital part of the Iranian establishment but separate from Iran's army, hit the Jaish al-Adl armed group with missile and drone strikes in a mountainous region in Pakistan close to the Iranian border. Iran said it targeted the Iranian "terrorist" group it blamed for recent attacks in the Iranian city of Rask in the southeastern province of Sistan-Baluchestan.

It's an election year in the US, which means you can expect a fresh tsunami of campaign ads in your feeds, in your inbox, and jammed in front of YouTube videos. This is also the first election of the AI era, where anyone can generate just about anything--an image, a Twitter bot, a speech--by typing a few lines of text into a prompt. Whether it's bad actors generating misleading deepfakes or candidates using text generators to write cringey campaign emails, AI is now firmly part of the election process. This week on Gadget Lab, WIRED senior politics writer Makenna Kelly joins us en route from the Iowa caucus to talk about how scammers and political campaigns alike are using AI to influence voters at the polls. Follow all of WIRED's coverage of the 2024 election and artificial intelligence.

The event opened Tuesday with Swiss President Viola Amherd calling for "global governance of AI," raising concerns the technology might supercharge disinformation as a throng of countries head to the polls. At a sleek cafe Microsoft set up across the street, CEO Satya Nadella sought to assuage concerns the AI revolution would leave the world's poorest behind, following the release of an International Monetary Fund report this week that found the technology is likely to worsen inequality and stoke social tensions. Over canapés and cocktails down the street at the Alpine Inn, Google CFO Ruth Porat promised to work with policymakers to "develop responsible regulation" and touted the company's investments in efforts to retrain workers.