Referential ambiguities arise in dialogue when a referring expression does not uniquely identify the intended referent for the addressee. Addressees usually detect such ambiguities immediately and work with the speaker to repair it using meta-communicative, Clarificational Exchanges (CE): a Clarification Request (CR) and a response. Here, we argue that the ability to generate and respond to CRs imposes specific constraints on the architecture and objective functions of multi-modal, visually grounded dialogue models. We use the SIMMC 2.0 dataset to evaluate the ability of different state-of-the-art model architectures to process CEs, with a metric that probes the contextual updates that arise from them in the model. We find that language-based models are able to encode simple multi-modal semantic information and process some CEs, excelling with those related to the dialogue history, whilst multi-modal models can use additional learning objectives to obtain disentangled object representations, which become crucial to handle complex referential ambiguities across modalities overall.

This year's International Conference on Machine Learning (ICML) is taking place in Honolulu, Hawai'i from 23-29 July. The winners of the outstanding paper awards for 2023 have now been announced. This paper introduces an interesting approach that aims to address the challenge of obtaining a learning rate free optimal bound for non-smooth stochastic convex optimization. The authors propose a novel method that overcomes the limitations imposed by traditional learning rate selection in optimizing such problems. This research makes a valuable and practical contribution to the field of optimization.

We study improving social conversational agents by learning from natural dialogue between users and a deployed model, without extra annotations. To implicitly measure the quality of a machine-generated utterance, we leverage signals like user response length, sentiment and reaction of the future human utterances in the collected dialogue episodes. Our experiments use the publicly released deployment data from BlenderBot (Xu et al., 2023). Human evaluation indicates improvements in our new models over baseline responses; however, we find that some proxy signals can lead to more generations with undesirable properties as well. For example, optimizing for conversation length can lead to more controversial or unfriendly generations compared to the baseline, whereas optimizing for positive sentiment or reaction can decrease these behaviors.

The future has arrived in Bakersfield, and I'm not sure I'm ready for it. For nearly three hours, the conversation was nonstop at the home of Audrey and Ken Mattlin, who happen to live with several robots. There's ElliQ, who resembles a table lamp and speaks mainly to Audrey, 84, whom the robot refers to by a nickname. As in, "How did you sleep, Jelly Bean?" Goo-goo-eyed Astro looks like a short-handled vacuum cleaner with an electronic tablet for a face. He scoots around the house on wheels and follows people on command.

In machine learning for sequential decision-making, an algorithmic agent learns to interact with an environment while receiving feedback in the form of a reward signal. However, in many unstructured real-world settings, such a reward signal is unknown and humans cannot reliably craft a reward signal that correctly captures desired behavior. To solve tasks in such unstructured and open-ended environments, we present Demonstration-Inferred Preference Reinforcement Learning (DIP-RL), an algorithm that leverages human demonstrations in three distinct ways, including training an autoencoder, seeding reinforcement learning (RL) training batches with demonstration data, and inferring preferences over behaviors to learn a reward function to guide RL. We evaluate DIP-RL in a tree-chopping task in Minecraft. Results suggest that the method can guide an RL agent to learn a reward function that reflects human preferences and that DIP-RL performs competitively relative to baselines. DIP-RL is inspired by our previous work on combining demonstrations and pairwise preferences in Minecraft, which was awarded a research prize at the 2022 NeurIPS MineRL BASALT competition, Learning from Human Feedback in Minecraft. Example trajectory rollouts of DIP-RL and baselines are located at https://sites.google.com/view/dip-rl.

If you subscribe to Apple Arcade ($5, £5 or AU$8 a month), you can play this game at no additional charge, and without ads or in-app purchases, which is why this version is called "Stardew Valley Plus." This game was developed by ConcernedApe. It was nominated for a handful of awards in 2016 and won the Golden Joystick Awards's Breakthrough Award that same year. Stardew Valley opens with you leaving your office job and moving back to your grandfather's rundown farm with the hope of living a simpler life. But if you scratch beneath the surface you'll find that this game is anything but simple. Sure, you can stay on your land as you grow crops, raise animals and fix your home, but there's so much to do in Stardew Valley Plus.

Kevin Mitnick, whose pioneering antics tricking employees in the 1980s and 1990s into helping him steal software and services from big phone and tech companies made him the most celebrated U.S. hacker, has died at age 59. Mitnick died Sunday in Las Vegas after a 14-month battle with pancreatic cancer, said Stu Sjouwerman, CEO of the security training firm KnowBe4, where Mitnick was chief hacking officer. His colorful career--from student tinkerer to FBI-hunted fugitive, imprisoned felon and finally respected cybersecurity professional, public speaker and author tapped for advice by U.S. lawmakers and global corporations--mirrors the evolution of society's grasp of the nuances of computer hacking. Through Mitnick's professional trajectory, and what many consider the misplaced prosecutorial zeal that put him behind bars for nearly five years until 2000, the public has learned how to better distinguish serious computer crime from the mischievous troublemaking of youths hellbent on proving their hacking prowess. "He never hacked for money," said Sjouwerman, who became Mitnick's business partner in 2011.

In order to model criminal networks for law enforcement purposes, a limited supply of data needs to be translated into validated agent-based models. What is missing in current criminological modelling is a systematic and transparent framework for modelers and domain experts that establishes a modelling procedure for computational criminal modelling that includes translating qualitative data into quantitative rules. For this, we propose FREIDA (Framework for Expert-Informed Data-driven Agent-based models). Throughout the paper, the criminal cocaine replacement model (CCRM) will be used as an example case to demonstrate the FREIDA methodology. For the CCRM, a criminal cocaine network in the Netherlands is being modelled where the kingpin node is being removed, the goal being for the remaining agents to reorganize after the disruption and return the network into a stable state. Qualitative data sources such as case files, literature and interviews are translated into empirical laws, and combined with the quantitative sources such as databases form the three dimensions (environment, agents, behaviour) of a networked ABM. Four case files are being modelled and scored both for training as well as for validation scores to transition to the computational model and application phase respectively. In the last phase, iterative sensitivity analysis, uncertainty quantification and scenario testing eventually lead to a robust model that can help law enforcement plan their intervention strategies. Results indicate the need for flexible parameters as well as additional case file simulations to be performed.

Language tests measure a person's ability to use a language in terms of listening, speaking, reading, or writing. Such tests play an integral role in academic, professional, and immigration domains, with entities such as educational institutions, professional accreditation bodies, and governments using them to assess candidate language proficiency. Recent advances in Artificial Intelligence (AI) and the discipline of Natural Language Processing have prompted language test providers to explore AI's potential applicability within language testing, leading to transformative activity patterns surrounding language instruction and learning. However, with concerns over AI's trustworthiness, it is imperative to understand the implications of integrating AI into language testing. This knowledge will enable stakeholders to make well-informed decisions, thus safeguarding community well-being and testing integrity. To understand the concerns and effects of AI usage in language tests, we conducted interviews and surveys with English test-takers. To the best of our knowledge, this is the first empirical study aimed at identifying the implications of AI adoption in language tests from a test-taker perspective. Our study reveals test-taker perceptions and behavioral patterns. Specifically, we identify that AI integration may enhance perceptions of fairness, consistency, and availability. Conversely, it might incite mistrust regarding reliability and interactivity aspects, subsequently influencing the behaviors and well-being of test-takers. These insights provide a better understanding of potential societal implications and assist stakeholders in making informed decisions concerning AI usage in language testing.

When Sunshine Henle's mother, Linda, died unexpectedly at the age of 72, Henle, a 42-year-old Floridian, was left with what she describes as a "gaping hole of silence" in her life. Even though Linda had lived in New York, where she worked as a Sunday school teacher, the pair had kept in constant contact through phone calls and texting. "I always knew she was there, no matter what – if I was upset, or if I just needed to talk. She would always respond," says Henle. In November, Linda collapsed in her home and was unable to move. Henle's brother Sam and her sister-in-law Julie took her to urgent care.