What does it take for a robot to hold a conversation with a room, not just a person? That was one of the questions at the heart of my last week (20th-24th July) at the Imperial Robotics Summer School, hosted at Imperial College, London; a week that sharpened my thinking and pushed me to look at robotics problems from angles I don't usually get to in my day-to-day work. The summer school brought together emerging researchers, academics, and industry professionals from across the robotics community for an intensive, hands-on programme. I came away having learned a huge amount, from expert-led lectures on robot kinematics, dynamics, sensing and control, and robot learning, through to specialised sessions on aerial robotics, robot intelligence, surgical robot vision, bio-inspired sensing and control, and personal assistive robotics. One of the standout parts of the week was getting into Imperial's robotics labs themselves, seeing research up close across adaptive and intelligent robotics, aerial robotics, robotic surgery, manipulation and touch, and assistive robotics.

Anne Fehres and Luke Conroy AI4Media Humans Do The Heavy Data Lifting Licenced by CC-BY 4.0 The Royal Statistical Society's AI Task Force has issued a critical mandate via a new paper, AI Regulation Needs Statistics, which demands that statistical principles actively shape global AI governance. The publication escalates the core argument of their foundational work, AI is Statistics . This earlier paper argued that AI is fundamentally statistical, meaning effective and ethical deployment is impossible without statistical literacy. You can watch our expert panel discuss the topic here . A major focus of that work was around the challenges of evaluating AIs, given that they are dynamic systems that continue to evolve once they have been deployed in the real world.

The Future of AI Research report, published in March 2025, aims to clearly identify the trajectory of AI research in a structured way. The report was led by outgoing AAAI President Francesca Rossi and covers 17 different AI topics . Members of the report team, and other selected AI practitioners, are taking part in a series of video panel discussions covering selected chapters from the report. In the next discussion in the collection, the four panellists tackle AI and scientific integrity. Lucy Smith is Senior Managing Editor for AIhub.

The talk presented in this podcast, "Where do Ethics Belong in Artificial Intelligence?", It was presented at Oregon State University by Houssam Abbas (assistant professor of electrical engineering) and Alicia Patterson (assistant professor of philosophy) as part of an AI seminar series. "Engineering Out Loud" is a podcast from the College of Engineering at Oregon State University. It is for anyone who wants to know more about how engineering is changing the world. Hear from researchers about how they are tackling humanity's biggest challenges, including enabling access to clean water, preparing and recovering from natural hazards, and improving human the health and safety.

This post contains a list of the AI-related seminars that are scheduled to take place in the next couple of months. All events detailed here are free and open for anyone to attend virtually. Anna Hedström (ETHZ) EPFL The Zoom link is here . Jie Chao (Concord Consortium) Raspberry PI Sign up here to join. Stefan Klein and Anna Bon The Digital Humanism (DIGHUM) Initiative The talk will be livestreamed on YouTube here .

Hosted by Ben Byford, The Machine Ethics Podcast brings together interviews with academics, authors, business leaders, designers and engineers on the subject of autonomous algorithms, artificial intelligence, machine learning, and technology's impact on society. In this episode we chat with Rebecca for the second time about: why intelligence isn't everything, whether LLM's are even safe, AI governance and guardrails, moral assurance, under-specification problems, lack of interdisciplinary work in robotics, that AI shouldn't be sold as a solution to everything, sidelining of AI ethics, what are the actual benefits of AI, whether AI progress will widen inequality, and more Rebecca Raper is a robotics lecturer and researcher at Cranfield University. She authored the book Raising Robots to be Good: a practical foray into the art and science of Machine Ethics . She designed and leads the UK's first Robotics apprenticeship. This podcast was created and is run by Ben Byford and collaborators.

We study how training data contributes to the emergence of toxic behaviors in large language models. Most prior work on reducing model toxicity adopts reactive approaches, such as fine-tuning pre-trained (and potentially toxic) models to align them with human values. In contrast, we propose a proactive approach-- IF-GUIDE--that leverages influence functions to identify and suppress harmful tokens in the training data. To this end, we first show that standard influence functions are ineffective at discovering harmful training records. We then present a novel adaptation that measures token-level attributions from training data to model toxicity, along with techniques for selecting toxic training documents and a learning objective that can be integrated into both pre-training and fine-tuning. Moreover, IF-GUIDE does not rely on human-preference data, which is typically required by existing alignment methods. In our evaluation, we demonstrate that IF-GUIDE substantially reduces both explicit and implicit toxicity--by up to 10 compared to uncensored models, and up to 3 compared to baseline alignment methods such as DPO and RAD--across both pre-training and fine-tuning scenarios. IF-GUIDE is computationally efficient: a billion-parameter model is not necessary for computing influence scores; a million-parameter model--with 7.5 fewer parameters--can effectively serve as a proxy for identifying harmful data.

Data quality is a critical driver of large language model performance, yet existing model-based selection methods focus almost exclusively on English, neglecting other languages that are essential in the training mix for multilingual LLMs. We introduce MuRating, a scalable framework that transfers high-quality English dataquality signals into a multilingual autorater, capable of handling 17 languages. MuRating aggregates multiple English autoraters via pairwise comparisons to learn unified document quality scores, then projects these judgments through translation to train a multilingual evaluator on monolingual, cross-lingual, and parallel text pairs. Applied to web data, MuRating selects balanced subsets of English and multilingual content to pretrain LLaMA-architecture models of 1.2B and 7B parameters. Compared to strong baselines, including QuRater, FineWeb2HQ, AskLLM, DCLM, our approach increases average accuracy on both English benchmarks and multilingual evaluations. Extensive analyses further validate that pairwise training provides greater stability and robustness than pointwise scoring, underscoring the effectiveness of MuRating as a general multilingual data-selection framework.

Model editing aims to efficiently revise incorrect or outdated knowledge within LLMs without incurring the high cost of full retraining and risking catastrophic forgetting. Currently, most LLM editing datasets are confined to narrow knowledge domains and cover a limited range of editing evaluation. They often overlook the broad scope of editing demands and the diversity of ripple effects resulting from edits. In this context, we introduce UNIEDIT, a unified benchmark for LLM editing grounded in open-domain knowledge. First, we construct editing samples by selecting entities from 25 common domains across five major categories, utilizing the extensive triple knowledge available in open-domain knowledge graphs to ensure comprehensive coverage of the knowledge domains. To address the issues of generality and locality in editing, we design an Neighborhood Multi-hop Chain Sampling (NMCS) algorithm to sample subgraphs based on a given knowledge piece to entail comprehensive ripple effects to evaluate. Finally, we employ proprietary LLMs to convert the sampled knowledge subgraphs into natural language text, guaranteeing grammatical accuracy and syntactical diversity. Extensive statistical analysis confirms the scale, comprehensiveness, and diversity of our UNIEDIT benchmark. We conduct comprehensive experiments across multiple LLMs and editors, analyzing their performance to highlight strengths and weaknesses in editing across open knowledge domains and various evaluation criteria, thereby offering valuable insights for future research endeavors.

Large language models (LLMs) are powerful but static; they lack mechanisms to adapt their weights in response to new tasks, knowledge, or examples. We introduce Self-Adapting LLMs (SEAL), a framework that enables LLMs to self-adapt by generating their own finetuning data and update directives. Given a new input, the model produces a self-edit--a generation that may restructure the information in different ways, specify optimization hyperparameters, or invoke tools for data augmentation and gradient-based updates.