Join us on the Venture Scientist Bootcamp, a full time, 4-month incubator at Mila, built specifically for deep tech founders with elite STEM backgrounds. You have until November 21, 2026 to apply!
The upcoming meeting, taking place on November 10 at Mila, will explore how we can collectively develop, govern, and deploy high-performing, reliable, and secure agentic systems by connecting academic researchers, industry experts, and practitioners.
We use cookies to analyze the browsing and usage of our website and to personalize your experience. You can disable these technologies at any time, but this may limit certain functionalities of the site. Read our Privacy Policy for more information.
Setting cookies
You can enable and disable the types of cookies you wish to accept. However certain choices you make could affect the services offered on our sites (e.g. suggestions, personalised ads, etc.).
Essential cookies
These cookies are necessary for the operation of the site and cannot be deactivated. (Still active)
Analytics cookies
Do you accept the use of cookies to measure the audience of our sites?
Multimedia Player
Do you accept the use of cookies to display and allow you to watch the video content hosted by our partners (YouTube, etc.)?
Publications
Seeing SDG 6 from space: Local-scale monitoring of piped water and sewage systems across Africa using satellite imagery and self-supervised learning
Access to drinking water and sanitation services is essential. Sustainable Development Goal 6 (SDG 6) aims to achieve universal access, but … (see more)progress monitoring remains constrained by costly, infrequent, and spatially uneven household surveys and censuses, particularly in data-scarce regions. To address this gap, this study develops a scalable remote-sensing framework for estimating area-level presence of piped water and sewage systems at 2.56 km spatial resolution across Africa. The framework integrates Sentinel-2 imagery, enumerator-observed system-presence records from Afrobarometer enumeration areas, 30 m population data, and Vision Transformer representations learned with DINO self-supervised learning. The best-performing models achieve held-out AUROC values of 91.54% for piped water and 93.24% for sewage across enumeration areas. Under leave-one-region-out cross-validation, this falls to 75.5% and 78.7% respectively, reflecting transfer difficulty to unsampled regions. Applied across 50 African countries, population-weighted piped water estimates closely track WHO/UNICEF JMP piped water access ( R 2 = 0.92 ), while sewage estimates show meaningful agreement with the broader JMP safely managed sanitation benchmark ( R 2 = 0.72 ). In countries without Afrobarometer survey coverage, the model achieves population-weighted mean absolute errors of 9.5% for piped water and 10.7% for sewage. A Nigeria application across 767 Local Government Areas shows how our framework’s fine-scale predictions reveal substantial subnational inequality, with the largest populations living where no piped water system is present reaching 1.187 million, and no sewage system 1.577 million. These findings show that DINO-based self-supervised learning using freely available satellite imagery can complement traditional household surveys, supporting SDG 6 monitoring, infrastructure planning, and environmental equity assessment.
The global humanitarian crisis is escalating due to conflicts, climate-related disasters, and infection outbreaks.1 Recent cuts by the USA a… (see more)nd other high-income donors to international aid, including considerable reductions in foreign assistance, have abruptly diminished crucial support for global health programmes, food security, and disaster relief.2 With overburdened humanitarian systems facing worsening resource constraints, data-driven aid allocation has become increasingly important for survival worldwide.
Social interactions between people of same and different generations shape longitudinal changes in interpersonal neural synchrony, loneliness, and social connection
Loneliness is globally acknowledged as a severe and burgeoning health risk, fueling interest in helping people of all ages form meaningful s… (see more)ocial connections. One promising approach consists of intergenerational social programs. While behavioral and qualitative evidence derived from such programs promise health and wellbeing benefits, the physiological consequences of repeated intergenerational encounters remain unknown. Insight into physiological changes will shed light on the mechanisms of social connection. We charted longitudinal changes in interpersonal neural synchrony (INS) in 31 intergenerational (older/younger adult) and 30 same-generation (younger adult) dyads across a six-session creative drawing program. At each session, dyads completed self-report measures, drew together and alone, and had their cortical activation recorded with fNIRS. In both groups, INS was greater while dyads drew together than alone. Across sessions, intergenerational dyads' INS decreased and same-generation dyads' INS increased. INS in RIFG~RTPJ and RIFG~RIFG were predictive of loneliness levels and feelings of social closeness, respectively. This exploratory longitudinal research reinforces the multi-faceted nature of INS dynamics as social connections are forged.
Neural networks trained on nonstationary tasks frequently lose the ability to fit new targets, a phenomenon referred to as loss of plasticit… (see more)y. We identify a novel source of plasticity loss due to the growing anisotropy of weight matrices'singular values during training, and analyze this phenomenon both empirically and theoretically. To mitigate this issue, we introduce SingularClip, a procedure that periodically clips the singular values of all weight matrices. We show that SingularClip performs strongly against baselines across a range of tasks in both continual supervised learning and deep reinforcement learning.
Abstract Social connection is fundamental to human wellbeing. Serotonergic psychedelics such as lysergic acid diethylamide (LSD) acutely hei… (see more)ghten subjective connectedness, yet their effects on real-time social connection remain poorly understood. Using EEG hyperscanning in a randomized, double-blind, placebo-controlled crossover study, we recorded neural activity simultaneously from both members of healthy romantic couples (N=25) who received LSD (50 μg) or placebo together, across resting and interactive states. LSD increased subjective connectedness, including feelings of love, closeness, trust, and being “in sync,” while reducing loneliness, compared to placebo. This affiliative shift dissociated from the drug’s pharmacokinetic time-course, remaining elevated as subjective intensity and plasma concentration declined. In parallel, LSD increased inter-brain synchrony during shared rest, carried specifically by theta-band amplitude-envelope coupling. Importantly, this effect survived two complementary controls. First, it exceeded coupling between unrelated individuals and second the effects depended on contemporaneous neural alignment rather than shared drug-induced dynamics. Exploratory analyses showed that romantic partners with greater resting synchrony reported greater feelings of connectedness. These findings provide the first evidence that a psychedelic enhances brain-to-brain coupling between people, linking a pharmacologically induced state of felt connection to a measurable signature shared across interacting brains.
Semantic Bandits: In-Context Exploration-Exploitation is Biased by Semantic Priors
David Eric Austin
Kaheer Suleman
Jackie Chi Kit Cheung
Large language models (LLMs) are increasingly deployed as decision-making agents in settings that require sophisticated environmental explor… (see more)ation. However, existing work has raised questions about how LLMs actually balance exploration and exploitation. Unlike classical agents, LLM agents engage with tasks through natural language, exposing them to semantic information with no formal counterpart in the task structure. We introduce the semantic bandit, an extension of the multi-armed bandit setting that explicitly considers the textual labels assigned to actions, and use it to study how semantic priors --- inductive biases arising from associations between language and expected reward learned during pre-training, shape LLM exploration behaviour. We find that semantically informative action labels reduce exploration in favour of exploitation, improving performance when aligned with the reward structure and severely degrading it when misaligned. We further find that negative rewards trigger substantially more exploration than equivalent positive rewards, consistent with an expected-scale bias induced by reward conventions common in pre-training data. Overall, we argue that the use of language to define the environment and rewards introduces unavoidable biases derived from the fact that the model is trained on word co-occurence, with implications for the reliability and robustness of LLM agents in real-world decision-making settings.
This technical report presents GeCo, our solution for the challenge at the 4th Workshop on UAVs in Multimedia (UAVM 2026), ACM Multimedia 20… (see more)26. We use a partially fine-tuned DINOv2 to extract features and fuse via cross-attention. The relative pose (heading and translation) is then regressed and regularized by geometric consistency loss. GeCo achieves a 0.00583 final score on the PairUAV dataset. Code is available at https://github.com/Link-ying/GeCo.
2026-08-15
UAVM @ ACM International Conference on Multimedia (poster)
In this work, we derive confidence intervals for the return process in discounted reward Markov Decision Processes with continuous state and… (see more) action spaces. These confidence bounds depend only on the statistics of the value function, which may be derived using dynamic programming. In the special case of MDPs with uniformly bounded value functions, simpler confidence intervals are provided for the return process. Finally, we study the effect of epistemic uncertainty on the derived confidence intervals. Numerical examples are provided to show how these bounds may be used in practice.
2026-08-14
Finding the Frame @ Reinforcement Learning Conference (published)
Text-to-image diffusion models can be misused to generate harmful content through adversarial or paraphrased prompts that bypass built-in sa… (see more)fety mechanisms. Existing concept erasure methods often suffer from limited robustness against adversarial prompts, degradation of benign generation quality, or reliance on inference-time interventions that introduce persistent computational overhead. To address these limitations, we formulate concept erasure as a domain alignment problem in the text representation space. We propose a lightweight Text Encoder Alignment framework (TEA) that fine-tunes only the text encoder while keeping the generative backbone fully frozen. Given concept--anchor prompt pairs, our method trains a discriminator to distinguish token-level representations of concept-containing prompts from those of safe anchor prompts, while updating the text encoder to make these representations indistinguishable. TEA introduces zero inference-time overhead and requires only a small number of fine-tuning steps, making it highly efficient to deploy at scale. Despite this efficiency, TEA achieves state-of-the-art erasure robustness against black-box and white-box adversarial attacks on Stable Diffusion v1.4, while preserving generation quality on benign prompts. Furthermore, TEA is model-agnostic and achieves the lowest attack success rate on Stable Diffusion v3.5, extending concept erasure to a Rectified Flow Transformer architecture with T5 conditioning where prior methods remain largely unexplored. Code is available at \href{https://github.com/alirezafarashah/TEA.git}{https://github.com/alirezafarashah/TEA.git}
AI competition is widely framed as a winner-take-all race. Mobile consumer data for the AI assistant category from 2023 through 2025 suggest… (see more)s otherwise: three strategies coexist, and all are growing. Scale (ChatGPT), adjacency (Gemini), and premium specialization (Claude) capture value in strategically distinct ways. Major launches reward the launcher without measurably harming rivals. These archetypes are not unique to AI; they recur whenever a disruptive technology opens a market before competition settles. For managers, the most important question is which strategy their distribution, economics, and customer base can sustain.