Publications

Neurophysiological effects of targeting sleep spindles with closed-loop auditory stimulation
Hugo R Jourde
Milo Sobral
Giovanni Beltrame
Emily B J Coffey
Sleep spindles are neural events unique to nonrapid eye movement sleep that play key roles in memory reactivation and consolidation. However… (see more), much of the evidence for their function remains correlational rather than causal. Closed-loop brain stimulation uses real-time monitoring of neural events (often via electroencephalography; EEG) to deliver precise auditory, magnetic, or electrical stimulation for research or therapeutic purposes. Automated online algorithms to detect and stimulate sleep spindles have recently been validated, but the time- and frequency-resolved physiological responses generated by them have not yet been documented. Building on the recent findings that sleep spindles do not block the transmission of sound to cortex, the present work investigates the neurophysiological responses to closed-loop auditory stimulation of sleep spindles. EEG data were collected from 10 healthy human adults (6 nights each), whilst sleep spindles were detected and in half the nights, targeted with auditory stimulation. Spindles were successfully stimulated before their offset in 97.6% of detections and did not disturb sleep. Comparing stimulation with sham, we observed that stimulation resulted in increased sigma activity (11–16 Hz) at about 1 second poststimulation but that stimulation occurring at the beginning of the spindle also resulted in early termination of the spindle. Finally, we observed that stimulating an evoked spindle did not elicit additional sigma activity. Our results validate the use of closed-loop auditory stimulation targeting sleep spindles, and document its neural effects, as a basis for future causal investigations concerning spindles’ roles in memory consolidation.
2025-07-06
Sleep Advances (published)
doi.org
Not All Data Are Unlearned Equally
Aravind Krishnan
Siva Reddy
Marius Mosbach
Machine unlearning is concerned with the task of removing knowledge learned from particular data points from a trained model. In the context… (see more) of large language models (LLMs), unlearning has recently received increased attention, particularly for removing knowledge about named entities from models for privacy purposes. While various approaches have been proposed to address the unlearning problem, most existing approaches treat all data points to be unlearned equally, i.e., unlearning that Montreal is a city in Canada is treated exactly the same as unlearning the phone number of the first author of this paper. In this work, we show that this all data is equal assumption does not hold for LLM unlearning. We study how the success of unlearning depends on the frequency of the knowledge we want to unlearn in the pre-training data of a model and find that frequency strongly affects unlearning, i.e., more frequent knowledge is harder to unlearn. Additionally, we uncover a misalignment between probability and generation-based evaluations of unlearning and show that this problem worsens as models become larger. Overall, our experiments highlight the need for better evaluation practices and novel methods for LLM unlearning that take the training data of models into account.
2025-07-06
colmweb.org/COLM/2025/Conference (accepted)
doi.org
openreview.net
Partial Perspectives: How LLMs Handle Logically Inconsistent Knowledge in Reasoning Tasks
Zichao Li
Ines Arous
Jackie CK Cheung
Most natural language reasoning tasks in the research community assume consistent input knowledge. Nevertheless, real-world scenarios often … (see more)involve inconsistent information, which might lead to divergent conclusions and are typically associated with varying levels of uncertainty. This raises a key research question: can large language models (LLMs) effectively handle uncertainty in their reasoning process to maximize knowledge consistency? In this paper, we propose a framework for evaluating reasoning over inconsistent knowledge. Our approach models uncertainty via weights of logical rules, leveraging Markov logic networks (MLN), which integrate probabilistic reasoning with first-order logic. This enables us to quantify inconsistencies in knowledge bases, and hence rigorously evaluate LLM reasoning. We introduce two tasks using this framework: 1) QA, which involves answering questions by integrating inconsistent knowledge; and 2) knowledge rectification, where we aim to rectify language models' acquired knowledge to improve consistency. We curate a dataset of 3,000 MLN-formatted knowledge bases to implement these tasks. We evaluate state-of-the-art LLMs on these tasks and highlight their limitations in uncertainty-aware reasoning over inconsistent logical knowledge.
2025-07-06
colmweb.org/COLM/2025/Conference (accepted)
openreview.net
openreview.net
Putting the Value Back in RL: Better Test-Time Scaling by Unifying LLM Reasoners With Verifiers
Kusha Sareen
Morgane M Moss
Alessandro Sordoni
Rishabh Agarwal
Arian Hosseini
2025-07-06
Conference on Language Modeling (accepted)
doi.org
openreview.net
RainShift: A Benchmark for Precipitation Downscaling Across Geographies
Paula Harder
Luca Schmidt
Francis Pelletier
Nicole Ludwig
Matthew Chantry
Christian Lessig
Alex Hernández-García
David Rolnick
Earth System Models (ESM) are our main tool for projecting the impacts of climate change. However, running these models at sufficient resolu… (see more)tion for local-scale risk-assessments is not computationally feasible. Deep learning-based super-resolution models offer a promising solution to downscale ESM outputs to higher resolutions by learning from data. Yet, due to regional variations in climatic processes, these models typically require retraining for each geographical area-demanding high-resolution observational data, which is unevenly available across the globe. This highlights the need to assess how well these models generalize across geographic regions. To address this, we introduce RainShift, a dataset and benchmark for evaluating downscaling under geographic distribution shifts. We evaluate state-of-the-art downscaling approaches including GANs and diffusion models in generalizing across data gaps between the Global North and Global South. Our findings reveal substantial performance drops in out-of-distribution regions, depending on model and geographic area. While expanding the training domain generally improves generalization, it is insufficient to overcome shifts between geographically distinct regions. We show that addressing these shifts through, for example, data alignment can improve spatial generalization. Our work advances the global applicability of downscaling methods and represents a step toward reducing inequities in access to high-resolution climate information.
2025-07-06
ArXiv (preprint)
doi.org
arxiv.org
Rethinking Safety in LLM Fine-tuning: An Optimization Perspective
Minseon Kim
Jin Myung Kwak
Lama Alssum
Bernard Ghanem
Philip Torr
David M. Krueger
Fazl Barez
Adel Bibi
Fine-tuning language models is commonly believed to inevitably harm their safety, i.e., refusing to respond to harmful user requests, even w… (see more)hen using harmless datasets, thus requiring additional safety measures. We challenge this belief through systematic testing, showing that poor optimization choices, rather than inherent trade-offs, often cause safety problems, measured as harmful responses to adversarial prompts. By properly selecting key training hyper-parameters, e.g., learning rate, batch size, and gradient steps, we reduce unsafe model responses from 16\% to approximately 5\%, as measured by keyword matching, while maintaining utility performance. Based on this observation, we propose a simple exponential moving average (EMA) momentum technique in parameter space that preserves safety performance by creating a stable optimization path and retains the original pre-trained model's safety properties. Our experiments on the Llama families across multiple datasets (Dolly, Alpaca, ORCA) demonstrate that safety problems during fine-tuning can largely be avoided without specialized interventions, outperforming existing approaches that require additional safety data while offering practical guidelines for maintaining both model performance and safety during adaptation.
2025-07-06
colmweb.org/COLM/2025/Conference (accepted)
doi.org
openreview.net
Statistical or Embodied? Comparing Colorseeing, Colorblind, Painters, and Large Language Models in Their Processing of Color Metaphors
Ethan O. Nadler
Douglas Guilbeault
Sofronia M. Ringold
T. R. Williamson
Antoine Bellemare‐Pepin
Iulia M. Comșa
Karim Jerbi CoCo Lab
Srini Narayanan
Lisa Aziz‐Zadeh
2025-07-06
Cognitive Science (published)
doi.org
Training Plug-and-Play Knowledge Modules with Deep Context Distillation
Lucas Caccia
Alan Ansell
Edoardo Ponti
Ivan Vulić
Alessandro Sordoni
Dynamically integrating new or rapidly evolving information after (Large) Language Model pre-training remains challenging, particularly in l… (see more)ow-data scenarios or when dealing with private and specialized documents. In-context learning and retrieval-augmented generation (RAG) face limitations, including their high inference costs and their inability to capture global document information. In this paper, we propose a way of modularizing knowledge by training document-level Knowledge Modules (KMs). KMs are lightweight components implemented as parameter-efficient LoRA modules, which are trained to store information about new documents and can be easily plugged into models on demand. We show that next-token prediction performs poorly as the training objective for KMs. We instead propose Deep Context Distillation: we learn KMs parameters such as to simulate hidden states and logits of a teacher that takes the document in context. Our method outperforms standard next-token prediction and pre-instruction training techniques, across two datasets. Finally, we highlight synergies between KMs and retrieval-augmented generation.
2025-07-06
colmweb.org/COLM/2025/Conference (accepted)
openreview.net
openreview.net
RAT: Bridging RNN Efficiency and Attention Accuracy in Language Modeling
Xiuying Wei
Anunay Yadav
Razvan Pascanu
Caglar Gulçehre
Transformers have become the cornerstone of modern large-scale language models; however, their dependence on softmax attention poses a major… (see more) computational bottleneck, particularly in long-context settings. In this work, rather than following prevalent approaches such as linear attention (or SSMs) and local attention, we introduce an intermediate design called \rat between recurrence and attention mechanisms. It partitions the input into chunks, applies a simple linear recurrence within each chunk to capture local dependencies, and then performs softmax attention across chunks to model long-range interactions. By adjusting the size of the chunk, \rat enables flexible trade-offs, combining the strengths of RNN and attention. Empirically, with a chunk size of 16, the \rat layer achieves a \(7\times\) improvement in training speed with 100K token sequences and \(9\times\) in generation at 4K sequence length, while maintaining similar or sometimes even better accuracy compared to standard attention. We demonstrate this by training 1.3B parameter models from scratch and performing large-scale evaluations, including short- and long-context benchmarks, as well as supervised fine-tuning~(SFT). We further propose a hybrid architecture that interleaves \rat with local attention. By combining efficient long-range modeling with strong local interactions, this hybrid design not only improves inference speed and reduces cache memory usage compared to attention, but also consistently enhances performance, for example, achieving an average 1 point gain in commonsense reasoning tasks, up to 4 points on code tasks, and a 1 point Rouge-L increase in a summarization SFT task. Code is available at https://github.com/CLAIRE-Labo/RAT
2025-07-05
ArXiv (preprint)
doi.org
arxiv.org
DOLPHIN advances single-cell transcriptomics beyond gene level by leveraging exon and junction reads
Kailu Song
Yumin Zheng
Bowen Zhao
David H. Eidelman
Jian Tang
Jun Ding
The advent of single-cell sequencing has revolutionized the study of cellular dynamics, providing unprecedented resolution into the molecula… (see more)r states and heterogeneity of individual cells. However, the rich potential of exon-level information and junction reads within single cells remains underutilized. Conventional gene-count methods overlook critical exon and junction data, limiting the quality of cell representation and downstream analyses such as subpopulation identification and alternative splicing detection. We introduce DOLPHIN, a deep learning method that integrates exon-level and junction read data, representing genes as graph structures. These graphs are processed by a variational graph autoencoder to improve cell embeddings. DOLPHIN not only demonstrates superior performance in cell clustering, biomarker discovery, and alternative splicing detection but also provides a distinct capability to detect subtle transcriptomic differences at the exon level that are often masked in gene-level analyses. By examining cellular dynamics with enhanced resolution, DOLPHIN provides new insights into disease mechanisms and potential therapeutic targets.
2025-07-03
Nature Communications (published)
doi.org
Extracting and Following Paths for Robust Relational Reasoning with Large Language Models
Ge Zhang
Mohammad Alomrani
Hongjian Gu
Jiaming Zhou
Yaochen Hu
B. Wang
Qun Liu
Mark J. Coates
Yingxue Zhang
Jianye HAO
2025-07-03
KDD.org/2025/Workshop/SKnow-LLM (oral)
openreview.net
openreview.net
Decoding Humor-Induced Amusement via Facial Expression Analysis: Toward Emotion-Aware Applications
Gabrielle Toupin
Arthur Dehgan
Marie Buffo
Clément Feyt
Golnoush Alamian
Karim Jerbi
Anne-Lise Saive
Humor is widely recognized for its positive effects on well-being, including stress reduction, mood enhancement, and cognitive benefits. Yet… (see more), the lack of reliable tools to objectively quantify amusement—particularly its temporal dynamics—has limited progress in this area. Existing measures often rely on self-report or coarse summary ratings, providing little insight into how amusement unfolds over time. To address this gap, we developed a Random Forest model to predict the intensity of amusement evoked by humorous video clips, based on participants’ facial expressions—particularly the co-activation of Facial Action Units 6 and 12 (“% Smile”)—and video features such as motion, saliency, and topic. Our results show that exposure to humorous content significantly increases “% Smile”, with amusement peaking toward the end of videos. Importantly, we observed emotional carry-over effects, suggesting that consecutive humorous stimuli can sustain or amplify positive emotional responses. Even when trained solely on humorous content, the model reliably predicted amusement intensity, underscoring the robustness of our approach. Overall, this study provides a novel, objective method to track amusement on a fine temporal scale, advancing the measurement of nonverbal emotional expression. These findings may inform the design of emotion-aware applications and humor-based therapeutic interventions to promote well-being and emotional health.
2025-07-02
Applied Sciences (published)
doi.org