Portrait of Blake Richards

Blake Richards

Core Academic Member
Canada CIFAR AI Chair
Associate Professor, McGill University, School of Computer Science and Department of Neurology and Neurosurgery
Google
Research Topics
Computational Neuroscience
Generative Models
Reinforcement Learning
Representation Learning

Biography

Blake Richards is an associate professor at the School of Computer Science and in the Department of Neurology and Neurosurgery at McGill University, and a core academic member of Mila – Quebec Artificial Intelligence Institute.

Richards’ research lies at the intersection of neuroscience and AI. His laboratory investigates universal principles of intelligence that apply to both natural and artificial agents.

He has received several awards for his work, including the NSERC Arthur B. McDonald Fellowship in 2022, the Canadian Association for Neuroscience Young Investigator Award in 2019, and a Canada CIFAR AI Chair in 2018. Richards was a Banting Postdoctoral Fellow at SickKids Hospital from 2011 to 2013.

He obtained his PhD in neuroscience from the University of Oxford in 2010, and his BSc in cognitive science and AI from the University of Toronto in 2004.

Current Students

Research Intern - Université de Montréal
Postdoctorate - McGill University
Postdoctorate - Université de Montréal
Principal supervisor :
PhD - McGill University
Co-supervisor :
PhD - McGill University
Principal supervisor :
PhD - McGill University
Postdoctorate - McGill University
PhD - McGill University
PhD - McGill University
Independent visiting researcher - Seoul National University
PhD - McGill University
Collaborating Alumni
PhD - McGill University
Independent visiting researcher - ETH Zurich
Collaborating researcher - Georgia Tech
Postdoctorate - McGill University
Undergraduate - McGill University
PhD - McGill University
Master's Research - McGill University
PhD - Université de Montréal
Principal supervisor :
Collaborating Alumni - McGill University
Independent visiting researcher
Collaborating Alumni - McGill University
Co-supervisor :
PhD - McGill University
Co-supervisor :
PhD - McGill University
Co-supervisor :
PhD - McGill University
Principal supervisor :
Master's Research - McGill University
Co-supervisor :
Independent visiting researcher - NA
Master's Research - McGill University
PhD - McGill University
Master's Research - McGill University
Co-supervisor :
Independent visiting researcher - Seoul National University
Independent visiting researcher - York University
PhD - McGill University
PhD - Concordia University
Principal supervisor :

Publications

Learning to combine top-down context and feed-forward representations under ambiguity with apical and basal dendrites
Nizar Islah
Guillaume Etter
Mashbayar Tugsbayar
Busra Tugce Gurbuz
The challenge of hidden gifts in multi-agent reinforcement learning
Dane Malenfant
Cooperation between people is not always obvious. Sometimes we benefit from actions that others have taken even when we are unaware that the… (see more)y took those actions. For example, if your neighbor chooses not to take a parking spot in front of your house when you are not there, you can benefit, even without being aware that they took this action. These “hidden gifts” represent an interesting challenge for multi-agent reinforcement learning (MARL), since assigning credit to your own actions correctly when the beneficial actions of others are hidden is non-trivial. Here, we study the impact of hidden gifts with a very simple MARL task. In this task, agents in a grid-world environment have individual doors to unlock in order to obtain individual rewards. As well, if all the agents unlock their door the group receives a larger collective reward. However, there is only one key for all of the doors, such that the collective reward can only be obtained when the agents drop the key for others after they use it. Notably, there is nothing to indicate to an agent that the other agents have dropped the key, thus the act of dropping the key for others is a “hidden gift”. We show that several different state-of-the-art RL algorithms, including MARL algorithms, fail to learn how to obtain the collective reward in this simple task. Interestingly, we find that independent model-free policy gradient agents can solve the task when we provide them with information about their action history, but MARL agents still cannot solve the task with action history. Finally, we derive a correction term for these independent agents, inspired by learning aware approaches, which reduces the variance in learning and helps them to converge to collective success more reliably. These results show how credit assignment in multi-agent settings can be particularly challenging in the presence of “hidden gifts”, and demonstrate that learning awareness can benefit these settings
Tracing the representation geometry of language models from pretraining to post-training
Melody Zixuan Li
Kumar Krishna Agrawal
Arna Ghosh
Komal Kumar Teru
The geometry of representations in a neural network can significantly impact downstream generalization. It is unknown how representation geo… (see more)metry changes in large language models (LLMs) over pretraining and post-training. Here, we characterize the evolving geometry of LLM representations using spectral methods (effective rank and eigenspectrum decay). With the OLMo and Pythia model families we uncover a consistent non-monotonic sequence of three distinct geometric phases in pretraining. An initial \warmup phase sees rapid representational compression. This is followed by an "entropy-seeking" phase, characterized by expansion of the representation manifold's effective dimensionality, which correlates with an increase in memorization. Subsequently, a "compression seeking" phase imposes anisotropic consolidation, selectively preserving variance along dominant eigendirections while contracting others, correlating with improved downstream task performance. We link the emergence of these phases to the fundamental interplay of cross-entropy optimization, information bottleneck, and skewed data distribution. Additionally, we find that in post-training the representation geometry is further transformed: Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) correlate with another "entropy-seeking" dynamic to integrate specific instructional or preferential data, reducing out-of-distribution robustness. Conversely, Reinforcement Learning with Verifiable Rewards (RLVR) often exhibits a "compression seeking" dynamic, consolidating reward-aligned behaviors and reducing the entropy in its output distribution. This work establishes the utility of spectral measures of representation geometry for understanding the multiphase learning dynamics within LLMs.
Language Agents Mirror Human Causal Reasoning Biases. How Can We Help Them Think Like Scientists?
Anthony GX-Chen
Dongyan Lin
Mandana Samiei
Rob Fergus
Kenneth Marino
Language Agents Mirror Human Causal Reasoning Biases. How Can We Help Them Think Like Scientists?
Anthony GX-Chen
Dongyan Lin
Mandana Samiei
Rob Fergus
Kenneth Marino
Language model (LM) agents are increasingly used as autonomous decision-makers who need to actively gather information to guide their decisi… (see more)ons. A crucial cognitive skill for such agents is the efficient exploration and understanding of the causal structure of the world -- key to robust, scientifically grounded reasoning. Yet, it remains unclear whether LMs possess this capability or exhibit systematic biases leading to erroneous conclusions. In this work, we examine LMs' ability to explore and infer causal relationships, using the well-established"Blicket Test"paradigm from developmental psychology. We find that LMs reliably infer the common, intuitive disjunctive causal relationships but systematically struggle with the unusual, yet equally (or sometimes even more) evidenced conjunctive ones. This"disjunctive bias"persists across model families, sizes, and prompting strategies, and performance further declines as task complexity increases. Interestingly, an analogous bias appears in human adults, suggesting that LMs may have inherited deep-seated reasoning heuristics from their training data. To this end, we quantify similarities between LMs and humans, finding that LMs exhibit adult-like inference profiles (but not children-like). Finally, we propose a test-time sampling method which explicitly samples and eliminates hypotheses about causal relationships from the LM. This scalable approach significantly reduces the disjunctive bias and moves LMs closer to the goal of scientific, causally rigorous reasoning.
Steering CLIP's vision transformer with sparse autoencoders
Sonia Joseph
Praneet Suresh
Ethan Goldfarb
Lorenz Hufe
Yossi Gandelsman
Robert Graham
Wojciech Samek
While vision models are highly capable, their internal mechanisms remain poorly understood-- a challenge which sparse autoencoders (SAEs) ha… (see more)ve helped address in language, but which remains underexplored in vision. We address this gap by training SAEs on CLIP's vision transformer and uncover key differences between vision and language processing, including distinct sparsity patterns for SAEs trained across layers and token types. We then provide the first systematic analysis of the steerability of CLIP's vision transformer by introducing metrics to quantify how precisely SAE features can be steered to affect the model's output. We find that 10-15% of neurons and features are steerable, with SAEs providing thousands more steerable features than the base model. Through targeted suppression of SAE features, we then demonstrate improved performance on three vision disentanglement tasks (CelebA, Waterbirds, and typographic attacks), finding optimal disentanglement in middle model layers, and achieving state-of-the-art performance on defense against typographic attacks. We release our CLIP SAE models and code to support future research in vision transformer interpretability.
Multi-agent cooperation through learning-aware policy gradients
Alexander Meulemans
Seijin Kobayashi
Johannes Von Oswald
Nino Scherrer
Eric Elmoznino
Blaise Aguera y Arcas
João Sacramento
Self-interested individuals often fail to cooperate, posing a fundamental challenge for multi-agent learning. How can we achieve cooperation… (see more) among self-interested, independent learning agents? Promising recent work has shown that in certain tasks cooperation can be established between learning-aware agents who model the learning dynamics of each other. Here, we present the first unbiased, higher-derivative-free policy gradient algorithm for learning-aware reinforcement learning, which takes into account that other agents are themselves learning through trial and error based on multiple noisy trials. We then leverage efficient sequence models to condition behavior on long observation histories that contain traces of the learning dynamics of other agents. Training long-context policies with our algorithm leads to cooperative behavior and high returns on standard social dilemmas, including a challenging environment where temporally-extended action coordination is required. Finally, we derive from the iterated prisoner's dilemma a novel explanation for how and when cooperation arises among self-interested learning-aware agents.
Multi-session, multi-task neural decoding from distinct cell-types and brain regions
Mehdi Azabou
Krystal Xuejing Pan
Vinam Arora
Ian Jarratt Knight
Eva L Dyer
Recent work has shown that scale is important for improved brain decoding, with more data leading to greater decoding accuracy. However, lar… (see more)ge-scale decoding across many different datasets is challenging because neural circuits are heterogeneous---each brain region contains a unique mix of cellular sub-types, and the responses to different stimuli are diverse across regions and sub-types. It is unknown whether it is possible to pre-train and transfer brain decoding models between distinct tasks, cellular sub-types, and brain regions. To address these questions, we developed a multi-task transformer architecture and trained it on the entirety of the Allen Institute's Brain Observatory dataset. This dataset contains responses from over 100,000 neurons in 6 areas of the brains of mice, observed with two-photon calcium imaging, recorded while the mice observed different types of visual stimuli. Our results demonstrate that transfer is indeed possible -combining data from different sources is beneficial for a number of downstream decoding tasks. As well, we can transfer the model between regions and sub-types, demonstrating that there is in fact common information in diverse circuits that can be extracted by an appropriately designed model. Interestingly, we found that the model's latent representations showed clear distinctions between different brain regions and cellular sub-types, even though it was never given any information about these distinctions. Altogether, our work demonstrates that training a large-scale neural decoding model on diverse data is possible, and this provides a means of studying the differences and similarities between heterogeneous neural circuits.
The oneirogen hypothesis: modeling the hallucinatory effects of classical psychedelics in terms of replay-dependent plasticity mechanisms
Colin Bredenberg
Fabrice Normandin
Classical psychedelics induce complex visual hallucinations in humans, generating percepts that are co-herent at a low level, but which have… (see more) surreal, dream-like qualities at a high level. While there are many hypotheses as to how classical psychedelics could induce these effects, there are no concrete mechanistic models that capture the variety of observed effects in humans, while remaining consistent with the known pharmacological effects of classical psychedelics on neural circuits. In this work, we propose the “oneirogen hypothesis”, which posits that the perceptual effects of classical psychedelics are a result of their pharmacological actions inducing neural activity states that truly are more similar to dream-like states. We simulate classical psychedelics’ effects via manipulating neural network models trained on perceptual tasks with the Wake-Sleep algorithm. This established machine learning algorithm leverages two activity phases, a perceptual phase (wake) where sensory inputs are encoded, and a generative phase (dream) where the network internally generates activity consistent with stimulus-evoked responses. We simulate the action of psychedelics by partially shifting the model to the ‘Sleep’ state, which entails a greater influence of top-down connections, in line with the impact of psychedelics on apical dendrites. The effects resulting from this manipulation capture a number of experimentally observed phenomena including the emergence of hallucinations, increases in stimulus-conditioned variability, and large increases in synaptic plasticity. We further provide a number of testable predictions which could be used to validate or invalidate our oneirogen hypothesis.
Top-down feedback matters: Functional impact of brainlike connectivity motifs on audiovisual integration
Mashbayar Tugsbayar
Mingze Li
Artificial neural networks (ANNs) are an important tool for studying neural computation, but many features of the brain are not captured by … (see more)standard ANN architectures. One notable missing feature in most ANN models is top-down feedback, i.e. projections from higher-order layers to lower-order layers in the network. Top-down feedback is ubiquitous in the brain, and it has a unique modulatory impact on activity in neocortical pyramidal neurons. However, we still do not understand its computational role. Here we develop a deep neural network model that captures the core functional properties of top-down feedback in the neocortex, allowing us to construct hierarchical recurrent ANN models that more closely reflect the architecture of the brain. We use this to explore the impact of different hierarchical recurrent architectures on an audiovisual integration task. We find that certain hierarchies, namely those that mimic the architecture of the human brain, impart ANN models with a light visual bias similar to that seen in humans. This bias does not impair performance on the audiovisual tasks. The results further suggest that different configurations of top-down feedback make otherwise identically connected models functionally distinct from each other, and from traditional feedforward-only models. Altogether our findings demonstrate that modulatory top-down feedback is a computationally relevant feature of biological brains, and that incorporating it into ANNs can affect their behavior and helps to determine the solutions that the network can discover.
Brain-like learning with exponentiated gradients
Jonathan Cornford
Roman Pogodin
Arna Ghosh
Kaiwen Sheng
Brendan A. Bicknell
Olivier Codol
Beverley A. Clark
Top-down feedback matters: Functional impact of brainlike connectivity motifs on audiovisual integration
Mashbayar Tugsbayar
Mingze Li