Publications

QGFN: Controllable Greediness with Action Values
Elaine Lau
Stephen Zhewen Lu
Ling Pan
Doina Precup
Emmanuel Bengio
Generative Flow Networks (GFlowNets; GFNs) are a family of reward/energy-based generative methods for combinatorial objects, capable of gene… (see more)rating diverse and high-utility samples. However, biasing GFNs towards producing high-utility samples is non-trivial. In this work, we leverage connections between GFNs and reinforcement learning (RL) and propose to combine the GFN policy with an action-value estimate,
2024-06-17
ICML.cc/2024/Workshop/SPIGM (poster)
doi.org
openreview.net
Reframing linguistic bootstrapping as joint inference using visually-grounded grammar induction models
Eva Portelance
Siva Reddy
Timothy John O'donnell
Semantic and syntactic bootstrapping posit that children use their prior knowledge of one linguistic domain, say syntactic relations, to hel… (see more)p later acquire another, such as the meanings of new words. Empirical results supporting both theories may tempt us to believe that these are different learning strategies, where one may precede the other. Here, we argue that they are instead both contingent on a more general learning strategy for language acquisition: joint learning. Using a series of neural visually-grounded grammar induction models, we demonstrate that both syntactic and semantic bootstrapping effects are strongest when syntax and semantics are learnt simultaneously. Joint learning results in better grammar induction, realistic lexical category learning, and better interpretations of novel sentence and verb meanings. Joint learning makes language acquisition easier for learners by mutually constraining the hypotheses spaces for both syntax and semantics. Studying the dynamics of joint inference over many input sources and modalities represents an important new direction for language modeling and learning research in both cognitive sciences and AI, as it may help us explain how language can be acquired in more constrained learning settings.
2024-06-17
ArXiv (preprint)
doi.org
arxiv.org
RepLiQA: A Question-Answering Dataset for Benchmarking LLMs on Unseen Reference Content
Joao Monteiro
Pierre-Andre Noel
Étienne Marcotte
Sai Rajeswar
Valentina Zantedeschi
David Vazquez
Nicolas Chapados
Chris Pal
Perouz Taslakian
Large Language Models (LLMs) are trained on vast amounts of data, most of which is automatically scraped from the internet. This data includ… (see more)es encyclopedic documents that harbor a vast amount of general knowledge (e.g., Wikipedia) but also potentially overlap with benchmark datasets used for evaluating LLMs. Consequently, evaluating models on test splits that might have leaked into the training set is prone to misleading conclusions. To foster sound evaluation of language models, we introduce a new test dataset named RepLiQA, suited for question-answering and topic retrieval tasks. RepLiQA is a collection of five splits of test sets, four of which have not been released to the internet or exposed to LLM APIs prior to this publication. Each sample in RepLiQA comprises (1) a reference document crafted by a human annotator and depicting an imaginary scenario (e.g., a news article) absent from the internet; (2) a question about the document's topic; (3) a ground-truth answer derived directly from the information in the document; and (4) the paragraph extracted from the reference document containing the answer. As such, accurate answers can only be generated if a model can find relevant content within the provided document. We run a large-scale benchmark comprising several state-of-the-art LLMs to uncover differences in performance across models of various types and sizes in a context-conditional language modeling setting. Released splits of RepLiQA can be found here: https://huggingface.co/datasets/ServiceNow/repliqa.
2024-06-17
ArXiv (preprint)
doi.org
arxiv.org
Revisiting Successor Features for Inverse Reinforcement Learning
Arnav Kumar Jain
Harley Wiltzer
Jesse Farebrother
Irina Rish
Glen Berseth
Sanjiban Choudhury
2024-06-17
ICML.cc/2024/Workshop/MFHAIA (poster)
openreview.net
openreview.net
On The Local Geometry of Deep Generative Manifolds
Ahmed Imtiaz Humayun
Ibtihel Amara
Candice Schumann
Golnoosh Farnadi
Negar Rostamzadeh
Mohammad Havaei
In this paper, we study theoretically inspired local geometric descriptors of the data manifolds approximated by pre-trained generative mode… (see more)ls. The descriptors – local scaling (ψ), local rank (ν), and local complexity (δ) — characterize the uncertainty, dimensionality, and smoothness on the learned manifold, using only the network weights and architecture. We investigate and emphasize their critical role in understanding generative models. Our analysis reveals that the local geometry is intricately linked to the quality and diversity of generated outputs. Additionally, we see that the geometric properties are distinct for out-of-distribution (OOD) inputs as well as for prompts memorized by Stable Diffusion, showing the possible application of our proposed descriptors for downstream detection and assessment of pre-trained generative models.
2024-06-17
ICML.cc/2024/Workshop/GRaM (published)
openreview.net
openreview.net
Using neural biomarkers to personalize dosing of vagus nerve stimulation
Antonin Berthon
Lorenz Wernisch
Myrta Stoukidi
Michael Thornton
Olivier Tessier-Lariviere
Pascal Fortier-Poisson
Jorin Mamen
Max Pinkney
Susannah Lee
Elvijs Sarkans
Luca Annecchino
Ben Appleton
Philip Garsed
Bret Patterson
Samuel Gonshaw
Matjaž Jakopec
Sudhakaran Shunmugam
Tristan Edwards
Aleksi Tukiainen
Joel Jennings … (see 3 more)
Guillaume Lajoie
Emil Hewage
Oliver Armitage
2024-06-17
Bioelectronic Medicine (published)
doi.org
Cell Morphology-Guided Small Molecule Generation with GFlowNets
Stephen Zhewen Lu
Ziqing Lu
Ehsan Hajiramezanali
Tommaso Biancalani
Yoshua Bengio
Gabriele Scalia
Michał Koziarski
2024-06-16
ICML.cc/2024/Workshop/AI4Science (poster)
doi.org
openreview.net
Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional Understanding
Le Zhang
Rabiul Awal
Aishwarya Agrawal
Vision-Language Models (VLMs), such as CLIP, exhibit strong image-text comprehension abilities, facilitating advances in several downstream … (see more)tasks such as zero-shot image classification, image-text retrieval, and text-to-image generation. However, the compositional reasoning abilities of existing VLMs remains subpar. The root of this limitation lies in the inadequate alignment between the images and captions in the pretraining datasets. Additionally, the current contrastive learning objective fails to focus on fine-grained grounding components like relations, actions, and attributes, resulting in"bag-of-words"representations. We introduce a simple and effective method to improve compositional reasoning in VLMs. Our method better leverages available datasets by refining and expanding the standard image-text contrastive learning framework. Our approach does not require specific annotations and does not incur extra parameters. When integrated with CLIP, our technique yields notable improvement over state-of-the-art baselines across five vision-language compositional benchmarks. We open-source our code at https://github.com/lezhang7/Enhance-FineGrained.
2024-06-16
2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (published)
doi.org
arxiv.org
Expressivity of Neural Networks with Fixed Weights and Learned Biases
Ezekiel Williams
Avery Hee-Woon Ryoo
Thomas Jiralerspong
Alexandre Payeur
Matt Perich
Luca Mazzucato
Guillaume Lajoie
2024-06-16
ICML.cc/2024/Workshop/HiLD (poster)
openreview.net
openreview.net
Gradient descent induces alignment between weights and the pre-activation tangents for deep non-linear networks
Daniel Beaglehole
Ioannis Mitliagkas
Atish Agarwala
Understanding the mechanisms through which neural networks extract statistics from input-label pairs is one of the most important unsolved p… (see more)roblems in supervised learning. Prior works have identified that the gram matrices of the weights in trained neural networks of general architectures are proportional to the average gradient outer product of the model, in a statement known as the Neural Feature Ansatz (NFA). However, the reason these quantities become correlated during training is poorly understood. In this work, we clarify the nature of this correlation and explain its emergence at early training times. We identify that the NFA is equivalent to alignment between the left singular structure of the weight matrices and the newly defined pre-activation tangent kernel. We identify a centering of the NFA that isolates this alignment and is robust to initialization scale. We show that, through this centering, the speed of NFA development can be predicted analytically in terms of simple statistics of the inputs and labels.
2024-06-16
ICML.cc/2024/Workshop/HiLD (poster)
openreview.net
openreview.net
Gradient Dissent in Language Model Training and Saturation
Andrei Mircea
Ekaterina Lobacheva
Irina Rish
We seek to shed light on language model (LM) saturation from the perspective of learning dynamics. To this end, we define a decomposition o… (see more)f the cross-entropy gradient, which forms a shared low-dimensional basis for analyzing the training dynamics of models across scales. Intuitively, this decomposition consists of attractive and repulsive components that increase the logit of the correct class and decrease the logits of incorrect classes, respectively. Our analysis in this subspace reveals a phenomenon we term \textit{gradient dissent}, characterized by gradient components becoming systematically opposed such that loss cannot be improved along one component without being degraded along the other. Notably, we find that complete opposition, which we term \textit{total dissent}, reliably occurs in tandem with the saturation of smaller LMs. Based on these results, we hypothesize that gradient dissent can provide a useful foundation for better understanding and mitigating saturation.
2024-06-16
ICML.cc/2024/Workshop/HiLD (poster)
openreview.net
openreview.net
Inpainting Galaxy Counts onto N-Body Simulations over Multiple Cosmologies and Astrophysics
Antoine Bourdin
Ronan Legin
Matthew Ho
Alexandre Adam
Yashar Hezaveh
Laurence Perreault-Levasseur
2024-06-16
ICML.cc/2024/Workshop/AI4Science (poster)
openreview.net
openreview.net