Publications

Understanding computations in the visual system requires a characterization of the distinct feature preferences of neurons in different visu… (see more)al cortical areas. However, we know little about how feature preferences of neurons within a given area relate to that area’s role within the global organization of visual cortex. To address this, we recorded from thousands of neurons across six visual cortical areas in mouse and leveraged generative AI methods combined with closed-loop neuronal recordings to identify each neuron’s visual feature preference. First, we discovered that the mouse’s visual system is globally organized to encode features in a manner invariant to the types of image transformations induced by self-motion. Second, we found differences in the visual feature preferences of each area and that these differences generalized across animals. Finally, we observed that a given area’s collection of preferred stimuli (‘own-stimuli’) drive neurons from the same area more effectively through their dynamic range compared to preferred stimuli from other areas (‘other-stimuli’). As a result, feature preferences of neurons within an area are organized to maximally encode differences among own-stimuli while remaining insensitive to differences among other-stimuli. These results reveal how visual areas work together to efficiently encode information about the external world.

2023-11-05

bioRxiv (preprint)

doi.org

Score-Based Likelihood Characterization for Inverse Problems in the Presence of Non-Gaussian Noise

Ronan Legin

Alexandre Adam

Yashar Hezaveh

Laurence Perreault-Levasseur

Likelihood analysis is typically limited to normally distributed noise due to the difficulty of determining the probability density function… (see more) of complex, high-dimensional, non-Gaussian, and anisotropic noise. This work presents Score-based LIkelihood Characterization (SLIC), a framework that resolves this issue by building a data-driven noise model using a set of noise realizations from observations. We show that the approach produces unbiased and precise likelihoods even in the presence of highly non-Gaussian correlated and spatially varying noise. We use diffusion generative models to estimate the gradient of the probability density of noise with respect to data elements. In combination with the Jacobian of the physical model of the signal, we use Langevin sampling to produce independent samples from the unbiased likelihood. We demonstrate the effectiveness of the method using real data from the Hubble Space Telescope and James Webb Space Telescope.

2023-11-03

NeurIPS.cc/2023/Workshop/Deep_Inverse (poster)

openreview.net

Empowering Clinicians with MeDT: A Framework for Sepsis Treatment

Aamer Abdul Rahman

Pranav Agarwal

Vincent Michalski

Rita Noumeir

Samira Ebrahimi Kahou

2023-11-02

NeurIPS.cc/2023/Workshop/GCRL (published)

openreview.net

Goal Misgeneralization as Implicit Goal Conditioning

Diego Dorn

Neel Alex

David Scott Krueger

2023-11-02

NeurIPS.cc/2023/Workshop/GCRL (published)

openreview.net

How does fine-tuning affect your model? Mechanistic analysis on procedural tasks

Samyak Jain

Robert Kirk

Ekdeep Singh Lubana

Robert P. Dick

Hidenori Tanaka

Tim Rocktäschel

Edward Grefenstette

David Scott Krueger

Fine-tuning large pre-trained models has become the *de facto* strategy for developing models that are safe to deploy. However, there has be… (see more)en little work that explains how fine-tuning alters the underlying capabilities learnt by a model during pretraining: does fine-tuning yield entirely novel capabilities or does it just modulate existing ones? We address this question empirically in *synthetic* settings with mechanistic interpretability tools (e.g., network pruning and probing) to understand how the model's underlying capabilities are changing. Our extensive analysis of the effects of fine-tuning shows: (i) fine-tuning rarely alters the underlying model capabilities; (ii) a minimal transformation, which we call a 'wrapper', is typically learned on top of the underlying model capabilities; and (iii) further fine-tuning on a task where such wrapped capabilities are relevant leads to sample-efficient "revival'' of the capability, i.e., the model begins reusing this capability in a few gradient steps. *This indicates practitioners can unintentionally remove a model's safety wrapper by merely fine-tuning it on a superficially unrelated task.* We additionally perform analysis on language models trained on the TinyStories dataset to support our claims in a more realistic setup.

2023-11-02

NeurIPS.cc/2023/Workshop/UniReps (poster)

openreview.net

Multimodal and Force-Matched Imitation Learning with a See-Through Visuotactile Sensor

Trevor Ablett

Oliver Limoyo

Adam Sigal

Affan Jilani

Jonathan Kelly

Kaleem Siddiqi

Francois Hogan

Gregory Dudek

Kinesthetic Teaching is a popular approach to collecting expert robotic demonstrations of contact-rich tasks for imitation learning (IL), bu… (see more)t it typically only measures motion, ignoring the force placed on the environment by the robot. Furthermore, contact-rich tasks require accurate sensing of both reaching and touching, which can be difficult to provide with conventional sensing modalities. We address these challenges with a See-Through-your-Skin (STS) visuotactile sensor, using the sensor both (i) as a measurement tool to improve kinesthetic teaching, and (ii) as a policy input in contact-rich door manipulation tasks. An STS sensor can be switched between visual and tactile modes by leveraging a semi-transparent surface and controllable lighting, allowing for both pre-contact visual sensing and during-contact tactile sensing with a single sensor. First, we propose tactile force matching, a methodology that enables a robot to match forces read during kinesthetic teaching using tactile signals. Second, we develop a policy that controls STS mode switching, allowing a policy to learn the appropriate moment to switch an STS from its visual to its tactile mode. Finally, we study multiple observation configurations to compare and contrast the value of visual and tactile data from an STS with visual data from a wrist-mounted eye-in-hand camera. With over 3,000 test episodes from real-world manipulation experiments, we find that the inclusion of force matching raises average policy success rates by 62.5%, STS mode switching by 30.3%, and STS data as a policy input by 42.5%. Our results highlight the utility of see-through tactile sensing for IL, both for data collection to allow force matching, and for policy execution to allow accurate task feedback.

2023-11-02

ArXiv (preprint)

arxiv.org

Is Bigger Always Better? Democratizing AI Protein Discovery

AI Policy Compass

Supervision Requests

Publications

Is Bigger Always Better? Democratizing AI Protein Discovery

AI Policy Compass

Supervision Requests

Popular keywords:

Publications