Ekdeep Singh Lubana

I am a postdoc at Harvard University as part of the CBS-NTT Program on Physics of Intelligence. I did my PhD co-affiliated with EECS, University of Michigan and CBS, Harvard, and was advised by Robert Dick and Hidenori Tanaka.

I am generally interested in designing (faithful) abstractions of phenomena relevant to controlling or aligning neural networks. I am also very interested in better understanding training dynamics of neural networks, especially via a statistical physics perspective.

I graduated with a Bachelor's degree in ECE from Indian Institute of Technology (IIT), Roorkee in 2019. My research in undergraduate was primarily focused on embedded systems, such as energy-efficient machine vision systems.

Email  /  CV  /  Google Scholar  /  Github

We use Formal languages to analyze the limitations of SAEs, finding, similar to prior work in disentangled representation learning, that SAEs find correlational features; explicit biasing is necessary to induce causality.

We instantiate a synthetic knowledge graph domain to study how model editing protocols harm broader capabilities, demonstrating all representational organization of different concepts is destroyed under counterfactul edits.

We create a theoretical abstraction of our prior work on compositional generalization and justify the peculiar learning dynamics observed therein, finding there was in fact a quadruple descent embedded therein!

We implicate rapid acquisition of structures underlying the data generating process as the source of sudden learning of capabilities, and analogize knowledge centric capabilities to the process of graph percolation that undergoes a formal second-order phase transition.

We analyze a model's learning dynamics in "concept space" and identify sudden transitions where the model, when latently intervened, demonstrates a capability, even if input prompting does not show said capability.

We use formal languages as a model system to identify the mechanistic changes induced by safety fine-tuning, and how jailbreaks bypass said mechanisms, verifying our claims on Llama models.

We show the acquisition of structures underlying a data-generating process is the driving cause for abrupt learning in Transformers.

We identify and discuss 18 foundational challenges in assuring the alignment and safety of large language models (LLMs) and pose 200+ concrete research questions.

We formalize and define a notion of composition of primitive capabilities learned via autoregressive modeling by a Transformer, showing the model's capabilities can "explode", i.e., combinatorially increase if it can compose.

We cast stepwise inference methods in LLMs as a graph navigation task, finding a synthetic model is sufficient to explain and identify novel characteristics of such methods.

We show fine-tuning leads to learning of minimal transformations of a pretrained model's capabilities, like a "wrapper", by using procedural tasks defined using Tracr, PCFGs, and TinyStories.

We analyze different LLMs' abilities to model binary sequences generated via different pseduo-random processes, such as a formal automaton, and find that with scale, LLMs are (almost) able to simulate these processes via mere context conditioning.

We propose and analyze a pipeline for re-casting an LLM as a generic reward function that interacts with an LVM to enable embodied AI tasks.

We analyze compositionality in diffusion models, showing that there is a sudden emergence of this capability if models are allowed sufficient training to learn the relevant primitive capabilities.

We show models that rely on entirely different mechanisms for making their predictions can exhibit mode connectivity, but generally the ones that are mechanistically similar are linearly connected.

We present a highly detailed analysis of the landscape of several self-supervised learning objectives to clarify the role of representational collapse.

We propose a theoretical framework that demonstrates limitations of popular graph augmentation strategies for self-supervised learning.

We propose an unsupervised learning method that exploits client heterogeneity to enable privacy preserving, SOTA performance unsupervised federated learning.

We develop a general theory to understand the role of normalization layers in improving training dynamics of a neural network at initialization.

This work demonstrates how quadratic regularization methods for preventing catastrophic forgetting in deep networks rely on a simple heuristic under-the-hood: Interpolation.

A unified, theoretically-grounded framework for network pruning that helps justify often used heuristics in the field.

An image signal processing pipeline that allows use of out-of-the-box deep neural networks on RAW images directly retrieved from image sensors.

An energy-efficient machine vision framework inspired by the concept of Fovea in biological vision. Also see follow-up work presented at CVPR workshop, 2020.

An efficient imaging system that accurately calculates chlorophyll content in leaves by using RAW images.

Website template source available here.