Page Not Found
Page not found. Your pixels are in another canvas.
Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
Welcome to my webpage
About me
Page not in menu
This is a page not in th emain menu
Posts
Hello
Published:
This is the first blog post, intended to test this medium out. I don’t intend to write regularly, but will probably put some stuff up from time to time. I intend to mainly focus on things that effort went into, but that couldn’t make it to a full-fledged paper. I may also do some posts about other stuff that’s interesting.
projects
Submodular Subset Selection for Long-Document Question Answering
Using submodular optimization to select spans from long documents.
Blockchain simulation with Selfish and Stubborn Attacks
An extensive blockchain simulator, that can also simulate selfish and stubborn mining attacks.
Automated Data Augmentation for Robustness
Automatically generating augmentions without rules to make Text-to-SQL models more robust.
Theoretical Bounds for Group Testing
Theoretical Performance Guarantees for COVID-19 Group Testing.
Text-to-Speech conversion with Diffusion Models
Using Diffusion Models to convert Text to Speech.
Data Augmentation to break Feedback Loops
Using Data Augmentation to break a negative feedback loop of MetricGANs.
Reverse Dictionary
A Reverse Dictionary + A high quality dataset of (word, meaning) pairs.
Computable Performance Bounds on Sparse Recovery
Tighter, readily verifiable bounds on sparse recovery of signals.
RTL-to-C Decompiler
Recovering source code from the compiled RTL.
Raft Distributed System & Sharded K-V Store
A Golang implemenation of the Raft consensus protocol.
publications
Performance Bounds for LASSO under Multiplicative Noise: Applications to Pooled RT-PCR Testing
Signal Processing, Vol. 214, January 2024, 2023
Performance bounds for Group Testing of, e.g., COVID-19.
Prompted Opinion Summarization with GPT-3.5
ACL 2023 (Findings), 2023
Novel evaluation metrics for summarization in the GPT-3.5 era.
Benchmarking and Improving Text-to-SQL Generation Under Ambiguity
EMNLP 2023 (Main), 2023
Current Text-to-SQL conversion systems fall flat on their face when faced with ambiguity. We demonstrate this by introducing a new benchmark (AmbiQT), then propose a novel method improving coverage by up to 2.5x.
Improving Language Understanding from Screenshots
arXiv 2024, 2024
Multimodal Language Models can’t read well. We introduce a novel patch-and-text loss to remedy that.
The Heuristic Core: Understanding Subnetwork Generalization in Pretrained Language Models
ACL 2024 (Main), 2024
Structured pruning reveals surprising insights about how Pretrained LMs generalize.
Finding Transformer Circuits with Edge Pruning
arXiv 2024, 2024
A faster and more precise circuit-finding method that also scales to multi-billion parameter models.
talks
Talk 1 on Relevant Topic in Your Field
Published:
This is a description of your talk, which is a markdown files that can be all markdown-ified like any other post. Yay markdown!
Conference Proceeding talk 3 on Relevant Topic in Your Field
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
teaching
Teaching experience 1
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Teaching experience 2
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.