8 citations · 8 across the 9 of their papers we have counts for
9 papers
Improving Robustness In Sparse Autoencoders via Masked Regularization
Vivek Narayanaswamy, Kowshik Thopalli, Bhavya Kailkhura +1
Sparse autoencoders (SAEs) are widely used in mechanistic interpretability to project LLM activations onto sparse latent spaces. However, sparsity alone is an imperfect proxy for i…
ProtAlign: Contrastive learning paradigm for Sequence and structure alignment
Aditya Ranganath, Hasin Us Sami, Kowshik Thopalli +2
Protein language models often take into consideration the alignment between a protein sequence and its textual description. However, they do not take structural information into co…
Interpretable and Steerable Concept Bottleneck Sparse Autoencoders
Akshay Kulkarni, Tsui-Wei Weng, Vivek Narayanaswamy +3
Sparse autoencoders (SAEs) promise a unified approach for mechanistic interpretability, concept discovery, and model steering in LLMs and LVLMs. However, realizing this potential r…
VERIRAG: A Post-Retrieval Auditing of Scientific Study Summaries
Shubham Mohole, Hongjun Choi, Shusen Liu +6
Can democratized information gatekeepers and community note writers effectively decide what scientific information to amplify? Lacking domain expertise, such gatekeepers rely on au…
Leveraging Registers in Vision Transformers for Robust Adaptation
Srikar Yellapragada, Kowshik Thopalli, Vivek Narayanaswamy +5
Vision Transformers (ViTs) have shown success across a variety of tasks due to their ability to capture global image representations. Recent studies have identified the existence o…
On the Use of Anchoring for Training Vision Models
Vivek Narayanaswamy, Kowshik Thopalli, Rushil Anirudh +3
Anchoring is a recent, architecture-agnostic principle for training deep neural networks that has been shown to significantly improve uncertainty estimation, calibration, and extra…
On-the-fly Object Detection using StyleGAN with CLIP Guidance
Yuzhe Lu, Shusen Liu, Jayaraman J. Thiagarajan +2
We present a fully automated framework for building object detectors on satellite imagery without requiring any human annotation or intervention. We achieve this by leveraging the…
Low Shot Learning with Untrained Neural Networks for Imaging Inverse Problems
Oscar Leong, Wesam Sakla
Employing deep neural networks as natural image priors to solve inverse problems either requires large amounts of data to sufficiently train expressive generative models or can suc…
Remote Sensor Design for Visual Recognition with Convolutional Neural Networks
Lucas Jaffe, Michael Zelinski, Wesam Sakla
While deep learning technologies for computer vision have developed rapidly since 2012, modeling of remote sensing systems has remained focused around human vision. In particular,…