Diganta Misra
YOU?
Author Swipe
View article: FreshBrew: A Benchmark for Evaluating AI Agents on Java Code Migration
FreshBrew: A Benchmark for Evaluating AI Agents on Java Code Migration Open
AI coding assistants are rapidly becoming integral to modern software development. A key challenge in this space is the continual need to migrate and modernize codebases in response to evolving software ecosystems. Traditionally, such migr…
View article: GitChameleon 2.0: Evaluating AI Code Generation Against Python Library Version Incompatibilities
GitChameleon 2.0: Evaluating AI Code Generation Against Python Library Version Incompatibilities Open
The rapid evolution of software libraries poses a considerable hurdle for code generation, necessitating continuous adaptation to frequent version updates while preserving backward compatibility. While existing code evolution benchmarks pr…
View article: Bridging the Data Provenance Gap Across Text, Speech and Video
Bridging the Data Provenance Gap Across Text, Speech and Video Open
Progress in AI is driven largely by the scale and quality of training data. Despite this, there is a deficit of empirical analysis examining the attributes of well-established datasets beyond text. In this work we conduct the largest and f…
View article: GitChameleon: Unmasking the Version-Switching Capabilities of Code Generation Models
GitChameleon: Unmasking the Version-Switching Capabilities of Code Generation Models Open
The rapid evolution of software libraries presents a significant challenge for code generation models, which must adapt to frequent version updates while maintaining compatibility with previous versions. Existing code completion benchmarks…
View article: Consent in Crisis: The Rapid Decline of the AI Data Commons
Consent in Crisis: The Rapid Decline of the AI Data Commons Open
General-purpose artificial intelligence (AI) systems are built on massive swathes of public web data, assembled into corpora such as C4, RefinedWeb, and Dolma. To our knowledge, we conduct the first, large-scale, longitudinal audit of the …
View article: Just Say the Name: Online Continual Learning with Category Names Only via Data Generation
Just Say the Name: Online Continual Learning with Category Names Only via Data Generation Open
Requiring extensive human supervision is often impractical for continual learning due to its cost, leading to the emergence of 'name-only continual learning' that only provides the name of new concepts (e.g., classes) without providing sup…
View article: Uncovering the Hidden Cost of Model Compression
Uncovering the Hidden Cost of Model Compression Open
In an age dominated by resource-intensive foundation models, the ability to efficiently adapt to downstream tasks is crucial. Visual Prompting (VP), drawing inspiration from the prompting techniques employed in Large Language Models (LLMs)…
View article: Challenging Common Assumptions about Catastrophic Forgetting
Challenging Common Assumptions about Catastrophic Forgetting Open
Building learning agents that can progressively learn and accumulate knowledge is the core goal of the continual learning (CL) research field. Unfortunately, training a model on new data usually compromises the performance on past data. In…
View article: APP: Anytime Progressive Pruning
APP: Anytime Progressive Pruning Open
With the latest advances in deep learning, there has been a lot of focus on the online learning paradigm due to its relevance in practical settings. Although many methods have been investigated for optimal learning settings in scenarios wh…
View article: Rotate to Attend: Convolutional Triplet Attention Module
Rotate to Attend: Convolutional Triplet Attention Module Open
Benefiting from the capability of building inter-dependencies among channels or spatial locations, attention mechanisms have been extensively studied and broadly used in a variety of computer vision tasks recently. In this paper, we invest…
View article: Mish: A Self Regularized Non-Monotonic Neural Activation Function
Mish: A Self Regularized Non-Monotonic Neural Activation Function Open
The concept of non-linearity in a Neural Network is introduced by an
activation function which serves an integral role in the training and
performance evaluation of the network. Over the years of theoretical research,
many activation funct…
View article: Mish: A Self Regularized Non-Monotonic Activation Function
Mish: A Self Regularized Non-Monotonic Activation Function Open
We propose $\textit{Mish}$, a novel self-regularized non-monotonic activation function which can be mathematically defined as: $f(x)=x\tanh(softplus(x))$. As activation functions play a crucial role in the performance and training dynamics…
View article: Advanced Image Processing for Astronomical Images
Advanced Image Processing for Astronomical Images Open
Image Processing in Astronomy is a major field of research and involves a lot of techniques pertaining to improve analyzing the properties of the celestial objects or obtaining preliminary inference from the image data. In this paper, we p…
View article: Image Processing on IOPA Radiographs: A comprehensive case study on Apical Periodontitis
Image Processing on IOPA Radiographs: A comprehensive case study on Apical Periodontitis Open
With the recent advancements in Image Processing Techniques and development of new robust computer vision algorithms, new areas of research within Medical Diagnosis and Biomedical Engineering are picking up pace. This paper provides a comp…