News

One paper accepted to the ICML 2025! Reach out to corresponding authors, Suchith Prabhu or Bhavyajeet Singh to know more! Here’s a summary of the work:

---

In a text classification task, given a query, we aim to predict the labels relevant to that query. In many cases, additional information about the query or the label is available (called metadata or memory) and can be leveraged to make better predictions. Currently popular methods, such as RAG, which retrieve this metadata, and augment it with the model input for classification or generation, tend to have high latency and are sensitive to noise. We propose a two-stage technique to utilize this extra information while also meeting the latency constraints. First, we train a powerful oracle model that takes advantage of the metadata assuming a best-case scenario where this information is also available during inference. Then, we train an off-the-shelf classifier model as a disciple that learns to mimic the behaviour of the oracle, but under a more challenging scenario, wherein the metadata is not know apriori. In this way, we get the best of both worlds ? A model that is both efficient and fast, while benefiting from the improved accuracy gained by learning from the powerful oracle model. We observe that this training technique (which we call Metadata-infused Oracle Guidance for Improving Classification, or MOGIC) improves overall accuracy of any existing classifier, while also offering a novel approach to incorporating extra information into the classification settings.

One paper accepted to the Industry track at The WebConf 2025! Reach out to corresponding author and key contributor, Anshul Mittal to know more!

My Ph.D. Thesis was awarded the IUPRAI Doctoral Dissertation Award 23 in the Pattern Recognition and Machine Learning discipline. The award consists of a Certificate which was presented at the Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP) at IIITB from 13th to 15th December, 2024. A big shout out to Chandra Sir for receiving the certificate on my behalf (I was at NeurIPS 2024 during the award ceremony!)

I was awarded the IEI Young Engineers Award 2024-25 in the Computer Engineering discipline. The award consists of a Plaque and a Certificate which was presented during the inaugural session of the 37th National Convention of Computer Engineers at Chandigarh, November 22-23, 2024.

One paper accepted to the NeurIPS 2024 ENLSP Workshop! See you in Vancouver, Canada!! Yet again, reach out to corresponding author and key contributor, Bhawna Paliwal to know more!

One paper accepted to the EMNLP WiNLP 2024 Workshop! Reach out to corresponding author and key contributor, Bhawna Paliwal to know more!

One paper accepted to ACM KDD 2024! .See you in Barcelona, Spain Reach out to corresponding author and key contributor, Sachin Yadav to know more!

My Ph.D. research received the Prof. Satish Dhawan Research Award for the year 2023, for my contributions relating generative adversarial networks and diffusion models to high-dimension interpolation, Fourier approximations, and partial differential equations in very large dimensional space. For mode details, check out the Official Website

Interested in listening in on my research on GANs, high-dimensional Variational Calclulus, Fourier theory, and score-based Langevin Sampling? Be sure to check out the entire recording on Youtube: