CS Katha Barta | ସଂଗଣକ ବିଜ୍ଞାନ କଥା ବାର୍ତା

Hosted by Subhankar Mishra's Lab
People -> Rucha Bhalchandra Joshi, Subhankar Mishra

CS Katha Barta 2025

Upcoming Talks

  1. Dr. Phani Motamarri Assistant Professor, IISc Bangalore
    • Date: November 07 2025, 14:30 hours IST
    • Title: TBD
    • Abstract TBD

  2. Dr. Konduri Aditya Assistant Professor, IISc Bangalore
    • Date: November 14 2025, 15:00 hours IST
    • Title: TBD
    • Abstract TBD

  3. Dr. Chirag Jain Assistant Professor, IISc Bangalore
    • Date: November 21 2025, 14:30 hours IST
    • Title: TBD
    • Abstract TBD

  4. Dr. Yogesh Simmhan Associate Professor, IISc Bangalore
    • Date: January 30 2026, 15:00 hours IST
    • Title: TBD
    • Abstract TBD

  5. Dr. Priyesh Shukla Assistant Professor, IIIT Hyderabad
    • Date: February 13 2026, 15:00 hours IST
    • Title: TBD
    • Abstract TBD

  6. Dr. Adarsh Barik Assistant Professor, IIT Delhi
    • Date: March 13 2026, 15:00 hours IST
    • Title: Sequential Decision Making Under Uncertainty: Parameter-free Algorithms for the Stochastically Extended Adversarial Model
    • Abstract I will discuss the problem of sequential decision making under uncertainty. In particular, I will propose the first parameter-free algorithms and their regret bounds for the Stochastically Extended Adversarial (SEA) model, a framework that bridges adversarial and stochastic online convex optimization. Existing approaches for the SEA model require prior knowledge of problem-specific parameters, such as the diameter of the domain and the Lipschitz constant of the loss functions, which limits their practical applicability. Addressing this, we have developed parameter-free methods by leveraging the Optimistic Online Newton Step (OONS) algorithm to eliminate the need for these parameters. We first establish a comparator-adaptive algorithm for the scenario with unknown domain diameter but known Lipschitz constant, and then extend this to the more general setting where both the diameter and the Lipschitz constant are unknown, attaining the comparator-and Lipschitz-adaptive algorithm.

      Reference: Parameter-free Algorithms for the Stochastically Extended Adversarial Model. Authors: Shuche Wang, Adarsh Barik, Peng Zhao, Vincent Y. F. Tan (Appearing in NeurIPS 2025)

Past Talks

  1. Dr. Vaanathi Sundaresan Assistant Professor, IISc Bangalore
    • Date: October 03 2025, 14:30 hours IST
    • Title: Artificial Intelligence for biomarker extraction in medical images Youtube
    • Abstract The talk will provide an overview of fundamentals of artificial intelligence (AI)-based deep learning models and review a few applications of AI for identifying imaging biomarkers/anomalies on various imaging modalities. Another key discussion point of the talk will be to improve the robustness of the deep learning tools by tackling one of the major practical challenges in the AI-based tool development: limited availability of manually labelled data for training in the low data regimes. The talk will focus on a technique used for synthetic lesion generation in medical imaging for efficient training of anomaly segmentation models. Future avenues of the research include for the detection of anomalies (abnormalities) using multiple diverse imaging modalities, and their classification and uncertainty quantification.

  2. Dr. Jibesh Patra Assistant Professor, IIT Kharagpur
    • Date: August 25 2025, 14:30 hours IST
    • Title: LLMs meet Software Engineering: a Review and Applications Youtube
    • Abstract Large Language Models (LLMs) are rapidly transforming the landscape of software engineering, offering unprecedented capabilities in code generation, analysis, debugging, and maintenance. In this talk, I will provide a brief review of the areas where LLMs have been applied to address various software engineering tasks, highlight key weaknesses that require further research, and conclude with a detailed discussion of a concrete application.

  3. Tanay Narshana Google
    • Date: April 25 2025,
    • Title: Structured pruning of neural networks without access to training data
    • Abstract Deep Learning models have now become ubiquitous. However, the hardware requirements to deploy SoTA models are increasing at a faster rate than what Moore's law can deliver. This makes such models challenging to deploy. Model compression, particularly pruning, is one way to alleviate this problem. Modern, multi-branched neural network architectures often possess complex interconnections like residual connections between layers, which we call coupled channels (CCs). Most existing works are typically designed for pruning single-branch models like VGG-nets. While these methods yield accurate subnetworks, the improvements in inference times, when applied to multi-branch networks, are comparatively modest. These methods do not prune CCs, which we observe contribute significantly to inference time. Moreover, pruning without access to training data is challenging and is gaining traction owing to privacy concerns and computational costs associated with fine-tuning. In this talk, we will see some recent advances towards pruning neural networks without access to training data.
  4. Dr. Abhishek Singh Accenture
    • Date: April 11 2025, 11:00 hours IST
    • Title: Multi-Agent Retrieval-Augmented Generation (RAG): A Collaborative AI Framework for Enhanced Information Processing Youtube
    • Abstract Multi-Agent Retrieval-Augmented Generation (RAG) enhances AI-driven reasoning by combining specialized agents for retrieval, analysis, and content generation. This collaborative approach improves accuracy, minimizes hallucinations, and scales efficiently across applications like research assistants, legal analysis, and customer support. This talk explores multi-agent RAG’s architecture, benefits over single-agent models, and key challenges, including agent coordination and retrieval bias. We discuss optimization strategies, reinforcement learning for self-improvement, and future research directions. Multi-agent RAG represents the next step in intelligent, fact-based AI reasoning, bridging structured retrieval with advanced generative capabilities.
  5. Dr. Rucha Deshpande Research Affiliate, University of Illinois Urbana-Champaign
    • Date: April 04 2025, 16:00 hours IST
    • Title: Multi-stage evaluation of generative models in biomedical imaging Datasets
    • Abstract Generative models have the potential to revolutionize biomedical imaging. However, in this mission-critical domain, the evaluation of generative models is imperative to ensure patient safety. Designing evaluation frameworks for generative models is essential at different stages in the biomedical-tool development process. In this talk, I will focus on generative models of images for data augmentation applications. I will discuss the limitations of some existing approaches and present some of my work on (i) rule-out tests, (ii) in-silico testing and (iii) post-hoc testing for clinical datasets.
  6. Dr. Pascal Welke Assistant Professor for Data Science, Lancaster University , Leipzig
    • Date: March 21 2025, 14:30 hours IST
    • Title: Expressive Graph Embeddings via Homomorphism Counts Youtube Slides
    • Abstract I will give a high-level overview of graph representation learning that uses homomorphism counting in one way or the other. Homomorphism counting is a way to measure 'how often' a given pattern appears in a graph. In the context of (message passing) graph neural networks (GNNs), homomorphism counting is mainly used in two areas: (1) Quantifying what GNNs can do and where they fail and (2) improving the capabilities of GNNs. Special interest in both these areas lies on the expressivity of GNNs, i.e., their ability to learn different representations for nonisomorphic graphs. I will present and discuss the basics, as well as recent results in this interesting and active area of research.
  7. Dr. Sayan Ranu IIT Delhi
    • Date: March 21 2025, 11:00 hours IST
    • Title: GraphTrail: Translating GNN Predictions into Human-Interpretable Logical Rules Youtube
    • Abstract Instance-level explanation of graph neural networks (GNNs) is a well-studied area. These explainers, however, only explain an instance (e.g., a graph) and fail to uncover the combinatorial reasoning learned by a GNN from the training data towards making its predictions. In this work, we introduce GraphTrail, the first end-to-end, global, post-hoc GNN explainer that translates the functioning of a black-box GNN model to a boolean formula over the (sub)graph level concepts without relying on local explainers. GraphTrail is unique in automatically mining the discriminative subgraph-level concepts using Shapley values. Subsequently, the GNN predictions are mapped to a human-interpretable boolean formula over these concepts through symbolic regression. Extensive experiments across diverse datasets and GNN architectures demonstrate significant improvement over existing global explainers in mapping GNN predictions to faithful logical formulae. The robust and accurate performance of GraphTrail makes it invaluable for improving GNNs and facilitates adoption in domains with strict transparency requirements. Reference : Armgaan, Burouj, Manthan Dalmia, Sourav Medya, and Sayan Ranu. "GraphTrail: Translating GNN predictions into human-interpretable logical rules." Advances in Neural Information Processing Systems 37 (2024): 123443-123470.
  8. Dr. Struan Robertson Biovia R&D Scientific Application Director, BIOVIA Materials Studio, DS Solutions Lab Private Ltd.
    • Date: January 17 2025, 15:00 hours
    • Title: Materials Modelling at Dassault Systèmes BIOVIA
    • Abstract The Materials Simulation team of BIOVIA has been engaged in the development of electronic and molecular simulation applications for over three decades. At the centre of this activity is the notion of multi-scale physics. An overview of three contemporary areas of interest spanning a number of scales will be discussed: the development of machine learnt potentials, in conjunction with the University of Cambridge1, for use in molecular dynamics simulations, the application of mesoscale methods to the simulation and understanding of lipid bilayer and liposome formation2 and the extension of the molecular dynamics method to granular dynamics3 with an application to battery electrode structure analysis.
      1. Batatia, I. et al "MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fields", Advances in Neural Information Processing Systems, 11423-11436 (2023).
      2. Development of Innovative Drugs Using Materials Studio
      3. Jing Bi et al “Multiscale modeling for the science and engineering of materials” International Journal for Multiscale Computational Engineering, 19, 1-80 (2021).
  9. Dr. Sambeet Mishra University of South-Eastern Norway
    • Date: January 03 2025, 14:00 hours
    • Title: Electricity market operation in Nordics – An overview
    • Abstract Electricity markets and their associated operational structures play a pivotal role in ensuring a secure, reliable, and economically efficient energy supply. By facilitating competition among diverse power producers - from conventional fossil-fuel generators to renewable energy sources - electricity markets promote transparency in pricing and stimulate innovation. Key market mechanisms, such as day-ahead auctions and intraday trading, help align generation with demand, encouraging optimal resource allocation and minimizing imbalances in real time.On an operational level, Transmission System Operators (TSOs) oversee grid reliability through balancing markets and ancillary services, ensuring electricity flows reliably across interconnected networks. These operators deploy mechanisms like reserve capacity activation and frequency control to stabilize the system whenever unexpected deviations in supply or demand occur. Furthermore, the integration of distributed energy resources and the rise of prosumers introduce new complexity and opportunities, including peer-to-peer trading and localized market initiatives. Overall, the interplay between electricity market design and operational frameworks underpins the modern power sector’s resilience, adaptability, and efficiency. By continuously refining these market structures and coordinating operations across borders and jurisdictions, stakeholders can foster a robust and sustainable energy ecosystem that meets evolving societal needs.

CS Katha Barta Past years



Home People Research Teaching Events