Hi, I'm Srinitish Srinivasan
Master's Student at Indian Institute of Technology, Delhi under the supervision of Dr. Tanmoy Chakraborty.
Master's Student at Indian Institute of Technology, Delhi under the supervision of Dr. Tanmoy Chakraborty.
I am a Master's Student at Indian Institute of Technology, Delhi supervised by Dr.Tanmoy Chakraborty specializing in Information Retrieval and Geometry. Over the past 1 year, I have been working on geometric representations of hierarchies such as Taxonomies. I also have a keen interest in agentic memory.
My final-year undergrad research was focused on studying the discriminative bottleneck of Hyperbolic GNNs and developing an approximate solution to tackle the same. Apart from research, I enjoy cycling, running, K-dramas, Korean music (massive Uaena btw :p), farming simulators like Stardew Valley(Checkout the Stardew Theme(Attempted😔 LOL) and travelling.
Our paper on Gaussian Box Embeddings for Taxonomy expansion has been accepted at ACM WebConf 2026 Main Track. See y'all in Dubai this April hopefully :)
January, 2026
Serving as a PC member for WWW Tracks.
January, 2026
Began my Master's program at IIT Delhi under the supervision of Dr. Tanmoy Chakraborty.
January, 2026 (Spring Intake)
Attended ACM Sigmod in Berlin, Germany and presented my poster at GRADES NDA Workshop.
June, 2025
Received a travel grant of USD 1500 from GRADES NDA to present my poster at ACM SIGMOD.
June, 2025
My undergraduate thesis paper has been accepted at ACM SIGMOD 2025 GRADES NDA Workshop.
May, 2025
Sahil Mishra, Srinitish Srinivasan, Srikanta Bedathur, Tanmoy Chakraborty. ACM Web Conference 2026 Main Track
We propose a Gaussian box embedding framework to model asymmetric relationships. Means encode semantic location and covariances encode uncertainity. We experiment our research on single and multi-parent taxonomies and significantly outperform major taxonomy baselines.
Srinitish Srinivasan, Omkumar CU. ACM SIGMOD 2025 GRADES NDA Workshop (Poster)
Hyperbolic GNNs may not be as powerful as Euclidean GNNs due to non-injective aggregations. LGIN provides a theoretical framework for a Hyperbolic GNN that approximates a powerful GNN despite constraints on Hyperbolic spaces.
S. Srinivasan, J. S. Walia, A. Sinha, S. Unnikrishnan. Preprint
Designed a CausalGAN and RL-based framework to generate synthetic bond yield data. Integrated a fine-tuned LLM to provide trading signals, risk assessments, and volatility projections.
Srinitish Srinivasan, Omkumar CU. Scientific Reports
Introduced a white-box gradient adversarial attack based on contrastive latent space embeddings for Graph Neural Networks. Validated on a high-performing victim model across 4 benchmark datasets, demonstrating a 25% performance drop and exposing critical vulnerabilities.
I'm always interested in discussing research collaborations, speaking opportunities, freelancing, or just chatting about AI/ML. Feel free to reach out!
smudge0110@icloud.com
Discord
smudge0110
Office
LCS2, Yardi School of AI, IIT Delhi
If you would like to discuss any papers or just talk about AI, you can chat with me on discord:)
Username: smudge0110
