-Download-d2a8ff?style=for-the-badge&logo=adobeacrobatreader&logoColor=white){kind=icon}
BS-MS student at Indian Institute of Science Education and Research, Kolkata (Chemistry Major, Computer Science Minor, CGPA 8.2). My work sits at the intersection of computational chemistry, AI/ML research, and information retrieval. I co-founded two MeitY-funded deeptech startups and have published at ECIR 2026, FIRE 2025, and TREC 2024.
| Current Research | Hybrid RAG architectures, DFT-based catalyst modelling, query reformulation for NLP |
| Learning | LAMMPS, HPC workflows, advanced DFT, Agentic AI frameworks |
| Looking to Collaborate | ML, Data Science, Molecular Simulations, Quantum Chemistry |
| Contact | sbs22ms076@iiserkol.ac.in |
Attention Heads / Transformer Architecture
Molecular Orbital Spin Diagram — [VO(SALIEP)(DTP)]
Gradient Descent Loss Landscape
Molecular Dynamics Simulation — LAMMPS
Neural Activation Pulse — Spiking NN
Quantum Spin Grid — Ising Model
| Year | Venue | Title |
|---|---|---|
| 2026 | ECIR 2026 (34.5% acceptance) | AgriIR: A Scalable Framework for Domain-Specific Knowledge Retrieval |
| 2025 | FIRE 2025 | Hierarchical Opinion Classification using Large Language Models |
| 2024 | TREC 2024 (NIST) | IISERK@ToT_2024: Query Reformulation and Layered Retrieval |
| WIP | To be submitted | Computational Modeling of [VO(SALIEP)(DTP)] as Water Reducing Catalyst (DFT/B3LYP) |
| Startup | Domain | Grant | Status |
|---|---|---|---|
| Synapse | AI-Fintech — democratising ML for smart trading | MeitY GENESIS EiR | Funded; DPIIT Q1 2026 |
| UnderWater AI | DeepTech — underwater vision for marine species ID | MeitY GENESIS EiR | Funded; DPIIT Q1 2026 |
flowchart LR
A[Problem Statement] --> B[Literature Review]
B --> C[Dataset & Baseline]
C --> D[Model Design]
D --> E[Experiments & Ablations]
E --> F{Results Satisfactory?}
F -- No --> D
F -- Yes --> G[Paper Writing]
G --> H[Peer Review]
H --> I[Publication ECIR / FIRE / TREC]
I --> J[Open-Source Release]
style A fill:#1e3a5f,stroke:#58a6ff,color:#c9d1d9
style I fill:#2d1f4a,stroke:#d2a8ff,color:#c9d1d9
style J fill:#1f3a2d,stroke:#56d364,color:#c9d1d9
Can you replicate the complex from Shuvam's computational chemistry research? Step through the synthesis:
Step 1 — Choose your central metal
You need a redox-active transition metal capable of oxo-coordination for water reduction.
-
Select Vanadium (V)
Excellent choice. Vanadium(IV) oxo-complexes are known water-reduction catalysts.
-
-
Add Salen-type ligand (SALIEP)
SALIEP provides strong N/O donors that stabilise V(IV). Now choose the co-ligand.
-
Add dithiophosphate (DTP)
You built [VO(SALIEP)(DTP)] — the target complex from the DFT/B3LYP study. Run Gaussian with the B3LYP functional to compute MO energies and map the water-reduction pathway. Correct. This is exactly the compound Shuvam modelled computationally.
Add bipyridine (bpy)
Interesting coordination, but different from the target. Try dithiophosphate (DTP).
-
-
Add only H2O as ligand
Water alone does not form the stable complex needed. Try a stronger donor ligand like SALIEP.
-
-
Select Iron (Fe)
Iron forms great catalysts in other systems, but this specific DFT study uses Vanadium. Try again.
Design the retrieval architecture step by step:
Step 1 — Choose your retriever
-
Dense retrieval only (vector embeddings)
Handles semantic similarity well, but misses exact keyword matches for rare technical terms. Upgrade?
-
-
Add BM25 sparse retrieval in parallel
Now you have hybrid retrieval. How do you merge the two ranked lists?
-
Reciprocal Rank Fusion (RRF)
Perfect. RRF combines ranked lists without score calibration. Add HyDE (hypothetical document embeddings) for query refinement and wrap in a Streamlit UI — you have replicated the ECIR 2026 / IISER-K intranet system.
Weighted linear score combination
Works, but requires per-domain calibration. RRF is more robust. Try again.
-
-
-
BM25 sparse only
Fast and interpretable, but misses paraphrases. Upgrade to hybrid for better recall.
