About
I am a final year Electrical Engineering student at Nirma University. I architect neural nets and exact solvers that run fast.
I primarily work on reinforcement learning on combinatorial spaces and language models. I'm currently working on Deep RL solvers for NP-hard combinatorial problems at Indian Institute of Management Bangalore (IIMB), and previously engineered and optimized sequential architectures with SIT-NVIDIA AI Centre (SNAIC).
I work on game theory, adversarial economics, and sequential decision processes. My hobbies are algorithmic music composition and playing chess. Whether you're building in adjacent spaces, exploring topologies, or just up for a game, feel free to reach out.
Interests: Model Quantization, Efficient Inference, Reinforcement Learning, Neural Combinatorial Optimization.
Academic Background
Recent Updates
2026
- Virtually volunteering at ACL 2026 in San Diego with the AV team alongside Damira.
- Selected as recipient of the ACM SIGMOD/PODS 2026 India Fellowship.
- Kabir Murjani. Zero-Copy Semantic Contagion: An In-Memory Streaming Architecture for Evolving Attention Graphs. Accepted at ACM SIGMOD FinDS, 2026.
- Started a research internship on deep reinforcement learning for neural combinatorial optimization at the Indian Institute of Management Bangalore, under the guidance of Prof. Abhay Sobhanan.
- Elected General Secretary of the IEEE Computer Society chapter at Nirma University.
- Kabir Murjani. LURE: Latent Utility Reward Erosion as a Bayesian Signaling Game in Multi-Step Agent Interactions. Accepted at MathAI 2026, Sochi, Russia.
- The Geometry of Context: Topological Optimization for Prompting with Online Supervision submitted to ACL Rolling Review, May 2026.
- Kabir Murjani. Semantic Language-Agnostic Framework for Multi-Modal Content Similarity. Accepted at IEEE ICCISD 2026.
- Judges Hallucinate, Embeddings Don't: Retrieval-Augmented Latent Regression for Dialogue Alignment submitted to Transactions on Machine Learning Research.
2025
- Kabir Murjani. SaNcHaR: Adaptive Topology Routing and Quantized Edge Inference. Accepted at IEEE ICC 2026.
- Weight-Space Teleportation: Discovering LLM Reasoning via Bilevel Evolution (with Parth Vyas) submitted to Transactions on Machine Learning Research.
- Collaborating with Dr. Timothy Liu at the NVIDIA AI Center at Singapore Institute of Technology on quantized edge inference and adaptive routing architectures.
- Lead Aniate Labs to explore open source applied AI tooling at the intersection of language models and combinatorial solvers.
- Presented early results on DEED manifold compression at an internal seminar at Nirma University's EE department.
- Contributed to the CRAFT-5 dataset: 2,384 RLAIF examples for preference tuning, released publicly on Hugging Face.
2024
- Joined Team Dyaus at Nirma University, building a CanSat model for the Türksat Satellite Competition 2024.
- Finished 3rd place at the Indian Institute of Technology Kanpur Chess Masters Premier League 2.0 among 60+ universities.