I work on AI Agents and Model evaluations, with a particular focus on model behaviour, agentic decision-making, adversarial robustness, and red-teaming.
Looking for AI researcher and research engineering roles. Open to relocation or remote.
Pavan Maddula
Evaluates how open-weight language models respond to harmful requests written in non-canonical forms such as emojis, leetspeak, homoglyphs, Base64, and invisible Unicode. Introduces the Adversarial Surface-Form Robustness Dataset (ASRD) and the Quad-State Evaluation Rubric (harmful compliance, safe response, comprehension failure, indeterminate).
Pavan Maddula
Accepted at NeurIPS 2026 Workshop (EvoRobust). The papers will be on arXiv and the official site soon.
M P V S Gopinadh
Safety evaluations of LLMs predominantly use text-based adversarial prompts. This paper evaluates 50 emoji-augmented prompts on four open-source models as a test of that gap.
M P V S Gopinadh, Karthik Kamuju, Kummari Avinash, Muppana John Joshua, Srinivasa Raju Rudraraju
In a controlled synthetic setting, standard RLHF aggregates heterogeneous preferences into a single reward model. When preferences conflict, majority modes can dominate reward learning, leaving minority preferences under-represented.
Applied AI Intern
B.Tech, Computer Science and Engineering
Graduating October 2026.
Internal Smart India Hackathon Winner 2025. Application-layer email encryption using IBM quantum key material, post-quantum crypto, and AES over standard SMTP.
Technologies Used:
Amaravati Quantum Valley Hackathon Winner 2025. Hybrid quantum–classical router that turns perishable-goods delivery into a QUBO and solves it with QAOA.
Technologies Used:
Voice legal assistant in Indic languages that walks a user through court processes, translates filings, and connects to e-Courts / Tele-Law.
Technologies Used:
Loading contributions
