# Pranay Mahendrakar — Research > Open-access research by Pranay Mahendrakar (ORCID 0009-0003-7224-029X) on large language models, mechanistic interpretability, alignment, evaluation and AI safety. 15 papers, each deposited on Zenodo with a permanent DOI and released under CC BY 4.0. Licence: CC BY 4.0 — reuse freely with attribution to Pranay Mahendrakar. Cite the DOI, not this URL. The DOI is the durable identifier. Canonical site: https://research.pranaymahendrakar.com/ Author site: https://pranaymahendrakar.com/ Contact: pranaymahendrakar@sonytech.in ## Papers - [Memory Architectures Beyond Attention: Disambiguating Four Memory Concepts and the Long-Context Reasoning Frontier](https://research.pranaymahendrakar.com/p/memory-architectures-beyond-attention) — 2026. DOI: 10.5281/zenodo.19855022 State-space models did not merely "open a door" beyond attention; they walked through it. Mamba, Mamba-2, Samba, Jamba, Granite 4, Hymba, and a growing family of hybrid attention-SSM architectures… - [Formal Verification of Neural Network Safety Beyond Toy Examples: Three Distinct Gaps and a Specification-First Research Agenda](https://research.pranaymahendrakar.com/p/formal-verification-of-neural-network-safety-beyond-toy) — 2026. DOI: 10.5281/zenodo.19854889 Formal verification of neural networks has matured into a real research area. Tools such as alpha-beta-CROWN, ERAN, and Marabou now reliably verify L-infinity robustness properties of ReLU networks… - [Causal Representation Learning from Observational Video: Identifiability Assumptions and the Gap Between Synthetic and Real-World Settings](https://research.pranaymahendrakar.com/p/causal-representation-learning-from-observational-video) — 2026. DOI: 10.5281/zenodo.19854728 Causal representation learning (CRL) — the recovery of latent causal variables and their causal graph from high-dimensional observations — has produced a substantial body of theoretical results in… - [Neuromorphic Computing for On-Device LLM Inference: Why the Three-Layer Integration Gap Matters More Than the Algorithm Layer](https://research.pranaymahendrakar.com/p/neuromorphic-computing-for-on-device-llm-inference) — 2026. DOI: 10.5281/zenodo.19854579 Spiking neural networks (SNNs) on neuromorphic hardware are routinely proposed as the path to energy-efficient on-device inference for language models. The framing usually treats this as a single… - [Cross-Lingual Hallucination Patterns in Indic Languages: A Typology-Aware Research Agenda for Dravidian and Indo-Aryan Comparison](https://research.pranaymahendrakar.com/p/cross-lingual-hallucination-patterns-in-indic-languages) — 2026. DOI: 10.5281/zenodo.19854165 Multilingual hallucination in large language models has begun to receive systematic attention. Recent work has measured aggregate hallucination rates across 19 to 30 languages… - [AI-Generated Text Detection Under Paraphrasing: What Has Been Solved, What Has Not, and Why Bias Matters](https://research.pranaymahendrakar.com/p/ai-generated-text-detection-under-paraphrasing) — 2026. DOI: 10.5281/zenodo.19854026 The detection of AI-generated text under adversarial transformation — particularly paraphrasing — is widely characterised as an unsolved problem. The reality is more structured. Two technically… - [Energy-Based Models for Reasoning: A Critical Assessment of Theoretical Advantages and a Research Agenda](https://research.pranaymahendrakar.com/p/energy-based-models-for-reasoning) — 2026. DOI: 10.5281/zenodo.19853899 Modern reasoning systems are dominated by autoregressive models trained with reinforcement learning on reasoning trajectories — the o1, R1, and Claude 3.7 family of "thinking" models. Energy-based… - [Catastrophic Forgetting in Continual RLHF: A Measurement Framework for Round-Over-Round Capability Degradation](https://research.pranaymahendrakar.com/p/catastrophic-forgetting-in-continual-rlhf) — 2026. DOI: 10.5281/zenodo.19853746 Reinforcement learning from human feedback (RLHF) is widely understood to incur an alignment tax: aligning a language model with human preferences can degrade capabilities the base model possessed… - [Beyond ASL: AI for Low-Resource Sign Languages A Research Agenda for Indian and African Contexts](https://research.pranaymahendrakar.com/p/beyond-asl-ai-for-low-resource-sign-languages-a-research) — 2026. DOI: 10.5281/zenodo.19853618 There are over 300 sign languages in active use worldwide, serving an estimated 70 million Deaf signers. Despite this, the overwhelming majority of AI research on sign languages targets American Sign… - [Emergent Covert Signaling in Multi-Agent LLM Negotiation: A Conceptual Framework and Experimental Protocol](https://research.pranaymahendrakar.com/p/emergent-covert-signaling-in-multi-agent-llm-negotiation) — 2026. DOI: 10.5281/zenodo.19853493 When multiple large-language-model agents negotiate, communicate, or compete, do they spontaneously develop covert signalling — channels of communication that human observers cannot decode? Recent… - [Mechanistic Interpretability of In-Context Learning: A Survey of Known Circuits and Open Problems](https://research.pranaymahendrakar.com/p/mechanistic-interpretability-of-in-context-learning) — 2026. DOI: 10.5281/zenodo.19853292 In-context learning (ICL) — the ability of a transformer language model to acquire a new input-output mapping from a handful of demonstrations in its prompt, with no weight updates — remains the most… - [Sheaf-Theoretic Semantics and Quantum Contextuality in Large Language Models: A Unified Categorical Framework for Understanding Semantic Coherence and Hallucination Phenomena](https://research.pranaymahendrakar.com/p/sheaf-theoretic-semantics-and-quantum-contextuality-in) — 2025. DOI: 10.5281/zenodo.18074071 This paper introduces a novel theoretical framework for understanding semantic processing in Large Language Models through the lens of sheaf theory and quantum contextuality. We propose that the… - [Quantum Mirrors of the Mind: Breaking the Barriers Between Human Consciousness and Artificial Intelligence](https://research.pranaymahendrakar.com/p/quantum-mirrors-of-the-mind) — 2024. DOI: 10.5281/zenodo.14047259 In the nascent field of quantum consciousness computing, we present groundbreaking research that fundamentally transforms our understanding of both human consciousness and artificial intelligence… - [An Intelligent Eye in the Sky: AI-Infused Drones for Autonomous High-Tech Security Operations](https://research.pranaymahendrakar.com/p/an-intelligent-eye-in-the-sky) — 2024. DOI: 10.5281/zenodo.14041518 As security concerns continue to escalate globally, there is an increasing demand for highly responsive, intelligent surveillance systems capable of proactively managing and mitigating threats. This… - [The Emotional Intelligence Paradox in Large Language Models](https://research.pranaymahendrakar.com/p/the-emotional-intelligence-paradox-in-large-language-models) — 2024. DOI: 10.5281/zenodo.14040453 The emergence of Large Language Models (LLMs) has revolutionized our understanding of artificial intelligence's capabilities in emotional processing. These models demonstrate remarkable proficiency… ## Topics - [Interpretability](https://research.pranaymahendrakar.com/topics/interpretability) — 3 papers. Opening the model up — circuits, features, and what "explaining a behaviour" actually means. - [Reasoning & Memory](https://research.pranaymahendrakar.com/topics/reasoning) — 4 papers. How models hold context, carry state, and compose steps beyond next-token prediction. - [Alignment & RLHF](https://research.pranaymahendrakar.com/topics/alignment) — 1 papers. What training on human preference does to a model over time, and what it quietly costs. - [Evaluation & Detection](https://research.pranaymahendrakar.com/topics/evaluation) — 4 papers. Measuring what models do rather than what benchmarks say they do. - [Multilingual & Indic NLP](https://research.pranaymahendrakar.com/topics/multilingual) — 2 papers. Failure modes that only appear once you leave English. - [Multi-Agent Systems](https://research.pranaymahendrakar.com/topics/agents) — 1 papers. What emerges when models talk to each other instead of to us. - [Safety & Verification](https://research.pranaymahendrakar.com/topics/safety) — 3 papers. Guarantees, specifications, and the gap between a proof and a deployed system. - [Vision & Video](https://research.pranaymahendrakar.com/topics/vision) — 2 papers. Perception systems, and what they can and cannot infer from what they see. - [Systems & Hardware](https://research.pranaymahendrakar.com/topics/systems) — 1 papers. Inference where the compute budget is real — on-device, at the edge, off the datacentre. - [Accessibility & Low-Resource](https://research.pranaymahendrakar.com/topics/accessibility) — 1 papers. Research agendas for the users and languages that datasets leave out. - [Mathematical Foundations](https://research.pranaymahendrakar.com/topics/theory) — 4 papers. Category theory, sheaves, and formal structure applied to systems that were built empirically. - [Cognition & Consciousness](https://research.pranaymahendrakar.com/topics/cognition) — 2 papers. The uncomfortable questions at the edge of the field. - [Security & Defence](https://research.pranaymahendrakar.com/topics/security) — 1 papers. Applied systems built for threat detection and situational awareness. ## Machine-readable - [Sitemap](https://research.pranaymahendrakar.com/sitemap.xml) - [RSS feed](https://research.pranaymahendrakar.com/feed.xml) - [Full abstracts](https://research.pranaymahendrakar.com/llms-full.txt) - [Zenodo record set](https://zenodo.org/search?q=metadata.creators.person_or_org.identifiers.identifier%3A%220009-0003-7224-029X%22)