Purusharth Malik

Currently tinkering with efficient RL and diffusion language models.

Research engineer at Conscious Engines in Bengaluru, where I work on reinforcement learning for both autoregressive and diffusion language models. Before this I led post-training of 30B models at Gnani.ai and built LLM systems at Swiggy, after studying mathematics at the University of Delhi and AI at CHRIST University.

My playlist, as CLIP sees it

Writing

Long-form notes from whatever rabbit hole I fell into that month. Posts sit near each other on the map when they cover related ideas. Pick a topic to filter.

  1. 15 min Automatic Speech Recognition (ASR) From Scratch (With Intuition) Why speech is so much harder than text for a transformer, and how Wav2Vec2, Whisper, Conformers and transducers get around it.
  2. 20 min Is Latent Reasoning The Future? Hierarchical and tiny recursive models reason in latent space instead of tokens. Is that where reasoning goes next?
  3. 7 min LoRA Can Now Make Your LLMs Multimodal! VoRA adds vision to a language model through LoRA layers instead of a separate encoder.
  4. 8 min You Don't Always Need An MCP Client What the Model Context Protocol actually is, and how to call an MCP server without a client.
  5. 14 min The Biggest Enemy of Generative Modeling The normalising constant, and how VAEs, GANs, score matching and diffusion each learned to avoid it.
  6. 16 min Is your LLM “playing along” with your guardrails? Alignment faking: when a model behaves well only because it believes it is being watched.
  7. 11 min How did we get to vLLM, and what was its genius? How LLM serving grew out of Flask apps, and why PagedAttention changed the economics of inference.
  8. 10 min Transformer²: The Death of LoRA? Sakana's Transformer² adapts weights at inference time with singular value fine-tuning. Does that make LoRA obsolete?
  9. 8 min Stop treating your LLM like a black box, you MORON! A first look at mechanistic interpretability: circuits, induction heads and reading what a transformer computes.
  10. 9 min Chain-of-Thought — All the Language Models are Just Extremely Intelligent Toddlers Why chain-of-thought works, seen through control theory and a very enthusiastic toddler.

Research

Reinforcement learning for language models: how to make it cheaper, and the odd ways it changes a model. Full list on Google Scholar.

arXiv 2610.15371 October 2026 technical report

A Sovereign, Indic-First, Reasoning Model

S. S. Raj, P. Pasunuti, P. Chatterjee, D. Maan, P. Malik, N. Sarkar, A. Benki

Gnani-Evon-v3.3 is a 30B-parameter hybrid Mamba-Transformer mixture-of-experts model for reasoning and tool use in English and eight Indian languages, built from NVIDIA's Nemotron-3-Nano. The central finding is a side effect of reinforcement learning: rewards on verifiable tasks improved maths and science, but because they never checked the answer language, the share of Indic questions answered in English rose from 8.7% to 91.7%.

Before RL8.7%
After RL91.7%

Abstract PDF

Work

Seven years plotted as a training run. Each checkpoint is a place I learned something. Select one to read the log.