AI Engineer · September 23, 2026

From Scratch to SOTA: Training a 3B State-Space Vision Model — Krishna Prasad Srinivasan, Sarvam

video AI Engineering Model Evaluation

From Scratch to SOTA: Training a 3B State-Space Vision Model — Krishna Prasad Srinivasan, Sarvam video thumbnail

Why it matters

Krishna Prasad Srinivasan explains Sarvam’s three-billion-parameter document model, combining block-level OCR with a state-space language backbone. Training progresses from language pretraining through vision, OCR specialization and verifiable rewards. A surrounding harness handles layout and reading order, while a workbench supports human review. The talk emphasizes Indian-language coverage and source fidelity; its leaderboard claims remain reported results.

My takeaway: Test layout, reading order, character accuracy and tables separately on representative languages and documents. Preserve errors present in the original text, and evaluate confidence scores before using them to automate review.

Keep exploring

More curated notes connected through AI Engineering and Model Evaluation.

OpenAI News · framework

Pacing model development in an era of cyber-critical capabilities

OpenAI says preliminary evidence that Astra may meet its Critical cybersecurity threshold led it to pause frontier reinforcement-learning work for two weeks and keep its largest planned run on hold. New safeguards include stronger workload and network isolation, continuous boundary testing, token-level monitoring that escalates suspicious tool activity, and broader alignment checks for deception, reward hacking, and unauthorized access.

OpenAI News · framework

A blueprint for democratic governance of frontier AI

OpenAI proposes a three-part U.S. frontier-AI governance model: harmonize emerging state safety laws into a federal baseline, strengthen CAISI as an evaluation and standards institution, and coordinate a broader resilience program. Proposed controls include severe-risk evaluations, transparency reports, independent audits, safety-incident reporting, model-weight security, whistleblower protection, and periodic technical assessments.

OpenAI News · framework

OpenAI’s Frontier Governance Framework

OpenAI's 22-page Frontier Governance Framework maps its frontier-model processes to California's Transparency in Frontier AI Act and the EU AI Act's general-purpose AI code. It documents lifecycle risk assessment, cyber-offense and other risk tiers, mitigation and residual-risk decisions, critical-incident handling, security risk management, model reporting, external review, responsibility allocation, and change control.