From fcc64c1a60226f04de30d8cbfa4747a9806e36ed Mon Sep 17 00:00:00 2001 From: Sandeep Kunkunuru Date: Sun, 28 Jun 2026 08:32:37 +0530 Subject: [PATCH] Add Samyama KG (Agent+Graph @ VLDB 2026) to University Projects & Extensions --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index a9491d14..59060a82 100644 --- a/README.md +++ b/README.md @@ -260,6 +260,7 @@ AssetOpsBench is being extended by university research groups exploring new asse - **Performance Optimzation of the TSFM Agent in an Industrial Agentic Benchmark** - Developed an optimization framework for IBM's TinyTimeMixer(TTM) model by implementing model pre-loading, torch.compile graph fusion, and replacing Huggingface abstractions with direct batched model calls. We achieved 3.3X reduction in workflow latency and 68% decrease in total execution time while maintaining zero-shot forecast quality on industrial sensor data. [Alisha Vinod](https://github.com/alishavinod), [Jonathan Ang](https://github.com/mao1e), [Sanjaii Vijayakumar](https://github.com/sanjaiiv04), [Thomas Ajai](https://github.com/thomasajai), Columbia University . [repo](https://github.com/alishavinod/AssetOpsBench) - **Visual Inspection Agent for AssetOpsBench** - Adds a vision modality to AssetOpsBench via an MCP-connected Visual Inspection Agent and 22 hand-authored visual inspection scenarios across pumps, induction motors, power transformers, and wind turbine blades. Benchmarks AWQ W4A16 quantization and vLLM serving optimizations on Qwen2.5-VL-7B and Llama-3-LLaVA-NeXT-8B, with an LLM-as-a-judge scoring pipeline for accuracy evaluation. [Amaan Sheikh](https://github.com/amaan784), [Aman Upganlawar](https://github.com/amanupg), [Madhav Rajkondawar](https://github.com/madhavrajk), [Yang-Jung (Eric) Chen](https://github.com/ericyangchen), Columbia University · [repo](https://github.com/amaan784/hpml-final-project) - **Agentic AI Workflows for Naval Operations and Maintenance** — Exploring AssetOpsBench for evaluating agentic AI workflows, with future extensions using digital-twin-generated synthetic data. [Priyam Dalmia](https://github.com/priyamDalmia), [Chin-Teng Lin](https://profiles.uts.edu.au/Chin-Teng.Lin), [Fred Chang](https://profiles.uts.edu.au/Fred.Chang), University of Technology Sydney + - **Knowledge Graphs as the Missing Data Layer for LLM-Based Industrial Asset Operations** — Treats a typed knowledge graph as the *data layer* for AssetOpsBench agents: holding the model and orchestration fixed, the same GPT-4 rises from 65% to 82–83% with LLM-generated Cypher and to 99% with deterministic graph handlers on the 139-scenario snapshot, plus Generation-Augmented Knowledge (GAK) — provenance-tagged enrichment — for the non-deterministic FMSR scenarios. Accepted at Agents+Graph @ VLDB 2026. Madhulatha Mandarapu, Sandeep Kunkunuru (VaidhyaMegha / Samyama) · [paper](https://arxiv.org/abs/2605.26874) · [repo](https://github.com/samyama-ai/assetops-kg) --- ## Call for Scenario Contribution