Bhanu Prakash Vangala

Three threads that look unrelated from the outside. They are one question asked three ways. Can anyone else check this?

1. 01

   Trustworthy outputs

   Knowing when a scientific answer is invented

   A benchmark and a multi-stage detector for hallucination in materials-science question answering, combining self-consistency checking, retrieval against curated sources, and a knowledge graph that flags low-connectivity fact fragments as likely fabrications. It cuts hallucination rates by about 30% and reaches F1 0.95 on cross-domain inconsistency detection. The number is the least interesting part. What I wanted was a pipeline you can interrogate. Ask why a response got flagged and you get a reason back, not a score.

   AAAI 2025 Spring SymposiumAAAI 2025 Spring Symposium

2. 02

   Reproducible artifacts

   Can anyone else actually run it?

   100 standardised prompts given to Claude, Codex and Gemini agents, and the 300 resulting projects executed in clean containers. Only 68.3% ran out of the box: Python 89%, Java 44%. The agents declared about three dependencies per project; the projects pulled in around 49 at runtime. That 13.5x gap does not disappear. It lands on whoever picks the code up next. "It ran on my machine" and "it is reproducible" are two different claims, and our benchmarks have quietly been scoring the first one.

   AAAI 2026 RAI WorkshopAI MagazineACM REP 2026

3. 03

   Accountable systems at scale

   Nine models, a fixed number of GPUs

   A Kubernetes-native multi-tenant serving framework that classifies queries by complexity, routes them across nine models from 1B to 27B parameters using Thompson Sampling, and manages warm pools through a custom cold-start state machine. Across 310,190 inference requests on the NRP Nautilus cluster it reached 61% GPU utilization against 31% for static deployment, cutting GPU-hours by 46%. Most of that comes from one decision: stop holding nine models resident when the traffic does not call for them.

   IEEE CLOUD 2026AAAI 2026 DAI Workshop

A real shell over this CV. It reads the same knowledge base the assistant answers from, so it cannot tell you anything the rest of the site does not. Try ls, cat papers/pick-and-spin.md, or ask what is pick and spin.

1. 2026.08Completed my Research Data Science internship at Microsoft in Redmond, WA: temporal featurization for predictive Windows retention across 1B+ users.
2. 2026.06Pick-and-Spin: Cold-Start-Aware Routing for Self-Hosted LLM Serving was accepted as an oral at IEEE CLOUD 2026.
3. 2026.05Beyond Functional Correctness was accepted as an oral at ACM REP 2026.
4. 2026.05Submitted CAMP: Consumption-Aware Memory Prediction for Scientific Workflows to IEEE Cluster 2026.
5. 2026.04Received the EECS Graduate Travel Fellowship from the University of Missouri College of Engineering.

1. May 2026 – Aug 2026

   Research Data Science Intern

   Microsoft · Redmond, WA

   With Juan-Arturo Herrera, Anqi Cheng, Kyle Hatridge

   • Built a reusable temporal featurization framework (TFT / TCN) for predictive Windows retention across 1B+ users, 5,000+ features and 15+ years of Windows and Devices telemetry, a +45% PR-AUC lift over baseline, driven by lag-based trajectory signals with SHAP interpretability.
   • Built the Cosmos / SCOPE data layer over Azure streams and data lakes, and automated Copilot Studio feature-analysis workflows.

   TFT/TCNAzureCosmos/SCOPESHAPCopilot Studio

2. Dec 2023 – Present

   Graduate Research & Teaching Assistant

   Radiant Lab & Data Intensive Computing Lab, University of Missouri · Columbia, MO

   • Radiant Lab (NASA / NSF). Drove NASA-funded research on LLMs, coding-agent reproducibility and dependency resolution; designed the SciUnit ptrace audit harness; first-authored multiple peer-reviewed papers.
   • Data Intensive Computing Lab (DoD / NSF). Built hallucination-detection pipelines; delivered a 40% geospatial-accuracy lift on UAV workflows.
   • Kubernetes / Helm on NRP Nautilus HPC. GPU quota management and deployment automation for 9 self-hosted LLMs.
   • TA, Web Development (MERN). Mentored 115+ students; built CI/CD scaffolding and grading automation on GitLab.

   KubernetesHelmvLLMSLURMptrace

3. May 2022 – Jan 2023

   Volunteer Research Intern

   Adobe Research · Remote

   • Built large-scale web scraping and information-extraction pipelines with automated quality control for ML workflows.

One per thread. Mine is the name in bold.

1. 

   Resource-Aware Multi-Model Serving for GPU Cloud Infrastructure (Pick-and-Spin)

   Bhanu Prakash Vangala, Tanu Malik

   Nine models from 1B to 27B routed by Thompson Sampling with a cold-start state machine. 310,190 requests on NRP Nautilus: 61% GPU utilization against 31% for static deployment, cutting GPU-hours by 46%.

   IEEE CLOUD 2026 · Oral orchestrationsystemsinference

   What it's about

   Serving many fine-tuned models on a fixed GPU pool forces a choice between keeping everything warm (expensive) and cold-starting on demand (slow). Pick-and-Spin treats routing as a bandit problem and makes residency an explicit, learned decision rather than a static policy.

2. 

   AI-Generated Code Is Not Reproducible (Yet): Dependency Gaps in Coding Agents

   Bhanu Prakash Vangala, Ali Adibifar, Tanu Malik, Ashish Gehani

   100 prompts given to Claude, Codex and Gemini. Of the 300 resulting projects only 68.3% ran in a clean container: Python 89%, Java 44%. Agents declared about 3 dependencies per project; the projects pulled in around 49 at runtime, a 13.5x gap.

   AAAI 2026 RAI Workshop · Oral reproducibilityagentsevaluation

   What it's about

   Code from coding agents runs where it was written and breaks everywhere else. We audited 300 projects generated by Claude, Gemini and Codex and measured how often the declared environment fails to match what the code actually needs.

   Paper

3. 

   HalluMat: Detecting Hallucinations in LLM-Generated Materials Science Content Through Multi-Stage Verification

   Bhanu Prakash Vangala, Syed Mahmud, Prabhat Neupane, Janani Selvaraj, Jianlin Cheng

   Self-consistency checking, retrieval against curated sources, and a knowledge graph that flags low-connectivity fact fragments. Cuts hallucination rates by about 30% and reaches F1 0.95 on cross-domain inconsistency detection.

   AAAI 2025 Spring Symposium · Oral hallucinationtrustworthy-aibenchmarks

   What it's about

   A benchmark and detector for hallucination in materials-science LLMs, combining retrieval augmentation (IR, NER and semantic similarity) with intrinsic consistency checks. Introduces the Paraphrased Hallucination Consistency Score, which asks whether a model contradicts itself when the same question is worded differently.

   Paper

The funded programs this work lives inside, and the people I do it with.

• Reproducible Containers for Collaborative Analytics

  NASA AISTLLMOps · Kubernetes · HPC

  With Dr. Tanu Malik (University of Missouri), Dr. Ashish Gehani (SRI International), Dr. Kwo-Sen Kuo (NASA), Dr. Abhilash Jindal (IIT Delhi)

  FlexiFlow

  Bandit-based model switching, FastAPI routing with GPU telemetry, Prometheus + Grafana observability. Demonstrated at SIGMOD.

  Pick-and-Spin

  Thompson Sampling with a Cold-Start State Machine: 9.2% cold-starts across 310K runs and 61% GPU utilization, against 31% for the static baseline.

  Self-hosting LLMs

  Helm + vLLM LLM-as-a-Service on NSF Nautilus with KEDA autoscaling; serverless on AWS SageMaker and Lambda with scale-to-zero.

  Coding-agent reproducibility

  300 repositories generated by Claude, Gemini and Codex, replayed via SLURM; the SciUnit ptrace harness extended to Java and JavaScript.

• TRACE: Autonomous Experimentation Lab using Agentic AI

  NSFAgentic AI · MCP · gRPC

  With Dr. Tanu Malik (University of Missouri), Dr. Matt Maschmann (University of Missouri), Dr. Derek T. Anderson (University of Missouri)

  MCP & tooling

  Authored custom MCP servers and agent skills wrapping Nanoscribe and SEM instrument APIs; ran 50+ automated experiment cycles with per-call provenance.

  Multi-agent orchestration

  Coordinated agents with Google ADK and Agent2Agent (A2A) over gRPC and Protocol Buffers, behind a FastAPI control plane with pytest and GitHub Actions CI for reproducible runs.

• Accelerating Materials Design through AI and Machine Learning

  ERDC, DoDAI · ML · NLP

  With Dr. Jianlin Cheng (University of Missouri), Dr. Grant Scott (University of Missouri), Dr. Prasad Calyam (University of Missouri), Dr. Chitta Baral (Arizona State University), Dr. Lenore Dai (Arizona State University)

  HalluFormer

  A BigBird span-level hallucination classifier: F1 0.947 on MultiNLI and 0.728 on ANAH.

  HalluMat

  The HalluMatData benchmark with retrieval augmentation over IR, NER and semantic similarity: a 30% hallucination reduction.

• LearnLLM.dev

  FounderLive

  A GeeksforGeeks-style learning platform for building with large language models, built full-stack from schema to deployment, with Vercel CI/CD. 1,000+ active users.

  Next.jsTypeScriptPrismaSupabase

  learnllm.dev

• ReflectMemory: persistent memory for long-context reasoning

  Prototype

  Stores and re-injects chain-of-thought embeddings so a long-running agent keeps a stable line of reasoning across sessions instead of restarting it.

• ChatMed: grounded medical question answering

  Completed

  A symptom-guidance assistant built on BioGPT and grounded in PubMed articles.

• 2025

  Google Ph.D. Fellowship Nominee (NLP track)

  Top 3 of 6,000 participants

• 2026

  EECS Graduate Travel Fellowship

  University of Missouri

• 2026

  Chameleon Cloud Travel Award, top 10 proposals

  NSF Chameleon Cloud Infrastructure

• 2025

  Outstanding Reviewer Award

  NeurIPS 2025, AI for Accelerated Materials Design (AI4MAT) track

• 2025

  Outstanding Master's Student Award

  University of Missouri

  
• 2025

  Runner-Up, AI for Social Good Hackathon

  MUIDSI x IBM · VisionAI, $1,000

  
• 2022-2023

  Dean's Research Excellence Award, Best Thesis Award, Top-2 Academic Performer

  Vellore Institute of Technology

1. Aug 2023 – Jun 2027 (expected)

   Ph.D., Computer Science

   University of Missouri · Columbia, MO · GPA 3.9 / 4.0

   • Thesis area: trustworthy and reproducible LLM-based agentic systems; multi-model orchestration; provenance tracing.
   • Advised by Dr. Tanu Malik (Radiant Lab).
   • Google Ph.D. Fellowship Nominee (NLP track, 2025); EECS Travel Fellowship ‘26; Chameleon top-10 presentation ‘26.

2. Aug 2023 – May 2025

   M.S., Computer Science

   University of Missouri · Columbia, MO · GPA 4.0 / 4.0

   • Thesis: Deploying LLMs as a Service in a Kubernetes HPC Cluster.
   • Advised by Dr. Grant J. Scott and Dr. Jianlin Cheng.
   • Outstanding Master’s Student Award (2025); Runner-up, MUIDSI Hackathon (2025).

3. May 2019 – Apr 2023

   B.Tech, CSE (Data Analytics)

   Vellore Institute of Technology · Vellore, India · GPA 8.8 / 10

   • Thesis: Multilingual Sentiment Analysis on KOO User Posts.
   • Advisors: Dr. P. Kumaraguru (IIIT Hyderabad) and Dr. Soughbhagya.
   • Dean’s Research Excellence Award (2023); Top-2 Academic Performer (2022); Merit Scholarship.

Invited talks & presentations

Apr 2026

Evaluating Dependency Gaps in LLM-Generated Code · Sixth Chameleon User Meeting, NCAR Mesa Lab, Boulder, CO

Jan 2026

AI-Generated Code Is Not Reproducible (Yet) · AAAI 2026 RAI Workshop, Singapore

Jan 2026

Efficient Multi-Model Orchestration for Self-Hosted LLMs · AAAI 2026 DAI Workshop, Singapore

Apr 2025

Hallucination detection in scientific LLMs · AAAI Spring Symposium 2025 · AI for Scientific Discovery

Presenting hallucination-detection work at the AAAI Spring Symposium 2025.

Reviewing

Outstanding Reviewer, NeurIPS 2025 (AI4MAT)ACM CAIS 2026 (Main + AEC)NeurIPS 2026 (Main + AEC)ICLR 2025CIKM 2025IEEE 2024

Teaching

Fall 2025, Fall 2024, Spring 2024, Fall 2023

Teaching Assistant, Web Development (MERN stack) · University of Missouri. Mentored 115+ students; built CI/CD scaffolding and grading automation on GitLab.

Happy to talk about agentic systems, reproducibility, or serving LLMs at scale. I'm open to collaborations and to speaking invitations.

Or ask the assistant in the corner. It only knows what's on this page, and it will tell you which section it took each answer from.