Work

Selected applied ML systems and research engineering work in agents, multimodal systems, post-training, and evaluation.

Agents and evaluation

Agentic systems and reliable evaluation

Benchmarks, computer-use agents, and evaluation protocols for foundation models.

EMNLP 2026 Main

DSAgentBench

A benchmark for evaluating whether AI agents can complete end-to-end data-science workflows in real computer environments using notebooks, IDEs, terminals, browsers, and databases.

Evidence: 275 diverse tasks across the data-science lifecycle, 15 evaluated models, and deterministic evaluators. The best reported agent reached 56.70% task success.

  • Agents
  • Computer Use
  • Evaluation
  • Data Science
  • Tool Orchestration

Vector Institute · Foundation-model evaluation · 2026 preprint

Fine-Grained Benchmark Generation

A reference-grounded multi-agent pipeline for generating, verifying, repairing, and deduplicating technically demanding evaluation tasks.

Contribution: Built OCR ingestion and a multi-agent designer and verifier workflow with iterative repair, trace-aware validation, and semantic deduplication.

Evidence: Trace-aware quality control connects source ingestion to final benchmark validation.

  • OCR
  • Multi-agent Systems
  • Benchmark Generation
  • Evaluation
  • Deduplication

EACL 2026 Findings · Multimodal agents

DashboardQA

A benchmark for agents that answer questions through real interactive dashboards.

Contribution: Co-created the benchmark to expose failures in grounding, planning, GUI interaction, and multi-view reasoning.

Evidence: Tests filters, tabs, view switching, visual grounding, and cross-view reasoning in realistic dashboard environments.

  • Multimodal Agents
  • GUI Interaction
  • Benchmarks
  • Planning
  • Visual Reasoning

ACL and EMNLP 2025 Industry Tracks · Evaluation

Large and Tiny LVLM Judges

Automated evaluation protocols for chart models using large and compact vision-language model judges.

Contribution: Evaluated judge reliability, robustness, and efficiency across chart comprehension and reasoning tasks.

Evidence: A 2B judge matched a 7B baseline while reducing inference latency.

  • Model-as-Judge
  • VLMs
  • Evaluation
  • Efficiency

Multimodal systems

Data pipelines and visual reasoning

Large-scale multimodal data preparation and rigorous chart understanding benchmarks.

MICCAI 2026 · Multimodal medical AI

Open-PMC-18M

An open multimodal dataset and scalable pipeline linking biomedical figures with captions and subcaptions for medical vision-language learning.

Contribution: Owned preprocessing and batched vLLM inference for Qwen2.5-VL and Qwen2.5 summary generation.

Evidence: Scales compound-figure extraction, summarization, and OpenCLIP training across 18 million biomedical image-text pairs with optimized batched VLM inference.

  • VLMs
  • vLLM
  • Data Pipelines
  • Medical AI
  • HPC

ACL 2025 Findings · Benchmarking

ChartQAPro

A challenging chart question-answering benchmark built around diverse real-world visualizations.

Contribution: Co-created the benchmark and evaluation protocol for open and closed vision-language models.

Evidence: 1,341 charts and 1,948 questions evaluated 21 VLMs.

  • Chart QA
  • VLMs
  • Benchmarking
  • Multimodal Reasoning

Post-training and generation

Executable and data-driven generation

Feedback-driven post-training and agentic workflows for visualization and narrative generation.

EACL 2026 Main · Post-training

RL-Text2Vis

A GRPO framework that evaluates text-to-visualization outputs after code execution using textual, executable, and visual feedback.

Contribution: Co-developed post-execution multimodal feedback for aligning generated text, code, and rendered visualizations.

Evidence: Improves code executability and chart quality over strong prompting and supervised baselines.

  • GRPO
  • Post-training
  • Code Generation
  • Visualization
  • VLM Evaluation

EMNLP 2024 Main · Agentic generation

DataNarrative

An Actor-Critic workflow for planning, reflecting on, and revising data-driven stories with visualizations.

Contribution: Introduced a benchmark and multi-agent workflow for automated data-driven storytelling.

Evidence: Includes 1,449 real-world data stories for system and human evaluation.

  • Multi-agent Systems
  • Data Storytelling
  • Visualization
  • Evaluation