Qiran Hu

AC3S: Adaptive Conditioning for 3D-Aware Synthetic Data Generation

• [1] Eric Ji, Qiran Hu, Wufei Ma, Sarthak Jain, Yingying Li, Minh N. Do, Yaoyao Liu. AC3S: Adaptive Conditioning for 3D-Aware Synthetic Data Generation. European Conference on Computer Vision (ECCV), 2026.

Links: arXiv, Code, Video, BibTeX

REVA: Reusable Evidence View Aggregation for Context-Efficient RAG Serving

• [2] Tuan Nguyen, Qiran Hu, Banruo Liu, Khoa D. Doan, Kok-Seng Wong, Fan Lai. REVA: Reusable Evidence View Aggregation for Context-Efficient RAG Serving. IEEE International Conference on Data Mining (ICDM), 2026.

Links: arXiv, Code, BibTeX

ACDN: Agent-Aware Content Delivery Network

• [3] Tuan Nguyen, Qiran Hu, Dibyadeep Saha, Banruo Liu, Khoa D. Doan, Kok-Seng Wong, Fan Lai. ACDN: Agent-Aware Content Delivery Network. Under Review.

SV4D 3.0: Single-Step 3D-Aware Diffusion for Multi-View-Consistent 4D Scene Generation

• [4] Qiran Hu, Wei Cao, Yaoyao Liu. SV4D 3.0: Single-Step 3D-Aware Diffusion for Multi-View-Consistent 4D Scene Generation. Under Review.

AISim: Using LLM-Simulation as Epistemic Scaffolds for Early Stage Qualitative Research Design

• [5] Hangyue Zhang, Qiran Hu, Ziyi Zhang, Hyanghee Park, Yun Huang. AISim: Using LLM-Simulation as Epistemic Scaffolds for Early Stage Qualitative Research Design. Under Review.

AlphaWiSE: Adaptive Weight Interpolation for Continual Multimodal Representation Learning

• [6] Sarthak Jain, Qiran Hu, Zhen Zhu, Yaoyao Liu. AlphaWiSE: Adaptive Weight Interpolation for Continual Multimodal Representation Learning. Under Review.

UIUC Computer Vision and Machine Learning Group

Undergraduate Research Assistant - Advised by Professor Yaoyao Liu, 2025.05-Present, Champaign, IL

• Develop adaptive conditioning methods for 3D-aware synthetic data generation to enhance world model understanding and embodied agent performance in interactive simulations with geometry-conditioned diffusion approaches, reducing FID by 32.8% on ImageNet and enhancing pose accuracy by 4.2x on PASCAL3D+.
• Conduct large-scale foundation model training across TB-level datasets on National Center for Supercomputing Applications (NCSA) HPC clusters to enforce multi-view consistency with 4-bit NF4 quantization and low-level custom kernels, improving pose accuracy by 11.3% on PASCAL3D+ and reducing generation latency by 78.7% at p95.
• Design camera-controlled novel view synthesis on video generation pipelines to advance real-time perception for SLAM, visual odometry, and 3D reconstruction, decreasing LPIPS by 21.0% on GSO and FV4D by 52.0% on OmniObject3D.

Links: Lab

Multimodal Continual Learning Project

Undergraduate Research Assistant, 2026.02-Present, Champaign, IL

• Selected for NVIDIA Academic Grant Program Award to streamline multimodal foundation models in class-incremental learning across audio, image, and text without catastrophic forgetting and cross-modal alignment drift, increasing R@1 by 27.6% on AudioSet.
• Implement post-hoc tensor-level weight-interpolation methods for multimodal retrieval on National Artificial Intelligence Research Resource (NAIRR) HPC clusters, minimizing trainable parameters from 182M to 499 sigmoid-parameterized coefficients and increasing R@1 by 33.5% on AudioSet.
• Optimize checkpoint fusion pipelines to compose frozen checkpoints into one deployable model with no additional inference time, boosting last-task accuracy by 40.9% on UrbanSound8K.

Links: NVIDIA Grant

REVA: Reusable Evidence View Aggregation for Context-Efficient RAG Serving

Undergraduate Research Assistant, University of Illinois Urbana-Champaign, 2026.02-2026.09, Champaign, IL

• Proposed attention-based scoring for post-retrieval RAG context compression to reuse generator attention traces across queries and update the system offline, achieving a 91.6% cache hit rate on HotpotQA.
• Developed reusable evidence views to scale compression cost with unique documents rather than query volume, improving F1 by 13.2% on Natural Questions and decreasing online compression overhead by 6.1x at under 40 ms per request.
• Optimized online serving to keep context compression off the GPU critical path for high-volume production RAG traffic under strict per-request latency targets, minimizing compression latency by 99.3% compared to EXIT and 99.8% compared to FaviComp.

Memoria

Founding Technical Lead, 2026.01-Present, Champaign, IL

• Lead end-to-end agentic workflow deployments across MCP servers, sub-agents, and agent skills with multi-agent orchestration, permission-aware tool calling, and policy guardrails, accelerating product delivery by 4.0x compared to traditional approaches.
• Manage production operations for deployed workflows with logging, evaluation harnesses, and monthly improvement cycles with client stakeholders, saving 90.5% in serving cost.
• Optimize enterprise workflows with self-evolving per-user memory and cost-aware model routing across sessions, saving 96.0% in token cost compared to GPT-4 Turbo.

Links: Website

Two by Two Learning

Full Stack Developer, 2025.08-2026.08, Champaign, IL

• Launched NOODEIA to help K-12 students falling behind grade level with multi-agent tutoring systems to plan, critique, and monitor each user with long-horizon memory, boosting user confidence by 2.4x in counterbalanced within-subjects studies.
• Designed self-evolving long-term memory architectures to replace recency-biased FIFO memory architectures by retrieving contextually relevant prior interactions, accelerating memory queries by 3.6x compared to PostgreSQL.
• Deployed complexity-aware model selection across planner, retrieval, solver, and critic stages to score each request and reserve frontier-tier inference for priority calls, eliminating 89.9% of monthly serving cost compared to GPT-4o.

Links: Website

WRC, University of Illinois Urbana-Champaign

Data Analyst, 2024.08-2024.12, Champaign, IL

• Built paired pre/post analytics pipelines over survey data from 9,935 incoming students to better allocate program resources in the upcoming years, increasing correct responses among the next cohort by 14.0% with 61.9% fewer ambiguous responses.
• Conducted A/B tests on two consent scenarios stratified across five gender-identity subgroups to locate where misconceptions persisted after each workshop, increasing accuracy on consent comprehension by 19.5%.
• Proposed scenario-based learning modules for underrepresented subgroups by coding open-ended bystander responses into five-theme taxonomies, minimizing spread in direct-intervention rates by 5.6x.

Long-Form Video-Language and Audio-Visual Social Understanding

Undergraduate Research Assistant, University of Illinois Urbana-Champaign, 2025.12-2026.05, Champaign, IL

• Trained streaming video-language models with temporal transformer blocks for long-form video understanding beyond 30-minute sequences, boosting zero-shot accuracy by 17.4%.
• Designed context fluidity pipelines to fuse facial action units, body pose, and prosody through cross-modal attention and infer social intent and conversational role from raw recordings, achieving 89.1% accuracy on speaker-role classification.
• Built end-to-end annotation pipelines for full-length clinical sessions with automatic transcription and labeling, increasing speaker-role inversion accuracy to 90.0%.

Multi-agent Research Synthesis Engine

Undergraduate Research Assistant, 2025.11-2026.05, Champaign, IL

• Orchestrated eight specialized agents across a 12-step workflow for automated literature synthesis to cover planning, retrieval, drafting, reflection, and safety review in a single loop with LLM-as-judge evaluation, achieving 95.5% accuracy on deep research pipelines.
• Developed concurrent multi-source retrieval across Semantic Scholar and Tavily with production-grade fallback handling for API failures, minimizing query latency by 40.2%.
• Built customized Model Context Protocol servers to centralize governed tool access behind unified interfaces over academic databases, code repositories, and document stores, minimizing serving latency by 87.5%.

Links: Project Page

Realistic Neural Style Transfer Architecture

Undergraduate Research Assistant, 2025.01-2025.08

• Proposed style transfer frameworks to maintain photorealistic results under highly abstract styles with VGG perceptual losses and edge-preserving constraints, improving SSIM by 77.0% and MS-SSIM by 49.0% compared to TensorFlow's NST.
• Proposed multi-layer Gram matrix losses with adaptive layer weighting to suppress texture and chromatic artifacts, boosting SSIM by 4.4x and MS-SSIM by 6.4x compared to ChatGPT-4o.

Links: GitHub

Anime Statistics and Analysis Platform, ASAP

Undergraduate Research Assistant, 2025.02-2025.06

• Deployed interactive R Shiny analytics platforms to surface anime popularity trends and market opportunities with live Jikan REST API data and predictive analysis on shinyapps.io.

Links: GitHub

CS 107 Data Science Discovery, University of Illinois Urbana-Champaign

Teaching Assistant, 2023.08-2026.05, Champaign, IL

• Led weekly lab sections and office hours for in-person and online sessions, mentoring 1,200 students every semester through data science foundations in Python, statistical inference, data wrangling, and machine learning.
• Authored DISCOVERY Guides on the course website to provide detailed explanations with applied Python and statistics walkthroughs.
• Designed problem sets, exam questions, test suites, and autograder scripts to deliver instant, consistent feedback to 1,200 students every semester on Mastery Platform.

Links: Guides, Mastery

Languages

• Chinese (Native)
• English (Native)
• Spanish (Elementary)

Certifications and Honors

• Neo4j Certified Professional
• Neo4j Graph Data Science Certification

Links: Neo4j Professional, Neo4j GDS

Education

• Columbia University, New York City, NY
• M.S. in Data Science
• Fu Foundation School of Engineering and Applied Science
• Courses: High Performance Machine Learning, Algorithms
• 2026.08 - 2028.05

Education

• University of Illinois Urbana-Champaign, Champaign, IL
• B.S. in Data Science and Information Science
• Minors: Computer Science and Statistics
• Siebel School of Computing and Data Science
• Honors: Dean's List and James Scholar
• Courses: Applied Machine Learning, Generative AI for Human-AI Collaboration, Advanced AI Web-App Development, Graph Databases, Data Visualization, Computational Photography, Linear Algebra with Computational Applications
• 2022.08 - 2026.05

OnePromptClaudeCode

Lead Developer, 2026.03-Present

• Lead development of an MIT-licensed open-source agent harness for agentic software development, minimizing setup time by 99.5%.
• Design three-tier capability routers for the agent harness to optimize tokens, latency, and cost on every turn, with keyword matching and session-memory recall ahead of a 4.5 s model reasoning pass, resolving intent in 120 ms and running 37.5x faster than routing every prompt through the model.
• Implement secure agent execution runtime with four lifecycle hooks to gate every tool call before it runs, eliminating 92.7% of router latency.

Links: GitHub