Projects

AURA: Autoresearch via Reflective Adaptation for Compound AI Systems

Inspired by Karpathy's *autoresearch* direction, AURA is a sample-efficient prompt optimizer for compound AI systems: after every rollout it hands the full trace back to the LLM and asks for one named edit to its own prompt. Across multi-hop QA, instruction following, and AIME-style math, AURA matches GRPO with up to 35× fewer rollouts and beats MIPROv2 by ~10 points on aggregate.

LLM
Prompt Optimization
Compound AI
Reflection
Autoresearch

Continually Learning Interactive Robot

An embodied agent that keeps expanding its behavior repertoire through ongoing human–robot interaction — new skills, new object concepts, and new language grounding are acquired online rather than baked in at training time.

HRI
Continual Learning
Multimodal
Agent

Thinking-with-Image: RL for Tool-Augmented Visual Reasoning

Reproduced and extended the VTool-R1 / ReFocus line of work so a VLM actively rewrites the chart it is reading — masking, boxing, and highlighting the relevant rows and columns mid-reasoning — turning thinking-in-text into thinking-in-image. The tool-using policy is trained end-to-end with RL (veRL + GRPO + DAPO). On ChartQA-style QA with Qwen2.5-VL-3B, answer accuracy rose from 62% to 96%.

RL
veRL
DAPO
GRPO
Qwen2.5-VL
vLLM

Real-time Packaging QA on a Hazardous-Explosive Production Line

Industrial vision QA system for a live hazardous-powder-explosive packaging line. ≥ 99% accuracy over a 30-day production run on the customer's RTX 4060; operator-level alarms via a fixed-protocol online-monitoring API.

Multi-scale Feat
Boundary Loss
Cython
TensorRT
Reparam

Legal-Domain LLM Assistant

A legal-service LLM built with Southwest University of Political Science and Law (SWUPL) and Beijing Chaoxing Tianxia: RoPE-extended long-context backbone, legal knowledge graph + vector DB, tool-calling and form-filling agent, and a small intent/NER model that rewrites user questions into formal logical symbols for reasoning.

LLM
RoPE
Knowledge Graph
RAG
Agent
NER

GNN-Accelerated MILP Scheduling for Industrial Electroplating

Formulated aerospace-part electroplating scheduling as a large-scale MILP and trained a GNN on historical schedules to provide warm-start solutions and variable priorities. FENNEL graph partitioning + high-confidence variable fixing reduced the effective search space by ≈ 10×; average solve time ≳ 10× faster.

MILP
GNN
FENNEL
Gurobi