Dr. Bin Liu
Hey there 👋
I'm Dr. Bin Liu
Engineer, Researcher, Designer, and Sneakerhead

AI scientist and manager based in Houston, working on enterprise agent systems and the platforms they run on. Never defined by any single title or discipline, I like to learn by doing and sharing what I learn.

This site is where I share what I'm working on and what I'm learning: projects and CV up top, a blog for workflow notes and paper reads, and lecture notes across computational intelligence, physics, mechanical engineering, and mathematics.

Say hello
Selected projects

Multi-Agent Orchestrator

Conversational entry point that classifies user intent, routes to specialist agents, and orchestrates multi-step autonomous plans with human approval.

LangGraphMulti-AgentPython
Enterprise project →

Voice Control Bridge

Hands-free, real-time audio control of the plant system with native speech understanding, barge-in, and natural turn-taking.

Realtime AudioWebSocketReact
Enterprise project →

Root Cause Analysis Agent

A parallel agent swarm that investigates equipment failures across an institutional knowledge graph, the public web, and internal documentation, with human-in-the-loop plan review.

LangGraphAgent SwarmRAG
Enterprise project →
Latest from blog

ConceptSeg-R1: teaching a segmenter to induce the rule, not just solve the instance
Paper notes

Paper notes on ConceptSeg-R1 — RL-style reasoning over SAM 3's prompt space, using Meta-GRPO to infer transferable segmentation rules from a few visual demonstrations.

LocateAnything: decoding bounding boxes in parallel instead of one token at a time
Paper notes

Paper notes on NVIDIA's LocateAnything — a 3B vision-language grounding model that treats boxes as atomic units via Parallel Box Decoding, hitting 10× the throughput of comparable VLMs.

MiniMind-O: training a from-scratch omni model over a weekend
Weekend build

A hands-on plan for MiniMind-O — a ~0.1B end-to-end omni model that takes text/audio/image in and emits text + streaming speech, with the mini pipeline running in ~2 hours on one RTX 3090.
© 2026 Dr. Bin Liu