-
KAIST
- https://seongsubae.info
Highlights
- Pro
Lists (3)
Sort Name ascending (A-Z)
Starred repositories
[TACL'26] VoiceBench: Benchmarking LLM-Based Voice Assistants
ICLR 2026 - official implementation for "MathNet: a Global Multimodal Benchmark for Mathematical Reasoning and Retrieval"
Practical, Colab-friendly notebooks for fine-tuning and running audio AI models
[ICLR 2026] Code for the paper "Graph-of-Agents: A Graph-based Framework for Multi-Agent LLM Collaboration"
The agent that grows with you
MedAutoBench — Medical AutoResearch Benchmark for Autonomous AI Agents
Using a personal Slack workspace and a custom Slack bot to (1) control a Claude Code agent running in a server's tmux session, and (2) make direct Anthropic API calls to the Claude model — independ…
RadAgent: A tool-using AI agent for stepwise interpretation of chest computed tomography
Speaker diarization for Python — "who spoke when?" CPU-only, no API keys, Apache 2.0. ~10.8% DER on VoxConverse, 8x faster than real-time.
🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
Local-first session intelligence and analytics for coding agents, supporting Claude Code, Codex, and 14 other agents. Also: 100x faster replacement for ccusage!
[CVPR 2026 Oral] Official implementation for "MEDIC-AD: Towards Medical Vision-Language Model's Clinical Intelligence"
Evaluation kit for K-MetBench, a multimodal benchmark for expert meteorological reasoning, geo-cultural alignment, and weather-domain QA in Korean.
AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, GitHub Copilot CLI, OpenClaw, Factory Droid, Trae, Google Antigravity). Turn any folder of code, docs, papers, images, o…
MONAI Label is an intelligent open source image labeling and learning tool.
Claude Code skills for medical research — literature search, reporting guidelines, statistical analysis, publication figures. Built by a physician-researcher, tested on real publications. MIT licen…
Multilingual Multi-institutional EHR prediction
Installable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill c…
CheXOne: A Reasoning-Enabled Vision–Language Foundation Model for Chest X-ray Interpretation
Academic Research Skills for Claude Code: research → write → review → revise → finalize
[ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Rule