Wonmin Byeon

@wonmin_byeon

Researcher

California

wonmin-byeon.github.io

Joined March 2020

292 Following

1,071 Followers

Replies Reposts Media

Pinned
Wonmin Byeon
@wonmin_byeon
Mar 4
🚀 New paper: Mamba–Transformer hybrid VLMs can go fast without forgetting. We introduce stateful token reduction for long-video VLMs. ✅ Only 25% of visual tokens 🚀 3.8–4.2× faster prefilling (TTFT) 🎯 Near-baseline accuracy (can exceed baseline with light finetuning)
3
Wonmin Byeon
@wonmin_byeon
Nov 2
Excited to share AgentBaton, our work at #NVIDIA showing how well-timed handoffs to a smaller model can cut costs by 65.9% on average while maintaining or improving accuracy.
Jindong Jiang
@JindongJiang
Nov 2
When should an AI agent pass the baton? 🚀 Introducing our work AgentBaton from NVIDIA Research: efficient model collaboration through well-timed handoffs. We study how capable and efficient models can collaborate without fine-tuning either one: who starts, when to switch, and
1
Wonmin Byeon
@wonmin_byeon
Jul 6
I'm at #ICML2026! Reach out if you’d like to discuss hybrid models, efficient LLMs/VLMs, memory models, or related topics.
2
Wonmin Byeon
@wonmin_byeon
Feb 27
It’s been months since we introduced STORM, and it’s great to see so many video discussions! ⛈️🎥 To catch up on our token-efficient long video understanding work, check out these reviews (Some are AI-generated but very useful!). Huge thanks to the creators! 🙌 The links ↓
Wonmin Byeon
@wonmin_byeon
Aug 19, 2025
🚀 New paper: STORM — Efficient VLM for Long Video Understanding STORM cuts compute costs by up to 8× and reduces decoding latency by 2.4–2.9×, while achieving state-of-the-art performance. Details + paper link in the thread ↓
1
Wonmin Byeon
@wonmin_byeon
Dec 16, 2025
NVIDIA’s hybrid model just got bigger, faster, and stronger.
Bryan Catanzaro
@ctnzr
Dec 15, 2025
Today, @nvidia is launching the open Nemotron 3 model family, starting with Nano (30B-3A), which pushes the frontier of accuracy and inference efficiency with a novel hybrid SSM Mixture of Experts architecture. Super and Ultra are coming in the next few months.

Wonmin Byeon

Wonmin Byeon’s posts