Seonglae Cho

seonglae's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

commented a paper about 7 hours ago

AgentRoom: Concurrent Multi-Agent Coding in a CRDT-Backed Shared Workspace

Paper • 2608.23740 • Published 3 days ago • 5 •

3

updated a model about 11 hours ago

seonglae/vls-speech-head

Updated about 11 hours ago

published a model about 11 hours ago

seonglae/vls-speech-head

Updated about 11 hours ago

authored 2 papers about 13 hours ago

Automata from Agent Traces: Failure and Next-Step Prediction

Paper • 2608.23670 • Published 3 days ago • 4

AgentRoom: Concurrent Multi-Agent Coding in a CRDT-Backed Shared Workspace

Paper • 2608.23740 • Published 3 days ago • 5

upvoted a paper about 15 hours ago

AgentRoom: Concurrent Multi-Agent Coding in a CRDT-Backed Shared Workspace

Paper • 2608.23740 • Published 3 days ago • 5

submitted a paper to Daily Papers about 15 hours ago

AgentRoom: Concurrent Multi-Agent Coding in a CRDT-Backed Shared Workspace

Paper • 2608.23740 • Published 3 days ago • 5

upvoted a paper about 15 hours ago

Automata from Agent Traces: Failure and Next-Step Prediction

Paper • 2608.23670 • Published 3 days ago • 4

submitted a paper to Daily Papers about 15 hours ago

Automata from Agent Traces: Failure and Next-Step Prediction

Paper • 2608.23670 • Published 3 days ago • 4

updated a dataset about 20 hours ago

seonglae/vls-100k

Viewer • Updated about 19 hours ago • 74.9k

published a dataset about 20 hours ago

seonglae/vls-100k

Viewer • Updated about 19 hours ago • 74.9k

updated a dataset 1 day ago

seonglae/vls-10k

Viewer • Updated about 15 hours ago • 9.99k • 2

updated 2 Spaces 1 day ago

Paused

OptimismBench

🎲

Sleeping

AgentRoom

🏠

Explore multi‑agent coding collaboration in a shared workspace

updated 2 Spaces 3 days ago

Running

Automata from Agent Traces

🔁

Explore agent behavior with interactive FSM visualizations

Paused

PaaT: Probe as a Tool for Proprioceptive Language Agents

🔀

updated 3 Spaces 6 days ago

Paused

Confidence Manifold

🧭

Running

4

CorrSteer: Correlation-Based Steering of Language Models via Sparse Autoencoders

🧭

4

Steer language model output by clicking visual layers

Paused

Control Reinforcement Learning

🎛

Explore LLM token decisions with feature‑driven visualizations

upvoted a paper 27 days ago

Control Reinforcement Learning: Interpretable Token-Level Steering of LLMs via Sparse Autoencoder Features

Paper • 2602.10437 • Published Feb 12 • 2