HAICOSYSTEM: An Ecosystem for Sandboxing Safety Risks in Human-AI Interactions
Paper • 2409.16427 • Published • 1
Hyunwoo Kim
heanu
AI & ML interests
Think think think
Recent Activity
authored a paper 10 days ago
HAICOSYSTEM: An Ecosystem for Sandboxing Safety Risks in Human-AI
Interactions authored a paper 10 days ago
SimpleToM: Exposing the Gap between Explicit ToM Inference and Implicit
ToM Application in LLMs authored a paper 10 days ago
Retro-Search: Exploring Untaken Paths for Deeper and Efficient ReasoningOrganizations
authored 8
papers 10 days ago
SimpleToM: Exposing the Gap between Explicit ToM Inference and Implicit ToM Application in LLMs
Paper • 2410.13648 • Published
Retro-Search: Exploring Untaken Paths for Deeper and Efficient Reasoning
Paper • 2504.04383 • Published
Social World Models
Paper • 2509.00559 • Published • 1
Long Grounded Thoughts: Distilling Compositional Visual Reasoning Chains at Scale
Paper • 2511.05705 • Published • 10
Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text
Paper • 2601.22975 • Published • 110
Privasis: Synthesizing the Largest "Public" Private Dataset from Scratch
Paper • 2602.03183 • Published • 11
Hypothesis-Driven Theory-of-Mind Reasoning for Large Language Models
Paper • 2502.11881 • Published
published a
dataset 10 days ago
updated a
dataset 10 days ago
liked a
dataset 22 days ago
liked a
Space about 1 month ago
upvoted a paper 2 months ago
submitted a
paper to Daily Papers 2 months ago
upvoted a paper 2 months ago
upvoted an article 3 months ago
Article
Nemotron-Personas: Improve AI Training With the First Synthetic Personas Dataset Aligned to Real-World Distributions
•
25
upvoted a paper 3 months ago
liked a
model 4 months ago
upvoted a paper 9 months ago
upvoted a paper 10 months ago