Johns Hopkins University

university

Verified

https://www.jhu.edu/

Activity Feed Request to join this org

AI & ML interests

AI, Machine Learning, Interdisciplinary Collaboration

Recent Activity

Chuanyang-Jin authored a paper 13 days ago

IdeaScientist: Orchestrating Agents for Grounded Scientific Ideation

Chuanyang-Jin authored a paper 13 days ago

Into the Unknown: Benchmarking AI agents on open scientific research problems

Chuanyang-Jin authored a paper 13 days ago

HyperTrace: Hypothesis-Based Preference Tracing for Online LLM Personalization

View all activity

Papers

Accurate but Not Humble: Evaluating Epistemic Humility in LLM Agents under Knowledge Conflict

Gricea: An Open Science Platform for Conversational AI Research

View all Papers

authored a paper 5 days ago

Training Foundation Models with a Single Algorithm

Paper • 2610.40564 • Published 6 days ago • 13

submitted a paper to Daily Papers 5 days ago

Training Foundation Models with a Single Algorithm

Paper • 2610.40564 • Published 6 days ago • 13

authored 4 papers 13 days ago

IdeaScientist: Orchestrating Agents for Grounded Scientific Ideation

Paper • 2610.04074 • Published 26 days ago • 2

Into the Unknown: Benchmarking AI agents on open scientific research problems

Paper • 2610.19159 • Published 22 days ago • 56

HyperTrace: Hypothesis-Based Preference Tracing for Online LLM Personalization

Paper • 2609.09835 • Published Sep 9 • 1

Humanity's Last Exam

Paper • 2501.14249 • Published Jul 28 • 77

KaiserWhoLearns

submitted a paper to Daily Papers 26 days ago

Accurate but Not Humble: Evaluating Epistemic Humility in LLM Agents under Knowledge Conflict

Paper • 2610.12360 • Published 27 days ago • 8

submitted a paper to Daily Papers about 1 month ago

Gricea: An Open Science Platform for Conversational AI Research

Paper • 2609.22039 • Published Sep 18 • 11

authored 3 papers about 1 month ago

Trust Functions: Near-Lossless Weak-to-Strong Generalization by Learning When to Trust the Weak Teacher

Paper • 2606.01000 • Published May 31 • 7

AgentOdyssey: Open-Ended Long-Horizon Text Game Generation for Test-Time Continual Learning Agents

Paper • 2606.24893 • Published May 29 • 9

Continual Learning Mechanisms Compose for Long-Horizon Memorization

Paper • 2609.06986 • Published Sep 7 • 59

submitted a paper to Daily Papers about 2 months ago

Continual Learning Mechanisms Compose for Long-Horizon Memorization

Paper • 2609.06986 • Published Sep 7 • 59

submitted a paper to Daily Papers about 2 months ago

EvoSafeHarness: Evolving Model- and Domain-Specific Harnesses for Securing Agents

Paper • 2609.05903 • Published Sep 5 • 45

submitted a paper to Daily Papers 3 months ago

Multimodal Speaker Verification as a Threat to Speaker Anonymization

Paper • 2607.19636 • Published Jul 22 • 2

submitted a paper to Daily Papers 4 months ago

PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception

Paper • 2606.28322 • Published Jun 26 • 42

submitted a paper to Daily Papers 4 months ago

AgentOdyssey: Open-Ended Long-Horizon Text Game Generation for Test-Time Continual Learning Agents

Paper • 2606.24893 • Published May 29 • 9

authored a paper 4 months ago

Self-Compacting Language Model Agents

Paper • 2606.23525 • Published Jun 22 • 19

authored 2 papers 5 months ago

Strong Teacher Not Needed? On Distillation in LLM Pretraining

Paper • 2605.23857 • Published May 22 • 1

i1: A Simple and Fully Open Recipe for Strong Text-to-Image Models

Paper • 2606.11289 • Published Jun 9 • 20

authored a paper 5 months ago

MindZero: Learning Online Mental Reasoning With Zero Annotations

Paper • 2606.00240 • Published May 29 • 4