Center for Language and Speech Processing @ JHU

university

https://www.clsp.jhu.edu/

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

KaiserWhoLearns authored a paper 8 days ago

What Effort Level Should I Choose? On the Economics of Reasoning Effort in LLM Agents

KaiserWhoLearns submitted a paper 8 days ago

What Effort Level Should I Choose? On the Economics of Reasoning Effort in LLM Agents

Chuanyang-Jin authored a paper 13 days ago

IdeaScientist: Orchestrating Agents for Grounded Scientific Ideation

View all activity

Papers

Where Does Retrieval-Based Open-Ended Evaluation Fail? Automatic Taxonomy Induction from Long-Form Medical Answer Factuality Verification

Convergent Emergence of In-Context Learning Across Modalities

View all Papers

KaiserWhoLearns

authored a paper 8 days ago

What Effort Level Should I Choose? On the Economics of Reasoning Effort in LLM Agents

Paper • 2610.34491 • Published 11 days ago • 22

KaiserWhoLearns

submitted a paper to Daily Papers 8 days ago

What Effort Level Should I Choose? On the Economics of Reasoning Effort in LLM Agents

Paper • 2610.34491 • Published 11 days ago • 22

authored a paper 13 days ago

IdeaScientist: Orchestrating Agents for Grounded Scientific Ideation

Paper • 2610.04074 • Published 27 days ago • 2

authored 2 papers 13 days ago

AdaProb: Efficient Machine Unlearning via Adaptive Probability

Paper • 2411.02622 • Published Apr 9 • 1

Exploring The Empirical Privacy Landscape of Synthetic Data

Paper • 2610.22659 • Published 21 days ago • 4

authored 3 papers 13 days ago

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

Paper • 2610.19159 • Published 23 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

authored a paper 13 days ago

SynthTextEval: Synthetic Text Data Generation and Evaluation for High-Stakes Domains

Paper • 2507.07229 • Published Jul 9, 2025 • 11

submitted a paper to Daily Papers 13 days ago

Exploring The Empirical Privacy Landscape of Synthetic Data

Paper • 2610.22659 • Published 21 days ago • 4

KaiserWhoLearns

authored a paper 27 days ago

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

Paper • 2610.12360 • Published 28 days ago • 8

KaiserWhoLearns

submitted a paper to Daily Papers 27 days ago

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

Paper • 2610.12360 • Published 28 days ago • 8

authored 4 papers 30 days ago

Medical Text Simplification: Optimizing for Readability with Unlikelihood Training and Reranked Beam Search Decoding

Paper • 2310.11191 • Published Oct 26, 2023

Same Verdict, Different Reasons: LLM-as-a-Judge and Clinician Disagreement on Medical Chatbot Completeness

Paper • 2604.16383 • Published Mar 26

Where Does Retrieval-Based Open-Ended Evaluation Fail? Automatic Taxonomy Induction from Long-Form Medical Answer Factuality Verification

Paper • 2609.30467 • Published Sep 24 • 4

How to Interpret Agent Behavior

Paper • 2605.13625 • Published May 13 • 1

submitted a paper to Daily Papers about 1 month ago

Where Does Retrieval-Based Open-Ended Evaluation Fail? Automatic Taxonomy Induction from Long-Form Medical Answer Factuality Verification

Paper • 2609.30467 • Published Sep 24 • 4

KaiserWhoLearns

authored 3 papers about 1 month ago

PrimeScientist: Strategic Allocation of Research Effort in Autonomous Research

Paper • 2609.17846 • Published Sep 15 • 2

Last Translation Benchmark

Paper • 2609.04173 • Published Sep 3 • 42

How to Interpret Agent Behavior

Paper • 2605.13625 • Published May 13 • 1