Johns Hopkins University

university

Verified

https://www.jhu.edu/

JohnsHopkins

Activity Feed Request to join this org

AI & ML interests

AI, Machine Learning, Interdisciplinary Collaboration

Recent Activity

cozzyde submitted a paper 2 days ago

Continual Learning Mechanisms Compose for Long-Horizon Memorization

andyc03 submitted a paper 7 days ago

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

ash56 submitted a paper about 2 months ago

Multimodal Speaker Verification as a Threat to Speaker Anonymization

View all activity

Papers

Continual Learning Mechanisms Compose for Long-Horizon Memorization

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

View all Papers

cozzyde

submitted a paper to Daily Papers 2 days ago

Continual Learning Mechanisms Compose for Long-Horizon Memorization

Paper • 2609.06986 • Published 11 days ago • 302

andyc03

submitted a paper to Daily Papers 7 days ago

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

Paper • 2609.05903 • Published 13 days ago • 63

mahwizzzz

posted an update 8 days ago

Post

I implemented the attention-free bidirectional encoder architecture Avey-B for Urdu a compact 24.87M-parameter language encoder built for efficient Urdu NLP research.

Original Avey-B paper: Avey-B (2602.15814)
Urdu model: mahwizzzz/avey-b-ur

mahwizzzz

posted an update about 1 month ago

Post

205

If you're into running models locally, this might be worth checking out.
https://local.ai/mahwiz/invite

ash56

submitted a paper to Daily Papers about 2 months ago

Multimodal Speaker Verification as a Threat to Speaker Anonymization

Paper • 2607.19636 • Published Jul 22 • 2

llwswyn

submitted a paper to Daily Papers 3 months ago

PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception

Paper • 2606.28322 • Published Jun 26 • 43

cozzyde

submitted a paper to Daily Papers 3 months ago

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

Paper • 2606.24893 • Published May 29 • 9

Chuanyang-Jin

submitted a paper to Daily Papers 4 months ago

MindZero: Learning Online Mental Reasoning With Zero Annotations

Paper • 2606.00240 • Published May 29 • 5

mahwizzzz

posted an update 4 months ago

Post

397

Released lafzyn , built over Qwen, an Urdu language model that converts Urdu text into IPA phonetic transcription, with GGUF builds for local inference.

Release contents:
- mahwizzzz/lafzyn: full weights
- mahwizzzz/lafzyn-gguf: quantized builds

Try it out 🤗
Demo: https://huggingface.co/spaces/mahwizzzz/Lafzyn