Columbia University

university

Verified

https://www.columbia.edu

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

Deema authored a paper about 1 month ago

FactCheckmate: Preemptively Detecting and Mitigating Hallucinations in LMs

Deema authored a paper about 1 month ago

Covert Assistance: Helpful LLM Agents Evade Oversight in Multi-Agent Systems

Deema submitted a paper about 1 month ago

Covert Assistance: Helpful LLM Agents Evade Oversight in Multi-Agent Systems

View all activity

Papers

Two-Fidelity Best-Action Identification for Stochastic Minimax Tree

Minimalist Visual Inertial Odometry

View all Papers

mahwizzzz

posted an update 6 days ago

Post

1,026

Released: Urdu Streaming Zipformer 20M

Introducing Urdu Streaming ASR, a compact causal Zipformer transducer developed for Urdu speech recognition.

FLEURS Urdu (299 utterances):
WER: 28.03%
CER: 11.96%

Model: mahwizzzz/Urdu-Streaming-Zipformer-20M
Source: https://github.com/mwzkhalil/Urdu-Streaming-ASR

2 replies

mahwizzzz

posted an update about 2 months ago

Post

284

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: https://huggingface.co/mahwizzzz/avey-b-ur

mahwizzzz

posted an update 3 months ago

Post

220

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

velezbeltran

authored a paper 5 months ago

The Reward Was in Your Data All Along: Correcting Flow Matching with Discriminator-Guided RL

Paper • 2606.19162 • Published Jun 17 • 22

velezbeltran

submitted a paper to Daily Papers 5 months ago

The Reward Was in Your Data All Along: Correcting Flow Matching with Discriminator-Guided RL

Paper • 2606.19162 • Published Jun 17 • 22

PeterLauLukCh

submitted a paper to Daily Papers 5 months ago

Two-Fidelity Best-Action Identification for Stochastic Minimax Tree

Paper • 2606.01708 • Published Jun 1 • 3

mahwizzzz

posted an update 5 months ago

Post

407

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