University of Alberta

university

Verified

https://www.ualberta.ca/

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

mnahid authored a paper about 1 month ago

PARTAB: Partition-Aware Reasoning with Structured Evidence for Scalable Table Understanding

tafseer-nayeem authored a paper 6 months ago

Are Large Vision Language Models up to the Challenge of Chart Comprehension and Reasoning? An Extensive Investigation into the Capabilities and Limitations of LVLMs

tafseer-nayeem authored a paper 6 months ago

How Does "English (US)" Become the Default? Triangulating Structural Bias Towards American English Across the LLM Pipeline

View all activity

Papers

Who Gets a Token, and What Does It Carry? Unequal Name Support and Concept Access in Large Language Models

How Does "English (US)" Become the Default? Triangulating Structural Bias Towards American English Across the LLM Pipeline

View all Papers

mnahid

authored a paper about 1 month ago

PARTAB: Partition-Aware Reasoning with Structured Evidence for Scalable Table Understanding

Paper • 2608.24082 • Published Aug 25

yongchanghao

submitted a paper to Daily Papers 6 months ago

Cactus: Accelerating Auto-Regressive Decoding with Constrained Acceptance Speculative Sampling

Paper • 2604.04987 • Published Apr 5 • 4

LiyaoJiang

submitted a paper to Daily Papers 7 months ago

RAISE: Requirement-Adaptive Evolutionary Refinement for Training-Free Text-to-Image Alignment

Paper • 2603.00483 • Published Feb 28 • 3

AmirhoseinGH

submitted a paper to Daily Papers 9 months ago

Can LLMs Predict Their Own Failures? Self-Awareness via Internal Circuits

Paper • 2512.20578 • Published Dec 23, 2025 • 87

Sagaust

published a Space 10 months ago

README

🐠

mnahid

authored 2 papers 12 months ago

Rethinking Schema Linking: A Context-Aware Bidirectional Retrieval Approach for Text-to-SQL

Paper • 2510.14296 • Published Oct 16, 2025

PRISM: Agentic Retrieval with LLMs for Multi-Hop Question Answering

Paper • 2510.14278 • Published Oct 16, 2025

mnahid

authored a paper almost 2 years ago

Comprehending Real Numbers: Development of Bengali Real Number Speech Corpus

Paper • 1803.10136 • Published Mar 27, 2018

yongchanghao

authored a paper almost 2 years ago

Teacher Forcing Recovers Reward Functions for Text Generation

Paper • 2210.08708 • Published Oct 17, 2022

yongchanghao

posted an update almost 2 years ago

Post

3857

We just released a paper (NeuZip) that compresses VRAM in a lossless manner to run larger models. This should be particularly useful when VRAM is insufficient during training/inference. Specifically, we look inside each floating number and find that the exponents are highly compressible (as shown in the figure below).

Read more about the work at NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks (2410.20650)