University of Alberta

university

Verified

https://www.ualberta.ca/

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

yongchanghao submitted a paper 27 days ago

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

LiyaoJiang authored a paper 2 months ago

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

LiyaoJiang submitted a paper 2 months ago

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

View all activity

Papers

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

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

View all Papers

authored 2 papers 27 days 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

Paper • 2406.00257 • Published Jun 1, 2024

Which English Do LLMs Prefer? Triangulating Structural Bias Towards American English in Foundation Models

Paper • 2604.04204 • Published Apr 5 • 1

submitted a paper to Daily Papers 27 days ago

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

Paper • 2604.04987 • Published Apr 5 • 3

submitted a paper to Daily Papers 2 months ago

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

Paper • 2603.00483 • Published Feb 28 • 3

authored a paper 4 months ago

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

Paper • 2512.20578 • Published Dec 23, 2025 • 86

submitted a paper to Daily Papers 4 months ago

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

Paper • 2512.20578 • Published Dec 23, 2025 • 86

published a Space 5 months ago

README

authored 2 papers 7 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

authored 2 papers 7 months ago

OpinioRAG: Towards Generating User-Centric Opinion Highlights from Large-scale Online Reviews

Paper • 2509.00285 • Published Aug 30, 2025

SurveyGen: Quality-Aware Scientific Survey Generation with Large Language Models

Paper • 2508.17647 • Published Aug 25, 2025

authored a paper 10 months ago

On the Role of Reviewer Expertise in Temporal Review Helpfulness Prediction

Paper • 2303.00923 • Published Feb 22, 2023

authored a paper over 1 year ago

Comprehending Real Numbers: Development of Bengali Real Number Speech Corpus

Paper • 1803.10136 • Published Mar 27, 2018

authored a paper over 1 year ago

Teacher Forcing Recovers Reward Functions for Text Generation

Paper • 2210.08708 • Published Oct 17, 2022

posted an update over 1 year ago

Post

3835

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)

authored 2 papers over 1 year ago

DTT: An Example-Driven Tabular Transformer for Joinability by Leveraging Large Language Models

Paper • 2303.06748 • Published Mar 12, 2023

Evaluating Cross-Domain Text-to-SQL Models and Benchmarks

Paper • 2310.18538 • Published Oct 27, 2023

authored a paper almost 2 years ago

TexGen: Text-Guided 3D Texture Generation with Multi-view Sampling and Resampling

Paper • 2408.01291 • Published Aug 2, 2024 • 12

authored 2 papers almost 2 years ago

Large Language Models are Pretty Good Zero-Shot Video Game Bug Detectors

Paper • 2210.02506 • Published Oct 5, 2022

Zoom is what you need: An empirical study of the power of zoom and spatial biases in image classification

Paper • 2304.05538 • Published Apr 11, 2023 • 2