activity
20162025
most citedIA-RED: Interpretability-Aware Redundancy Reduction for Vision Transformers

68 citations · 278 across the 31 of their papers we have counts for

collaborators
Showing 2024Show all

15 papers · 1 filter

cs.LG2024

Scaling Stick-Breaking Attention: An Efficient Implementation and In-depth Study

Shawn Tan, Songlin Yang, Aaron Courville +2

The self-attention mechanism traditionally relies on the softmax operator, necessitating positional embeddings like RoPE, or position biases to account for token order. But current…

cs.CL20241 cited

Power Scheduler: A Batch Size and Token Number Agnostic Learning Rate Scheduler

Yikang Shen, Matthew Stallone, Mayank Mishra +6

Finding the optimal learning rate for language model pretraining is a challenging task. This is not only because there is a complicated correlation between learning rate, batch siz…

cs.CV2024

SITAR: Semi-supervised Image Transformer for Action Recognition

Owais Iqbal, Omprakash Chakraborty, Aftab Hussain +2

Recognizing actions from a limited set of labeled videos remains a challenge as annotating visual data is not only tedious but also can be expensive due to classified nature. Moreo…

cs.AI20241 cited

Scaling Granite Code Models to 128K Context

Matt Stallone, Vaibhav Saxena, Leonid Karlinsky +19

This paper introduces long-context Granite code models that support effective context windows of up to 128K tokens. Our solution for scaling context length of Granite 3B/8B code mo…

cs.DC2024

The infrastructure powering IBM's Gen AI model development

Talia Gershon, Seetharami Seelam, Brian Belgodere +143

AI Infrastructure plays a key role in the speed and cost-competitiveness of developing and deploying advanced AI models. The current demand for powerful AI infrastructure for model…

cs.LG20241 cited

Granite-Function Calling Model: Introducing Function Calling Abilities via Multi-task Learning of Granular Tasks

Ibrahim Abdelaziz, Kinjal Basu, Mayank Agarwal +23

Large language models (LLMs) have recently shown tremendous promise in serving as the backbone to agentic systems, as demonstrated by their performance in multi-faceted, challengin…