223 citations · 372 across the 13 of their papers we have counts for
15 papers
Evolving Deeper LLM Thinking
Kuang-Huei Lee, Ian Fischer, Yueh-Hua Wu +4
We explore an evolutionary search strategy for scaling inference time compute in Large Language Models. The proposed approach, Mind Evolution, uses a language model to generate, re…
Making Images from Images: Interleaving Denoising and Transformation
Shumeet Baluja, David Marwood, Ashwin Baluja
Simply by rearranging the regions of an image, we can create a new image of any subject matter. The definition of regions is user definable, ranging from regularly and irregularly-…
Diversity and Diffusion: Observations on Synthetic Image Distributions with Stable Diffusion
David Marwood, Shumeet Baluja, Yair Alon
Recent progress in text-to-image (TTI) systems, such as StableDiffusion, Imagen, and DALL-E 2, have made it possible to create realistic images with simple text prompts. It is temp…
Texture for Colors: Natural Representations of Colors Using Variable Bit-Depth Textures
Shumeet Baluja
Numerous methods have been proposed to transform color and grayscale images to their single bit-per-pixel binary counterparts. Commonly, the goal is to enhance specific attributes…
Table-Based Neural Units: Fully Quantizing Networks for Multiply-Free Inference
Michele Covell, David Marwood, Shumeet Baluja +1
In this work, we propose to quantize all parts of standard classification networks and replace the activation-weight--multiply step with a simple table-based lookup. This approach…
Neural Image Decompression: Learning to Render Better Image Previews
Shumeet Baluja, Dave Marwood, Nick Johnston +1
A rapidly increasing portion of Internet traffic is dominated by requests from mobile devices with limited- and metered-bandwidth constraints. To satisfy these requests, it has bec…
No Multiplication? No Floating Point? No Problem! Training Networks for Efficient Inference
Shumeet Baluja, David Marwood, Michele Covell +1
For successful deployment of deep neural networks on highly--resource-constrained devices (hearing aids, earbuds, wearables), we must simplify the types of operations and the memor…
Representing Images in 200 Bytes: Compression via Triangulation
David Marwood, Pascal Massimino, Michele Covell +1
A rapidly increasing portion of internet traffic is dominated by requests from mobile devices with limited and metered bandwidth constraints. To satisfy these requests, it has beco…
Empirical Explorations in Training Networks with Discrete Activations
Shumeet Baluja
We present extensive experiments training and testing hidden units in deep networks that emit only a predefined, static, number of discretized values. These units provide benefits…
Adversarial Transformation Networks: Learning to Generate Adversarial Examples
Shumeet Baluja, Ian Fischer
Multiple different approaches of generating adversarial examples have been proposed to attack deep neural networks. These approaches involve either directly computing gradients wit…
Deep Learning for Explicitly Modeling Optimization Landscapes
Shumeet Baluja
In all but the most trivial optimization problems, the structure of the solutions exhibit complex interdependencies between the input parameters. Decades of research with stochasti…
Traffic Lights with Auction-Based Controllers: Algorithms and Real-World Data
Shumeet Baluja, Michele Covell, Rahul Sukthankar
Real-time optimization of traffic flow addresses important practical problems: reducing a driver's wasted time, improving city-wide efficiency, reducing gas emissions and improving…
Learning Typographic Style
Shumeet Baluja
Typography is a ubiquitous art form that affects our understanding, perception, and trust in what we read. Thousands of different font-faces have been created with enormous variati…
Labeling the Features Not the Samples: Efficient Video Classification with Minimal Supervision
Marius Leordeanu, Alexandra Radu, Shumeet Baluja +1
Feature selection is essential for effective visual recognition. We propose an efficient joint classifier learning and feature selection method that discovers sparse, compact repre…
Variable Rate Image Compression with Recurrent Neural Networks
George Toderici, Sean M. O'Malley, Sung Jin Hwang +5
A large fraction of Internet traffic is now driven by requests from mobile devices with relatively small screens and often stringent bandwidth requirements. Due to these factors, i…