5 citations · 13 across the 9 of their papers we have counts for
9 papers
SonicSampler: Unified Tile-Aware Kernels for LLM Sampling and Speculative Verification
Pragaash Ponnusamy, Shivam Sahni, Jue Wang +1
Sampling in LLM inference comprises a combinatorial set of logit processing, token selection, and verification operations for speculative decoding. However, existing implementation…
Search Your Block Floating Point Scales!
Tanmaey Gupta, Hayden Prairie, Xiaoxia Wu +10
Quantization has emerged as a standard technique for accelerating inference for generative models by enabling faster low-precision computations and reduced memory transfers. Recent…
Understanding and Steering the Cognitive Behaviors of Reasoning Models at Test-Time
Zhenyu Zhang, Xiaoxia Wu, Zhongzhu Zhou +7
Large Language Models (LLMs) often rely on long chain-of-thought (CoT) reasoning to solve complex tasks. While effective, these trajectories are frequently inefficient, leading to…
Training-Free Activation Sparsity in Large Language Models
James Liu, Pragaash Ponnusamy, Tianle Cai +3
Activation sparsity can enable practical inference speedups in large language models (LLMs) by reducing the compute and memory-movement required for matrix multiplications during t…
Mechanistic Design and Scaling of Hybrid Architectures
Michael Poli, Armin W Thomas, Eric Nguyen +9
The development of deep learning architectures is a resource-demanding process, due to a vast design space, long prototyping times, and high compute costs associated with at-scale…
Self-Aware Feedback-Based Self-Learning in Large-Scale Conversational AI
Pragaash Ponnusamy, Clint Solomon Mathialagan, Gustavo Aguilar +2
Self-learning paradigms in large-scale conversational AI agents tend to leverage user feedback in bridging between what they say and what they mean. However, such learning, particu…
A Vocabulary-Free Multilingual Neural Tokenizer for End-to-End Task Learning
Md Mofijul Islam, Gustavo Aguilar, Pragaash Ponnusamy +3
Subword tokenization is a commonly used input pre-processing step in most recent NLP models. However, it limits the models' ability to leverage end-to-end task learning. Its freque…
Personalized Query Rewriting in Conversational AI Agents
Alireza Roshan-Ghias, Clint Solomon Mathialagan, Pragaash Ponnusamy +2
Spoken language understanding (SLU) systems in conversational AI agents often experience errors in the form of misrecognitions by automatic speech recognition (ASR) or semantic gap…
Feedback-Based Self-Learning in Large-Scale Conversational AI Agents
Pragaash Ponnusamy, Alireza Roshan Ghias, Chenlei Guo +1
Today, most large-scale conversational AI agents (e.g. Alexa, Siri, or Google Assistant) are built using manually annotated data to train the different components of the system. Ty…