11 citations · 43 across the 16 of their papers we have counts for
11 papers · 1 filter
DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation
Zining Liu, Yunhai Hu, Tianhua Xia +4
Speculative decoding (SD) has proven to be an effective technique for accelerating autoregressive generation in large language models (LLMs) however, its application to vision-lang…
CodeQuant: Unified Clustering and Quantization for Enhanced Outlier Smoothing in Low-Precision Mixture-of-Experts
Xiangyang Yin, Xingyu Liu, Tianhua Xia +5
Outliers have emerged as a fundamental bottleneck in preserving accuracy for low-precision large models, particularly within Mixture-of-Experts (MoE) architectures that are increas…
TapOut: A Bandit-Based Approach to Dynamic Speculative Decoding
Aditya Sridhar, Nish Sinnadurai, Sean Lie +1
Speculative decoding accelerates LLMs by using a lightweight draft model to generate tokens autoregressively before verifying them in parallel with a larger target model. However,…
REAP the Experts: Why Pruning Prevails for One-Shot MoE compression
Mike Lasby, Ivan Lazarevich, Nish Sinnadurai +3
Sparsely-activated Mixture-of-Experts (SMoE) models offer efficient pre-training and low latency but their large parameter counts create significant memory overhead, motivating res…
MASSV: Multimodal Adaptation and Self-Data Distillation for Speculative Decoding of Vision-Language Models
Mugilan Ganesan, Shane Segal, Ankur Aggarwal +3
Speculative decoding significantly accelerates language model inference by enabling a lightweight draft model to propose multiple tokens that a larger target model verifies simulta…
Self-Data Distillation for Recovering Quality in Pruned Large Language Models
Vithursan Thangarasa, Ganesh Venkatesh, Mike Lasby +2
Large language models have driven significant progress in natural language processing, but their deployment requires substantial compute and memory resources. As models scale, comp…
Sparse-IFT: Sparse Iso-FLOP Transformations for Maximizing Training Efficiency
Vithursan Thangarasa, Shreyas Saxena, Abhay Gupta +1
Recent research has focused on weight sparsity in deep neural network training to reduce FLOPs, aiming for improved efficiency (test accuracy w.r.t training FLOPs). However, sparse…
SPDF: Sparse Pre-training and Dense Fine-tuning for Large Language Models
Vithursan Thangarasa, Abhay Gupta, William Marshall +5
The pre-training and fine-tuning paradigm has contributed to a number of breakthroughs in Natural Language Processing (NLP). Instead of directly training on a downstream task, lang…
RevBiFPN: The Fully Reversible Bidirectional Feature Pyramid Network
Vitaliy Chiley, Vithursan Thangarasa, Abhay Gupta +3
This work introduces RevSilo, the first reversible bidirectional multi-scale feature fusion module. Like other reversible methods, RevSilo eliminates the need to store hidden activ…
Enabling Continual Learning with Differentiable Hebbian Plasticity
Vithursan Thangarasa, Thomas Miconi, Graham W. Taylor
Continual learning is the problem of sequentially learning new tasks or knowledge while protecting previously acquired knowledge. However, catastrophic forgetting poses a grand cha…
Self-Paced Learning with Adaptive Deep Visual Embeddings
Vithursan Thangarasa, Graham W. Taylor
Selecting the most appropriate data examples to present a deep neural network (DNN) at different stages of training is an unsolved challenge. Though practitioners typically ignore…