most citedREAP the Experts: Why Pruning Prevails for One-Shot MoE compression

1 citations · 1 across the 3 of their papers we have counts for

collaborators

10 papers

cs.LG2026

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…

cs.AI2026

DREAM-R: Multimodal Speculative Reasoning with RL-Based Refined Drafting, Precise Verification, and Fully Parallel Execution

Yunhai Hu, Zining Liu, Xiangyang Yin +5

Speculative reasoning has recently been proposed as a means to accelerate reasoning-intensive generation in large multimodal models, but its effectiveness is often constrained by m…

cs.LG20261 cited

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…

cs.LG2026

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…

cs.LG2025

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,…

cs.CL2025

DREAM: Drafting with Refined Target Features and Entropy-Adaptive Cross-Attention Fusion for Multimodal Speculative Decoding

Yunhai Hu, Tianhua Xia, Zining Liu +6

Speculative decoding (SD) has emerged as a powerful method for accelerating autoregressive generation in large language models (LLMs), yet its integration into vision-language mode…