Papers by Zhihang Yuan
Spec-VLA: Speculative Decoding for Vision-Language-Action Models with Relaxed Acceptance (2025.emnlp-main)
Copied to clipboard
| Challenge: | Visual Language Models (VLMs) have significant parameter size and autoregressive (AR) decoding nature impose considerable computational demands on VLA models. |
| Approach: | They propose a framework to relax acceptance utilizing the relative distances represented by the action tokens of the VLA model. |
| Outcome: | Empirical results show that the proposed framework improves the speed of the prediction task by 44%. |
VocabTailor: Dynamic Vocabulary Selection for Downstream Tasks in Small Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing static vocabulary pruning designs that reduce memory usage suffer from rigid, one-size-fits-all designs that cause information loss during the prefill stage and lack flexibility. |
| Approach: | They propose a decoupled dynamic vocabulary selection framework that addresses memory constraints through offloading embedding and implements a hybrid static-dynamic vocabulary selection strategy for LM Head. |
| Outcome: | The proposed framework reduces memory usage by 99% with minimal or no degradation in performance. |
GSQ-Tuning: Group-Shared Exponents Integer in Fully Quantized Training for LLMs On-Device Fine-tuning (2025.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) fine-tuning techniques require large Floating Point(FP) computation and are impractical for resource-constrained edge devices. |
| Approach: | They propose a framework for on-device LLM fine-tuning that eliminates the need for floating-point operations in both inference and training. |
| Outcome: | The proposed framework reduces memory and compute costs while reducing memory usage. |