Papers by Dongjie Yang

5 papers
PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference (2024.findings-acl)

Copied to clipboard

Challenge: Existing methods to reduce memory usage for large language models neglect inter-layer dependency between layers and huge memory consumption in pre-computation.
Approach: They propose a method that compresses the KV cache by layer-wise retaining crucial context.
Outcome: The proposed method reduces memory usage by layer-wise retaining crucial context . it can improve 2.2x throughput compared to Accelerate with over 54% memory reduction .
PACHAT: Persona-Aware Speech Assistant for Multi-party Dialogue (2025.emnlp-main)

Copied to clipboard

Challenge: Extensive research on spoken dialogue systems has advanced the development of intelligent voice assistants, but integration of role information within speech remains an underexplored area.
Approach: They propose a language-based spoken dialogue system that integrates role information within speech to generate contextually appropriate responses.
Outcome: The proposed architecture achieves speaker-specific responses, character understanding, and the generation of targeted replies in multi-party dialogue scenarios, surpassing existing spoken dialogue systems.
Learning Better Masking for Better Language Model Pre-training (2023.acl-long)

Copied to clipboard

Challenge: Existing PrLMs adopt a Random-Token Masking strategy with a fixed masking ratio and different contents are masked by an equal probability throughout the training.
Approach: They propose two scheduled masking approaches that adaptively tune masking ratio and masked content in different training stages, which improves pre-training efficiency and effectiveness.
Outcome: The proposed methods improve the pre-training efficiency and effectiveness on the downstream tasks.
Are LLMs Aware that Some Questions are not Open-ended? (2024.findings-emnlp)

Copied to clipboard

Challenge: Large language models (LLMs) have shown impressive capability to answer questions in a wide range of scenarios.
Approach: They propose a method that enhances the question awareness of LLMs by adaptively adjusting the output distributions based on question features.
Outcome: The proposed method improves the question awareness of LLMs by adaptively adjusting the output distributions based on question features.
RefGPT: Dialogue Generation of GPT, by GPT, and for GPT (2023.findings-emnlp)

Copied to clipboard

Challenge: Large Language Models (LLMs) have impressive capability to resolve a wide range of NLP tasks by fine-tuning high-quality instruction data.
Approach: They propose a method to generate huge truthful and customized dialogues without worrying about factual errors caused by the model hallucination.
Outcome: The proposed method solves the model hallucination in dialogue generation by restricting the LLMs to leverage the given reference instead of reciting their own knowledge to generate dialogues.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations