2 citations · 4 across the 14 of their papers we have counts for
14 papers
DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation
Xin Cheng, Xingkai Yu, Chenze Shao +30
Speculative decoding accelerates Large Language Model (LLM) inference by decoupling draft generation from target verification. While recent parallel drafters efficiently propose lo…
Qwen-Image-Agent: Bridging the Context Gap in Real-World Image Generation
Zekai Zhang, Jiahao Li, Jie Zhang +18
While text-to-image (T2I) models have achieved remarkable progress, they struggle with real-world requests that are often underspecified, implicit, or dependent on up-to-date knowl…
FIRP: Faster LLM inference via future intermediate representation prediction
Pengfei Wu, Jiahao Liu, Zhuocheng Gong +5
Recent advancements in Large Language Models (LLMs) have shown remarkable performance across a wide range of tasks. Despite this, the auto-regressive nature of LLM decoding, which…
Graph-Structured Speculative Decoding
Zhuocheng Gong, Jiahao Liu, Ziyue Wang +5
Speculative decoding has emerged as a promising technique to accelerate the inference of Large Language Models (LLMs) by employing a small language model to draft a hypothesis sequ…
E-Bench: Towards Evaluating the Ease-of-Use of Large Language Models
Zhenyu Zhang, Bingguang Hao, Jinpeng Li +2
Most large language models (LLMs) are sensitive to prompts, and another synonymous expression or a typo may lead to unexpected results for the model. Composing an optimal prompt fo…
Towards Detecting LLMs Hallucination via Markov Chain-based Multi-agent Debate Framework
Xiaoxi Sun, Jinpeng Li, Yan Zhong +2
The advent of large language models (LLMs) has facilitated the development of natural language text generation. It also poses unprecedented challenges, with content hallucination e…
Parallel Decoding via Hidden Transfer for Lossless Large Language Model Acceleration
Pengfei Wu, Jiahao Liu, Zhuocheng Gong +5
Large language models (LLMs) have recently shown remarkable performance across a wide range of tasks. However, the substantial number of parameters in LLMs contributes to significa…
StyleChat: Learning Recitation-Augmented Memory in LLMs for Stylized Dialogue Generation
Jinpeng Li, Zekai Zhang, Quan Tu +3
Large Language Models (LLMs) demonstrate superior performance in generative scenarios and have attracted widespread attention. Among them, stylized dialogue generation is essential…
What Makes Quantization for Large Language Models Hard? An Empirical Study from the Lens of Perturbation
Zhuocheng Gong, Jiahao Liu, Jingang Wang +3
Quantization has emerged as a promising technique for improving the memory and computational efficiency of large language models (LLMs). Though the trade-off between performance an…
PPTC-R benchmark: Towards Evaluating the Robustness of Large Language Models for PowerPoint Task Completion
Zekai Zhang, Yiduo Guo, Yaobo Liang +2
The growing dependence on Large Language Models (LLMs) for finishing user instructions necessitates a comprehensive understanding of their robustness to complex task completion in…
PPTC Benchmark: Evaluating Large Language Models for PowerPoint Task Completion
Yiduo Guo, Zekai Zhang, Yaobo Liang +2
Recent evaluations of Large Language Models (LLMs) have centered around testing their zero-shot/few-shot capabilities for basic natural language tasks and their ability to translat…
Improving Input-label Mapping with Demonstration Replay for In-context Learning
Zhuocheng Gong, Jiahao Liu, Qifan Wang +4
In-context learning (ICL) is an emerging capability of large autoregressive language models where a few input-label demonstrations are appended to the input to enhance the model's…
Retrieval-based Knowledge Transfer: An Effective Approach for Extreme Large Language Model Compression
Jiduan Liu, Jiahao Liu, Qifan Wang +5
Large-scale pre-trained language models (LLMs) have demonstrated exceptional performance in various natural language processing (NLP) tasks. However, the massive size of these mode…
SCALE: Synergized Collaboration of Asymmetric Language Translation Engines
Xin Cheng, Xun Wang, Tao Ge +4
In this paper, we introduce SCALE, a collaborative framework that connects compact Specialized Translation Models (STMs) and general-purpose Large Language Models (LLMs) as one uni…