23 citations · 37 across the 16 of their papers we have counts for
16 papers
Fitting Is Not Enough: Smoothness in Extremely Quantized LLMs
Yuzhuang Xu, Xu Han, Yuxuan Li +2
Large language models (LLMs) achieve strong performance but incur high deployment costs, motivating extremely low-bit but lossy quantization. Existing quantization algorithms mainl…
HUOZIIME: An On-Device LLM-enhanced Input Method for Deep Personalization
Baocai Shan, Yuzhuang Xu, Wanxiang Che
Mobile input method editors (IMEs) are the primary interface for text input, yet they remain constrained to manual typing and struggle to produce personalized text. While lightweig…
ArcLight: A Lightweight LLM Inference Architecture for Many-Core CPUs
Yuzhuang Xu, Xu Han, Yuxuan Li +1
Although existing frameworks for large language model (LLM) inference on CPUs are mature, they fail to fully exploit the computation potential of many-core CPU platforms. Many-core…
Judge Q: Trainable Queries for Optimized Information Retention in KV Cache Eviction
Yijun Liu, Yixuan Wang, Yuzhuang Xu +4
Large language models (LLMs) utilize key-value (KV) cache to store historical information during sequence processing. The size of KV cache grows linearly as the length of the seque…
CAMERA: Multi-Matrix Joint Compression for MoE Models via Micro-Expert Redundancy Analysis
Yuzhuang Xu, Xu Han, Yuanchi Zhang +5
Large Language Models (LLMs) with Mixture-of-Experts (MoE) architectures are distinguished by their strong performance scaling with increasing parameters across a wide range of tas…
Think Before You Accept: Semantic Reflective Verification for Faster Speculative Decoding
Yixuan Wang, Yijun Liu, Shiyu ji +4
Large language models (LLMs) suffer from high inference latency due to the auto-regressive decoding process. Speculative decoding accelerates inference by generating multiple draft…
Lookahead Q-Cache: Achieving More Consistent KV Cache Eviction via Pseudo Query
Yixuan Wang, Shiyu Ji, Yijun Liu +4
Large language models (LLMs) rely on key-value cache (KV cache) to accelerate decoding by reducing redundant computations. However, the KV cache memory usage grows substantially wi…
Perspective Transition of Large Language Models for Solving Subjective Tasks
Xiaolong Wang, Yuanchi Zhang, Ziyue Wang +5
Large language models (LLMs) have revolutionized the field of natural language processing, enabling remarkable progress in various tasks. Different from objective tasks such as com…
CRVQ: Channel-Relaxed Vector Quantization for Extreme Compression of LLMs
Yuzhuang Xu, Shiyu Ji, Qingfu Zhu +1
Powerful large language models (LLMs) are increasingly expected to be deployed with lower computational costs, enabling their capabilities on resource-constrained devices. Post-tra…
ActiView: Evaluating Active Perception Ability for Multimodal Large Language Models
Ziyue Wang, Chi Chen, Fuwen Luo +6
Active perception, a crucial human capability, involves setting a goal based on the current understanding of the environment and performing actions to achieve that goal. Despite si…
Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language Models
Bowen Ping, Shuo Wang, Hanqing Wang +7
Fine-tuning is a crucial process for adapting large language models (LLMs) to diverse applications. In certain scenarios, such as multi-tenant serving, deploying multiple LLMs beco…
A Survey on Large Language Models with Multilingualism: Recent Advances and New Frontiers
Kaiyu Huang, Fengran Mo, Xinyu Zhang +10
The rapid development of Large Language Models (LLMs) demonstrates remarkable multilingual capabilities in natural language processing, attracting global attention in both academia…
UltraLink: An Open-Source Knowledge-Enhanced Multilingual Supervised Fine-tuning Dataset
Haoyu Wang, Shuo Wang, Yukun Yan +9
Open-source large language models (LLMs) have gained significant strength across diverse fields. Nevertheless, the majority of studies primarily concentrate on English, with only l…
OneBit: Towards Extremely Low-bit Large Language Models
Yuzhuang Xu, Xu Han, Zonghan Yang +5
Model quantification uses low bit-width values to represent the weight matrices of existing models to be quantized, which is a promising approach to reduce both storage and computa…
Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf
Yuzhuang Xu, Shuo Wang, Peng Li +4
Communication games, which we refer to as incomplete information games that heavily depend on natural language communication, hold significant research value in fields such as econ…
Pluggable Neural Machine Translation Models via Memory-augmented Adapters
Yuzhuang Xu, Shuo Wang, Peng Li +4
Although neural machine translation (NMT) models perform well in the general domain, it remains rather challenging to control their generation behavior to satisfy the requirement o…