335 citations · 1.7k across the 86 of their papers we have counts for
17 papers · 1 filter
RMB: Reward Model Boosting Mitigates Reward Hacking
Jiabin Fan, Dezhi Ye, Yongchang Hao +1
Reinforcement Learning from Human Feedback (RLHF) is a powerful technique for aligning large language models (LLMs) with human preference. However, it often suffers from the reward…
Cactus: Accelerating Auto-Regressive Decoding with Constrained Acceptance Speculative Sampling
Yongchang Hao, Lili Mou
Speculative sampling (SpS) has been successful in accelerating the decoding throughput of auto-regressive large language models by leveraging smaller draft models. SpS strictly enf…
Do Neural Networks Lose Plasticity in a Gradually Changing World?
Tianhui Liu, Lili Mou
Continual learning has become a trending topic in machine learning. Recent studies have discovered an interesting phenomenon called loss of plasticity, referring to neural networks…
LoRAQuant: Mixed-Precision Quantization of LoRA to Ultra-Low Bits
Amir Reza Mirzaei, Yuqiao Wen, Yanshuai Cao +1
Low-Rank Adaptation (LoRA) has become a popular technique for parameter-efficient fine-tuning of large language models (LLMs). In many real-world scenarios, multiple adapters are l…
Exploring Model Invariance with Discrete Search for Ultra-Low-Bit Quantization
Yuqiao Wen, Yanshuai Cao, Lili Mou
Large language models have been increasing in size due to their success in a wide range of applications. This calls for a pressing need to reduce memory usage to make them more acc…
Revisiting Intermediate-Layer Matching in Knowledge Distillation: Layer-Selection Strategy Doesn't Matter (Much)
Zony Yu, Yuqiao Wen, Lili Mou
Knowledge distillation (KD) is a popular method of transferring knowledge from a large "teacher" model to a small "student" model. Previous work has explored various layer-selectio…
NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks
Yongchang Hao, Yanshuai Cao, Lili Mou
The performance of neural networks improves when more parameters are used. However, the model sizes are constrained by the available on-device memory during training and inference.…
Ginger: An Efficient Curvature Approximation with Linear Complexity for General Neural Networks
Yongchang Hao, Yanshuai Cao, Lili Mou
Second-order optimization approaches like the generalized Gauss-Newton method are considered more powerful as they utilize the curvature information of the objective function with…
Flora: Low-Rank Adapters Are Secretly Gradient Compressors
Yongchang Hao, Yanshuai Cao, Lili Mou
Despite large neural networks demonstrating remarkable abilities to complete different tasks, they require excessive memory usage to store the optimization states for training. To…
Teacher Forcing Recovers Reward Functions for Text Generation
Yongchang Hao, Yuxin Liu, Lili Mou
Reinforcement learning (RL) has been widely used in text generation to alleviate the exposure bias issue or to utilize non-parallel datasets. The reward function plays an important…
MBCT: Tree-Based Feature-Aware Binning for Individual Uncertainty Calibration
Siguang Huang, Yunli Wang, Lili Mou +4
Most machine learning classifiers only concern classification accuracy, while certain applications (such as medical diagnosis, meteorological forecasting, and computation advertisi…
Simulated annealing for optimization of graphs and sequences
Xianggen Liu, Pengyong Li, Fandong Meng +5
Optimization of discrete structures aims at generating a new structure with the better property given an existing one, which is a fundamental problem in machine learning. Different…
Generalized Equivariance and Preferential Labeling for GNN Node Classification
Zeyu Sun, Wenjie Zhang, Lili Mou +3
Existing graph neural networks (GNNs) largely rely on node embeddings, which represent a node as a vector by its identity, type, or content. However, graphs with unattributed nodes…
TreeGen: A Tree-Based Transformer Architecture for Code Generation
Zeyu Sun, Qihao Zhu, Yingfei Xiong +3
A code generation system generates programming language code based on an input natural language description. State-of-the-art approaches rely on neural networks for code generation…
A Grammar-Based Structural CNN Decoder for Code Generation
Zeyu Sun, Qihao Zhu, Lili Mou +3
Code generation maps a program description to executable source code in a programming language. Existing approaches mainly rely on a recurrent neural network (RNN) as the decoder.…
Coupling Distributed and Symbolic Execution for Natural Language Queries
Lili Mou, Zhengdong Lu, Hang Li +1
Building neural networks to query a knowledge base (a table) with natural language is an emerging research topic in deep learning. An executor for table querying typically requires…
Convolutional Neural Networks over Tree Structures for Programming Language Processing
Lili Mou, Ge Li, Lu Zhang +2
Programming language processing (similar to natural language processing) is a hot research topic in the field of software engineering; it has also aroused growing interest in the a…