4 citations · 6 across the 11 of their papers we have counts for
11 papers
Fast Weight Attention for Continual Learning
Yifan Zhang, Steve Ta, Jasper Zhang +8
Recurrent fast-weight memories and selective state-space models compress an expanding context into a fixed-size recurrent state, making the state transition an online learning rule…
Group Representational Position Encoding
Yifan Zhang, Zixiang Chen, Yifeng Liu +6
We present GRAPE (Group Representational Position Encoding), a unified framework for positional encoding based on group actions. GRAPE unifies two families of mechanisms: (i) multi…
Causal Attention with Lookahead Keys
Zhuoqing Song, Peng Sun, Huizhuo Yuan +1
In standard causal attention, each token's query, key, and value (QKV) are static and encode only preceding context. We introduce CAuSal aTtention with Lookahead kEys (CASTLE), an…
On the Design of KL-Regularized Policy Gradient Algorithms for LLM Reasoning
Yifan Zhang, Yifeng Liu, Huizhuo Yuan +3
Policy gradient algorithms have been successfully applied to enhance the reasoning capabilities of large language models (LLMs). KL regularization is ubiquitous, yet the design sur…
ConfRover: Simultaneous Modeling of Protein Conformation and Dynamics via Autoregression
Yuning Shen, Lihao Wang, Huizhuo Yuan +3
Understanding protein dynamics is critical for elucidating their biological functions. The increasing availability of molecular dynamics (MD) data enables the training of deep gene…
RSPO: Regularized Self-Play Alignment of Large Language Models
Xiaohang Tang, Sangwoong Yoon, Seongho Son +3
Self-play-based policy optimization has emerged as an effective approach for fine-tuning large language models (LLMs), formulating preference optimization as a two-player game. How…
Tensor Product Attention Is All You Need
Yifan Zhang, Yifeng Liu, Huizhuo Yuan +4
Scaling language models to handle longer input sequences typically necessitates large key-value (KV) caches, resulting in substantial memory overhead during inference. In this pape…
Towards Simple and Provable Parameter-Free Adaptive Gradient Methods
Yuanzhe Tao, Yifeng Liu, Huizhuo Yuan +3
Optimization algorithms such as AdaGrad and Adam have significantly advanced the training of deep models by dynamically adjusting the learning rate during the optimization process.…
MARS: Unleashing the Power of Variance Reduction for Training Large Models
Huizhuo Yuan, Yifeng Liu, Shuang Wu +2
Training deep neural networks--and more recently, large models demands efficient and scalable optimizers. Adaptive gradient algorithms like Adam, AdamW, and their variants have bee…
Accelerated Preference Optimization for Large Language Model Alignment
Jiafan He, Huizhuo Yuan, Quanquan Gu
Reinforcement Learning from Human Feedback (RLHF) has emerged as a pivotal tool for aligning large language models (LLMs) with human preferences. Direct Preference Optimization (DP…
Beyond Bradley-Terry Models: A General Preference Model for Language Model Alignment
Yifan Zhang, Ge Zhang, Yue Wu +2
Modeling human preferences is crucial for aligning foundation models with human values. Traditional reward modeling methods, such as the Bradley-Terry (BT) reward model, fall short…