28 citations · 97 across the 33 of their papers we have counts for
33 papers
The Path Not Taken: RLVR Provably Learns Off the Principals
Hanqing Zhu, Zhenyu Zhang, Hanxian Huang +11
Reinforcement Learning with Verifiable Rewards (RLVR) reliably improves the reasoning performance of large language models, yet it appears to modify only a small fraction of parame…
LLMs Can Get "Brain Rot": A Pilot Study on Twitter/X
Shuo Xing, Junyuan Hong, Yifan Wang +5
We propose and test the LLM Brain Rot Hypothesis: continual exposure to junk web text induces lasting cognitive decline in large language models (LLMs). To unveil junk effects, we…
On-the-Fly Adaptive Distillation of Transformer to Dual-State Linear Attention
Yeonju Ro, Zhenyu Zhang, Souvik Kundu +2
Large language models (LLMs) excel at capturing global token dependencies via self-attention but face prohibitive compute and memory costs on lengthy inputs. While sub-quadratic me…
R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference
Zhenyu Zhang, Zechun Liu, Yuandong Tian +3
Large Language Models (LLMs), while demonstrating remarkable capabilities across various applications, present significant challenges during inference due to their substantial mode…
SEAL: Steerable Reasoning Calibration of Large Language Models for Free
Runjin Chen, Zhenyu Zhang, Junyuan Hong +2
Large Language Models (LLMs), such as OpenAI's o1-series have demonstrated compelling capabilities for complex reasoning tasks via the extended chain-of-thought (CoT) reasoning mec…
GradientStabilizer:Fix the Norm, Not the Gradient
Tianjin Huang, Zhangyang Wang, Haotian Hu +10
Training instability in modern deep learning systems is frequently triggered by rare but extreme gradient-norm spikes, which can induce oversized parameter updates, corrupt optimiz…
Mask-Enhanced Autoregressive Prediction: Pay Less Attention to Learn More
Xialie Zhuang, Zhikai Jia, Jianjin Li +4
Large Language Models (LLMs) are discovered to suffer from accurately retrieving key information. To address this, we propose Mask-Enhanced Autoregressive Prediction (MEAP), a simp…
APOLLO: SGD-like Memory, AdamW-level Performance
Hanqing Zhu, Zhenyu Zhang, Wenyan Cong +7
Large language models (LLMs) are notoriously memory-intensive during training, particularly with the popular AdamW optimizer. This memory burden necessitates using more or higher-e…
Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients
Zhenyu Zhang, Ajay Jaiswal, Lu Yin +4
Training Large Language Models (LLMs) is memory-intensive due to the large number of parameters and associated optimization states. GaLore, a recent method, reduces memory usage by…
From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories, and Applications
Ajay Jaiswal, Yifan Wang, Lu Yin +6
Large Language Models' (LLMs) weight matrices can often be expressed in low-rank form with potential to relax memory and compute resource requirements. Unlike prior efforts that fo…
Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encoding
Zhenyu Zhang, Runjin Chen, Shiwei Liu +5
This paper aims to overcome the "lost-in-the-middle" challenge of large language models (LLMs). While recent advancements have successfully enabled LLMs to perform stable language…
GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection
Jiawei Zhao, Zhenyu Zhang, Beidi Chen +3
Training Large Language Models (LLMs) presents significant memory challenges, predominantly due to the growing size of weights and optimizer states. Common memory-reduction approac…
Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference
Harry Dong, Xinyu Yang, Zhenyu Zhang +3
Many computational factors limit broader deployment of large language models. In this paper, we focus on a memory bottleneck imposed by the key-value (KV) cache, a computational sh…
QuantumSEA: In-Time Sparse Exploration for Noise Adaptive Quantum Circuits
Tianlong Chen, Zhenyu Zhang, Hanrui Wang +6
Parameterized Quantum Circuits (PQC) have obtained increasing popularity thanks to their great potential for near-term Noisy Intermediate-Scale Quantum (NISQ) computers. Achieving…
Sparsity-Guided Holistic Explanation for LLMs with Interpretable Inference-Time Intervention
Zhen Tan, Tianlong Chen, Zhenyu Zhang +1
Large Language Models (LLMs) have achieved unprecedented breakthroughs in various natural language processing domains. However, the enigmatic ``black-box'' nature of LLMs remains a…
Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity
Lu Yin, You Wu, Zhenyu Zhang +10
Large Language Models (LLMs), renowned for their remarkable performance across diverse domains, present a challenge when it comes to practical deployment due to their colossal mode…
Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy
Pingzhi Li, Zhenyu Zhang, Prateek Yadav +4
Sparsely activated Mixture-of-Experts (SMoE) has shown promise to scale up the learning capacity of neural networks, however, they have issues like (a) High Memory Usage, due to du…
JoMA: Demystifying Multilayer Transformers via JOint Dynamics of MLP and Attention
Yuandong Tian, Yiping Wang, Zhenyu Zhang +2
We propose Joint MLP/Attention (JoMA) dynamics, a novel mathematical framework to understand the training procedure of multilayer Transformer architectures. This is achieved by int…
HO: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models
Zhenyu Zhang, Ying Sheng, Tianyi Zhou +9
Large Language Models (LLMs), despite their recent impressive accomplishments, are notably cost-prohibitive to deploy, particularly for applications involving long-content generati…
Are Large Kernels Better Teachers than Transformers for ConvNets?
Tianjin Huang, Lu Yin, Zhenyu Zhang +5
This paper reveals a new appeal of the recently emerged large-kernel Convolutional Neural Networks (ConvNets): as the teacher in Knowledge Distillation (KD) for small-kernel ConvNe…
Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together!
Shiwei Liu, Tianlong Chen, Zhenyu Zhang +4
Sparse Neural Networks (SNNs) have received voluminous attention predominantly due to growing computational and memory footprints of consistently exploding parameter count in large…
Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers
Tianlong Chen, Zhenyu Zhang, Ajay Jaiswal +2
Despite their remarkable achievement, gigantic transformers encounter significant drawbacks, including exorbitant computational and memory footprints during training, as well as se…
Robust Weight Signatures: Gaining Robustness as Easy as Patching Weights?
Ruisi Cai, Zhenyu Zhang, Zhangyang Wang
Given a robust model trained to be resilient to one or multiple types of distribution shifts (e.g., natural image corruptions), how is that "robustness" encoded in the model weight…
QuanGCN: Noise-Adaptive Training for Robust Quantum Graph Convolutional Networks
Kaixiong Zhou, Zhenyu Zhang, Shengyuan Chen +4
Quantum neural networks (QNNs), an interdisciplinary field of quantum computing and machine learning, have attracted tremendous research interests due to the specific quantum advan…