81 citations · 150 across the 48 of their papers we have counts for
9 papers · 1 filter
Activation Sparsity with Weight Approximation for Faster LLM Decoding on Offloaded Weights
JuneHyung Kim, Sankeerth Durvasula, Nandita Vijaykumar
Deploying LLMs on consumer-grade GPUs with insufficient memory to hold their weights can result in prohibitively slow inference, because decoding repeatedly transfers offloaded wei…
QPILOTS: Efficient Test-Time Q-Steering for Flow Policies
Yifan Ruan, Chenyang Cao, Andreas Burger +7
Flow-matching and diffusion policies are expressive action generators, but optimizing them with temporal-difference reinforcement learning (RL) remains difficult. Effective policy…
TuneShift-KD: Knowledge Distillation and Transfer for Fine-tuned Models
Yushi Guan, Jeanine Ohene-Agyei, Daniel Kwan +3
To embed domain-specific or specialized knowledge into pre-trained foundation models, fine-tuning using techniques such as parameter efficient fine-tuning (e.g. LoRA) is a common p…
AccelOpt: A Self-Improving LLM Agentic System for AI Accelerator Kernel Optimization
Genghan Zhang, Shaowei Zhu, Anjiang Wei +6
We present AccelOpt, a self-improving large language model (LLM) agentic system that autonomously optimizes kernels for emerging AI acclerators, eliminating the need for expert-pro…
DEQuify your force field: More efficient simulations using deep equilibrium models
Andreas Burger, Luca Thiede, Alán Aspuru-Guzik +1
Machine learning force fields show great promise in enabling more accurate molecular dynamics simulations compared to manually derived ones. Much of the progress in recent years wa…
HIP: Hessian Interatomic Potentials without derivatives
Andreas Burger, Luca Thiede, Nikolaj Rønne +5
Molecular Hessians, the second derivatives of the potential energy, are fundamental to many workflows in computational chemistry. Usually, accurate Hessians are computationally exp…
DPQuant: Efficient and Differentially-Private Model Training via Dynamic Quantization Scheduling
Yubo Gao, Renbo Tu, Gennady Pekhimenko +1
Differentially-Private SGD (DP-SGD) and its adaptive variant DP-Adam are powerful techniques to protect user privacy when using sensitive data to train neural networks. During trai…
INRet: A General Framework for Accurate Retrieval of INRs for Shapes
Yushi Guan, Daniel Kwan, Ruofan Liang +4
Implicit neural representations (INRs) have become an important method for encoding various data types, such as 3D objects or scenes, images, and videos. They have proven to be par…
Echo: Compiler-based GPU Memory Footprint Reduction for LSTM RNN Training
Bojian Zheng, Abhishek Tiwari, Nandita Vijaykumar +1
The Long-Short-Term-Memory Recurrent Neural Networks (LSTM RNNs) are a popular class of machine learning models for analyzing sequential data. Their training on modern GPUs, howeve…