200 citations · 549 across the 29 of their papers we have counts for
32 papers
LeanStream: A Speculate-and-Refine Streaming Framework for Efficient on-Device LLM Inference
Renyuan Liu, Yuyang Leng, Kaiyan Liu +7
On-device LLM inference is attractive for privacy and responsiveness, but remains challenging on mobile and embedded devices because model weights far exceed available DRAM. Prior…
Physical Self-Supervised Learning: IMU Sensing without Manual Labels
Yuyang Leng, Renyuan Liu, Shaohan Hu +4
Deep neural networks have become a promising approach for IMU-based sensing, but their scalability is fundamentally limited by costly labeled data and poor robustness to heterogene…
Best-of-Better-: Generating Pre-Aligned Responses with In-Context Learning
Eric Lei, Hsiang Hsu, Chun-Fu Chen
Inference-time alignment methods, such as Best-of-, offer a flexible alternative to training-based alignment by using reward models to select high-quality responses generated by…
ECA: Efficient Continual Alignment for Open-Ended Image-to-Text Generation
Jiangtao Kong, Peijun Zhao, Chun-Fu Chen +4
Incremental Learning (IL) for Open-ended Image-to-Text Generation (OpenITG) enables models to continuously generate accurate, contextually relevant text for new images while preser…
Model-Agnostic Utility-Preserving Biometric Information Anonymization
Chun-Fu Chen, Bill Moriarty, Shaohan Hu +4
The recent rapid advancements in both sensing and machine learning technologies have given rise to the universal collection and utilization of people's biometrics, such as fingerpr…
MaSS: Multi-attribute Selective Suppression for Utility-preserving Data Transformation from an Information-theoretic Perspective
Yizhuo Chen, Chun-Fu Chen, Hsiang Hsu +3
The growing richness of large-scale datasets has been crucial in driving the rapid advancement and wide adoption of machine learning technologies. The massive collection and usage…
Machine Unlearning for Image-to-Image Generative Models
Guihong Li, Hsiang Hsu, Chun-Fu Chen +1
Machine unlearning has emerged as a new paradigm to deliberately forget data samples from a given model in order to adhere to stringent regulations. However, existing machine unlea…
OVOR: OnePrompt with Virtual Outlier Regularization for Rehearsal-Free Class-Incremental Learning
Wei-Cheng Huang, Chun-Fu Chen, Hsiang Hsu
Recent works have shown that by using large pre-trained models along with learnable prompts, rehearsal-free methods for class-incremental learning (CIL) settings can achieve superi…
Dropout-Based Rashomon Set Exploration for Efficient Predictive Multiplicity Estimation
Hsiang Hsu, Guihong Li, Shaohan Hu +2
Predictive multiplicity refers to the phenomenon in which classification tasks may admit multiple competing models that achieve almost-equally-optimal performance, yet generate con…
Fast-NTK: Parameter-Efficient Unlearning for Large-Scale Models
Guihong Li, Hsiang Hsu, Chun-Fu Chen +1
The rapid growth of machine learning has spurred legislative initiatives such as ``the Right to be Forgotten,'' allowing users to request data removal. In response, ``machine unlea…
Procedural Image Programs for Representation Learning
Manel Baradad, Chun-Fu Chen, Jonas Wulff +4
Learning image representations using synthetic data allows training neural networks without some of the concerns associated with real images, such as privacy and bias. Existing wor…
MaSS: Multi-attribute Selective Suppression
Chun-Fu Chen, Shaohan Hu, Zhonghao Shi +5
The recent rapid advances in machine learning technologies largely depend on the vast richness of data available today, in terms of both the quantity and the rich content contained…
VALHALLA: Visual Hallucination for Machine Translation
Yi Li, Rameswar Panda, Yoon Kim +4
Designing better machine translation systems by considering auxiliary inputs such as images has attracted much attention in recent years. While existing methods show promising perf…
Temporal Relevance Analysis for Video Action Models
Quanfu Fan, Donghyun Kim, Chun-Fu +4
In this paper, we provide a deep analysis of temporal modeling for action recognition, an important but underexplored problem in the literature. We first propose a new approach to…
Task2Sim : Towards Effective Pre-training and Transfer from Synthetic Data
Samarth Mishra, Rameswar Panda, Cheng Perng Phoo +5
Pre-training models on Imagenet or other massive datasets of real images has led to major advances in computer vision, albeit accompanied with shortcomings related to curation cost…
Dynamic Network Quantization for Efficient Video Inference
Ximeng Sun, Rameswar Panda, Chun-Fu Chen +3
Deep convolutional networks have recently achieved great success in video recognition, yet their practical realization remains a challenge due to the large amount of computational…
Can An Image Classifier Suffice For Action Recognition?
Quanfu Fan, Chun-Fu, Chen +1
We explore a new perspective on video understanding by casting the video recognition problem as an image recognition task. Our approach rearranges input video frames into super ima…
Dynamic Distillation Network for Cross-Domain Few-Shot Recognition with Unlabeled Data
Ashraful Islam, Chun-Fu Chen, Rameswar Panda +3
Most existing works in few-shot learning rely on meta-learning the network on a large base dataset which is typically from the same domain as the target dataset. We tackle the prob…
RegionViT: Regional-to-Local Attention for Vision Transformers
Chun-Fu Chen, Rameswar Panda, Quanfu Fan
Vision transformer (ViT) has recently shown its strong capability in achieving comparable results to convolutional neural networks (CNNs) on image classification. However, vanilla…
AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognition
Rameswar Panda, Chun-Fu Chen, Quanfu Fan +4
Multi-modal learning, which focuses on utilizing various modalities to improve the performance of a model, is widely used in video recognition. While traditional multi-modal learni…
Detector-Free Weakly Supervised Grounding by Separation
Assaf Arbelle, Sivan Doveh, Amit Alfassy +14
Nowadays, there is an abundance of data involving images and surrounding free-form text weakly corresponding to those images. Weakly Supervised phrase-Grounding (WSG) deals with th…
CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification
Chun-Fu Chen, Quanfu Fan, Rameswar Panda
The recently developed vision transformer (ViT) has achieved promising results on image classification compared to convolutional neural networks. Inspired by this, in this paper, w…
A Broad Study on the Transferability of Visual Representations with Contrastive Learning
Ashraful Islam, Chun-Fu Chen, Rameswar Panda +3
Tremendous progress has been made in visual representation learning, notably with the recent success of self-supervised contrastive learning methods. Supervised contrastive learnin…
Improved Techniques for Quantizing Deep Networks with Adaptive Bit-Widths
Ximeng Sun, Rameswar Panda, Chun-Fu Chen +6
Quantizing deep networks with adaptive bit-widths is a promising technique for efficient inference across many devices and resource constraints. In contrast to static methods that…