Search Results for author: Chen Huang

Found 44 papers, 13 papers with code

Towards Analyzing and Understanding the Limitations of DPO: A Theoretical Perspective

no code implementations6 Apr 2024 Duanyu Feng, Bowen Qin, Chen Huang, Zheng Zhang, Wenqiang Lei

Direct Preference Optimization (DPO), which derives reward signals directly from pairwise preference data, has shown its effectiveness on aligning Large Language Models (LLMs) with human preferences.

Concept -- An Evaluation Protocol on Conversation Recommender Systems with System-centric and User-centric Factors

no code implementations4 Apr 2024 Chen Huang, Peixin Qin, Yang Deng, Wenqiang Lei, Jiancheng Lv, Tat-Seng Chua

The conversational recommendation system (CRS) has been criticized regarding its user experience in real-world scenarios, despite recent significant progress achieved in academia.

Recommendation Systems

Strength Lies in Differences! Towards Effective Non-collaborative Dialogues via Tailored Strategy Planning

no code implementations11 Mar 2024 Tong Zhang, Chen Huang, Yang Deng, Hongru Liang, Jia Liu, Zujie Wen, Wenqiang Lei, Tat-Seng Chua

We investigate non-collaborative dialogue agents that must engage in tailored strategic planning for diverse users to secure a favorable agreement.

Arellano-Bond LASSO Estimator for Dynamic Linear Panel Models

no code implementations1 Feb 2024 Victor Chernozhukov, Iván Fernández-Val, Chen Huang, Weining Wang

We illustrate our approach with an application to the short and long-term effects of the opening of K-12 schools and other policies on the spread of COVID-19 using weekly county-level panel data from the United States.

Time Series

Overcoming the Pitfalls of Vision-Language Model Finetuning for OOD Generalization

no code implementations29 Jan 2024 Yuhang Zang, Hanlin Goh, Josh Susskind, Chen Huang

Then we propose a novel approach OGEN to address this pitfall, with the main focus on improving the OOD GENeralization of finetuned models.

Language Modelling Zero-Shot Learning

Cross-Space Adaptive Filter: Integrating Graph Topology and Node Attributes for Alleviating the Over-smoothing Problem

1 code implementation26 Jan 2024 Chen Huang, Haoyang Li, Yifan Zhang, Wenqiang Lei, Jiancheng Lv

To this end, various methods have been proposed to create an adaptive filter by incorporating an extra filter (e. g., a high-pass filter) extracted from the graph topology.

Attribute Node Classification

DREditor: An Time-efficient Approach for Building a Domain-specific Dense Retrieval Model

1 code implementation23 Jan 2024 Chen Huang, Duanyu Feng, Wenqiang Lei, Jiancheng Lv

Motivated by this, we develop a time-efficient approach called DREditor to edit the matching rule of an off-the-shelf dense retrieval model to suit a specific domain.


Towards Equipping Transformer with the Ability of Systematic Compositionality

1 code implementation12 Dec 2023 Chen Huang, Peixin Qin, Wenqiang Lei, Jiancheng Lv

One of the key factors in language productivity and human cognition is the ability of systematic compositionality, which refers to understanding composed unseen examples of seen primitives.

LiDAR: Sensing Linear Probing Performance in Joint Embedding SSL Architectures

no code implementations7 Dec 2023 Vimal Thilak, Chen Huang, Omid Saremi, Laurent Dinh, Hanlin Goh, Preetum Nakkiran, Joshua M. Susskind, Etai Littwin

In this paper, we introduce LiDAR (Linear Discriminant Analysis Rank), a metric designed to measure the quality of representations within JE architectures.

Adaptivity and Modularity for Efficient Generalization Over Task Complexity

no code implementations13 Oct 2023 Samira Abnar, Omid Saremi, Laurent Dinh, Shantel Wilson, Miguel Angel Bautista, Chen Huang, Vimal Thilak, Etai Littwin, Jiatao Gu, Josh Susskind, Samy Bengio

We investigate how the use of a mechanism for adaptive and modular computation in transformers facilitates the learning of tasks that demand generalization over the number of sequential computation steps (i. e., the depth of the computation graph).


Cryo-Electron Ptychography: Applications and Potential in Biological Characterisation

no code implementations9 Sep 2023 Chen Huang, Judy S. Kim, Angus I. Kirkland

There is a clear need for developments in characterisation techniques that provide detailed information about structure-function relationships in biology.

3D Reconstruction Single Particle Analysis

DUET: 2D Structured and Approximately Equivariant Representations

1 code implementation28 Jun 2023 Xavier Suau, Federico Danieli, T. Anderson Keller, Arno Blaas, Chen Huang, Jason Ramapuram, Dan Busbridge, Luca Zappella

We propose 2D strUctured and EquivarianT representations (coined DUET), which are 2d representations organized in a matrix structure, and equivariant with respect to transformations acting on the input data.

Self-Supervised Learning Transfer Learning

Semi-Supervised and Long-Tailed Object Detection with CascadeMatch

no code implementations24 May 2023 Yuhang Zang, Kaiyang Zhou, Chen Huang, Chen Change Loy

This paper focuses on long-tailed object detection in the semi-supervised learning setting, which poses realistic challenges, but has rarely been studied in the literature.

Long-tailed Object Detection Object +3

MAST: Masked Augmentation Subspace Training for Generalizable Self-Supervised Priors

no code implementations7 Mar 2023 Chen Huang, Hanlin Goh, Jiatao Gu, Josh Susskind

We do so by Masked Augmentation Subspace Training (or MAST) to encode in the single feature space the priors from different data augmentations in a factorized way.

Instance Segmentation Self-Supervised Learning +1

Unified Vision and Language Prompt Learning

1 code implementation13 Oct 2022 Yuhang Zang, Wei Li, Kaiyang Zhou, Chen Huang, Chen Change Loy

Prompt tuning, a parameter- and data-efficient transfer learning paradigm that tunes only a small number of parameters in a model's input space, has become a trend in the vision community since the emergence of large vision-language models like CLIP.

Domain Generalization Few-Shot Learning +2

Pre-Training Representations of Binary Code Using Contrastive Learning

no code implementations11 Oct 2022 Yifan Zhang, Chen Huang, Yueke Zhang, Kevin Cao, Scott Thomas Andersen, Huajie Shao, Kevin Leach, Yu Huang

To the best of our knowledge, COMBO is the first language representation model that incorporates source code, binary code, and comments into contrastive code representation learning and unifies multiple tasks for binary code analysis.

Computer Security Contrastive Learning +2

A Weighted Random Forest Based PositioningAlgorithm for 6G Indoor Communications

no code implementations22 Aug 2022 Yang Wu, Yinghua Wang, Jie Huang, Cheng-Xiang Wang, Chen Huang

Due to the indoor none-line-of-sight (NLoS) propagation and multi-access interference (MAI), it is a great challenge to achieve centimeter-level positioning accuracy in indoor scenarios.

Position Prediction as an Effective Pretraining Strategy

1 code implementation15 Jul 2022 Shuangfei Zhai, Navdeep Jaitly, Jason Ramapuram, Dan Busbridge, Tatiana Likhomanenko, Joseph Yitan Cheng, Walter Talbott, Chen Huang, Hanlin Goh, Joshua Susskind

This pretraining strategy which has been used in BERT models in NLP, Wav2Vec models in Speech and, recently, in MAE models in Vision, forces the model to learn about relationships between the content in different parts of the input using autoencoding related objectives.

Position speech-recognition +1

Efficient Representation Learning via Adaptive Context Pooling

no code implementations5 Jul 2022 Chen Huang, Walter Talbott, Navdeep Jaitly, Josh Susskind

Inspired by the success of ConvNets that are combined with pooling to capture long-range dependencies, we learn to pool neighboring features for each token before computing attention in a given attention layer.

Representation Learning

An Empirical Study of Language Model Integration for Transducer based Speech Recognition

no code implementations31 Mar 2022 Huahuan Zheng, Keyu An, Zhijian Ou, Chen Huang, Ke Ding, Guanglu Wan

Based on the DR method, we propose a low-order density ratio method (LODR) by replacing the estimation with a low-order weak language model.

Language Modelling speech-recognition +1

Open-Vocabulary DETR with Conditional Matching

1 code implementation22 Mar 2022 Yuhang Zang, Wei Li, Kaiyang Zhou, Chen Huang, Chen Change Loy

To this end, we propose a novel open-vocabulary detector based on DETR -- hence the name OV-DETR -- which, once trained, can detect any object given its class name or an exemplar image.

Language Modelling object-detection +1

Artificial intelligence enabled radio propagation for communications-Part I: Channel characterization and antenna-channel optimization

no code implementations24 Nov 2021 Chen Huang, Ruisi He, Bo Ai, Andreas F. Molisch, Buon Kiong Lau, Katsuyuki Haneda, Bo Liu, Cheng-Xiang Wang, Mi Yang, Claude Oestges, Zhangdui Zhong

To provide higher data rates, as well as better coverage, cost efficiency, security, adaptability, and scalability, the 5G and beyond 5G networks are developed with various artificial intelligence techniques.

Artificial intelligence enabled radio propagation for communications-Part II: Scenario identification and channel modeling

no code implementations24 Nov 2021 Chen Huang, Ruisi He, Bo Ai, Andreas F. Molisch, Buon Kiong Lau, Katsuyuki Haneda, Bo Liu, Cheng-Xiang Wang, Mi Yang, Claude Oestges, Zhangdui Zhong

This two-part paper investigates the application of artificial intelligence (AI) and in particular machine learning (ML) to the study of wireless propagation channels.

A Geometry-Based Stochastic Model for Truck Communication Channels in Freeway Scenarios

no code implementations20 Oct 2021 Chen Huang, Rui Wang, Cheng-Xiang Wang, Pan Tang, Andreas F. Molisch

We validate this model by contrasting the root-mean-square delay spread and the angular spreads of departure/arrival derived from the channel model with the outcomes directly derived from the measurements.

Collision Avoidance

A Dot Product Attention Free Transformer

no code implementations29 Sep 2021 Shuangfei Zhai, Walter Talbott, Nitish Srivastava, Chen Huang, Hanlin Goh, Ruixiang Zhang, Joshua M. Susskind

We introduce Dot Product Attention Free Transformer (DAFT), an efficient variant of Transformers \citep{transformer} that eliminates the query-key dot product in self attention.

Image Classification Language Modelling

An Attention Free Transformer

6 code implementations28 May 2021 Shuangfei Zhai, Walter Talbott, Nitish Srivastava, Chen Huang, Hanlin Goh, Ruixiang Zhang, Josh Susskind

We introduce Attention Free Transformer (AFT), an efficient variant of Transformers that eliminates the need for dot product self attention.


Uniform Inference on High-dimensional Spatial Panel Networks

no code implementations16 May 2021 Victor Chernozhukov, Chen Huang, Weining Wang

We propose employing a debiased-regularized, high-dimensional generalized method of moments (GMM) framework to perform inference on large-scale spatial panel networks.

MetricOpt: Learning to Optimize Black-Box Evaluation Metrics

no code implementations CVPR 2021 Chen Huang, Shuangfei Zhai, Pengsheng Guo, Josh Susskind

This leads to consistent improvements since the value function provides effective metric supervision during finetuning, and helps to correct the potential bias of loss-only supervision.

Image Classification Image Retrieval +3

FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentation

1 code implementation ICCV 2021 Yuhang Zang, Chen Huang, Chen Change Loy

We propose a simple yet effective method, Feature Augmentation and Sampling Adaptation (FASA), that addresses the data scarcity issue by augmenting the feature space especially for rare classes.

Instance Segmentation Segmentation +2

Addressing the Loss-Metric Mismatch with Adaptive Loss Alignment

no code implementations15 May 2019 Chen Huang, Shuangfei Zhai, Walter Talbott, Miguel Angel Bautista, Shih-Yu Sun, Carlos Guestrin, Josh Susskind

In most machine learning training paradigms a fixed, often handcrafted, loss function is assumed to be a good proxy for an underlying evaluation metric.

General Classification Meta-Learning +2

Dense Intrinsic Appearance Flow for Human Pose Transfer

1 code implementation CVPR 2019 Yining Li, Chen Huang, Chen Change Loy

Unlike existing methods, we propose to estimate dense and intrinsic 3D appearance flow to better guide the transfer of pixels between poses.

Pose Transfer

Pose Guided Human Video Generation

no code implementations ECCV 2018 Ceyuan Yang, Zhe Wang, Xinge Zhu, Chen Huang, Jianping Shi, Dahua Lin

Human pose, on the other hand, can represent motion patterns intrinsically and interpretably, and impose the geometric constraints regardless of appearance.

Generative Adversarial Network motion prediction +1

Deep Imbalanced Learning for Face Recognition and Attribute Prediction

1 code implementation1 Jun 2018 Chen Huang, Yining Li, Chen Change Loy, Xiaoou Tang

Data for face analysis often exhibit highly-skewed class distribution, i. e., most data belong to a few majority classes, while the minority classes only contain a scarce amount of instances.

Attribute Face Recognition +1

Mask-aware Photorealistic Face Attribute Manipulation

no code implementations24 Apr 2018 Ruoqi Sun, Chen Huang, Jianping Shi, Lizhuang Ma

The task of face attribute manipulation has found increasing applications, but still remains challeng- ing with the requirement of editing the attributes of a face image while preserving its unique details.

Attribute Face Recognition +1

CNNs are Globally Optimal Given Multi-Layer Support

no code implementations7 Dec 2017 Chen Huang, Chen Kong, Simon Lucey

Stochastic Gradient Descent (SGD) is the central workhorse for training modern CNNs.

Learning Policies for Adaptive Tracking with Deep Feature Cascades

no code implementations ICCV 2017 Chen Huang, Simon Lucey, Deva Ramanan

Our fundamental insight is to take an adaptive approach, where easy frames are processed with cheap features (such as pixel values), while challenging frames are processed with invariant but expensive deep features.

Decision Making Visual Object Tracking

Learning to Disambiguate by Asking Discriminative Questions

no code implementations ICCV 2017 Yining Li, Chen Huang, Xiaoou Tang, Chen-Change Loy

In particular, each tuple consists of a pair of images and 4. 6 discriminative questions (as positive samples) and 5. 9 non-discriminative questions (as negative samples) on average.

Benchmarking Image Captioning +4

Need for Speed: A Benchmark for Higher Frame Rate Object Tracking

1 code implementation ICCV 2017 Hamed Kiani Galoogahi, Ashton Fagg, Chen Huang, Deva Ramanan, Simon Lucey

In this paper, we propose the first higher frame rate video dataset (called Need for Speed - NfS) and benchmark for visual object tracking.

Visual Object Tracking

Local Similarity-Aware Deep Feature Embedding

no code implementations NeurIPS 2016 Chen Huang, Chen Change Loy, Xiaoou Tang

Existing deep embedding methods in vision tasks are capable of learning a compact Euclidean space from images, where Euclidean distances correspond to a similarity metric.

Image Retrieval Retrieval +2

Spatially Supervised Recurrent Convolutional Neural Networks for Visual Object Tracking

2 code implementations19 Jul 2016 Guanghan Ning, Zhi Zhang, Chen Huang, Zhihai He, Xiaobo Ren, Haohong Wang

In this paper, we develop a new approach of spatially supervised recurrent convolutional neural networks for visual object tracking.

Binary Classification object-detection +3

Learning Deep Representation for Imbalanced Classification

no code implementations CVPR 2016 Chen Huang, Yining Li, Chen Change Loy, Xiaoou Tang

We further demonstrate that more discriminative deep representation can be learned by enforcing a deep network to maintain both inter-cluster and inter-class margins.

Classification General Classification +2

Discriminative Sparse Neighbor Approximation for Imbalanced Learning

no code implementations3 Feb 2016 Chen Huang, Chen Change Loy, Xiaoou Tang

These methods further deteriorate on small, imbalanced data that has a large degree of class overlap.

Cannot find the paper you are looking for? You can Submit a new open access paper.