Search Results for author: Yu Kang

Found 35 papers, 12 papers with code

OmniRL: In-Context Reinforcement Learning by Large-Scale Meta-Training in Randomized Worlds

no code implementations5 Feb 2025 Fan Wang, Pengtao Shao, Yiming Zhang, Bo Yu, Shaoshan Liu, Ning Ding, Yang Cao, Yu Kang, Haifeng Wang

We introduce OmniRL, a highly generalizable in-context reinforcement learning (ICRL) model that is meta-trained on hundreds of thousands of diverse tasks.

Few-Shot Learning Imitation Learning +5

DI-BENCH: Benchmarking Large Language Models on Dependency Inference with Testable Repositories at Scale

no code implementations23 Jan 2025 Linghao Zhang, Junhao Wang, Shilin He, Chaoyun Zhang, Yu Kang, Bowen Li, Jiaheng Wen, Chengxing Xie, Maoquan Wang, Yufan Huang, Elsie Nallipogu, QIngwei Lin, Yingnong Dang, Saravan Rajmohan, Dongmei Zhang, Qi Zhang

Large Language Models have advanced automated software development, however, it remains a challenge to correctly infer dependencies, namely, identifying the internal components and external packages required for a repository to successfully run.

Benchmarking

C3oT: Generating Shorter Chain-of-Thought without Compromising Effectiveness

no code implementations16 Dec 2024 Yu Kang, Xianghui Sun, Liangyu Chen, Wei Zou

Generating Chain-of-Thought (CoT) before deriving the answer can effectively improve the reasoning capabilities of large language models (LLMs) and significantly improve the accuracy of the generated answer.

Large Language Model-Brained GUI Agents: A Survey

1 code implementation27 Nov 2024 Chaoyun Zhang, Shilin He, Jiaxu Qian, Bowen Li, Liqun Li, Si Qin, Yu Kang, Minghua Ma, Guyue Liu, QIngwei Lin, Saravan Rajmohan, Dongmei Zhang, Qi Zhang

This has paved the way for a new generation of LLM-brained GUI agents capable of interpreting complex GUI elements and autonomously executing actions based on natural language instructions.

Code Generation Language Modeling +5

Towards Unifying Feature Interaction Models for Click-Through Rate Prediction

no code implementations19 Nov 2024 Yu Kang, Junwei Pan, Jipeng Jin, Shudong Huang, Xiaofeng Gao, Lei Xiao

Modeling feature interactions plays a crucial role in accurately predicting click-through rates (CTR) in advertising systems.

Click-Through Rate Prediction

VMAD: Visual-enhanced Multimodal Large Language Model for Zero-Shot Anomaly Detection

no code implementations30 Sep 2024 Huilin Deng, Hongchen Luo, Wei Zhai, Yang Cao, Yu Kang

Furthermore, we introduce the Real Industrial Anomaly Detection (RIAD), a comprehensive IAD dataset with detailed anomaly descriptions and analyses, offering a valuable resource for MLLM-based IAD development.

Anomaly Detection Language Modeling +4

Improving embedding with contrastive fine-tuning on small datasets with expert-augmented scores

no code implementations19 Aug 2024 Jun Lu, David Li, Bill Ding, Yu Kang

This paper presents an approach to improve text embedding models through contrastive fine-tuning on small datasets augmented with expert scores.

Semantic Textual Similarity Text Retrieval

PEAR: Phrase-Based Hand-Object Interaction Anticipation

no code implementations31 Jul 2024 Zichen Zhang, Hongchen Luo, Wei Zhai, Yang Cao, Yu Kang

To address this, we propose a novel model, PEAR (Phrase-Based Hand-Object Interaction Anticipation), which jointly anticipates interaction intention and manipulation.

Object

FMamba: Mamba based on Fast-attention for Multivariate Time-series Forecasting

no code implementations20 Jul 2024 Shusen Ma, Yu Kang, Peng Bai, Yun-Bo Zhao

Technically, we first extract the temporal features of the input variables through an embedding layer, then compute the dependencies among input variables via the fast-attention module.

Mamba Multivariate Time Series Forecasting +1

Token-Mol 1.0: Tokenized drug design with large language model

1 code implementation10 Jul 2024 Jike Wang, Rui Qin, Mingyang Wang, Meijing Fang, Yangyang Zhang, Yuchen Zhu, Qun Su, Qiaolin Gou, Chao Shen, Odin Zhang, Zhenxing Wu, Dejun Jiang, Xujun Zhang, Huifeng Zhao, Xiaozhe Wan, Zhourui Wu, Liwei Liu, Yu Kang, Chang-Yu Hsieh, Tingjun Hou

This model encodes all molecular information, including 2D and 3D structures, as well as molecular property data, into tokens, which transforms classification and regression tasks in drug discovery into probabilistic prediction problems, thereby enabling learning through a unified paradigm.

Drug Design Drug Discovery +7

Benchmarking General-Purpose In-Context Learning

1 code implementation27 May 2024 Fan Wang, Chuan Lin, Yang Cao, Yu Kang

In-context learning (ICL) empowers generative models to address new tasks effectively and efficiently on the fly, without relying on any artificially crafted optimization techniques.

Benchmarking Decision Making +6

Bidirectional Progressive Transformer for Interaction Intention Anticipation

no code implementations9 May 2024 Zichen Zhang, Hongchen Luo, Wei Zhai, Yang Cao, Yu Kang

Building upon this relationship, a novel Bidirectional prOgressive Transformer (BOT), which introduces a Bidirectional Progressive mechanism into the anticipation of interaction intention is established.

Prediction Trajectory Forecasting

Deep Geometry Handling and Fragment-wise Molecular 3D Graph Generation

no code implementations15 Mar 2024 Odin Zhang, Yufei Huang, Shichen Cheng, Mengyao Yu, Xujun Zhang, Haitao Lin, Yundian Zeng, Mingyang Wang, Zhenxing Wu, Huifeng Zhao, Zaixi Zhang, Chenqing Hua, Yu Kang, Sunliang Cui, Peichen Pan, Chang-Yu Hsieh, Tingjun Hou

Most earlier 3D structure-based molecular generation approaches follow an atom-wise paradigm, incrementally adding atoms to a partially built molecular fragment within protein pockets.

Graph Generation

Exponential Cluster Synchronization in Fast Switching Network Topologies: A Pinning Control Approach with Necessary and Sufficient Conditions

no code implementations18 Feb 2024 Ku Du, Yu Kang

Within the context of fast switching framework, we initially examine the necessary conditions, commencing with the transformation of the consensus problem into a stability problem, introducing a new variable to make the coupled system achieve cluster synchronization if the system is controllable; communication topology switching fast enough and the coupling strength should be sufficiently robust.

UFO: A UI-Focused Agent for Windows OS Interaction

1 code implementation8 Feb 2024 Chaoyun Zhang, Liqun Li, Shilin He, Xu Zhang, Bo Qiao, Si Qin, Minghua Ma, Yu Kang, QIngwei Lin, Saravan Rajmohan, Dongmei Zhang, Qi Zhang

We introduce UFO, an innovative UI-Focused agent to fulfill user requests tailored to applications on Windows OS, harnessing the capabilities of GPT-Vision.

Navigate

Automated Root Causing of Cloud Incidents using In-Context Learning with GPT-4

no code implementations24 Jan 2024 Xuchao Zhang, Supriyo Ghosh, Chetan Bansal, Rujia Wang, Minghua Ma, Yu Kang, Saravan Rajmohan

The results reveal that our in-context learning approach outperforms the previous fine-tuned large language models such as GPT-3 by an average of 24. 8\% across all metrics, with an impressive 49. 7\% improvement over the zero-shot model.

In-Context Learning

Xpert: Empowering Incident Management with Query Recommendations via Large Language Models

no code implementations19 Dec 2023 YuXuan Jiang, Chaoyun Zhang, Shilin He, Zhihao Yang, Minghua Ma, Si Qin, Yu Kang, Yingnong Dang, Saravan Rajmohan, QIngwei Lin, Dongmei Zhang

This paper presents a thorough empirical study on the utilization of queries of KQL, a DSL employed for incident management in a large-scale cloud management system at Microsoft.

Management

TaskWeaver: A Code-First Agent Framework

1 code implementation29 Nov 2023 Bo Qiao, Liqun Li, Xu Zhang, Shilin He, Yu Kang, Chaoyun Zhang, Fangkai Yang, Hang Dong, Jue Zhang, Lu Wang, Minghua Ma, Pu Zhao, Si Qin, Xiaoting Qin, Chao Du, Yong Xu, QIngwei Lin, Saravan Rajmohan, Dongmei Zhang

TaskWeaver provides support for rich data structures, flexible plugin usage, and dynamic plugin selection, and leverages LLM coding capabilities for complex logic.

Natural Language Understanding

E-MLB: Multilevel Benchmark for Event-Based Camera Denoising

1 code implementation21 Mar 2023 Saizhe Ding, Jinze Chen, Yang Wang, Yu Kang, Weiguo Song, Jie Cheng, Yang Cao

Event cameras, such as dynamic vision sensors (DVS), are biologically inspired vision sensors that have advanced over conventional cameras in high dynamic range, low latency and low power consumption, showing great application potential in many fields.

Denoising

Self-Supervised Audio-and-Text Pre-training with Extremely Low-Resource Parallel Data

1 code implementation10 Apr 2022 Yu Kang, Tianqiao Liu, Hang Li, Yang Hao, Wenbiao Ding

Our pre-training framework consists of the following components: (1) Intra-modal Denoising Auto-Encoding (IDAE), which is able to reconstruct input text (audio) representations from a noisy version of itself.

Denoising

Phrase-Based Affordance Detection via Cyclic Bilateral Interaction

4 code implementations24 Feb 2022 Liangsheng Lu, Wei Zhai, Hongchen Luo, Yu Kang, Yang Cao

In this paper, we explore to perceive affordance from a vision-language perspective and consider the challenging phrase-based affordance detection problem, i. e., given a set of phrases describing the action purposes, all the object regions in a scene with the same affordance should be detected.

Affordance Detection

Reviewing continual learning from the perspective of human-level intelligence

no code implementations23 Nov 2021 Yifan Chang, Wenbo Li, Jian Peng, Bo Tang, Yu Kang, Yinjie Lei, Yuanmiao Gui, Qing Zhu, Yu Liu, Haifeng Li

Different from previous reviews that mainly focus on the catastrophic forgetting phenomenon in CL, this paper surveys CL from a more macroscopic perspective based on the Stability Versus Plasticity mechanism.

Continual Learning

Do What Nature Did To Us: Evolving Plastic Recurrent Neural Networks For Generalized Tasks

no code implementations29 Sep 2021 Fan Wang, Hao Tian, Haoyi Xiong, Hua Wu, Yang Cao, Yu Kang, Haifeng Wang

While artificial neural networks (ANNs) have been widely adopted in machine learning, researchers are increasingly obsessed by the gaps between ANNs and natural neural networks (NNNs).

Meta-Learning

Evolving Decomposed Plasticity Rules for Information-Bottlenecked Meta-Learning

2 code implementations8 Sep 2021 Fan Wang, Hao Tian, Haoyi Xiong, Hua Wu, Jie Fu, Yang Cao, Yu Kang, Haifeng Wang

In contrast, biological neural networks (BNNs) can adapt to various new tasks by continually updating the neural connections based on the inputs, which is aligned with the paradigm of learning effective learning rules in addition to static parameters, e. g., meta-learning.

Memorization Meta-Learning

A Multimodal Machine Learning Framework for Teacher Vocal Delivery Evaluation

1 code implementation15 Jul 2021 Hang Li, Yu Kang, Yang Hao, Wenbiao Ding, Zhongqin Wu, Zitao Liu

The quality of vocal delivery is one of the key indicators for evaluating teacher enthusiasm, which has been widely accepted to be connected to the overall course qualities.

BIG-bench Machine Learning

Multimodal Learning For Classroom Activity Detection

no code implementations22 Oct 2019 Hang Li, Yu Kang, Wenbiao Ding, Song Yang, Songfan Yang, Gale Yan Huang, Zitao Liu

The experimental results demonstrate the benefits of our approach on learning attention based neural network from classroom data with different modalities, and show our approach is able to outperform state-of-the-art baselines in terms of various evaluation metrics.

Action Detection Activity Detection

On Secure and Usable Program Obfuscation: A Survey

no code implementations3 Oct 2017 Hui Xu, Yangfan Zhou, Yu Kang, Michael R. Lyu

On the other hand, the performance requirement for model-oriented obfuscation approaches is too weak to develop practical program obfuscation solutions.

Cryptography and Security Software Engineering

Fast Haze Removal for Nighttime Image Using Maximum Reflectance Prior

no code implementations CVPR 2017 Jing Zhang, Yang Cao, Shuai Fang, Yu Kang, Chang Wen Chen

Then, we propose a simple but effective image prior, maximum reflectance prior, to estimate the varying ambient illumination.

Computational Efficiency

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