1 code implementation • 18 Dec 2024 • Baolong Bi, Shaohan Huang, Yiwei Wang, Tianchi Yang, Zihan Zhang, Haizhen Huang, Lingrui Mei, Junfeng Fang, Zehao Li, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang, Shenghua Liu
Reliable responses from large language models (LLMs) require adherence to user instructions and retrieved information.
no code implementations • 14 Dec 2024 • Jia Hu, Zhexi Lian, Haoran Wang, Zihan Zhang, Ruoxi Qian, Duo Li, Jaehyun, So, Junnian Zheng
The current Adaptive Cruise Control (ACC) systems are vulnerable to "road bully" such as cut-ins.
1 code implementation • 26 Nov 2024 • Zhu Xu, Zhiqiang Zhao, Zihan Zhang, Yuchi Liu, Quanwei Shen, Fei Liu, Yu Kuang, Jian He, Conglin Liu
Tokenization methods like Byte-Pair Encoding (BPE) enhance computational efficiency in large language models (LLMs) but often obscure internal character structures within tokens.
no code implementations • 26 Nov 2024 • Zihan Zhang, Jason D. Lee, Simon S. Du, Yuxin Chen
This work investigates stepsize-based acceleration of gradient descent with {\em anytime} convergence guarantees.
1 code implementation • 17 Oct 2024 • Wenhan Han, Meng Fang, Zihan Zhang, Yu Yin, Zirui Song, Ling Chen, Mykola Pechenizkiy, Qingyu Chen
The integration of large language model (LLM) techniques in the field of medical analysis has brought about significant advancements, yet the scarcity of large, diverse, and well-annotated datasets remains a major challenge.
1 code implementation • 13 Oct 2024 • Hairong Wang, Lingchao Mao, Zihan Zhang, Jing Li
Liver cancer is a leading cause of mortality worldwide, and accurate CT-based tumor segmentation is essential for diagnosis and treatment.
1 code implementation • 13 Oct 2024 • Shanzhi Yin, Zihan Zhang, Bolin Chen, Shiqi Wang, Yan Ye
This paper proposes to learn generative priors from the motion patterns instead of video contents for generative video compression.
1 code implementation • 11 Oct 2024 • Bolin Chen, Shanzhi Yin, Zihan Zhang, Jie Chen, Ru-Ling Liao, Lingyu Zhu, Shiqi Wang, Yan Ye
Recently, deep generative models have greatly advanced the progress of face video coding towards promising rate-distortion performance and diverse application functionalities.
no code implementations • 13 Sep 2024 • Ziqian Wang, Jiayao Sun, Zihan Zhang, Xingchen Li, Jie Liu, Lei Xie
Our proposed system supports both streaming and non-streaming modes.
1 code implementation • 17 Jul 2024 • Ting Jiang, Minghui Song, Zihan Zhang, Haizhen Huang, Weiwei Deng, Feng Sun, Qi Zhang, Deqing Wang, Fuzhen Zhuang
We propose a single modality training approach for E5-V, where the model is trained exclusively on text pairs.
no code implementations • 10 Jun 2024 • Zihan Zhang, Xianjun Xia, Chuanzeng Huang, Yijian Xiao, Lei Xie
Moreover, we introduce a lightweight post-processing module after packet loss restoration to recover speech distortions and remove residual noise in the audio signal.
no code implementations • 3 Jun 2024 • Victor Boone, Zihan Zhang
In recent years, significant attention has been directed towards learning average-reward Markov Decision Processes (MDPs).
no code implementations • 23 May 2024 • Yuxuan Liu, Tianchi Yang, Zihan Zhang, Minghui Song, Haizhen Huang, Weiwei Deng, Feng Sun, Qi Zhang
Generative retrieval, a promising new paradigm in information retrieval, employs a seq2seq model to encode document features into parameters and decode relevant document identifiers (IDs) based on search queries.
1 code implementation • 20 May 2024 • Ting Jiang, Shaohan Huang, Shengyue Luo, Zihan Zhang, Haizhen Huang, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang, Deqing Wang, Fuzhen Zhuang
Low-rank adaptation is a popular parameter-efficient fine-tuning method for large language models.
no code implementations • 2 Apr 2024 • Xiang Xiang, Zihan Zhang, Jing Ma, Yao Deng
Parkinson's Disease (PD) is the second most common neurodegenerative disorder.
1 code implementation • 29 Mar 2024 • Qinhao Zhou, Zihan Zhang, Xiang Xiang, Ke Wang, Yuchuan Wu, Yongbin Li
As intelligent agents, LLMs need to have the capabilities of task planning, long-term memory, and the ability to leverage external tools to achieve satisfactory performance.
no code implementations • 15 Mar 2024 • Zihan Zhang, Jason D. Lee, Yuxin Chen, Simon S. Du
A recent line of works showed regret bounds in reinforcement learning (RL) can be (nearly) independent of planning horizon, a. k. a.~the horizon-free bounds.
1 code implementation • 28 Feb 2024 • Shuhua Shi, Shaohan Huang, Minghui Song, Zhoujun Li, Zihan Zhang, Haizhen Huang, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang
As one of the most popular parameter-efficient fine-tuning (PEFT) methods, low-rank adaptation (LoRA) is commonly applied to fine-tune large language models (LLMs).
1 code implementation • 26 Feb 2024 • Zihan Zhang, Meng Fang, Ling Chen
Based on our findings, we propose Time-Aware Adaptive Retrieval (TA-ARE), a simple yet effective method that helps LLMs assess the necessity of retrieval without calibration or additional training.
no code implementations • 24 Feb 2024 • Yuxuan Liu, Tianchi Yang, Shaohan Huang, Zihan Zhang, Haizhen Huang, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang
Large language models (LLMs) have emerged as a promising alternative to expensive human evaluations.
no code implementations • 22 Feb 2024 • Miao Xin, Zhongrui You, Zihan Zhang, Taoran Jiang, Tingjia Xu, Haotian Liang, Guojing Ge, Yuchen Ji, Shentong Mo, Jian Cheng
We present SpaceAgents-1, a system for learning human and multi-robot collaboration (HMRC) strategies under microgravity conditions.
no code implementations • 19 Feb 2024 • Yuxuan Liu, Tianchi Yang, Shaohan Huang, Zihan Zhang, Haizhen Huang, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang
Diffusion models have demonstrated exceptional capability in generating high-quality images, videos, and audio.
1 code implementation • 14 Jan 2024 • Ting Jiang, Shaohan Huang, Shengyue Luo, Zihan Zhang, Haizhen Huang, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang, Deqing Wang, Fuzhen Zhuang
To enhance the domain-specific capabilities of large language models, continued pre-training on a domain-specific corpus is a prevalent method.
no code implementations • 8 Jan 2024 • Zihan Zhang, Jiayao Sun, Xianjun Xia, Chuanzeng Huang, Yijian Xiao, Lei Xie
Packet loss is a common and unavoidable problem in voice over internet phone (VoIP) systems.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
no code implementations • 15 Dec 2023 • Ziqian Wang, Xinfa Zhu, Zihan Zhang, YuanJun Lv, Ning Jiang, Guoqing Zhao, Lei Xie
Given the intrinsic similarity between speech generation and speech enhancement, harnessing semantic information holds potential advantages for speech enhancement tasks.
no code implementations • 8 Dec 2023 • Zihan Zhang, Wenhao Zhan, Yuxin Chen, Simon S. Du, Jason D. Lee
Focusing on a hypothesis class of Vapnik-Chervonenkis (VC) dimension d, we propose a novel algorithm that yields an varepsilon-optimal randomized hypothesis with a sample complexity on the order of (d+k)/varepsilon^2 (modulo some logarithmic factor), matching the best-known lower bound.
no code implementations • 4 Nov 2023 • Jing-Yan Liao, Parth Doshi, Zihan Zhang, David Paz, Henrik Christensen
While High Definition (HD) Maps have long been favored for their precise depictions of static road elements, their accessibility constraints and susceptibility to rapid environmental changes impede the widespread deployment of autonomous driving, especially in the motion forecasting task.
1 code implementation • 23 Oct 2023 • Zihan Zhang, Meng Fang, Ling Chen, Mohammad-Reza Namazi-Rad
In this work, we establish a CIT benchmark consisting of learning and evaluation protocols.
1 code implementation • 23 Oct 2023 • Zihan Zhang, Meng Fang, Fanghua Ye, Ling Chen, Mohammad-Reza Namazi-Rad
Dialogue state tracking (DST) plays an important role in task-oriented dialogue systems.
1 code implementation • 20 Oct 2023 • Zhaoyang Wang, Shaohan Huang, Yuxuan Liu, Jiahai Wang, Minghui Song, Zihan Zhang, Haizhen Huang, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang
In this paper, we propose a tailored learning approach to distill such reasoning ability to smaller LMs to facilitate the democratization of the exclusive reasoning ability.
no code implementations • 19 Oct 2023 • Tianchi Yang, Minghui Song, Zihan Zhang, Haizhen Huang, Weiwei Deng, Feng Sun, Qi Zhang
Generative retrieval, which is a new advanced paradigm for document retrieval, has recently attracted research interests, since it encodes all documents into the model and directly generates the retrieved documents.
1 code implementation • 11 Oct 2023 • Zihan Zhang, Meng Fang, Ling Chen, Mohammad-Reza Namazi-Rad, Jun Wang
Although large language models (LLMs) are impressive in solving various tasks, they can quickly be outdated after deployment.
no code implementations • 7 Oct 2023 • Zihan Zhang, Jiayao Sun, Xianjun Xia, Ziqian Wang, Xiaopeng Yan, Yijian Xiao, Lei Xie
Utilization of speaker representation has extended the frontier of AEC, thus attracting many researchers' interest in personalized acoustic echo cancellation (PAEC).
1 code implementation • 23 Sep 2023 • Yuxuan Liu, Tianchi Yang, Shaohan Huang, Zihan Zhang, Haizhen Huang, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang
Recent advancements in large language models (LLMs) on language modeling and emergent capabilities make them a promising reference-free evaluator of natural language generation quality, and a competent alternative to human evaluation.
no code implementations • 9 Aug 2023 • Shaohua Guan, Zhichao Zhang, Zihan Zhang, Hualin Shi
The metabolic network plays a crucial role in regulating bacterial metabolism and growth, but it is subject to inherent molecular stochasticity.
no code implementations • 31 Jul 2023 • Zihan Zhang, Lei Shi, Ding-Xuan Zhou
In this paper, we aim to fill this gap by establishing a novel and elegant oracle-type inequality, which enables us to deal with the boundedness restriction of the target function, and using it to derive sharp convergence rates for fully connected ReLU DNN classifiers trained with logistic loss.
no code implementations • 27 Jul 2023 • Zihan Zhang, Richard Liu, Kfir Aberman, Rana Hanocka
The gradual nature of a diffusion process that synthesizes samples in small increments constitutes a key ingredient of Denoising Diffusion Probabilistic Models (DDPM), which have presented unprecedented quality in image synthesis and been recently explored in the motion domain.
no code implementations • 25 Jul 2023 • Zihan Zhang, Yuxin Chen, Jason D. Lee, Simon S. Du
While a number of recent works achieved asymptotically minimal regret in online RL, the optimality of these results is only guaranteed in a ``large-sample'' regime, imposing enormous burn-in cost in order for their algorithms to operate optimally.
no code implementations • 28 Jun 2023 • Zihan Zhang, Qiaomin Xie
In the online setting, we propose model-free RL algorithms based on reference-advantage decomposition.
1 code implementation • 16 May 2023 • Ziheng Li, Shaohan Huang, Zihan Zhang, Zhi-Hong Deng, Qiang Lou, Haizhen Huang, Jian Jiao, Furu Wei, Weiwei Deng, Qi Zhang
Recent studies have shown that dual encoder models trained with the sentence-level translation ranking task are effective methods for cross-lingual sentence embedding.
no code implementations • 6 May 2023 • Beiduo Chen, Shaohan Huang, Zihan Zhang, Wu Guo, ZhenHua Ling, Haizhen Huang, Furu Wei, Weiwei Deng, Qi Zhang
Besides, two self-correction courses are proposed to bridge the chasm between the two encoders by creating a "correction notebook" for secondary-supervision.
no code implementations • 14 Mar 2023 • Mingshuai Liu, Shubo Lv, Zihan Zhang, Runduo Han, Xiang Hao, Xianjun Xia, Li Chen, Yijian Xiao, Lei Xie
Achieving 0. 446 in the final score and 0. 517 in the P. 835 score, our system ranks 4th in the non-real-time track.
no code implementations • 13 Mar 2023 • Zihan Zhang, Shimin Zhang, Mingshuai Liu, Yanhong Leng, Zhe Han, Li Chen, Lei Xie
This paper describes a Two-step Band-split Neural Network (TBNN) approach for full-band acoustic echo cancellation.
no code implementations • 31 Jan 2023 • Runlong Zhou, Zihan Zhang, Simon S. Du
We further initiate the study on model-free algorithms with variance-dependent regret bounds by designing a reference-function-based algorithm with a novel capped-doubling reference update schedule.
no code implementations • CVPR 2023 • Zihan Zhang, Xiang Xiang
We demonstrate the effectiveness of our logit-based OOD detection methods on CIFAR-10, CIFAR-100 and ImageNet and establish state-of-the-art performance.
no code implementations • 1 Dec 2022 • Zihan Zhang, Philip Rodgers, Peter Kilpatrick, Ivor Spence, Blesson Varghese
We identify idling resources on the server and devices due to sequential computation and communication as the principal cause of low resource utilization.
1 code implementation • 28 Oct 2022 • Zihan Zhang, Jinfeng Li, Ning Shi, Bo Yuan, Xiangyu Liu, Rong Zhang, Hui Xue, Donghong Sun, Chao Zhang
Despite of the superb performance on a wide range of tasks, pre-trained language models (e. g., BERT) have been proved vulnerable to adversarial texts.
no code implementations • 15 Oct 2022 • Zihan Zhang, Yuhang Jiang, Yuan Zhou, Xiangyang Ji
Meanwhile, we show that to achieve $\tilde{O}(\mathrm{poly}(S, A, H)\sqrt{K})$ regret, the number of batches is at least $\Omega\left(H/\log_A(K)+ \log_2\log_2(K) \right)$, which matches our upper bound up to logarithmic terms.
1 code implementation • 10 Oct 2022 • Hongyi Zheng, Yanyu Chen, Zihan Zhang
Our project probes the relationship between temperatures and the blossom date of cherry trees.
no code implementations • 8 Sep 2022 • Christopher Yeung, Benjamin Pham, Zihan Zhang, Katherine T. Fountaine, Aaswath P. Raman
From higher computational efficiency to enabling the discovery of novel and complex structures, deep learning has emerged as a powerful framework for the design and optimization of nanophotonic circuits and components.
no code implementations • 21 May 2022 • Zihan Zhang, Xiang Xiang, Xuehua Peng, Jianbo Shao
Neuroblastoma is one of the most common cancers in infants, and the initial diagnosis of this disease is difficult.
1 code implementation • 5 May 2022 • Peizhuo Li, Kfir Aberman, Zihan Zhang, Rana Hanocka, Olga Sorkine-Hornung
We present GANimator, a generative model that learns to synthesize novel motions from a single, short motion sequence.
1 code implementation • NAACL 2022 • Zihan Zhang, Meng Fang, Ling Chen, Mohammad-Reza Namazi-Rad
Recent work incorporates pre-trained word embeddings such as BERT embeddings into Neural Topic Models (NTMs), generating highly coherent topics.
no code implementations • 24 Mar 2022 • Zihan Zhang, Xiangyang Ji, Simon S. Du
This paper gives the first polynomial-time algorithm for tabular Markov Decision Processes (MDP) that enjoys a regret bound \emph{independent on the planning horizon}.
no code implementations • 28 Feb 2022 • Zihan Zhang, Xiang Xiang
The real-world data distribution is essentially long-tailed, which poses great challenge to the deep model.
Ranked #14 on
Long-tail Learning
on CIFAR-100-LT (ρ=10)
1 code implementation • 12 Jan 2022 • Ting Jiang, Jian Jiao, Shaohan Huang, Zihan Zhang, Deqing Wang, Fuzhen Zhuang, Furu Wei, Haizhen Huang, Denvy Deng, Qi Zhang
We propose PromptBERT, a novel contrastive learning method for learning better sentence representation.
1 code implementation • 2 Nov 2021 • Wenyu Zhu, Zhiyao Feng, Zihan Zhang, Jianjun Chen, Zhijian Ou, Min Yang, Chao Zhang
Recovering binary programs' call graphs is crucial for inter-procedural analysis tasks and applications based on them. transfer One of the core challenges is recognizing targets of indirect calls (i. e., indirect callees).
1 code implementation • 21 Oct 2021 • Ting Jiang, Shaohan Huang, Zihan Zhang, Deqing Wang, Fuzhen Zhuang, Furu Wei, Haizhen Huang, Liangjie Zhang, Qi Zhang
While pre-trained language models have achieved great success on various natural language understanding tasks, how to effectively leverage them into non-autoregressive generation tasks remains a challenge.
no code implementations • 15 Oct 2021 • Zihan Zhang, Xiangyang Ji, Yuan Zhou
We study the optimal batch-regret tradeoff for batch linear contextual bandits.
no code implementations • 21 May 2021 • Zhiliang Tian, Wei Bi, Zihan Zhang, Dongkyu Lee, Yiping Song, Nevin L. Zhang
The task requires models to generate personalized responses for a speaker given a few conversations from the speaker and a social network.
no code implementations • 9 Mar 2021 • Chaoping Xing, Zihan Zhang
In this paper, by introducing a novel metric closely related to the block permutation metric, we build a bridge between some advanced algebraic methods and codes in the block permutation metric.
Information Theory Combinatorics Information Theory
no code implementations • NeurIPS 2021 • Zihan Zhang, Jiaqi Yang, Xiangyang Ji, Simon S. Du
With the new confidence sets, we obtain the follow regret bounds: For linear bandits, we obtain an $\tilde{O}(poly(d)\sqrt{1 + \sum_{k=1}^{K}\sigma_k^2})$ data-dependent regret bound, where $d$ is the feature dimension, $K$ is the number of rounds, and $\sigma_k^2$ is the \emph{unknown} variance of the reward at the $k$-th round.
no code implementations • NeurIPS 2020 • Zihan Zhang, Yuan Zhou, Xiangyang Ji
We study the reinforcement learning problem in the setting of finite-horizon1episodic Markov Decision Processes (MDPs) with S states, A actions, and episode length H. We propose a model-free algorithm UCB-ADVANTAGE and prove that it achieves \tilde{O}(\sqrt{H^2 SAT}) regret where T=KH and K is the number of episodes to play.
no code implementations • 12 Oct 2020 • Zihan Zhang, Simon S. Du, Xiangyang Ji
In the planning phase, the agent needs to return a near-optimal policy for arbitrary reward functions.
no code implementations • 28 Sep 2020 • Zihan Zhang, Xiangyang Ji, Simon S. Du
Episodic reinforcement learning generalizes contextual bandits and is often perceived to be more difficult due to long planning horizon and unknown state-dependent transitions.
no code implementations • 6 Jun 2020 • Zihan Zhang, Yuan Zhou, Xiangyang Ji
In this paper we consider the problem of learning an $\epsilon$-optimal policy for a discounted Markov Decision Process (MDP).
no code implementations • 21 Apr 2020 • Zihan Zhang, Yuan Zhou, Xiangyang Ji
We study the reinforcement learning problem in the setting of finite-horizon episodic Markov Decision Processes (MDPs) with $S$ states, $A$ actions, and episode length $H$.
no code implementations • NeurIPS 2019 • Zihan Zhang, Xiangyang Ji
We present an algorithm based on the \emph{Optimism in the Face of Uncertainty} (OFU) principle which is able to learn Reinforcement Learning (RL) modeled by Markov decision process (MDP) with finite state-action space efficiently.
no code implementations • 24 Mar 2019 • Ronghui You, Zihan Zhang, Suyang Dai, Shanfeng Zhu
Extreme multi-label text classification (XMTC) addresses the problem of tagging each text with the most relevant labels from an extreme-scale label set.
3 code implementations • NeurIPS 2019 • Ronghui You, Zihan Zhang, Ziye Wang, Suyang Dai, Hiroshi Mamitsuka, Shanfeng Zhu
We propose a new label tree-based deep learning model for XMTC, called AttentionXML, with two unique features: 1) a multi-label attention mechanism with raw text as input, which allows to capture the most relevant part of text to each label; and 2) a shallow and wide probabilistic label tree (PLT), which allows to handle millions of labels, especially for "tail labels".