44 citations · 280 across the 48 of their papers we have counts for
18 papers · 1 filter
Towards Accurate Loop Closure Detection in Semantic SLAM with 3D Semantic Covisibility Graphs
Zhentian Qian, Jie Fu, Jing Xiao
Loop closure is necessary for correcting errors accumulated in simultaneous localization and mapping (SLAM) in unknown environments. However, conventional loop closure methods base…
Mixup-Augmented Meta-Learning for Sample-Efficient Fine-Tuning of Protein Simulators
Jingbang Chen, Yian Wang, Xingwei Qu +4
Molecular dynamics simulations have emerged as a fundamental instrument for studying biomolecules. At the same time, it is desirable to perform simulations of a collection of parti…
Optimal Sensor Deception to Deviate from an Allowed Itinerary
Hazhar Rahmani, Arash Ahadi, Jie Fu
In this work, we study a class of deception planning problems in which an agent aims to alter a security monitoring system's sensor readings so as to disguise its adversarial itine…
On the Effectiveness of Speech Self-supervised Learning for Music
Yinghao Ma, Ruibin Yuan, Yizhi Li +12
Self-supervised learning (SSL) has shown promising results in various speech and natural language processing applications. However, its efficacy in music information retrieval (MIR…
Multimodal Imbalance-Aware Gradient Modulation for Weakly-supervised Audio-Visual Video Parsing
Jie Fu, Junyu Gao, Changsheng Xu
Weakly-supervised audio-visual video parsing (WS-AVVP) aims to localize the temporal extents of audio, visual and audio-visual event instances as well as identify the corresponding…
LyricWhiz: Robust Multilingual Zero-shot Lyrics Transcription by Whispering to ChatGPT
Le Zhuo, Ruibin Yuan, Jiahao Pan +10
We introduce LyricWhiz, a robust, multilingual, and zero-shot automatic lyrics transcription method achieving state-of-the-art performance on various lyrics transcription datasets,…
GIMLET: A Unified Graph-Text Model for Instruction-Based Molecule Zero-Shot Learning
Haiteng Zhao, Shengchao Liu, Chang Ma +5
Molecule property prediction has gained significant attention in recent years. The main bottleneck is the label insufficiency caused by expensive lab experiments. In order to allev…
MARBLE: Music Audio Representation Benchmark for Universal Evaluation
Ruibin Yuan, Yinghao Ma, Yizhi Li +22
In the era of extensive intersection between art and Artificial Intelligence (AI), such as image generation and fiction co-creation, AI for music remains relatively nascent, partic…
MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training
Yizhi Li, Ruibin Yuan, Ge Zhang +17
Self-supervised learning (SSL) has recently emerged as a promising paradigm for training generalisable models on large-scale data in the fields of vision, text, and speech. Althoug…
TPDM: Selectively Removing Positional Information for Zero-shot Translation via Token-Level Position Disentangle Module
Xingran Chen, Ge Zhang, Jie Fu
Due to Multilingual Neural Machine Translation's (MNMT) capability of zero-shot translation, many works have been carried out to fully exploit the potential of MNMT in zero-shot tr…
Interactive Natural Language Processing
Zekun Wang, Ge Zhang, Kexin Yang +19
Interactive Natural Language Processing (iNLP) has emerged as a novel paradigm within the field of NLP, aimed at addressing limitations in existing frameworks while aligning with t…
Probabilistic Planning with Prioritized Preferences over Temporal Logic Objectives
Lening Li, Hazhar Rahmani, Jie Fu
This paper studies temporal planning in probabilistic environments, modeled as labeled Markov decision processes (MDPs), with user preferences over multiple temporal goals. Existin…
Synthesis of Opacity-Enforcing Winning Strategies Against Colluded Opponent
Chongyang Shi, Abhishek N. Kulkarni, Hazhar Rahmani +1
This paper studies a language-based opacity enforcement in a two-player, zero-sum game on a graph. In this game, player 1 (P1) wins if it can achieve a secret temporal goal describ…
Optimizing Sensor Allocation against Attackers with Uncertain Intentions: A Worst-Case Regret Minimization Approach
Haoxiang Ma, Shuo Han, Charles A. Kamhoua +1
This paper is concerned with the optimal allocation of detection resources (sensors) to mitigate multi-stage attacks, in the presence of the defender's uncertainty in the attacker'…
Autonomous Search of Semantic Objects in Unknown Environments
Zhentian Qian, Jie Fu, Jing Xiao
This paper addresses the problem of enabling a robot to search for a semantic object, i.e., an object with a semantic label, in an unknown and GPS-denied environment. For the robot…
Optimal Decoy Resource Allocation for Proactive Defense in Probabilistic Attack Graphs
Haoxiang Ma, Shuo Han, Nandi Leslie +2
This paper investigates the problem of synthesizing proactive defense systems in which the defender can allocate deceptive targets and modify the cost of actions for the attacker w…
Quantitative Planning with Action Deception in Concurrent Stochastic Games
Chongyang Shi, Shuo Han, Jie Fu
We study a class of two-player competitive concurrent stochastic games on graphs with reachability objectives. Specifically, player 1 aims to reach a subset of game states, a…
CORGI-PM: A Chinese Corpus For Gender Bias Probing and Mitigation
Ge Zhang, Yizhi Li, Yaoyao Wu +5
As natural language processing (NLP) for gender bias becomes a significant interdisciplinary topic, the prevalent data-driven techniques such as large-scale language models suffer…