Search Results for author:
Found 55 papers, 13 papers with code
Timeline Summarization based on Event Graph Compression via Time-Aware Optimal Transport
Timeline Summarization identifies major events from a news collection and describes them following temporal order, with key dates tagged.
Policy Agnostic RL: Offline RL and Online RL Fine-Tuning of Any Class and Backbone
To address this issue, we develop an offline RL and online fine-tuning approach called policy-agnostic RL (PA-RL) that can effectively train multiple policy classes, with varying architectures and sizes.
DCF-DS: Deep Cascade Fusion of Diarization and Separation for Speech Recognition under Realistic Single-Channel Conditions
First, we sequentially integrate the NSD and SS modules within a joint training framework, enabling the separation module to leverage speaker time boundaries from the diarization module effectively.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
Identifying Sub-networks in Neural Networks via Functionally Similar Representations
Our approach offers meaningful insights into the behavior of neural networks with minimal human and computational cost.
Enhancing Multimodal Sentiment Analysis for Missing Modality through Self-Distillation and Unified Modality Cross-Attention
In multimodal sentiment analysis, collecting text data is often more challenging than video or audio due to higher annotation costs and inconsistent automatic speech recognition (ASR) quality.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
LabSafety Bench: Benchmarking LLMs on Safety Issues in Scientific Labs
With the increasing reliance on large language models (LLMs) for guidance in various fields, including laboratory settings, there is a growing concern about their reliability in critical safety-related decision-making.
Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge
LLM-as-a-Judge has been widely utilized as an evaluation method in various benchmarks and served as supervised rewards in model training.
Disentangled Representation Learning for Parametric Partial Differential Equations
Specifically, we introduce DisentangO, a novel hyper-neural operator architecture designed to unveil and disentangle the latent physical factors of variation embedded within the black-box neural operator parameters.
Incorporating Spatial Cues in Modular Speaker Diarization for Multi-channel Multi-party Meetings
This paper proposes a three-stage modular system to enhance single-channel neural speaker diarization systems and recognition performance by utilizing spatial cues from multi-channel speech to provide more accurate initialization for each stage of neural speaker diarization (NSD) decoding: (1) Overlap detection and continuous speech separation (CSS) on multi-channel speech are used to obtain cleaner single speaker speech segments for clustering, followed by the first NSD decoding pass.
Pathfinder for Low-altitude Aircraft with Binary Neural Network
A prior global topological map (e. g., the OpenStreetMap, OSM) can boost the performance of autonomous mapping by a ground mobile robot.
The USTC-NERCSLIP Systems for the CHiME-8 NOTSOFAR-1 Challenge
This technical report outlines our submission system for the CHiME-8 NOTSOFAR-1 Challenge.
Nonlocal Attention Operator: Materializing Hidden Knowledge Towards Interpretable Physics Discovery
In this work, we propose a novel neural operator architecture based on the attention mechanism, which we coin Nonlocal Attention Operator (NAO), and explore its capability towards developing a foundation physical model.
Multitask frame-level learning for few-shot sound event detection
This paper focuses on few-shot Sound Event Detection (SED), which aims to automatically recognize and classify sound events with limited samples.
PRIME: Scaffolding Manipulation Tasks with Behavior Primitives for Data-Efficient Imitation Learning
Imitation learning has shown great potential for enabling robots to acquire complex manipulation behaviors.
Self-Supervised Contrastive Pre-Training for Multivariate Point Processes
Self-supervision is one of the hallmarks of representation learning in the increasingly popular suite of foundation models including large language models such as BERT and GPT-3, but it has not been pursued in the context of multivariate event streams, to the best of our knowledge.
BEV-TSR: Text-Scene Retrieval in BEV Space for Autonomous Driving
Furthermore, there lack of well-formed retrieval datasets for effective evaluation.
Effective Causal Discovery under Identifiable Heteroscedastic Noise Model
We then propose an effective two-phase iterative DAG learning algorithm to address the increasing optimization difficulties and to learn a causal DAG from data with heteroscedastic variable noise under varying variance.
The USTC-NERCSLIP Systems for the CHiME-7 DASR Challenge
This technical report details our submission system to the CHiME-7 DASR Challenge, which focuses on speaker diarization and speech recognition under complex multi-speaker scenarios.
GSB: Group Superposition Binarization for Vision Transformer with Limited Training Samples
Compared with the full-precision one, the model with the binarization method replaces complex tensor multiplication with simple bit-wise binary operations and represents full-precision model parameters and activations with only 1-bit ones, which potentially solves the problem of model size and computational complexity, respectively.
BPT: Binary Point Cloud Transformer for Place Recognition
To solve this issue, we propose a binary point cloud transformer for place recognition.
MetaNO: How to Transfer Your Knowledge on Learning Hidden Physics
Gradient-based meta-learning methods have primarily been applied to classical machine learning tasks such as image classification.
An Actor-Centric Causality Graph for Asynchronous Temporal Inference in Group Activity
Third, we describe the nodes (actors) with causality features and learn the edges by fusing the causality relation with the appearance relation and distance relation.
Biomechanics-Guided Facial Action Unit Detection Through Force Modeling
In this paper, we propose a biomechanics-guided AU detection approach, where facial muscle activation forces are modelled, and are employed to predict AU activation.
Knowledge-augmented Deep Learning and Its Applications: A Survey
Based on our taxonomy, we provide a systematic review of existing techniques, different from existing works that survey integration approaches agnostic to taxonomy of knowledge.
Learning and Retrieval from Prior Data for Skill-based Imitation Learning
Imitation learning offers a promising path for robots to learn general-purpose behaviors, but traditionally has exhibited limited scalability due to high data supervision requirements and brittle generalization.
Phasic Self-Imitative Reduction for Sparse-Reward Goal-Conditioned Reinforcement Learning
It has been a recent trend to leverage the power of supervised learning (SL) towards more effective reinforcement learning (RL) methods.
Nonlocal Kernel Network (NKN): a Stable and Resolution-Independent Deep Neural Network
In this work, we propose a novel nonlocal neural operator, which we refer to as nonlocal kernel network (NKN), that is resolution independent, characterized by deep neural networks, and capable of handling a variety of tasks such as learning governing equations and classifying images.
Onsite Non-Line-of-Sight Imaging via Online Calibrations
There has been an increasing interest in deploying non-line-of-sight (NLOS) imaging systems for recovering objects behind an obstacle.
Logical Credal Networks
This paper introduces Logical Credal Networks, an expressive probabilistic logic that generalizes many prior models that combine logic and probability.
Image Feature Information Extraction for Interest Point Detection: A Review
The existing popular datasets and evaluation standards are provided and the performances for eighteen state-of-the-art approaches are evaluated and discussed.
DAGs with No Curl: An Efficient DAG Structure Learning Approach
To further improve efficiency, we propose a novel learning framework to model and learn the weighted adjacency matrices in the DAG space directly.
iELAS: An ELAS-Based Energy-Efficient Accelerator for Real-Time Stereo Matching on FPGA Platform
Stereo matching is a critical task for robot navigation and autonomous vehicles, providing the depth estimation of surroundings.
USTC-NELSLIP System Description for DIHARD-III Challenge
This system description describes our submission system to the Third DIHARD Speech Diarization Challenge.
Integer Programming for Causal Structure Learning in the Presence of Latent Variables
The problem of finding an ancestral acyclic directed mixed graph (ADMG) that represents the causal relationships between a set of variables is an important area of research on causal inference.
Non-line-of-Sight Imaging via Neural Transient Fields
We present a neural modeling framework for Non-Line-of-Sight (NLOS) imaging.
DAGs with No Fears: A Closer Look at Continuous Optimization for Learning Bayesian Networks
This paper re-examines a continuous optimization framework dubbed NOTEARS for learning Bayesian networks.
MCMH: Learning Multi-Chain Multi-Hop Rules for Knowledge Graph Reasoning
Multi-hop reasoning approaches over knowledge graphs infer a missing relationship between entities with a multi-hop rule, which corresponds to a chain of relationships.
Type-augmented Relation Prediction in Knowledge Graphs
Knowledge graph completion (also known as relation prediction) is the task of inferring missing facts given existing ones.
"And the Winner Is...": Dynamic Lotteries for Multi-group Fairness-Aware Recommendation
As recommender systems are being designed and deployed for an increasing number of socially-consequential applications, it has become important to consider what properties of fairness these systems exhibit.
A Multi-Channel Neural Graphical Event Model with Negative Evidence
Event datasets are sequences of events of various types occurring irregularly over the time-line, and they are increasingly prevalent in numerous domains.
Do Multi-hop Readers Dream of Reasoning Chains?
General Question Answering (QA) systems over texts require the multi-hop reasoning capability, i. e. the ability to reason with information collected from multiple passages to derive the answer.
Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering
Multi-hop question answering (QA) requires an information retrieval (IR) system that can find \emph{multiple} supporting evidence needed to answer the question, making the retrieval process very challenging.
Characterization of Overlap in Observational Studies
Overlap between treatment groups is required for non-parametric estimation of causal effects.
Generalized Linear Rule Models
Column generation is used to optimize over an exponentially large space of rules without pre-generating a large subset of candidates or greedily boosting rules one by one.
Does It Make Sense? And Why? A Pilot Study for Sense Making and Explanation
Introducing common sense to natural language understanding systems has received increasing research attention.
DAG-GNN: DAG Structure Learning with Graph Neural Networks
Learning a faithful directed acyclic graph (DAG) from samples of a joint distribution is a challenging combinatorial problem, owing to the intractable search space superexponential in the number of graph nodes.
A Sequential Set Generation Method for Predicting Set-Valued Outputs
Though SSG is sequential in nature, it does not penalize the ordering of the appearance of the set elements and can be applied to a variety of set output problems, such as a set of classification labels or sequences.
Proximal Graphical Event Models
Event datasets include events that occur irregularly over the timeline and are prevalent in numerous domains.
Identifying the Discourse Function of News Article Paragraphs
We test two hypotheses: first, that people can reliably annotate news articles with van Dijk{'}s theory; second, that we can reliably predict these labels using machine learning.
Parallel Bayesian Network Structure Learning
Recent advances in Bayesian Network (BN) structure learning have focused on local-to-global learning, where the graph structure is learned via one local subgraph at a time.
e-QRAQ: A Multi-turn Reasoning Dataset and Simulator with Explanations
In this paper we present a new dataset and user simulator e-QRAQ (explainable Query, Reason, and Answer Question) which tests an Agent's ability to read an ambiguous text; ask questions until it can answer a challenge question; and explain the reasoning behind its questions and answer.
Local-to-Global Bayesian Network Structure Learning
We introduce a new local-to-global structure learning algorithm, called graph growing structure learning (GGSL), to learn Bayesian network (BN) structures.
Structured Feature Selection
Then we apply structured feature selection to two applications: 1) We introduce a new method that enables STMB to scale up and show the competitive performance of our algorithms on large-scale image classification tasks.
Local Causal Discovery of Direct Causes and Effects
We focus on the discovery and identification of direct causes and effects of a target variable in a causal network.
