Search Results for author:
Found 76 papers, 26 papers with code
Eureka: Neural Insight Learning for Knowledge Graph Reasoning
The human recognition system has presented the remarkable ability to effortlessly learn novel knowledge from only a few trigger events based on prior knowledge, which is called insight learning.
HunyuanVideo: A Systematic Framework For Large Video Generative Models
In this report, we introduce HunyuanVideo, an innovative open-source video foundation model that demonstrates performance in video generation comparable to, or even surpassing, that of leading closed-source models.
Maximizing the Impact of Deep Learning on Subseasonal-to-Seasonal Climate Forecasting: The Essential Role of Optimization
This paper identifies that optimization, instead of network structure, could be the root cause of this performance gap, and then we develop a novel multi-stage optimization strategy to close the gap.
Gemma 2: Improving Open Language Models at a Practical Size
In this work, we introduce Gemma 2, a new addition to the Gemma family of lightweight, state-of-the-art open models, ranging in scale from 2 billion to 27 billion parameters.
The Llama 3 Herd of Models
This paper presents a new set of foundation models, called Llama 3.
Ranked #2 on
Multi-task Language Understanding
on MMLU
Selective Prompting Tuning for Personalized Conversations with LLMs
To alleviate those issues, we propose \textbf{S}elective \textbf{P}rompt \textbf{T}uning (SPT), which softly prompts LLMs for personalized conversations in a selective way.
SMP Challenge: An Overview and Analysis of Social Media Prediction Challenge
The research progress analysis provides an overall analysis of the solutions and trends in recent years.
SOK-Bench: A Situated Video Reasoning Benchmark with Aligned Open-World Knowledge
Learning commonsense reasoning from visual contexts and scenes in real-world is a crucial step toward advanced artificial intelligence.
STAR: A Benchmark for Situated Reasoning in Real-World Videos
This paper introduces a new benchmark that evaluates the situated reasoning ability via situation abstraction and logic-grounded question answering for real-world videos, called Situated Reasoning in Real-World Videos (STAR Benchmark).
Uncertainty-Aware Deployment of Pre-trained Language-Conditioned Imitation Learning Policies
Large-scale robotic policies trained on data from diverse tasks and robotic platforms hold great promise for enabling general-purpose robots; however, reliable generalization to new environment conditions remains a major challenge.
An Efficient MLP-based Point-guided Segmentation Network for Ore Images with Ambiguous Boundary
The precise segmentation of ore images is critical to the successful execution of the beneficiation process.
Efficient Segmentation with Texture in Ore Images Based on Box-supervised Approach
At the same time, the ore distribution is stacked, and it is difficult to identify the complete features.
The NeurIPS 2022 Neural MMO Challenge: A Massively Multiagent Competition with Specialization and Trade
In this paper, we present the results of the NeurIPS-2022 Neural MMO Challenge, which attracted 500 participants and received over 1, 600 submissions.
Distance-Based Propagation for Efficient Knowledge Graph Reasoning
A new class of methods have been proposed to tackle this problem by aggregating path information.
LPFormer: An Adaptive Graph Transformer for Link Prediction
These methods perform predictions by using the output of an MPNN in conjunction with a "pairwise encoding" that captures the relationship between nodes in the candidate link.
Benchmarking Robustness and Generalization in Multi-Agent Systems: A Case Study on Neural MMO
We present the results of the second Neural MMO challenge, hosted at IJCAI 2022, which received 1600+ submissions.
Evaluating Large Language Models on Graphs: Performance Insights and Comparative Analysis
Yet, the application of LLMs to graph data remains under-explored.
Data Cross-Segmentation for Improved Generalization in Reinforcement Learning Based Algorithmic Trading
In a typical set-up, supervised learning is used to predict the future prices of assets, and those predictions drive a simple trading and execution strategy.
BatchGNN: Efficient CPU-Based Distributed GNN Training on Very Large Graphs
We present BatchGNN, a distributed CPU system that showcases techniques that can be used to efficiently train GNNs on terabyte-sized graphs.
Learning from Children: Improving Image-Caption Pretraining via Curriculum
The difficulty is progressively increased with each new phase by adding one more concept per caption.
FR-Net:A Light-weight FFT Residual Net For Gaze Estimation
Furthermore, our method outperforms existing lightweight methods in terms of accuracy and efficiency for the gaze estimation task.
Faster OreFSDet : A Lightweight and Effective Few-shot Object Detector for Ore Images
For the ore particle size detection, obtaining a sizable amount of high-quality ore labeled data is time-consuming and expensive.
Learning Situation Hyper-Graphs for Video Question Answering
The proposed method is trained in an end-to-end manner and optimized by a VQA loss with the cross-entropy function and a Hungarian matching loss for the situation graph prediction.
Ranked #6 on
Video Question Answering
on AGQA 2.0 balanced
Visual Fault Detection of Multi-scale Key Components in Freight Trains
Fault detection for key components in the braking system of freight trains is critical for ensuring railway transportation safety.
Personalized Dialogue Generation with Persona-Adaptive Attention
Persona-based dialogue systems aim to generate consistent responses based on historical context and predefined persona.
Compressing Pre-trained Transformers via Low-Bit NxM Sparsity for Natural Language Understanding
Furthermore, we present and inexpensive, heuristic-driven search algorithm that identifies promising heterogeneous compression configurations that meet a compression ratio constraint.
A Lightweight NMS-free Framework for Real-time Visual Fault Detection System of Freight Trains
In this paper, we propose a lightweight NMS-free framework to achieve real-time detection and high accuracy simultaneously.
DeepFD: Automated Fault Diagnosis and Localization for Deep Learning Programs
Besides, for fault localization, DeepFD also outperforms the existing works, correctly locating 42% faulty programs, which almost doubles the best result (23%) achieved by the existing works.
DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection
In this paper, we propose two novel techniques: InverseAug that inverses geometric-related augmentations, e. g., rotation, to enable accurate geometric alignment between lidar points and image pixels, and LearnableAlign that leverages cross-attention to dynamically capture the correlations between image and lidar features during fusion.
NxMTransformer: Semi-Structured Sparsification for Natural Language Understanding via ADMM
In particular, we propose to formulate the NxM sparsity as a constrained optimization problem and use Alternating Direction Method of Multipliers (ADMM) to optimize the downstream tasks while taking the underlying hardware constraints into consideration.
Counterfactual Debiasing Inference for Compositional Action Recognition
By doing that, our proposed CDN method can better recognize unseen action instances by debiasing the effect of appearances.
HoloFormer: Deep Compression of Pre-Trained Transforms via Unified Optimization of N:M Sparsity and Integer Quantization
In this work, we propose a unified, systematic approach to learning N:M sparsity and integer quantization for pre-trained Transformers using the Alternating Directions Method of Multipliers (ADMM).
IGNNITION: Bridging the Gap Between Graph Neural Networks and Networking Systems
In this article, we present IGNNITION, a novel open-source framework that enables fast prototyping of GNNs for networking systems.
Is Machine Learning Ready for Traffic Engineering Optimization?
In our evaluation, we compare our MARL+GNN system with DEFO, a network optimizer based on Constraint Programming that represents the state of the art in TE.
BIG-bench Machine Learning
Multi-agent Reinforcement Learning
+1
The Graph Neural Networking Challenge: A Worldwide Competition for Education in AI/ML for Networks
During the last decade, Machine Learning (ML) has increasingly become a hot topic in the field of Computer Networks and is expected to be gradually adopted for a plethora of control, monitoring and management tasks in real-world deployments.
Token-Level Supervised Contrastive Learning for Punctuation Restoration
Punctuation is critical in understanding natural language text.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+6
TeCANet: Temporal-Contextual Attention Network for Environment-Aware Speech Dereverberation
In this paper, we exploit the effective way to leverage contextual information to improve the speech dereverberation performance in real-world reverberant environments.
Privacy-Preserving Kickstarting Deep Reinforcement Learning with Privacy-Aware Learners
We then develop a kickstarted deep reinforcement learning algorithm for the student that is privacy-aware because we calibrate its objective with the parameters of the teacher's privacy mechanism.
Efficient Mining of Frequent Subgraphs with Two-Vertex Exploration
Frequent Subgraph Mining (FSM) is the key task in many graph mining and machine learning applications.
Graph Mining
Databases
Performance
Analogical Reasoning for Visually Grounded Compositional Generalization
Children acquire language subconsciously by observing the surrounding world and listening to descriptions.
MG-SAGC: A multiscale graph and its self-adaptive graph convolution network for 3D point clouds
To enhance the ability of neural networks to extract local point cloud features and improve their quality, in this paper, we propose a multiscale graph generation method and a self-adaptive graph convolution method.
Enhancing Neural Models with Vulnerability via Adversarial Attack
2) There is no previous work considering adversarial attack to improve the performance of NLSM tasks.
Audio-visual Multi-channel Integration and Recognition of Overlapped Speech
Automatic speech recognition (ASR) technologies have been significantly advanced in the past few decades.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
The Bright Side and the Dark Side of Hybrid Organic Inorganic Perovskites
The previously developed bistable amphoteric native defect (BAND) model is used for a comprehensive explanation of the unique photophysical properties and for understanding the remarkable performance of perovskites as photovoltaic materials.
Applied Physics Materials Science
Constrained Active Classification Using Partially Observable Markov Decision Processes
The proposed framework relies on assigning a classification belief (a probability distribution) to the attributes of interest.
Byzantine-Resilient Distributed Hypothesis Testing With Time-Varying Network Topology
We study the problem of distributed hypothesis testing over a network of mobile agents with limited communication and sensing ranges to infer the true hypothesis collaboratively.
Analogical Reasoning for Visually Grounded Language Acquisition
Children acquire language subconsciously by observing the surrounding world and listening to descriptions.
Temporal-Logic-Based Reward Shaping for Continuing Reinforcement Learning Tasks
Reward shaping is a common approach for incorporating domain knowledge into reinforcement learning in order to speed up convergence to an optimal policy.
Reward Machines for Cooperative Multi-Agent Reinforcement Learning
In cooperative multi-agent reinforcement learning, a collection of agents learns to interact in a shared environment to achieve a common goal.
GAIA: A Fine-grained Multimedia Knowledge Extraction System
We present the first comprehensive, open source multimedia knowledge extraction system that takes a massive stream of unstructured, heterogeneous multimedia data from various sources and languages as input, and creates a coherent, structured knowledge base, indexing entities, relations, and events, following a rich, fine-grained ontology.
Active Finite Reward Automaton Inference and Reinforcement Learning Using Queries and Counterexamples
We compare our algorithm with the state-of-the-art RL algorithms for non-Markovian reward functions, such as Joint Inference of Reward machines and Policies for RL (JIRP), Learning Reward Machine (LRM), and Proximal Policy Optimization (PPO2).
Learning the Compositional Visual Coherence for Complementary Recommendations
Towards this end, in this paper, we propose a novel Content Attentive Neural Network (CANN) to model the comprehensive compositional coherence on both global contents and semantic contents.
Audio-visual Multi-channel Recognition of Overlapped Speech
Automatic speech recognition (ASR) of overlapped speech remains a highly challenging task to date.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
What Do Questions Exactly Ask? MFAE: Duplicate Question Identification with Multi-Fusion Asking Emphasis
We firstly propose to explore the asking emphasis of a question as a key factor in DQI.
Ranked #1 on
Community Question Answering
on Quora Question Pairs
Dynamic Spatiotemporal Graph Neural Network with Tensor Network
Dynamic spatial graph construction is a challenge in graph neural network (GNN) for time series data problems.
Population pharmacokinetics and dosing regimen optimization of tacrolimus in Chinese lung transplant recipients
Given the nonlinear kinetics of tacrolimus and large variability, population pharmacokinetic model should be combined with therapeutic drug monitoring to optimize individualized therapy.
Audio-visual Recognition of Overlapped speech for the LRS2 dataset
Experiments on overlapped speech simulated from the LRS2 dataset suggest the proposed AVSR system outperformed the audio only baseline LF-MMI DNN system by up to 29. 98\% absolute in word error rate (WER) reduction, and produced recognition performance comparable to a more complex pipelined system.
Ranked #5 on
Audio-Visual Speech Recognition
on LRS2
Audio-Visual Speech Recognition
Automatic Speech Recognition (ASR)
+4
General Partial Label Learning via Dual Bipartite Graph Autoencoder
Compared to the traditional Partial Label Learning (PLL) problem, GPLL relaxes the supervision assumption from instance-level -- a label set partially labels an instance -- to group-level: 1) a label set partially labels a group of instances, where the within-group instance-label link annotations are missing, and 2) cross-group links are allowed -- instances in a group may be partially linked to the label set from another group.
Ranked #1 on
Partial Label Learning
on MPII Movie Description
Theme-Matters: Fashion Compatibility Learning via Theme Attention
This model associates themes with the pairwise compatibility with attention, and thus compute the outfit-wise compatibility.
SMP Challenge: An Overview of Social Media Prediction Challenge 2019
In the SMP Challenge at ACM Multimedia 2019, we introduce a novel prediction task Temporal Popularity Prediction, which focuses on predicting future interaction or attractiveness (in terms of clicks, views or likes etc.)
Joint Inference of Reward Machines and Policies for Reinforcement Learning
The experiments show that learning high-level knowledge in the form of reward machines can lead to fast convergence to optimal policies in RL, while standard RL methods such as q-learning and hierarchical RL methods fail to converge to optimal policies after a substantial number of training steps in many tasks.
Outfit Compatibility Prediction and Diagnosis with Multi-Layered Comparison Network
Existing works about fashion outfit compatibility focus on predicting the overall compatibility of a set of fashion items with their information from different modalities.
Hard-Aware Fashion Attribute Classification
For "hard" attributes with insufficient training data, Deact brings more stable synthetic samples for training and further improve the performance.
MemNet: Memory-Efficiency Guided Neural Architecture Search with Augment-Trim learning
Recent studies on automatic neural architectures search have demonstrated significant performance, competitive to or even better than hand-crafted neural architectures.
Improving Reverberant Speech Training Using Diffuse Acoustic Simulation
We present an efficient and realistic geometric acoustic simulation approach for generating and augmenting training data in speech-related machine learning tasks.
Reward-Based Deception with Cognitive Bias
In this paper, we consider deceiving adversaries with bounded rationality and in terms of expected rewards.
Optimizing Sponsored Search Ranking Strategy by Deep Reinforcement Learning
From the advertisers' side, participating in ranking the search results by paying for the sponsored search advertisement to attract more awareness and purchase facilitates their commercial goal.
Beyond Keywords and Relevance: A Personalized Ad Retrieval Framework in E-Commerce Sponsored Search
Given a search request, ad retrieval module rewrites the query into bidding keywords, and uses these keywords as keys to select Top N ads through inverted indexes.
Sequential Prediction of Social Media Popularity with Deep Temporal Context Networks
With a joint embedding network, we obtain a unified deep representation of multi-modal user-post data in a common embedding space.
Time Matters: Multi-scale Temporalization of Social Media Popularity
We evaluate our approach on two large-scale Flickr image datasets with over 1. 8 million photos in total, for the task of popularity prediction.
DGCNN: Disordered Graph Convolutional Neural Network Based on the Gaussian Mixture Model
Convolutional neural networks (CNNs) can be applied to graph similarity matching, in which case they are called graph CNNs.
Ranked #1 on
Graph Classification
on AIDS
Learning Unified Embedding for Apparel Recognition
To ease the training difficulty, a novel learning scheme is proposed by using the output from specialized models as learning targets so that L2 loss can be used instead of triplet loss.
A Learning Based Optimal Human Robot Collaboration with Linear Temporal Logic Constraints
This paper considers an optimal task allocation problem for human robot collaboration in human robot systems with persistent tasks.
Feature Selection Parallel Technique for Remotely Sensed Imagery Classification
Remote sensing research focusing on feature selection has long attracted the attention of the remote sensing community because feature selection is a prerequisite for image processing and various applications.
Supervisor Synthesis of POMDP based on Automata Learning
The learning algorithm is sound and complete.
Bearing fault diagnosis based on spectrum images of vibration signals
Bearing fault diagnosis has been a challenge in the monitoring activities of rotating machinery, and it's receiving more and more attention.
