Search Results for author:
Found 110 papers, 37 papers with code
Fast Gradient Computation for Gromov-Wasserstein Distance
In this way, the original computational bottleneck is broken and the new entropic solution can be obtained with total quadratic time, which is almost optimal complexity.
SqueezeAttention: 2D Management of KV-Cache in LLM Inference via Layer-wise Optimal Budget
Optimizing the Key-Value (KV) cache of the Large Language Model (LLM) has been considered critical to saving the cost of inference.
Diffusion based Zero-shot Medical Image-to-Image Translation for Cross Modality Segmentation
To leverage generative learning for zero-shot cross-modality image segmentation, we propose a novel unsupervised image translation method.
Logic Query of Thoughts: Guiding Large Language Models to Answer Complex Logic Queries with Knowledge Graphs
Through the utilization of both knowledge graph reasoning and LLMs, it successfully derives answers for each subquestion.
Meta Operator for Complex Query Answering on Knowledge Graphs
To answer complex queries under incomplete knowledge, learning-based Complex Query Answering (CQA) models are proposed to directly learn from the query-answer samples to avoid the direct traversal of incomplete graph data.
RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation
We explore how iterative revising a chain of thoughts with the help of information retrieval significantly improves large language models' reasoning and generation ability in long-horizon generation tasks, while hugely mitigating hallucination.
DPAdapter: Improving Differentially Private Deep Learning through Noise Tolerance Pre-training
DPAdapter modifies and enhances the sharpness-aware minimization (SAM) technique, utilizing a two-batch strategy to provide a more accurate perturbation estimate and an efficient gradient descent, thereby improving parameter robustness against noise.
Soft Reasoning on Uncertain Knowledge Graphs
To bridge this gap, we study the setting of soft queries on uncertain knowledge, which is motivated by the establishment of soft constraint programming.
Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key?
Recent progress in LLMs discussion suggests that multi-agent discussion improves the reasoning abilities of LLMs.
Chimera: A Lossless Decoding Method for Accelerating Large Language Models Inference by Fusing all Tokens
Within this framework, we introduce a lightweight draft model that effectively utilizes previously generated tokens to predict subsequent words.
FedCQA: Answering Complex Queries on Multi-Source Knowledge Graphs via Federated Learning
An entity can be involved in various knowledge graphs and reasoning on multiple KGs and answering complex queries on multi-source KGs is important in discovering knowledge cross graphs.
A User-Friendly Framework for Generating Model-Preferred Prompts in Text-to-Image Synthesis
To bridge the distribution gap between user input behavior and model training datasets, we first construct a novel Coarse-Fine Granularity Prompts dataset (CFP) and propose a novel User-Friendly Fine-Grained Text Generation framework (UF-FGTG) for automated prompt optimization.
MuChin: A Chinese Colloquial Description Benchmark for Evaluating Language Models in the Field of Music
To this end, we present MuChin, the first open-source music description benchmark in Chinese colloquial language, designed to evaluate the performance of multimodal LLMs in understanding and describing music.
Selecting Large Language Model to Fine-tune via Rectified Scaling Law
The ever-growing ecosystem of LLMs has posed a challenge in selecting the most appropriate pre-trained model to fine-tune amidst a sea of options.
Transforming and Combining Rewards for Aligning Large Language Models
A common approach for aligning language models to human preferences is to first learn a reward model from preference data, and then use this reward model to update the language model.
Input Convex Lipschitz RNN: A Fast and Robust Approach for Engineering Tasks
Computational efficiency and non-adversarial robustness are critical factors in real-world engineering applications.
A New Method of Pixel-level In-situ U-value Measurement for Building Envelopes Based on Infrared Thermography
The potential energy loss of aging buildings traps building owners in a cycle of underfunding operations and overpaying maintenance costs.
Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospects
Intelligent agents stand out as a potential path toward artificial general intelligence (AGI).
Privacy-Preserved Neural Graph Databases
Neural graph databases (NGDBs) have emerged as a powerful paradigm that combines the strengths of graph databases (GDBs) and neural networks to enable efficient storage, retrieval, and analysis of graph-structured data which can be adaptively trained with LLMs.
NestE: Modeling Nested Relational Structures for Knowledge Graph Reasoning
NestE represents each atomic fact as a $1\times3$ matrix, and each nested relation is modeled as a $3\times3$ matrix that rotates the $1\times3$ atomic fact matrix through matrix multiplication.
Double-Flow GAN model for the reconstruction of perceived faces from brain activities
Face plays an important role in human's visual perception, and reconstructing perceived faces from brain activities is challenging because of its difficulty in extracting high-level features and maintaining consistency of multiple face attributes, such as expression, identity, gender, etc.
The Local Landscape of Phase Retrieval Under Limited Samples
We next consider the one-point strong convexity and show that as long as $n=\omega(d)$, with high probability, the landscape is one-point strongly convex in the local annulus: $\{w\in\mathbb{R}^d: o_d(1)\leqslant \|w-w^*\|\leqslant c\}$, where $w^*$ is the ground truth and $c$ is an absolute constant.
Learning Hierarchical Polynomials with Three-Layer Neural Networks
Our main result shows that for a large subclass of degree $k$ polynomials $p$, a three-layer neural network trained via layerwise gradient descent on the square loss learns the target $h$ up to vanishing test error in $\widetilde{\mathcal{O}}(d^k)$ samples and polynomial time.
On the Discussion of Large Language Models: Symmetry of Agents and Interplay with Prompts
Two ways has been discussed to unlock the reasoning capability of a large language model.
Input Convex LSTM: A Convex Approach for Fast Lyapunov-Based Model Predictive Control
Leveraging Input Convex Neural Networks (ICNNs), ICNN-based Model Predictive Control (MPC) successfully attains globally optimal solutions by upholding convexity within the MPC framework.
JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models
Achieving human-like planning and control with multimodal observations in an open world is a key milestone for more functional generalist agents.
The Janus Interface: How Fine-Tuning in Large Language Models Amplifies the Privacy Risks
In the attack, one can construct a PII association task, whereby an LLM is fine-tuned using a minuscule PII dataset, to potentially reinstate and reveal concealed PIIs.
GROOT: Learning to Follow Instructions by Watching Gameplay Videos
We propose to follow reference videos as instructions, which offer expressive goal specifications while eliminating the need for expensive text-gameplay annotations.
MCU: A Task-centric Framework for Open-ended Agent Evaluation in Minecraft
To pursue the goal of creating an open-ended agent in Minecraft, an open-ended game environment with unlimited possibilities, this paper introduces a task-centric framework named MCU for Minecraft agent evaluation.
Towards out-of-distribution generalizable predictions of chemical kinetics properties
Under this framework, we create comprehensive datasets to benchmark (1) the state-of-the-art ML approaches for reaction prediction in the OOD setting and (2) the state-of-the-art graph OOD methods in kinetics property prediction problems.
MelodyGLM: Multi-task Pre-training for Symbolic Melody Generation
In particular, subjective evaluations show that, on the melody continuation task, MelodyGLM gains average improvements of 0. 82, 0. 87, 0. 78, and 0. 94 in consistency, rhythmicity, structure, and overall quality, respectively.
CoC-GAN: Employing Context Cluster for Unveiling a New Pathway in Image Generation
We introduce this model with the novel structure as the Context Clustering Generative Adversarial Network (CoC-GAN), which offers a distinctive viewpoint in the domain of feature aggregating and dispatching.
ProAgent: Building Proactive Cooperative Agents with Large Language Models
Building agents with adaptive behavior in cooperative tasks stands as a paramount goal in the realm of multi-agent systems.
$\text{EFO}_{k}$-CQA: Towards Knowledge Graph Complex Query Answering beyond Set Operation
Learning-based methods are essential because they are capable of generalizing over unobserved knowledge.
Prompt Injection attack against LLM-integrated Applications
We deploy HouYi on 36 actual LLM-integrated applications and discern 31 applications susceptible to prompt injection.
Theoretical Analysis of Inductive Biases in Deep Convolutional Networks
To this end, we compare the performance of CNNs, locally-connected networks (LCNs), and fully-connected networks (FCNs) on a simple regression task, where LCNs can be viewed as CNNs without weight sharing.
REMAST: Real-time Emotion-based Music Arrangement with Soft Transition
Music as an emotional intervention medium has important applications in scenarios such as music therapy, games, and movies.
Wasserstein-Fisher-Rao Embedding: Logical Query Embeddings with Local Comparison and Global Transport
In contrast to existing scoring functions motivated by local comparison or global transport, this work investigates the local and global trade-off with unbalanced optimal transport theory.
SEAL: Simultaneous Label Hierarchy Exploration And Learning
Label hierarchy is an important source of external knowledge that can enhance classification performance.
Score-based Generative Modeling Through Backward Stochastic Differential Equations: Inversion and Generation
The proposed BSDE-based diffusion model represents a novel approach to diffusion modeling, which extends the application of stochastic differential equations (SDEs) in machine learning.
Rethinking Complex Queries on Knowledge Graphs with Neural Link Predictors
Moreover, we develop a new dataset containing ten new types of queries with features that have never been considered and therefore can provide a thorough investigation of complex queries.
Feature Mining for Encrypted Malicious Traffic Detection with Deep Learning and Other Machine Learning Algorithms
Currently, research on encrypted malicious traffic detection without decryption has focused on feature extraction and the choice of machine learning or deep learning algorithms.
SketchFFusion: Sketch-guided image editing with diffusion model
Sketch-guided image editing aims to achieve local fine-tuning of the image based on the sketch information provided by the user, while maintaining the original status of the unedited areas.
Ericson: An Interactive Open-Domain Conversational Search Agent
Open-domain conversational search (ODCS) aims to provide valuable, up-to-date information, while maintaining natural conversations to help users refine and ultimately answer information needs.
Associating Spatially-Consistent Grouping with Text-supervised Semantic Segmentation
In this work, we investigate performing semantic segmentation solely through the training on image-sentence pairs.
FCC: Fusing Conversation History and Candidate Provenance for Contextual Response Ranking in Dialogue Systems
In a multi-turn dialogue, to capture the gist of a conversation, contextual information serves as essential knowledge to achieve this goal.
InterviewBot: Real-Time End-to-End Dialogue System to Interview Students for College Admission
We present the InterviewBot that dynamically integrates conversation history and customized topics into a coherent embedding space to conduct 10 mins hybrid-domain (open and closed) conversations with foreign students applying to U. S. colleges for assessing their academic and cultural readiness.
SSL-Cleanse: Trojan Detection and Mitigation in Self-Supervised Learning
We evaluated SSL-Cleanse on various datasets using 1200 encoders, achieving an average detection success rate of 82. 2% on ImageNet-100.
Concept Algebra for (Score-Based) Text-Controlled Generative Models
This suggests these models have internal representations that encode concepts in a `disentangled' manner.
Decentralized Inexact Proximal Gradient Method With Network-Independent Stepsizes for Convex Composite Optimization
The proposed algorithm uses uncoordinated network-independent constant stepsizes and only needs to approximately solve a sequence of proximal mappings, which is advantageous for solving decentralized composite optimization problems where the proximal mappings of the nonsmooth loss functions may not have analytical solutions.
Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents
We investigate the challenge of task planning for multi-task embodied agents in open-world environments.
Zero-shot-Learning Cross-Modality Data Translation Through Mutual Information Guided Stochastic Diffusion
This paper proposes a new unsupervised zero-shot-learning method named Mutual Information guided Diffusion cross-modality data translation Model (MIDiffusion), which learns to translate the unseen source data to the target domain.
Logical Message Passing Networks with One-hop Inference on Atomic Formulas
On top of the query graph, we propose the Logical Message Passing Neural Network (LMPNN) that connects the local one-hop inferences on atomic formulas to the global logical reasoning for complex query answering.
Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon Prediction
We study the problem of learning goal-conditioned policies in Minecraft, a popular, widely accessible yet challenging open-ended environment for developing human-level multi-task agents.
Learning Transformation-Predictive Representations for Detection and Description of Local Features
The task of key-points detection and description is to estimate the stable location and discriminative representation of local features, which is essential for image matching.
Unified Multimodal Model with Unlikelihood Training for Visual Dialog
Prior work performs the standard likelihood training for answer generation on the positive instances (involving correct answers).
Unsupervised Echocardiography Registration through Patch-based MLPs and Transformers
In the meantime, recent studies show that the attention-based model (e. g., Transformer) can bring superior performance in pattern recognition tasks.
MICO: A Multi-alternative Contrastive Learning Framework for Commonsense Knowledge Representation
Commonsense reasoning tasks such as commonsense knowledge graph completion and commonsense question answering require powerful representation learning.
Tackling Instance-Dependent Label Noise with Dynamic Distribution Calibration
In this paper, to address the distribution shift in learning with instance-dependent label noise, a dynamic distribution-calibration strategy is adopted.
spred: Solving $L_1$ Penalty with SGD
We propose to minimize a generic differentiable objective with $L_1$ constraint using a simple reparametrization and straightforward stochastic gradient descent.
SongDriver: Real-time Music Accompaniment Generation without Logical Latency nor Exposure Bias
In this paper, we propose SongDriver, a real-time music accompaniment generation system without logical latency nor exposure bias.
The Causal Structure of Domain Invariant Supervised Representation Learning
Then, we characterize the causal structures that are compatible with this notion of invariance. With this in hand, we find conditions under which method-specific invariance notions correspond to real-world invariant structure, and we clarify the relationship between invariant structure and robustness to domain shifts.
Integrating Knowledge Graph embedding and pretrained Language Models in Hypercomplex Spaces
In our approach, we build on existing strong representations of single modalities and we use hypercomplex algebra to represent both, (i), single-modality embedding as well as, (ii), the interaction between different modalities and their complementary means of knowledge representation.
Upper Limb Movement Recognition utilising EEG and EMG Signals for Rehabilitative Robotics
Electromyography (EMG) signals and Electroencephalography (EEG) signals are used widely for upper limb movement classification.
OnePose: One-Shot Object Pose Estimation without CAD Models
We propose a new method named OnePose for object pose estimation.
Information-Directed Selection for Top-Two Algorithms
We consider the best-k-arm identification problem for multi-armed bandits, where the objective is to select the exact set of k arms with the highest mean rewards by sequentially allocating measurement effort.
Posterior Collapse of a Linear Latent Variable Model
This work identifies the existence and cause of a type of posterior collapse that frequently occurs in the Bayesian deep learning practice.
Surface Reconstruction from Point Clouds: A Survey and a Benchmark
For example, while deep learning methods are increasingly popular, our systematic studies suggest that, surprisingly, a few classical methods perform even better in terms of both robustness and generalization; our studies also suggest that the practical challenges of misalignment of point sets from multi-view scanning, missing of surface points, and point outliers remain unsolved by all the existing surface reconstruction methods.
Query2Particles: Knowledge Graph Reasoning with Particle Embeddings
The query embedding method is proposed to answer these queries by jointly encoding queries and entities to the same embedding space.
Utterance Rewriting with Contrastive Learning in Multi-turn Dialogue
Context modeling plays a significant role in building multi-turn dialogue systems.
A Neural-Symbolic Approach to Natural Language Understanding
Deep neural networks, empowered by pre-trained language models, have achieved remarkable results in natural language understanding (NLU) tasks.
Quasi-Balanced Self-Training on Noise-Aware Synthesis of Object Point Clouds for Closing Domain Gap
Such a challenge of Simulation-to-Reality (Sim2Real) domain gap could be mitigated via learning algorithms of domain adaptation; however, we argue that generation of synthetic point clouds via more physically realistic rendering is a powerful alternative, as systematic non-uniform noise patterns can be captured.
CLIP-GEN: Language-Free Training of a Text-to-Image Generator with CLIP
Once trained, the transformer can generate coherent image tokens based on the text embedding extracted from the text encoder of CLIP upon an input text.
Adversarial Attacks on ML Defense Models Competition
Due to the vulnerability of deep neural networks (DNNs) to adversarial examples, a large number of defense techniques have been proposed to alleviate this problem in recent years.
A Speaker-aware Parallel Hierarchical Attentive Encoder-Decoder Model for Multi-turn Dialogue Generation
Differing from prior work that solely relies on the content of conversation history to generate a response, we argue that capturing relative social relations among utterances (i. e., generated by either the same speaker or different persons) benefits the machine capturing fine-grained context information from a conversation history to improve context coherence in the generated response.
Benchmarking the Combinatorial Generalizability of Complex Query Answering on Knowledge Graphs
Besides, our work, for the first time, provides a benchmark to evaluate and analyze the impact of different operators and normal forms by using (a) 7 choices of the operator systems and (b) 9 forms of complex queries.
Economic Recession Prediction Using Deep Neural Network
We investigate the effectiveness of different machine learning methodologies in predicting economic cycles.
Non-negative matrix factorization algorithms greatly improve topic model fits
We report on the potential for using algorithms for non-negative matrix factorization (NMF) to improve parameter estimation in topic models.
Attention for Image Registration (AiR): an unsupervised Transformer approach
To further advance learning approaches in image registration, we introduce an attention mechanism in the deformable image registration problem.
Mending Neural Implicit Modeling for 3D Vehicle Reconstruction in the Wild
Reconstructing high-quality 3D objects from sparse, partial observations from a single view is of crucial importance for various applications in computer vision, robotics, and graphics.
Adaptive Tree Wasserstein Minimization for Hierarchical Generative Modeling
In this work, we consider OT over tree metrics, which is more general than the sliced Wasserstein and includes the sliced Wasserstein as a special case, and we propose a fast minimization algorithm in $O(n)$ for the optimal Wasserstein-1 transport plan between two distributions in the tree structure.
PV-NAS: Practical Neural Architecture Search for Video Recognition
Recently, deep learning has been utilized to solve video recognition problem due to its prominent representation ability.
Long Short-Term Memory Neuron Equalizer
In this work we propose a neuromorphic hardware based signal equalizer by based on the deep learning implementation.
Feature matching in Ultrasound images
Feature matching is an important technique to identify a single object in different images.
An Investigation of how Label Smoothing Affects Generalization
In this paper, as a step towards understanding why label smoothing is effective, we propose a theoretical framework to show how label smoothing provides in controlling the generalization loss.
A Relaxed Matching Procedure for Unsupervised BLI
Recently unsupervised Bilingual Lexicon Induction (BLI) without any parallel corpus has attracted much research interest.
Semi-Supervised Bilingual Lexicon Induction with Two-way Interaction
In this paper, we propose a new semi-supervised BLI framework to encourage the interaction between the supervised signal and unsupervised alignment.
Emora: An Inquisitive Social Chatbot Who Cares For You
Inspired by studies on the overwhelming presence of experience-sharing in human-human conversations, Emora, the social chatbot developed by Emory University, aims to bring such experience-focused interaction to the current field of conversational AI.
Quasi-symplectic Langevin Variational Autoencoder
The HVAE adapted the Hamiltonian dynamic flow into variational inference that significantly improves the performance of the posterior estimation.
Weakly-supervised 3D Shape Completion in the Wild
3D shape completion for real data is important but challenging, since partial point clouds acquired by real-world sensors are usually sparse, noisy and unaligned.
Segmentation of the Left Ventricle by SDD double threshold selection and CHT
Automatic and robust segmentation of the left ventricle (LV) in magnetic resonance images (MRI) has remained challenging for many decades.
A Deep Learning based Fast Signed Distance Map Generation
Signed distance map (SDM) is a common representation of surfaces in medical image analysis and machine learning.
TAL EmotioNet Challenge 2020 Rethinking the Model Chosen Problem in Multi-Task Learning
This paper introduces our approach to the EmotioNet Challenge 2020.
Volumization as a Natural Generalization of Weight Decay
We propose a novel regularization method, called \textit{volumization}, for neural networks.
End-To-End Graph-based Deep Semi-Supervised Learning
The quality of a graph is determined jointly by three key factors of the graph: nodes, edges and similarity measure (or edge weights), and is very crucial to the success of graph-based semi-supervised learning (SSL) approaches.
Structural-Aware Sentence Similarity with Recursive Optimal Transport
Moreover, we further develop Recursive Optimal Similarity (ROTS) for sentences with the valuable semantic insights from the connections between cosine similarity of weighted average of word vectors and optimal transport.
Semi-Supervised Deep Learning Using Improved Unsupervised Discriminant Projection
Deep learning demands a huge amount of well-labeled data to train the network parameters.
Higher-order Weighted Graph Convolutional Networks
Graph Convolution Network (GCN) has been recognized as one of the most effective graph models for semi-supervised learning, but it extracts merely the first-order or few-order neighborhood information through information propagation, which suffers performance drop-off for deeper structure.
Tackling Long-Tailed Relations and Uncommon Entities in Knowledge Graph Completion
Therefore, we propose a meta-learning framework that aims at handling infrequent relations with few-shot learning and uncommon entities by using textual descriptions.
CAMP: Cross-Modal Adaptive Message Passing for Text-Image Retrieval
Text-image cross-modal retrieval is a challenging task in the field of language and vision.
Ranked #9 on
Image Retrieval
on Flickr30K 1K test
Wasserstein-Fisher-Rao Document Distance
As a fundamental problem of natural language processing, it is important to measure the distance between different documents.
Persona-Aware Tips Generation
In order to exploit the persona information, we propose a framework based on adversarial variational auto-encoders (aVAE) for persona modeling from the historical tips and reviews of users and items.
Improving Referring Expression Grounding with Cross-modal Attention-guided Erasing
Referring expression grounding aims at locating certain objects or persons in an image with a referring expression, where the key challenge is to comprehend and align various types of information from visual and textual domain, such as visual attributes, location and interactions with surrounding regions.
Automatically Segmenting the Left Atrium from Cardiac Images Using Successive 3D U-Nets and a Contour Loss
In this preliminary study, we propose automated, two-stage, three-dimensional U-Nets with convolutional neural network, for the challenging task of left atrial segmentation.
Responding E-commerce Product Questions via Exploiting QA Collections and Reviews
Providing instant responses for product questions in E-commerce sites can significantly improve satisfaction of potential consumers.
Deep Recurrent Generative Decoder for Abstractive Text Summarization
We propose a new framework for abstractive text summarization based on a sequence-to-sequence oriented encoder-decoder model equipped with a deep recurrent generative decoder (DRGN).
Ranked #5 on
Text Summarization
on DUC 2004 Task 1
Neural Rating Regression with Abstractive Tips Generation for Recommendation
In essence, writing some tips and giving a numerical rating are two facets of a user's product assessment action, expressing the user experience and feelings.
Compressive Holographic Video
Compressive holography has been introduced as a method that allows 3D tomographic reconstruction at different depths from a single 2D image.
Competitive and Penalized Clustering Auto-encoder
In this paper, we present a novel regularization method based on a clustering algorithm which is able to classify the parameters into different groups.
