Search Results for author:
Found 580 papers, 197 papers with code
Toward Knowledge-Enriched Conversational Recommendation Systems
Conversational Recommendation Systems recommend items through language based interactions with users. In order to generate naturalistic conversations and effectively utilize knowledge graphs (KGs) containing background information, we propose a novel Bag-of-Entities loss, which encourages the generated utterances to mention concepts related to the item being recommended, such as the genre or director of a movie.
融合零指代识别的篇章级机器翻译(Context-aware Machine Translation Integrating Zero Pronoun Recognition)
“在汉语等其他有省略代词习惯的语言中, 通常会删掉可从上下文信息推断出的代词。尽管以Transformer为代表的的神经机器翻译模型取得了巨大的成功, 但这种省略现象依旧对神经机器翻译模型造成了很大的挑战。本文在Transformer基础上提出了一个融合零指代识别的翻译模型, 并引入篇章上下文来丰富指代信息。具体地, 该模型采用联合学习的框架, 在翻译模型基础上, 联合了一个分类任务, 即判别句子中省略代词在句子所表示的成分, 使得模型能够融合零指代信息辅助翻译。通过在中英对话数据集上的实验, 验证了本文提出方法的有效性, 与基准模型相比, 翻译性能提升了1. 48个BLEU值。”
Beyond 3DMM Space: Towards Fine-grained 3D Face Reconstruction
However, most of their training data is constructed by 3D Morphable Model, whose space spanned is only a small part of the shape space.
Multi-Weather Image Restoration via Histogram-Based Transformer Feature Enhancement
In this paper, we propose a Task Sequence Generator module that, in conjunction with the Task Intra-patch Block, effectively extracts task-specific features embedded in degraded images.
Multiple weather images restoration using the task transformer and adaptive mixup strategy
In this paper, we introduce a novel multi-task severe weather removal model that can effectively handle complex weather conditions in an adaptive manner.
Empowering Pre-Trained Language Models for Spatio-Temporal Forecasting via Decoupling Enhanced Discrete Reprogramming
Moreover, the linear mapping of continuous time series to a compressed subset vocabulary in reprogramming constrains the spatio-temporal semantic expressivity of PLMs and may lead to potential information bottleneck.
Denoising Pre-Training and Customized Prompt Learning for Efficient Multi-Behavior Sequential Recommendation
Its objective is to extract knowledge from extensive pre-training data and fine-tune the model for downstream tasks.
SG-GS: Photo-realistic Animatable Human Avatars with Semantically-Guided Gaussian Splatting
To address this issue, we propose SG-GS, which uses semantics-embedded 3D Gaussians, skeleton-driven rigid deformation, and non-rigid cloth dynamics deformation to create photo-realistic animatable human avatars from monocular videos.
CHASE: 3D-Consistent Human Avatars with Sparse Inputs via Gaussian Splatting and Contrastive Learning
To address this challenge, we propose CHASE, which introduces supervision from intrinsic 3D consistency across poses and 3D geometry contrastive learning, achieving performance comparable with sparse inputs to that with full inputs.
ViC: Virtual Compiler Is All You Need For Assembly Code Search
Assembly code search is vital for reducing the burden on reverse engineers, allowing them to quickly identify specific functions using natural language within vast binary programs.
Online Electric Vehicle Charging Detection Based on Memory-based Transformer using Smart Meter Data
It dynamically leverages coarse-scale historical information using an M-TR encoder from an extended global temporal window, in conjunction with an M-TR decoder that concentrates on a limited time frame, local window, aiming to capture the fine-scale characteristics of the smart meter data.
HARMONIC: Harnessing LLMs for Tabular Data Synthesis and Privacy Protection
In this paper, we take a step forward to explore LLMs for tabular data synthesis and privacy protection, by introducing a new framework HARMONIC for tabular data generation and evaluation.
SciPostLayout: A Dataset for Layout Analysis and Layout Generation of Scientific Posters
All of the posters and papers in our dataset are under the CC-BY license and are publicly available.
RRAM-Based Bio-Inspired Circuits for Mobile Epileptic Correlation Extraction and Seizure Prediction
Non-invasive mobile electroencephalography (EEG) acquisition systems have been utilized for long-term monitoring of seizures, yet they suffer from limited battery life.
Rina: Enhancing Ring-AllReduce with In-network Aggregation in Distributed Model Training
The emerging In-network Aggregation (INA) has been proposed to integrate with PS to mitigate its incast issue.
Reduced-Space Iteratively Reweighted Second-Order Methods for Nonconvex Sparse Regularization
This paper explores a specific type of nonconvex sparsity-promoting regularization problems, namely those involving $\ell_p$-norm regularization, in conjunction with a twice continuously differentiable loss function.
Poisoning with A Pill: Circumventing Detection in Federated Learning
Without direct access to the client's data, federated learning (FL) is well-known for its unique strength in data privacy protection among existing distributed machine learning techniques.
Overview of AI-Debater 2023: The Challenges of Argument Generation Tasks
In this paper we present the results of the AI-Debater 2023 Challenge held by the Chinese Conference on Affect Computing (CCAC 2023), and introduce the related datasets.
RBAD: A Dataset and Benchmark for Retinal Vessels Branching Angle Detection
Detecting retinal image analysis, particularly the geometrical features of branching points, plays an essential role in diagnosing eye diseases.
IPA-NeRF: Illusory Poisoning Attack Against Neural Radiance Fields
In this study, we contribute to this area by introducing the Illusory Poisoning Attack against Neural Radiance Fields (IPA-NeRF).
Learning Unlabeled Clients Divergence via Anchor Model Aggregation for Federated Semi-supervised Learning
Existing FedSemi methods typically fail to aggregate models from unlabeled clients due to their inherent unreliability, thus overlooking unique information from their heterogeneous data distribution, leading to sub-optimal results.
OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion
To address these challenges, we propose a novel unified open-vocabulary detection method called OV-DINO, which is pre-trained on diverse large-scale datasets with language-aware selective fusion in a unified framework.
Ranked #4 on
Zero-Shot Object Detection
on MSCOCO
(using extra training data)
Entropy Law: The Story Behind Data Compression and LLM Performance
Inspired by the information compression nature of LLMs, we uncover an ``entropy law'' that connects LLM performance with data compression ratio and first-epoch training loss, which reflect the information redundancy of a dataset and the mastery of inherent knowledge encoded in this dataset, respectively.
Seed-ASR: Understanding Diverse Speech and Contexts with LLM-based Speech Recognition
Modern automatic speech recognition (ASR) model is required to accurately transcribe diverse speech signals (from different domains, languages, accents, etc) given the specific contextual information in various application scenarios.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs
This report introduces FunAudioLLM, a model family designed to enhance natural voice interactions between humans and large language models (LLMs).
Foundations and Frontiers of Graph Learning Theory
Recent advancements in graph learning have revolutionized the way to understand and analyze data with complex structures.
Proximity Matters: Local Proximity Preserved Balancing for Treatment Effect Estimation
Heterogeneous treatment effect (HTE) estimation from observational data poses significant challenges due to treatment selection bias.
AutoFlow: Automated Workflow Generation for Large Language Model Agents
We believe that the automatic generation and interpretation of workflows in natural language represent a promising paradigm for solving complex tasks, particularly with the rapid development of LLMs.
Personalized Federated Continual Learning via Multi-granularity Prompt
In addition, we design a selective prompt fusion mechanism for aggregating knowledge of global prompts distilled from different clients.
Debiased Recommendation with Noisy Feedback
Ratings of a user to most items in recommender systems are usually missing not at random (MNAR), largely because users are free to choose which items to rate.
Efficient Low-rank Identification via Accelerated Iteratively Reweighted Nuclear Norm Minimization
We prove the global convergence of the proposed algorithm, guaranteeing that every limit point of the iterates is a critical point.
GVT2RPM: An Empirical Study for General Video Transformer Adaptation to Remote Physiological Measurement
Further, due to their customization of the transformer architecture, they cannot use the advancements made in general video transformers (GVT).
NTIRE 2024 Challenge on Night Photography Rendering
The top ranking participants' solutions effectively represent the state-of-the-art in nighttime photography rendering.
Probabilistic Conceptual Explainers: Trustworthy Conceptual Explanations for Vision Foundation Models
We introduce a variational Bayesian explanation framework, dubbed ProbAbilistic Concept Explainers (PACE), which models the distributions of patch embeddings to provide trustworthy post-hoc conceptual explanations.
BLoB: Bayesian Low-Rank Adaptation by Backpropagation for Large Language Models
Large Language Models (LLMs) often suffer from overconfidence during inference, particularly when adapted to downstream domain-specific tasks with limited data.
Multimodal Needle in a Haystack: Benchmarking Long-Context Capability of Multimodal Large Language Models
However, a comprehensive evaluation of their long-context capabilities remains underexplored.
Ranked #1000000000 on
Hallucination
on MMNeedle
Nemotron-4 340B Technical Report
We release the Nemotron-4 340B model family, including Nemotron-4-340B-Base, Nemotron-4-340B-Instruct, and Nemotron-4-340B-Reward.
Open-Vocabulary X-ray Prohibited Item Detection via Fine-tuning CLIP
To address aforementioned challenges, in this paper, we introduce distillation-based open-vocabulary object detection (OVOD) task into X-ray security inspection domain by extending CLIP to learn visual representations in our specific X-ray domain, aiming to detect novel prohibited item categories beyond base categories on which the detector is trained.
Reasoning or Simply Next Token Prediction? A Benchmark for Stress-Testing Large Language Models
We propose MMLU-SR, a novel dataset designed to measure the true comprehension abilities of Large Language Models (LLMs) by challenging their performance in question-answering tasks with modified terms.
OSPC: Detecting Harmful Memes with Large Language Model as a Catalyst
Utilizing the BLIP model for image captioning, PP-OCR and TrOCR for text recognition across multiple languages, and the Qwen LLM for nuanced language understanding, our system is capable of identifying harmful content in memes created in English, Chinese, Malay, and Tamil.
Towards Domain Adaptive Neural Contextual Bandits
Our approach learns a bandit model for the target domain by collecting feedback from the source domain.
Verbalized Probabilistic Graphical Modeling with Large Language Models
Faced with complex problems, the human brain demonstrates a remarkable capacity to transcend sensory input and form latent understandings of perceived world patterns.
Exploring User Retrieval Integration towards Large Language Models for Cross-Domain Sequential Recommendation
To this end, we propose a novel framework named URLLM, which aims to improve the CDSR performance by exploring the User Retrieval approach and domain grounding on LLM simultaneously.
MMCL: Boosting Deformable DETR-Based Detectors with Multi-Class Min-Margin Contrastive Learning for Superior Prohibited Item Detection
Prohibited Item detection in X-ray images is one of the most effective security inspection methods. However, differing from natural light images, the unique overlapping phenomena in X-ray images lead to the coupling of foreground and background features, thereby lowering the accuracy of general object detectors. Therefore, we propose a Multi-Class Min-Margin Contrastive Learning (MMCL) method that, by clarifying the category semantic information of content queries under the deformable DETR architecture, aids the model in extracting specific category foreground information from coupled features. Specifically, after grouping content queries by the number of categories, we employ the Multi-Class Inter-Class Exclusion (MIE) loss to push apart content queries from different groups.
Phonetic Enhanced Language Modeling for Text-to-Speech Synthesis
Recent language model-based text-to-speech (TTS) frameworks demonstrate scalability and in-context learning capabilities.
Spectrum-Aware Parameter Efficient Fine-Tuning for Diffusion Models
We introduce Spectral Orthogonal Decomposition Adaptation (SODA), which balances computational efficiency and representation capacity.
Exploring Diffusion Models' Corruption Stage in Few-Shot Fine-tuning and Mitigating with Bayesian Neural Networks
Through this modeling, we identify the primary cause of this corruption stage: a narrowed learning distribution inherent in the nature of few-shot fine-tuning.
FTS: A Framework to Find a Faithful TimeSieve
The field of time series forecasting has garnered significant attention in recent years, prompting the development of advanced models like TimeSieve, which demonstrates impressive performance.
Adapting Differentially Private Synthetic Data to Relational Databases
Existing differentially private (DP) synthetic data generation mechanisms typically assume a single-source table.
Delving into Differentially Private Transformer
Deep learning with differential privacy (DP) has garnered significant attention over the past years, leading to the development of numerous methods aimed at enhancing model accuracy and training efficiency.
Dataset Regeneration for Sequential Recommendation
The sequential recommender (SR) system is a crucial component of modern recommender systems, as it aims to capture the evolving preferences of users.
Match, Compare, or Select? An Investigation of Large Language Models for Entity Matching
Based on our findings, we further design a compound entity matching framework (ComEM) that leverages the composition of multiple strategies and LLMs.
Medical MLLM is Vulnerable: Cross-Modality Jailbreak and Mismatched Attacks on Medical Multimodal Large Language Models
Security concerns related to Large Language Models (LLMs) have been extensively explored, yet the safety implications for Multimodal Large Language Models (MLLMs), particularly in medical contexts (MedMLLMs), remain insufficiently studied.
AI-Generated Text Detection and Classification Based on BERT Deep Learning Algorithm
In conclusion, the AI-generated text detection model based on the BERT algorithm proposed in this study shows high accuracy and stability in experiments, providing an effective solution for related fields.
Implicit In-context Learning
In-context Learning (ICL) empowers large language models (LLMs) to adapt to unseen tasks during inference by prefixing a few demonstration examples prior to test queries.
Learning Partially Aligned Item Representation for Cross-Domain Sequential Recommendation
Cross-domain sequential recommendation (CDSR) aims to uncover and transfer users' sequential preferences across multiple recommendation domains.
A Click-Through Rate Prediction Method Based on Cross-Importance of Multi-Order Features
To verify that the FiiNet model can dynamically learn the importance of feature interaction combinations in a fine-grained manner and improve the model's recommendation performance and interpretability, this paper compares it with many click-through rate prediction models on two real datasets, proving that the FiiNet model incorporating the selective kernel network can effectively improve the recommendation effect and provide better interpretability.
A Newton Method for Hausdorff Approximations of the Pareto Front within Multi-objective Evolutionary Algorithms
In this work, we propose a set-based Newton method for Hausdorff approximations of the Pareto front to be used within multi-objective evolutionary algorithms.
COM3D: Leveraging Cross-View Correspondence and Cross-Modal Mining for 3D Retrieval
To address this issue, we propose COM3D, making the first attempt to exploit the cross-view correspondence and cross-modal mining to enhance the retrieval performance.
TimeMIL: Advancing Multivariate Time Series Classification via a Time-aware Multiple Instance Learning
Deep neural networks, including transformers and convolutional neural networks, have significantly improved multivariate time series classification (MTSC).
Reinforcement Learning for Edit-Based Non-Autoregressive Neural Machine Translation
Non-autoregressive (NAR) language models are known for their low latency in neural machine translation (NMT).
UCB-driven Utility Function Search for Multi-objective Reinforcement Learning
In Multi-objective Reinforcement Learning (MORL) agents are tasked with optimising decision-making behaviours that trade-off between multiple, possibly conflicting, objectives.
WHALE-FL: Wireless and Heterogeneity Aware Latency Efficient Federated Learning over Mobile Devices via Adaptive Subnetwork Scheduling
Although such fixed size subnetwork assignment enables FL training over heterogeneous mobile devices, it is unaware of (i) the dynamic changes of devices' communication and computing conditions and (ii) FL training progress and its dynamic requirements of local training contributions, both of which may cause very long FL training delay.
Continual Model-based Reinforcement Learning for Data Efficient Wireless Network Optimisation
We present a method that addresses the pain point of long lead-time required to deploy cell-level parameter optimisation policies to new wireless network sites.
Enhancing Boundary Segmentation for Topological Accuracy with Skeleton-based Methods
Topological consistency plays a crucial role in the task of boundary segmentation for reticular images, such as cell membrane segmentation in neuron electron microscopic images, grain boundary segmentation in material microscopic images and road segmentation in aerial images.
FedCRL: Personalized Federated Learning with Contrastive Shared Representations for Label Heterogeneity in Non-IID Data
FedCRL introduces contrastive representation learning (CRL) on shared representations to facilitate knowledge acquisition of clients.
Continual Learning of Large Language Models: A Comprehensive Survey
In this survey, we provide a comprehensive overview of the current research progress on LLMs within the context of CL.
Motor Focus: Ego-Motion Prediction with All-Pixel Matching
Furthermore, in the experiments part, we show the qualitative analysis of motor focus estimation between the conventional dense optical flow-based method and the proposed method.
URL: Universal Referential Knowledge Linking via Task-instructed Representation Compression
Linking a claim to grounded references is a critical ability to fulfill human demands for authentic and reliable information.
PGAHum: Prior-Guided Geometry and Appearance Learning for High-Fidelity Animatable Human Reconstruction
In this work, we introduce PGAHum, a prior-guided geometry and appearance learning framework for high-fidelity animatable human reconstruction.
Early detection of disease outbreaks and non-outbreaks using incidence data
In summary, we showed that there are statistical features that distinguish outbreak and non-outbreak sequences long before outbreaks occur.
A Two Dimensional Feature Engineering Method for Relation Extraction
The results indicate that two-dimensional feature engineering can take advantage of a two-dimensional sentence representation and make full use of prior knowledge in traditional feature engineering.
FastHDRNet: A new efficient method for SDR-to-HDR Translation
Modern displays nowadays possess the capability to render video content with a high dynamic range (HDR) and an extensive color gamut . However, the majority of available resources are still in standard dynamic range (SDR).
A Unified Framework for Adaptive Representation Enhancement and Inversed Learning in Cross-Domain Recommendation
To this end, we propose a Unified Framework for Adaptive Representation Enhancement and Inversed Learning in Cross-Domain Recommendation (AREIL).
PCToolkit: A Unified Plug-and-Play Prompt Compression Toolkit of Large Language Models
Prompt compression is an innovative method for efficiently condensing input prompts while preserving essential information.
END4Rec: Efficient Noise-Decoupling for Multi-Behavior Sequential Recommendation
In recommendation systems, users frequently engage in multiple types of behaviors, such as clicking, adding to a cart, and purchasing.
DOCTR: Disentangled Object-Centric Transformer for Point Scene Understanding
In this work, we propose a novel Disentangled Object-Centric TRansformer (DOCTR) that explores object-centric representation to facilitate learning with multiple objects for the multiple sub-tasks in a unified manner.
An early warning indicator trained on stochastic disease-spreading models with different noises
The timely detection of disease outbreaks through reliable early warning signals (EWSs) is indispensable for effective public health mitigation strategies.
Towards Human-Like Machine Comprehension: Few-Shot Relational Learning in Visually-Rich Documents
This approach aims to generate relation representations that are more aware of the spatial context and unseen relation in a manner similar to human perception.
Divide-Conquer Transformer Learning for Predicting Electric Vehicle Charging Events Using Smart Meter Data
To address this research gap, inspired by the concept of non-intrusive load monitoring (NILM), we develop a home charging prediction method using historical smart meter data.
Network-Aware Value Stacking of Community Battery via Asynchronous Distributed Optimization
Community battery systems have been widely deployed to provide services to the grid.
Safety-Aware Reinforcement Learning for Electric Vehicle Charging Station Management in Distribution Network
The increasing integration of electric vehicles (EVs) into the grid can pose a significant risk to the distribution system operation in the absence of coordination.
VisionGPT: LLM-Assisted Real-Time Anomaly Detection for Safe Visual Navigation
This paper explores the potential of Large Language Models(LLMs) in zero-shot anomaly detection for safe visual navigation.
CGI-DM: Digital Copyright Authentication for Diffusion Models via Contrasting Gradient Inversion
In response, we present Contrasting Gradient Inversion for Diffusion Models (CGI-DM), a novel method featuring vivid visual representations for digital copyright authentication.
StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models
The virtual API server contains a caching system and API simulators which are complementary to alleviate the change in API status.
Chronos: Learning the Language of Time Series
We introduce Chronos, a simple yet effective framework for pretrained probabilistic time series models.
Enhancing Plausibility Evaluation for Generated Designs with Denoising Autoencoder
As such, FID might not be suitable to assess the performance of DGMs for a generative design task.
Beyond MOT: Semantic Multi-Object Tracking
Current multi-object tracking (MOT) aims to predict trajectories of targets (i. e., ''where'') in videos.
AO-DETR: Anti-Overlapping DETR for X-Ray Prohibited Items Detection
Considering the significant overlapping phenomenon in X-ray prohibited item images, we propose an Anti-Overlapping DETR (AO-DETR) based on one of the state-of-the-art general object detectors, DINO.
Mixture-of-LoRAs: An Efficient Multitask Tuning for Large Language Models
These LoRA modules can be aligned with the expert design principles observed in Mixture-of-Experts (MoE).
FLAME Diffuser: Grounded Wildfire Image Synthesis using Mask Guided Diffusion
Thus, our proposed framework can generate a massive dataset of that images are high-quality and ground truth-paired, which well addresses the needs of the annotated datasets in specific tasks.
A Density-Guided Temporal Attention Transformer for Indiscernible Object Counting in Underwater Video
Dense object counting or crowd counting has come a long way thanks to the recent development in the vision community.
DOZE: A Dataset for Open-Vocabulary Zero-Shot Object Navigation in Dynamic Environments
Zero-Shot Object Navigation (ZSON) requires agents to autonomously locate and approach unseen objects in unfamiliar environments and has emerged as a particularly challenging task within the domain of Embodied AI.
Temporal-Aware Deep Reinforcement Learning for Energy Storage Bidding in Energy and Contingency Reserve Markets
To bridge this gap, we develop a novel BESS joint bidding strategy that utilizes deep reinforcement learning (DRL) to bid in the spot and contingency frequency control ancillary services (FCAS) markets.
All in an Aggregated Image for In-Image Learning
This paper introduces a new in-context learning (ICL) mechanism called In-Image Learning (I$^2$L) that combines demonstration examples, visual cues, and chain-of-thought reasoning into an aggregated image to enhance the capabilities of Large Multimodal Models (e. g., GPT-4V) in multimodal reasoning tasks.
Gradient-Guided Modality Decoupling for Missing-Modality Robustness
In aid of this indicator, we present a novel Gradient-guided Modality Decoupling (GMD) method to decouple the dependency on dominating modalities.
CLAP: Learning Transferable Binary Code Representations with Natural Language Supervision
At the core, our approach boosts superior transfer learning capabilities by effectively aligning binary code with their semantics explanations (in natural language), resulting a model able to generate better embeddings for binary code.
Building Flexible Machine Learning Models for Scientific Computing at Scale
Foundation models have revolutionized knowledge acquisition across domains, and our study introduces OmniArch, a paradigm-shifting approach designed for building foundation models in multi-physics scientific computing.
ASETF: A Novel Method for Jailbreak Attack on LLMs through Translate Suffix Embeddings
In addition, our approach can be generalized into a broader method for generating transferable adversarial suffixes that can successfully attack multiple LLMs, even black-box LLMs, such as ChatGPT and Gemini.
Should We Respect LLMs? A Cross-Lingual Study on the Influence of Prompt Politeness on LLM Performance
We investigate the impact of politeness levels in prompts on the performance of large language models (LLMs).
FinBen: A Holistic Financial Benchmark for Large Language Models
Our evaluation of 15 representative LLMs, including GPT-4, ChatGPT, and the latest Gemini, reveals several key findings: While LLMs excel in IE and textual analysis, they struggle with advanced reasoning and complex tasks like text generation and forecasting.
Large-scale Benchmarking of Metaphor-based Optimization Heuristics
The number of proposed iterative optimization heuristics is growing steadily, and with this growth, there have been many points of discussion within the wider community.
A Factor Graph Model of Trust for a Collaborative Multi-Agent System
In the field of Multi-Agent Systems (MAS), known for their openness, dynamism, and cooperative nature, the ability to trust the resources and services of other agents is crucial.
Benchmarking Large Language Models on Communicative Medical Coaching: a Novel System and Dataset
Traditional applications of natural language processing (NLP) in healthcare have predominantly focused on patient-centered services, enhancing patient interactions and care delivery, such as through medical dialogue systems.
The Future of Cognitive Strategy-enhanced Persuasive Dialogue Agents: New Perspectives and Trends
To depict the research trends of CogAgent, in this paper, we first present several fundamental cognitive psychology theories and give the formalized definition of three typical cognitive strategies, including the persuasion strategy, the topic path planning strategy, and the argument structure prediction strategy.
Partially Recentralization Softmax Loss for Vision-Language Models Robustness
However, it has been shown that multimodal NLP are vulnerable to adversarial attacks, where the outputs of a model can be dramatically changed by a perturbation to the input.
Harnessing the Plug-and-Play Controller by Prompting
The proposed approach aims to enhance the fluency of generated text by guiding the generation process with PPCs.
Understanding the planning of LLM agents: A survey
As Large Language Models (LLMs) have shown significant intelligence, the progress to leverage LLMs as planning modules of autonomous agents has attracted more attention.
FreDF: Learning to Forecast in Frequency Domain
Time series modeling is uniquely challenged by the presence of autocorrelation in both historical and label sequences.
Composite Active Learning: Towards Multi-Domain Active Learning with Theoretical Guarantees
In this paper, we propose the first general method, dubbed composite active learning (CAL), for multi-domain AL. Our approach explicitly considers the domain-level and instance-level information in the problem; CAL first assigns domain-level budgets according to domain-level importance, which is estimated by optimizing an upper error bound that we develop; with the domain-level budgets, CAL then leverages a certain instance-level query strategy to select samples to label from each domain.
Natural Counterfactuals With Necessary Backtracking
Counterfactual reasoning is pivotal in human cognition and especially important for providing explanations and making decisions.
Formal-LLM: Integrating Formal Language and Natural Language for Controllable LLM-based Agents
A stack-based LLM plan generation process is then conducted under the supervision of the automaton to ensure that the generated plan satisfies the constraints, making the planning process controllable.
TransTroj: Transferable Backdoor Attacks to Pre-trained Models via Embedding Indistinguishability
Adopting untrusted PTMs may suffer from backdoor attacks, where the adversary can compromise the downstream models by injecting backdoors into the PTM.
Attentive Convolutional Deep Reinforcement Learning for Optimizing Solar-Storage Systems in Real-Time Electricity Markets
This paper studies the synergy of solar-battery energy storage system (BESS) and develops a viable strategy for the BESS to unlock its economic potential by serving as a backup to reduce solar curtailments while also participating in the electricity market.
Reconfigurable AI Modules Aided Channel Estimation and MIMO Detection
Deep learning (DL) based channel estimation (CE) and multiple input and multiple output detection (MIMODet), as two separate research topics, have provided convinced evidence to demonstrate the effectiveness and robustness of artificial intelligence (AI) for receiver design.
Deep Reinforcement Learning for Voltage Control and Renewable Accommodation Using Spatial-Temporal Graph Information
Renewable energy resources (RERs) have been increasingly integrated into distribution networks (DNs) for decarbonization.
Learning to Trust Your Feelings: Leveraging Self-awareness in LLMs for Hallucination Mitigation
We evaluate the ability of Large Language Models (LLMs) to discern and express their internal knowledge state, a key factor in countering factual hallucination and ensuring reliable application of LLMs.
Driving Towards Inclusion: Revisiting In-Vehicle Interaction in Autonomous Vehicles
This paper presents a comprehensive literature review of the current state of in-vehicle human-computer interaction (HCI) in the context of self-driving vehicles, with a specific focus on inclusion and accessibility.
Hierarchical Continual Reinforcement Learning via Large Language Model
Despite the progress in continual reinforcement learning (CRL), existing methods often suffer from insufficient knowledge transfer, particularly when the tasks are diverse.
Energy-Based Concept Bottleneck Models: Unifying Prediction, Concept Intervention, and Probabilistic Interpretations
Our ECBMs address both limitations of existing CBMs, providing higher accuracy and richer concept interpretations.
Style-Consistent 3D Indoor Scene Synthesis with Decoupled Objects
The core strength of our pipeline lies in its ability to generate 3D scenes that are not only visually impressive but also exhibit features like photorealism, multi-view consistency, and diversity.
EndoGaussians: Single View Dynamic Gaussian Splatting for Deformable Endoscopic Tissues Reconstruction
The accurate 3D reconstruction of deformable soft body tissues from endoscopic videos is a pivotal challenge in medical applications such as VR surgery and medical image analysis.
Raidar: geneRative AI Detection viA Rewriting
We find that large language models (LLMs) are more likely to modify human-written text than AI-generated text when tasked with rewriting.
SlideAVSR: A Dataset of Paper Explanation Videos for Audio-Visual Speech Recognition
Audio-visual speech recognition (AVSR) is a multimodal extension of automatic speech recognition (ASR), using video as a complement to audio.
Audio-Visual Speech Recognition
Automatic Speech Recognition
+4
Avoiding strict saddle points of nonconvex regularized problems
For DIRL$_1$, we show the reweighted $\ell_1$ subproblem has support identification property so that DIRL$_1$ locally reverts to a gradient descent algorithm around a stationary point.
CycLight: learning traffic signal cooperation with a cycle-level strategy
This study introduces CycLight, a novel cycle-level deep reinforcement learning (RL) approach for network-level adaptive traffic signal control (NATSC) systems.
Enhancing Digital Hologram Reconstruction Using Reverse-Attention Loss for Untrained Physics-Driven Deep Learning Models with Uncertain Distance
Untrained Physics-based Deep Learning (DL) methods for digital holography have gained significant attention due to their benefits, such as not requiring an annotated training dataset, and providing interpretability since utilizing the governing laws of hologram formation.
HiBid: A Cross-Channel Constrained Bidding System with Budget Allocation by Hierarchical Offline Deep Reinforcement Learning
Online display advertising platforms service numerous advertisers by providing real-time bidding (RTB) for the scale of billions of ad requests every day.
Federated Continual Learning via Knowledge Fusion: A Survey
The key objective of FCL is to fuse heterogeneous knowledge from different clients and retain knowledge of previous tasks while learning on new ones.
Word length-aware text spotting: Enhancing detection and recognition in dense text image
Scene text spotting is essential in various computer vision applications, enabling extracting and interpreting textual information from images.
A Novel Field-Free SOT Magnetic Tunnel Junction With Local VCMA-Induced Switching
By integrating the local voltage-controlled magnetic anisotropy (VCMA) effect, Dzyaloshinskii-Moriya interaction (DMI) effect, and spin-orbit torque (SOT) effect, we propose a novel device structure for field-free magnetic tunnel junction (MTJ).
LARP: Language-Agent Role Play for Open-World Games
Language agents have shown impressive problem-solving skills within defined settings and brief timelines.
BrainVis: Exploring the Bridge between Brain and Visual Signals via Image Reconstruction
This leads to substantial limitations in existing works of visual stimuli reconstruction from EEG, such as difficulties in aligning EEG embeddings with the fine-grained semantic information and a heavy reliance on additional large self-collected dataset for training.
Learning to Prompt Knowledge Transfer for Open-World Continual Learning
This paper studies the problem of continual learning in an open-world scenario, referred to as Open-world Continual Learning (OwCL).
Zero-1-to-3: Domain-level Zero-shot Cognitive Diagnosis via One Batch of Early-bird Students towards Three Diagnostic Objectives
Consequently, we refine the cognitive states of cold-start students as diagnostic outcomes via virtual data, aligning with the diagnosis-oriented goal.
SkyMask: Attack-agnostic Robust Federated Learning with Fine-grained Learnable Masks
Federated Learning (FL) is becoming a popular paradigm for leveraging distributed data and preserving data privacy.
The Fallacy of Borda Count Method -- Why it is Useless with Group Intelligence and Shouldn't be Used with Big Data including Banking Customer Services
In this paper, we rely on the theory developed by Wang from 2021 to 2023 to demonstrate that online cultural rating platform rating data often evolve into Poisson/Pareto behavior, and individualistic voting preferences are predictable without any data input, so Borda Count Method (or, Range Voting Method) has intrinsic fallacy and should not be used as a voting theory method.