Search Results for author:
Found 598 papers, 198 papers with code
Detecting Health Advice in Medical Research Literature
We also conducted a case study that applied this prediction model to retrieve specific health advice on COVID-19 treatments from LitCovid, a large COVID research literature portal, demonstrating the usefulness of retrieving health advice sentences as an advanced research literature navigation function for health researchers and the general public.
Measuring and Mitigating Name Biases in Neural Machine Translation
In this paper we describe a new source of bias prevalent in NMT systems, relating to translations of sentences containing person names.
Mitigating Data Poisoning in Text Classification with Differential Privacy
NLP models are vulnerable to data poisoning attacks.
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.
Multi-Party Empathetic Dialogue Generation: A New Task for Dialog Systems
Empathetic dialogue assembles emotion understanding, feeling projection, and appropriate response generation.
PA Ph&Tech at SemEval-2022 Task 11: NER Task with Ensemble Embedding from Reinforcement Learning
From pretrained contextual embedding to document-level embedding, the selection and construction of embedding have drawn more and more attention in the NER domain in recent research.
数字人文视角下的《史记》《汉书》比较研究(A Comparative Study of Shiji and Hanshu from the Perspective of Digital Humanities)
"《史记》和《汉书》具有经久不衰的研究价值。尽管两书异同的研究已经较为丰富, 但研究的全面性、完备性、科学性、客观性均仍显不足。在数字人文的视角下, 本文利用计算语言学方法, 通过对字、词、命名实体、段落等的多粒度、多角度分析, 开展对于《史》《汉》的比较研究。首先, 本文对于《史》《汉》中的字、词、命名实体的分布和特点进行对比, 以遍历穷举的考察方式提炼出两书在主要内容上的相同点与不同点, 揭示了汉武帝之前和汉武帝到西汉灭亡两段历史时期在政治、文化、思想上的重要变革与承袭。其次, 本文使用一种融入命名实体作为外部特征的文本相似度算法对于《史记》《汉书》的异文进行自动发现, 成功识别出过去研究者通过人工手段没有发现的袭用段落, 使得我们对于《史》《汉》的承袭关系形成更加完整和立体的认识。再次, 本文通过计算异文段落之间的最长公共子序列来自动得出两段异文之间存在的差异, 从宏观统计上证明了《汉书》文字风格《史记》的差别, 并从微观上进一步对二者语言特点进行了阐释, 为理解《史》《汉》异文特点提供了新的角度和启发。本研究站在数字人文的视域下, 利用先进的计算方法对于传世千年的中国古代经典进行了再审视、再发现, 其方法对于今人研究古籍有一定的借鉴价值。”
Efficient Reinforcement Learning with Large Language Model Priors
In sequential decision-making (SDM) tasks, methods like reinforcement learning (RL) and heuristic search have made notable advances in specific cases.
Is the MMI Criterion Necessary for Interpretability? Degenerating Non-causal Features to Plain Noise for Self-Rationalization
In the optimization objectives of these methods, spurious features are still distinguished from plain noise, which hinders the discovery of causal rationales.
SparsePO: Controlling Preference Alignment of LLMs via Sparse Token Masks
Preference Optimization (PO) has proven an effective step for aligning language models to human-desired behaviors.
TimeCNN: Refining Cross-Variable Interaction on Time Point for Time Series Forecasting
Transformer-based models demonstrate significant potential in modeling cross-time and cross-variable interaction.
Hammer: Robust Function-Calling for On-Device Language Models via Function Masking
Large language models have demonstrated impressive value in performing as autonomous agents when equipped with external tools and API calls.
GenSim: A General Social Simulation Platform with Large Language Model based Agents
With the rapid advancement of large language models (LLMs), recent years have witnessed many promising studies on leveraging LLM-based agents to simulate human social behavior.
Mixture of Attentions For Speculative Decoding
The growth in the number of parameters of Large Language Models (LLMs) has led to a significant surge in computational requirements, making them challenging and costly to deploy.
SHAP-CAT: A interpretable multi-modal framework enhancing WSI classification via virtual staining and shapley-value-based multimodal fusion
For each dimension of the bag-level representation, attribution values are calculated to indicate how changes in the specific dimensions of the input affect the model output.
PathSeeker: Exploring LLM Security Vulnerabilities with a Reinforcement Learning-Based Jailbreak Approach
During our manual attempts to perform jailbreak attacks, we found that the vocabulary of the response of the target model gradually became richer and eventually produced harmful responses.
COCO-Occ: A Benchmark for Occluded Panoptic Segmentation and Image Understanding
To help address the occlusion problem in panoptic segmentation and image understanding, this paper proposes a new large-scale dataset, COCO-Occ, which is derived from the COCO dataset by manually labelling the COCO images into three perceived occlusion levels.
E2LLM: Encoder Elongated Large Language Models for Long-Context Understanding and Reasoning
In the realm of Large Language Models (LLMs), the ability to process long contexts is increasingly crucial for tasks such as multi-round dialogues, code generation, and document summarization.
AS-Speech: Adaptive Style For Speech Synthesis
In recent years, there has been significant progress in Text-to-Speech (TTS) synthesis technology, enabling the high-quality synthesis of voices in common scenarios.
Dual Advancement of Representation Learning and Clustering for Sparse and Noisy Images
Sparse and noisy images (SNIs), like those in spatial gene expression data, pose significant challenges for effective representation learning and clustering, which are essential for thorough data analysis and interpretation.
LanguaShrink: Reducing Token Overhead with Psycholinguistics
As large language models (LLMs) improve their capabilities in handling complex tasks, the issues of computational cost and efficiency due to long prompts are becoming increasingly prominent.
Self-evolving Agents with reflective and memory-augmented abilities
Large language models (LLMs) have made significant advances in the field of natural language processing, but they still face challenges such as continuous decision-making.
Reflective Human-Machine Co-adaptation for Enhanced Text-to-Image Generation Dialogue System
In this research, we aim to enhance the user-friendliness of our image generation system.
PAGE: Parametric Generative Explainer for Graph Neural Network
Due to the dimensionality reduction of features in the latent space of the auto-encoder, it becomes easier to extract causal features leading to the model's output, which can be easily employed to generate explanations.
Are LLM-based Recommenders Already the Best? Simple Scaled Cross-entropy Unleashes the Potential of Traditional Sequential Recommenders
Some studies have observed that LLMs, when fine-tuned by the cross-entropy (CE) loss with a full softmax, could achieve `state-of-the-art' performance in sequential recommendation.
Topological GCN for Improving Detection of Hip Landmarks from B-Mode Ultrasound Images
In this work, we propose a novel hip landmark detection model by integrating the Topological GCN (TGCN) with an Improved Conformer (TGCN-ICF) into a unified frame-work to improve detection performance.
xGen-VideoSyn-1: High-fidelity Text-to-Video Synthesis with Compressed Representations
We present xGen-VideoSyn-1, a text-to-video (T2V) generation model capable of producing realistic scenes from textual descriptions.
4D Diffusion for Dynamic Protein Structure Prediction with Reference Guided Motion Alignment
Protein structure prediction is pivotal for understanding the structure-function relationship of proteins, advancing biological research, and facilitating pharmaceutical development and experimental design.
Dynamic PDB: A New Dataset and a SE(3) Model Extension by Integrating Dynamic Behaviors and Physical Properties in Protein Structures
Despite significant progress in static protein structure collection and prediction, the dynamic behavior of proteins, one of their most vital characteristics, has been largely overlooked in prior research.
Adversarial Attack for Explanation Robustness of Rationalization Models
Based on this, we make a series of recommendations for improving rationalization models in terms of explanation.
MsMemoryGAN: A Multi-scale Memory GAN for Palm-vein Adversarial Purification
At the testing stage, given an adversarial sample, the MsMemoryGAN retrieves its most relevant normal patterns in memory for the reconstruction.
Advances in Multiple Instance Learning for Whole Slide Image Analysis: Techniques, Challenges, and Future Directions
Whole slide images (WSIs) are gigapixel-scale digital images of H\&E-stained tissue samples widely used in pathology.
Interpretable Machine Learning
Multiple Instance Learning
+2
xGen-MM (BLIP-3): A Family of Open Large Multimodal Models
The framework comprises meticulously curated datasets, a training recipe, model architectures, and a resulting suite of LMMs.
LLM4DSR: Leveraing Large Language Model for Denoising Sequential Recommendation
To tackle these challenges, we propose LLM4DSR, a tailored approach for denoising sequential recommendation using LLMs.
Experimental evaluation of offline reinforcement learning for HVAC control in buildings
In summary, this paper presents our well-structured investigations and new findings when applying offline reinforcement learning to building HVAC systems.
An Efficient Continuous Control Perspective for Reinforcement-Learning-based Sequential Recommendation
However, previous studies mainly focus on discrete action and policy spaces, which might have difficulties in handling dramatically growing items efficiently.
GlitchProber: Advancing Effective Detection and Mitigation of Glitch Tokens in Large Language Models
In this work, we aim to enhance the understanding of glitch tokens and propose techniques for their detection and mitigation.
HMDN: Hierarchical Multi-Distribution Network for Click-Through Rate Prediction
As the recommendation service needs to address increasingly diverse distributions, such as multi-population, multi-scenario, multitarget, and multi-interest, more and more recent works have focused on multi-distribution modeling and achieved great progress.
Lessons from Learning to Spin "Pens"
This serves two purposes: 1) pre-training a sensorimotor policy in simulation; 2) conducting open-loop trajectory replay in the real world.
SQLfuse: Enhancing Text-to-SQL Performance through Comprehensive LLM Synergy
Text-to-SQL conversion is a critical innovation, simplifying the transition from complex SQL to intuitive natural language queries, especially significant given SQL's prevalence in the job market across various roles.
EaDeblur-GS: Event assisted 3D Deblur Reconstruction with Gaussian Splatting
3D deblurring reconstruction techniques have recently seen significant advancements with the development of Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS).
Don't Throw Away Data: Better Sequence Knowledge Distillation
A critical component in knowledge distillation is the means of coupling the teacher and student.
Tissue-Contrastive Semi-Masked Autoencoders for Segmentation Pretraining on Chest CT
Existing Masked Image Modeling (MIM) depends on a spatial patch-based masking-reconstruction strategy to perceive objects'features from unlabeled images, which may face two limitations when applied to chest CT: 1) inefficient feature learning due to complex anatomical details presented in CT images, and 2) suboptimal knowledge transfer owing to input disparity between upstream and downstream models.
Human-like Episodic Memory for Infinite Context LLMs
Large language models (LLMs) have shown remarkable capabilities, but still struggle with processing extensive contexts, limiting their ability to maintain coherence and accuracy over long sequences.
How Deep is your Guess? A Fresh Perspective on Deep Learning for Medical Time-Series Imputation
By identifying conceptual gaps in the literature and existing reviews, we devise a taxonomy grounded on the inductive bias of neural imputation frameworks, resulting in a classification of existing deep imputation strategies based on their suitability for specific imputation scenarios and data-specific properties.
PocketLLM: Enabling On-Device Fine-Tuning for Personalized LLMs
To tackle this, we propose employing derivative-free optimization techniques to enable on-device fine-tuning of LLM, even on memory-limited mobile devices.
ROS-LLM: A ROS framework for embodied AI with task feedback and structured reasoning
Key features of the framework include: integration of ROS with an AI agent connected to a plethora of open-source and commercial LLMs, automatic extraction of a behavior from the LLM output and execution of ROS actions/services, support for three behavior modes (sequence, behavior tree, state machine), imitation learning for adding new robot actions to the library of possible actions, and LLM reflection via human and environment feedback.
D2LLM: Decomposed and Distilled Large Language Models for Semantic Search
In this paper, we present D2LLMs-Decomposed and Distilled LLMs for semantic search-that combines the best of both worlds.
Privacy Preserved Blood Glucose Level Cross-Prediction: An Asynchronous Decentralized Federated Learning Approach
Newly diagnosed Type 1 Diabetes (T1D) patients often struggle to obtain effective Blood Glucose (BG) prediction models due to the lack of sufficient BG data from Continuous Glucose Monitoring (CGM), presenting a significant "cold start" problem in patient care.
TSI-Bench: Benchmarking Time Series Imputation
Despite the development of numerous deep learning algorithms for time series imputation, the community lacks standardized and comprehensive benchmark platforms to effectively evaluate imputation performance across different settings.
SegHist: A General Segmentation-based Framework for Chinese Historical Document Text Line Detection
In this paper, we propose a general framework for historical document text detection (SegHist), enabling existing segmentation-based text detection methods to effectively address the challenges, especially text lines with high aspect ratios.
Estimating Difficulty Levels of Programming Problems with Pre-trained Model
As the demand for programming skills grows across industries and academia, students often turn to Programming Online Judge (POJ) platforms for coding practice and competition.
RACon: Retrieval-Augmented Simulated Character Locomotion Control
The retriever searches motion experts from a user-specified database in a task-oriented fashion, which boosts the responsiveness to the user's control.
Logic Synthesis with Generative Deep Neural Networks
While deep learning has achieved significant success in various domains, its application to logic circuit design has been limited due to complex constraints and strict feasibility requirement.
AICoderEval: Improving AI Domain Code Generation of Large Language Models
Therefore, we construct AICoderEval, a dataset focused on real-world tasks in various domains based on HuggingFace, PyTorch, and TensorFlow, along with comprehensive metrics for evaluation and enhancing LLMs' task-specific code generation capability.
UDQL: Bridging The Gap between MSE Loss and The Optimal Value Function in Offline Reinforcement Learning
However, we find that its principle can lead to overestimation phenomenon for the value function.
Learning to Discuss Strategically: A Case Study on One Night Ultimate Werewolf
Communication is a fundamental aspect of human society, facilitating the exchange of information and beliefs among people.
Reliable Object Tracking by Multimodal Hybrid Feature Extraction and Transformer-Based Fusion
In this study, we propose a novel multimodal hybrid tracker (MMHT) that utilizes frame-event-based data for reliable single object tracking.
Attaining Human`s Desirable Outcomes in Human-AI Interaction via Structural Causal Games
In human-AI interaction, a prominent goal is to attain human`s desirable outcome with the assistance of AI agents, which can be ideally delineated as a problem of seeking the optimal Nash Equilibrium that matches the human`s desirable outcome.
SEEP: Training Dynamics Grounds Latent Representation Search for Mitigating Backdoor Poisoning Attacks
Modern NLP models are often trained on public datasets drawn from diverse sources, rendering them vulnerable to data poisoning attacks.
BOSC: A Backdoor-based Framework for Open Set Synthetic Image Attribution
Extensive efforts have been made to explore unique representations of generative models and use them to attribute a synthetic image to the model that produced it.
BugBlitz-AI: An Intelligent QA Assistant
The evolution of software testing from manual to automated methods has significantly influenced quality assurance (QA) practices.
IHC Matters: Incorporating IHC analysis to H&E Whole Slide Image Analysis for Improved Cancer Grading via Two-stage Multimodal Bilinear Pooling Fusion
Immunohistochemistry (IHC) plays a crucial role in pathology as it detects the over-expression of protein in tissue samples.
Communications under Bursty Mixed Gaussian-impulsive Noise: Demodulation and Performance Analysis
For the MSK demodulation based on the Viterbi algorithm, we derive a lower and upper bound of BER.
Boundary-aware Decoupled Flow Networks for Realistic Extreme Rescaling
Recently developed generative methods, including invertible rescaling network (IRN) based and generative adversarial network (GAN) based methods, have demonstrated exceptional performance in image rescaling.
Distillation Matters: Empowering Sequential Recommenders to Match the Performance of Large Language Model
Owing to their powerful semantic reasoning capabilities, Large Language Models (LLMs) have been effectively utilized as recommenders, achieving impressive performance.
TuBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning
The implications of backdoor attacks on English-centric large language models (LLMs) have been widely examined - such attacks can be achieved by embedding malicious behaviors during training and activated under specific conditions that trigger malicious outputs.
Align-Free Multi-Plane Phase Retrieval
The multi-plane phase retrieval method provides a budget-friendly and effective way to perform phase imaging, yet it often encounters alignment challenges due to shifts along the optical axis in experiments.
Bridge to Non-Barrier Communication: Gloss-Prompted Fine-grained Cued Speech Gesture Generation with Diffusion Model
Therefore, we propose a novel Gloss-prompted Diffusion-based CS Gesture generation framework (called GlossDiff).
Domain Adaptive and Fine-grained Anomaly Detection for Single-cell Sequencing Data and Beyond
In response, we propose ACSleuth, a novel, reconstruction deviation-guided generative framework that integrates the detection, domain adaptation, and fine-grained annotating of anomalous cells into a methodologically cohesive workflow.
Nyonic Technical Report
This report details the development and key achievements of our latest language model designed for custom large language models.
Data-free Knowledge Distillation for Fine-grained Visual Categorization
Our approach utilizes an adversarial distillation framework with attention generator, mixed high-order attention distillation, and semantic feature contrast learning.
Data-free Knowledge Distillation
Fine-Grained Visual Categorization
+1
MTGA: Multi-view Temporal Granularity aligned Aggregation for Event-based Lip-reading
Then we design a spatio-temporal fusion module based on temporal granularity alignment, where the global spatial features extracted from event frames, together with the local relative spatial and temporal features contained in voxel graph list are effectively aligned and integrated.
Token-level Direct Preference Optimization
Fine-tuning pre-trained Large Language Models (LLMs) is essential to align them with human values and intentions.
Synthesizing Realistic Data for Table Recognition
By leveraging the actual structure and content of tables from Chinese financial announcements, we have developed the first extensive table annotation dataset in this domain.
Pre-processing matters: A segment search method for WSI classification
Pre-processing whole slide images (WSIs) can impact classification performance.
Open-Source AI-based SE Tools: Opportunities and Challenges of Collaborative Software Learning
We introduce a governance framework centered on federated learning (FL), designed to foster the joint development and maintenance of open-source AI code models while safeguarding data privacy and security.
Efficient Surgical Tool Recognition via HMM-Stabilized Deep Learning
Recognizing various surgical tools, actions and phases from surgery videos is an important problem in computer vision with exciting clinical applications.
SDPose: Tokenized Pose Estimation via Circulation-Guide Self-Distillation
To mitigate the problem of under-fitting, we design a transformer module named Multi-Cycled Transformer(MCT) based on multiple-cycled forwards to more fully exploit the potential of small model parameters.
Backdoor Attack on Multilingual Machine Translation
Our aim is to bring attention to these vulnerabilities within MNMT systems with the hope of encouraging the community to address security concerns in machine translation, especially in the context of low-resource languages.
CMAT: A Multi-Agent Collaboration Tuning Framework for Enhancing Small Language Models
Open large language models (LLMs) have significantly advanced the field of natural language processing, showcasing impressive performance across various tasks. Despite the significant advancements in LLMs, their effective operation still relies heavily on human input to accurately guide the dialogue flow, with agent tuning being a crucial optimization technique that involves human adjustments to the model for better response to such guidance. Addressing this dependency, our work introduces the TinyAgent model, trained on a meticulously curated high-quality dataset.
Parallel Proportional Fusion of Spiking Quantum Neural Network for Optimizing Image Classification
The recent emergence of the hybrid quantum-classical neural network (HQCNN) architecture has garnered considerable attention due to the potential advantages associated with integrating quantum principles to enhance various facets of machine learning algorithms and computations.
ALISA: Accelerating Large Language Model Inference via Sparsity-Aware KV Caching
In a single GPU-CPU system, we demonstrate that under varying workloads, ALISA improves the throughput of baseline systems such as FlexGen and vLLM by up to 3X and 1. 9X, respectively.
CHisIEC: An Information Extraction Corpus for Ancient Chinese History
Additionally, we have evaluated the capabilities of Large Language Models (LLMs) in the context of tasks related to ancient Chinese history.
Privacy-Preserving Face Recognition Using Trainable Feature Subtraction
Recognizable identity features within the image are encouraged by co-training a recognition model on its high-dimensional feature representation.
Learning Macroeconomic Policies based on Microfoundations: A Dynamic Stackelberg Mean Field Game Approach
This paper proposes a novel general framework named Dynamic Stackelberg Mean Field Games (Dynamic SMFG) to model such policymaking within sequential decision-making processes, with the government as the leader and households as dynamic followers.
Circuit Transformer: End-to-end Circuit Design by Predicting the Next Gate
Then, can circuits also be mastered by a a sufficiently large "circuit model", which can conquer electronic design tasks by simply predicting the next logic gate?
Bifurcated Attention: Accelerating Massively Parallel Decoding with Shared Prefixes in LLMs
This study introduces bifurcated attention, a method designed to enhance language model inference in shared-context batch decoding scenarios.
Restoring Ancient Ideograph: A Multimodal Multitask Neural Network Approach
Cultural heritage serves as the enduring record of human thought and history.
Post-Training Attribute Unlearning in Recommender Systems
The first component is distinguishability loss, where we design a distribution-based measurement to make attribute labels indistinguishable from attackers.
Segmentation Guided Sparse Transformer for Under-Display Camera Image Restoration
Specifically, we utilize sparse self-attention to filter out redundant information and noise, directing the model's attention to focus on the features more relevant to the degraded regions in need of reconstruction.
Scene Graph Aided Radiology Report Generation
Radiology report generation (RRG) methods often lack sufficient medical knowledge to produce clinically accurate reports.
Looking Ahead to Avoid Being Late: Solving Hard-Constrained Traveling Salesman Problem
To overcome this problem and to have an effective solution against hard constraints, we proposed a novel learning-based method that uses looking-ahead information as the feature to improve the legality of TSP with Time Windows (TSPTW) solutions.
A Comprehensive Survey on Process-Oriented Automatic Text Summarization with Exploration of LLM-Based Methods
Automatic Text Summarization (ATS), utilizing Natural Language Processing (NLP) algorithms, aims to create concise and accurate summaries, thereby significantly reducing the human effort required in processing large volumes of text.
Learn Suspected Anomalies from Event Prompts for Video Anomaly Detection
Most models for weakly supervised video anomaly detection (WS-VAD) rely on multiple instance learning, aiming to distinguish normal and abnormal snippets without specifying the type of anomaly.
Explainable Session-based Recommendation via Path Reasoning
This paper explores providing explainability for session-based recommendation (SR) by path reasoning.
Merino: Entropy-driven Design for Generative Language Models on IoT Devices
Generative Large Language Models (LLMs) stand as a revolutionary advancement in the modern era of artificial intelligence (AI).
DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning
In this work, we investigate the potential of large language models (LLMs) based agents to automate data science tasks, with the goal of comprehending task requirements, then building and training the best-fit machine learning models.
GARNN: An Interpretable Graph Attentive Recurrent Neural Network for Predicting Blood Glucose Levels via Multivariate Time Series
Accurate prediction of future blood glucose (BG) levels can effectively improve BG management for people living with diabetes, thereby reducing complications and improving quality of life.
Safe Task Planning for Language-Instructed Multi-Robot Systems using Conformal Prediction
To address this challenge, we introduce a new distributed LLM-based planner, called S-ATLAS for Safe plAnning for Teams of Language-instructed AgentS, that is capable of achieving user-defined mission success rates.
Small Language Model Is a Good Guide for Large Language Model in Chinese Entity Relation Extraction
Recently, large language models (LLMs) have been successful in relational extraction (RE) tasks, especially in the few-shot learning.
CyberDemo: Augmenting Simulated Human Demonstration for Real-World Dexterous Manipulation
We introduce CyberDemo, a novel approach to robotic imitation learning that leverages simulated human demonstrations for real-world tasks.
Bayesian Reward Models for LLM Alignment
To ensure that large language model (LLM) responses are helpful and non-toxic, a reward model trained on human preference data is usually used.
Case Study: Testing Model Capabilities in Some Reasoning Tasks
Large Language Models (LLMs) excel in generating personalized content and facilitating interactive dialogues, showcasing their remarkable aptitude for a myriad of applications.
Intelligent Agricultural Management Considering N$_2$O Emission and Climate Variability with Uncertainties
This study examines how artificial intelligence (AI), especially Reinforcement Learning (RL), can be used in farming to boost crop yields, fine-tune nitrogen use and watering, and reduce nitrate runoff and greenhouse gases, focusing on Nitrous Oxide (N$_2$O) emissions from soil.
Natural Language Reinforcement Learning
Reinforcement Learning (RL) has shown remarkable abilities in learning policies for decision-making tasks.
Understanding the Role of Cross-Entropy Loss in Fairly Evaluating Large Language Model-based Recommendation
Large language models (LLMs) have gained much attention in the recommendation community; some studies have observed that LLMs, fine-tuned by the cross-entropy loss with a full softmax, could achieve state-of-the-art performance already.
A Statistical Model of Bursty Mixed Gaussian-impulsive Noise: Model and Parameter Estimation
In the first part, we propose a closed-form heavy-tailed multivariate probability density function (PDF) that to model the bursty mixed noise.
Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement
We assess the effectiveness of ETPO within a simulated environment that models data science code generation as a series of multi-step interactive tasks; results underline ETPO's potential as a robust method for refining the interactive decision-making capabilities of language agents.
CounterCLR: Counterfactual Contrastive Learning with Non-random Missing Data in Recommendation
Recommender systems are designed to learn user preferences from observed feedback and comprise many fundamental tasks, such as rating prediction and post-click conversion rate (pCVR) prediction.
Deep Learning for Multivariate Time Series Imputation: A Survey
In this paper, we conduct a comprehensive survey on the recently proposed deep learning imputation methods.
InfoRank: Unbiased Learning-to-Rank via Conditional Mutual Information Minimization
Subsequently, we minimize the mutual information between the observation estimation and the relevance estimation conditioned on the input features.
A Framework to Implement 1+N Multi-task Fine-tuning Pattern in LLMs Using the CGC-LORA Algorithm
In practice, there are two prevailing ways, in which the adaptation can be achieved: (i) Multiple Independent Models: Pre-trained LLMs are fine-tuned a few times independently using the corresponding training samples from each task.
Skeleton-Guided Instance Separation for Fine-Grained Segmentation in Microscopy
One of the fundamental challenges in microscopy (MS) image analysis is instance segmentation (IS), particularly when segmenting cluster regions where multiple objects of varying sizes and shapes may be connected or even overlapped in arbitrary orientations.
Large Language Models Are Neurosymbolic Reasoners
A wide range of real-world applications is characterized by their symbolic nature, necessitating a strong capability for symbolic reasoning.
Adversarial Masking Contrastive Learning for vein recognition
To overcome this problem, in this paper, we propose an adversarial masking contrastive learning (AMCL) approach, that generates challenging samples to train a more robust contrastive learning model for the downstream palm-vein recognition task, by alternatively optimizing the encoder in the contrastive learning model and a set of latent variables.
Can AI Write Classical Chinese Poetry like Humans? An Empirical Study Inspired by Turing Test
Some argue that the essence of humanity, such as creativity and sentiment, can never be mimicked by machines.
Self-Contrast: Better Reflection Through Inconsistent Solving Perspectives
Experiments conducted on a series of reasoning and translation tasks with different LLMs serve to underscore the effectiveness and generality of our strategy.
Learning-based agricultural management in partially observable environments subject to climate variability
However, our study illuminates the need for agent retraining to acquire new optimal policies under extreme weather events.
Mudslide: A Universal Nuclear Instance Segmentation Method
Starting from the initial boundary Mudslide executes a pixel-by-pixel collapse along various force directions.
GazeCLIP: Towards Enhancing Gaze Estimation via Text Guidance
Over the past decade, visual gaze estimation has garnered increasing attention within the research community, owing to its wide-ranging application scenarios.
Maximum Likelihood CFO Estimation for High-Mobility OFDM Systems: A Chinese Remainder Theorem Based Method
Orthogonal frequency division multiplexing (OFDM) is a widely adopted wireless communication technique but is sensitive to the carrier frequency offset (CFO).
Enhanced Latent Multi-view Subspace Clustering
Specifically, we stack the data matrices from various views into the block-diagonal locations of the augmented matrix to exploit the complementary information.
Pangu-Agent: A Fine-Tunable Generalist Agent with Structured Reasoning
This paper presents a general framework model for integrating and learning structured reasoning into AI agents' policies.
Decoupling Representation and Knowledge for Few-Shot Intent Classification and Slot Filling
Therefore, current works first train a model on source domains with sufficiently labeled data, and then transfer the model to target domains where only rarely labeled data is available.
SLP-Net:An efficient lightweight network for segmentation of skin lesions
Prompt treatment for melanoma is crucial.
Multi-stages attention Breast cancer classification based on nonlinear spiking neural P neurons with autapses
Downsampling in deep networks may lead to loss of information, so for compensating the detail and edge information and allowing convolutional neural networks to pay more attention to seek the lesion region, we propose a multi-stages attention architecture based on NSNP neurons with autapses.
Large Language Models Play StarCraft II: Benchmarks and A Chain of Summarization Approach
StarCraft II is a challenging benchmark for AI agents due to the necessity of both precise micro level operations and strategic macro awareness.
DMT: Comprehensive Distillation with Multiple Self-supervised Teachers
Numerous self-supervised learning paradigms, such as contrastive learning and masked image modeling, have been proposed to acquire powerful and general representations from unlabeled data.
A survey on algorithms for Nash equilibria in finite normal-form games
This paper reviews various algorithms computing the Nash equilibrium and its approximation solutions in finite normal-form games from both theoretical and empirical perspectives.