Papers

New on arXiv

Sat 23 Mar 2024

118 papers

EduAgent: Generative Student Agents in LearningLLM agents and tool use → Educational agents and math problem solving
Improving Retrieval for RAG based Question Answering Models on Financial DocumentsRetrieval-augmented generation → RAG pipeline design and evaluation
Cost-Efficient Large Language Model Serving for Multi-turn Conversations with CachedAttentionEfficient LLM inference and serving → KV cache optimization
IllusionVQA: A Challenging Optical Illusion Dataset for Vision Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
X-Portrait: Expressive Portrait Animation with Hierarchical Motion AttentionDiffusion models → Audio, speech and music
Safe Reinforcement Learning for Constrained Markov Decision Processes with Stochastic Stopping TimeDeep reinforcement learning methods → Safe and constrained RL
Deep Gaussian Covariance Network with Trajectory Sampling for Data-Efficient Policy SearchWorld models → Latent dynamics models and model-based RL +1
Leveraging Zero-Shot Prompting for Efficient Language Model DistillationKnowledge distillation → Knowledge distillation for LLMs
SOEN-101: Code Generation by Emulating Software Process Models Using Large Language Model AgentsLLM agents and tool use → Software engineering coding agents
On the Stability of Learning in Network Games with Many PlayersDeep reinforcement learning methods → RL for games and combinatorial optimization
Centered Masking for Language-Image Pre-TrainingMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
VLM-CPL: Consensus Pseudo Labels from Vision-Language Models for Annotation-Free Pathological Image ClassificationMultimodal LLMs / vision-language models → Medical vision-language models
A Fairness-Oriented Reinforcement Learning Approach for the Operation and Control of Shared Micromobility ServicesDeep reinforcement learning methods → RL for games and combinatorial optimization
The Frontier of Data Erasure: Machine Unlearning for Large Language ModelsLLM safety and security → Machine unlearning
BEND: Bagging Deep Learning Training Based on Efficient Neural Network DiffusionDiffusion models → Diffusion foundations and sampling
iDAT: inverse Distillation Adapter-TuningKnowledge distillation → General knowledge distillation methods
Protecting Copyrighted Material with Unique Identifiers in Large Language Model TrainingLLM safety and security → Membership inference attacks
Few-shot Dialogue Strategy Learning for Motivational Interviewing via Inductive ReasoningLLM reasoning → Clinical and biomedical applications
Towards a RAG-based Summarization Agent for the Electron-Ion ColliderLLM agents and tool use → Web, search, and research agents
SceneX: Procedural Controllable Large-scale Scene GenerationWorld models → Video-generation world models and simulators
ASI as the New God: Technocratic Theocracy
Fine Tuning LLM for Enterprise: Practical Guidelines and Recommendations
Live and Learn: Continual Action Clustering with Incremental Views
Investigating Similarities Across Decentralized Financial (DeFi) Services
Holographic Global Convolutional Networks for Long-Range Prediction Tasks in Malware Detection
Boosting Few-Shot Learning via Attentive Feature Regularization
Detection of Problem Gambling with Less Features Using Machine Learning Methods
SAT Encoding of Partial Ordering Models for Graph Coloring Problems
Finding needles in a haystack: A Black-Box Approach to Invisible Watermark Detection
Understanding The Effectiveness of Lossy Compression in Machine Learning Training Sets
MapTracker: Tracking with Strided Memory Fusion for Consistent Vector HD Mapping
Deep Domain Adaptation: A Sim2Real Neural Approach for Improving Eye-Tracking Systems
Adaptive Super Resolution For One-Shot Talking-Head Generation
Advanced Feature Manipulation for Enhanced Change Detection Leveraging Natural Language Models
Explore until Confident: Efficient Exploration for Embodied Question Answering
Geotokens and Geotransformers
LlamBERT: Large-scale low-cost data annotation in NLP
Sample and Communication Efficient Fully Decentralized MARL Policy Evaluation via a New Approach: Local TD update
Understanding Domain-Size Generalization in Markov Logic Networks
Towards Adversarial Robustness And Backdoor Mitigation in SSL
Multi-agent transformer-accelerated RL for satisfaction of STL specifications
Towards Low-Energy Adaptive Personalization for Resource-Constrained Devices
MatchSeg: Towards Better Segmentation via Reference Image Matching
Human Motion Prediction under Unexpected Perturbation
STEntConv: Predicting Disagreement with Stance Detection and a Signed Graph Convolutional Network
VLUE: A New Benchmark and Multi-task Knowledge Transfer Learning for Vietnamese Natural Language Understanding
Fast and Unified Path Gradient Estimators for Normalizing Flows
TrustSQL: Benchmarking Text-to-SQL Reliability with Penalty-Based Scoring
Diffusion-based Aesthetic QR Code Generation via Scanning-Robust Perceptual Guidance
Integrated path stability selection
Cognitive resilience: Unraveling the proficiency of image-captioning models to interpret masked visual content
LAMPER: LanguAge Model and Prompt EngineeRing for zero-shot time series classification
RAAMove: A Corpus for Analyzing Moves in Research Article Abstracts
Using Large Language Models for OntoClean-based Ontology Refinement
Automated System-level Testing of Unmanned Aerial Systems
Initialisation and Network Effects in Decentralised Federated Learning
An edge detection-based deep learning approach for tear meniscus height measurement
Inpainting-Driven Mask Optimization for Object Removal
TablePuppet: A Generic Framework for Relational Federated Learning
Once for Both: Single Stage of Importance and Sparsity Search for Vision Transformer Compression
ARO: Large Language Model Supervised Robotics Text2Skill Autonomous Learning
Time-series Initialization and Conditioning for Video-agnostic Stabilization of Video Super-Resolution using Recurrent Networks
Spatio-Temporal Bi-directional Cross-frame Memory for Distractor Filtering Point Cloud Single Object Tracking
Scaling Learning based Policy Optimization for Temporal Logic Tasks by Controller Network Dropout
Carbon Intensity-Aware Adaptive Inference of DNNs
Computational Sentence-level Metrics Predicting Human Sentence Comprehension
The Impact of Evolutionary Computation on Robotic Design: A Case Study with an Underactuated Hand Exoskeleton
Efficient Data Access Paths for Mixed Vector-Relational Search
Innovative Quantitative Analysis for Disease Progression Assessment in Familial Cerebral Cavernous Malformations
MRC-based Nested Medical NER with Co-prediction and Adaptive Pre-training
Understanding Emergent Abilities of Language Models from the Loss Perspective
Boarding for ISS: Imbalanced Self-Supervised: Discovery of a Scaled Autoencoder for Mixed Tabular Datasets
In-Context Matting
Depth Estimation fusing Image and Radar Measurements with Uncertain Directions
Adversarial Defense Teacher for Cross-Domain Object Detection under Poor Visibility Conditions
Supervised Learning via Ensembles of Diverse Functional Representations: the Functional Voting Classifier
Modeling Unified Semantic Discourse Structure for High-quality Headline Generation
Graph Image Prior for Unsupervised Dynamic Cardiac Cine MRI Reconstruction
FusionINN: Decomposable Image Fusion for Brain Tumor Monitoring
Towards Human-Like Machine Comprehension: Few-Shot Relational Learning in Visually-Rich Documents
An Upload-Efficient Scheme for Transferring Knowledge From a Server-Side Pre-trained Generator to Clients in Heterogeneous Federated Learning
User-Side Realization
Leveraging Large Language Models for Preliminary Security Risk Analysis: A Mission-Critical Case Study
F-OAL: Forward-only Online Analytic Learning with Fast Training and Low Memory Footprint in Class Incremental Learning
Horoballs and the subgradient method
CodeShell Technical Report
On the Fragility of Active Learners for Text Classification
A Comparative Study of Artificial Potential Fields and Reciprocal Control Barrier Function-based Safety Filters
General LLMs as Instructors for Domain-Specific LLMs: A Sequential Fusion Method to Integrate Extraction and Editing
3D-TransUNet for Brain Metastases Segmentation in the BraTS2023 Challenge
Space Group Informed Transformer for Crystalline Materials Generation
Learnable WSN Deployment of Evidential Collaborative Sensing Model
Convection-Diffusion Equation: A Theoretically Certified Framework for Neural Networks
PEaCE: A Chemistry-Oriented Dataset for Optical Character Recognition on Scientific Documents
Ev-Edge: Efficient Execution of Event-based Vision Algorithms on Commodity Edge Platforms
Distributed Robust Learning based Formation Control of Mobile Robots based on Bioinspired Neural Dynamics
EDDA: A Encoder-Decoder Data Augmentation Framework for Zero-Shot Stance Detection
PNAS-MOT: Multi-Modal Object Tracking with Pareto Neural Architecture Search
Towards Identifiable Latent Additive Noise Models
Contact-aware Human Motion Generation from Textual Descriptions

All 118