Papers

New on arXiv

Sat 18 May 2024

112 papers

CoLay: Controllable Layout Generation through Multi-conditional Latent DiffusionDiffusion models → Image generation, text-to-image and editing
Case-Based Reasoning Approach for Solving Financial Question AnsweringLLM reasoning → Reasoning for agents, planning and code
MapCoder: Multi-Agent Code Generation for Competitive Problem SolvingLLM reasoning → Reasoning for agents, planning and code +1
PDE Control Gym: A Benchmark for Data-Driven Boundary Control of Partial Differential EquationsDeep reinforcement learning methods → RL theory and sample complexity
Optimal control barrier functions for RL based safe powertrain controlDeep reinforcement learning methods → RL for autonomous driving and traffic
Generalized Multi-Objective Reinforcement Learning with Envelope Updates in URLLC-enabled Vehicular NetworksEnd-to-end autonomous driving → Cooperative and V2X driving +1
On the Trajectory Regularity of ODE-based Diffusion SamplingDiffusion models → Diffusion foundations and sampling
Enhancing Fine-Grained Image Classifications via Cascaded Vision Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
The CAP Principle for LLM Serving: A Survey of Long-Context Large Language Model ServingEfficient LLM inference and serving → Serving systems and request scheduling
Visual Episodic Memory-based ExplorationDeep reinforcement learning methods → Deep RL algorithms and representations
Diffusion Model Driven Test-Time Image Adaptation for Robust Skin Lesion ClassificationDiffusion models → Medical imaging and segmentation
Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of ExpertsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
MAMCA -- Optimal on Accuracy and Efficiency for Automatic Modulation Classification with Extended Signal LengthState-space sequence models (S4, Mamba) → Core SSM architectures for language
Dreamer XL: Towards High-Resolution Text-to-3D Generation via Trajectory Score MatchingDiffusion models → 3D, point cloud and scene generation
TriLoRA: Integrating SVD for Advanced Style Personalization in Text-to-Image GenerationDiffusion models → Image generation, text-to-image and editing
The Power of Active Multi-Task Learning in Reinforcement Learning from Human FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
Towards Robust Policy: Enhancing Offline Reinforcement Learning with Adversarial Attacks and DefensesOffline RL and imitation learning from data → Offline RL algorithms
Learning from Imperfect Human Feedback: a Tale from Corruption-Robust DuelingLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
Automated Multi-level Preference for MLLMsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs +1
LG AI Research & KAIST at EHRSQL 2024: Self-Training Large Language Models with Pseudo-Labeled Unanswerable Questions for a Reliable Text-to-SQL System on EHRsSynthetic data and self-improvement for LLMs → Medical synthetic data and agents
Revisiting the Robust Generalization of Adversarial Prompt TuningMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
RuleFuser: An Evidential Bayes Approach for Rule Injection in Imitation Learned Planners and Predictors for Robustness under Distribution ShiftsOffline RL and imitation learning from data → Imitation and offline RL for driving
AquaLoRA: Toward White-box Protection for Customized Stable Diffusion Models via Watermark LoRADiffusion models → Robustness, privacy and adversarial aspects +1
Towards SAR Automatic Target Recognition MultiCategory SAR Image Classification Based on Light Weight Vision Transformer
Fully Exploiting Every Real Sample: SuperPixel Sample Gradient Model Stealing
Detection of Moving Objects in Earth Observation Satellite Images
EnterpriseEM: Fine-tuned Embeddings for Enterprise Semantic Search
Towards Gradient-based Time-Series Explanations through a SpatioTemporal Attention Network
LeaPformer: Enabling Linear Transformers for Autoregressive and Simultaneous Tasks via Learned Proportions
Real-Time Go-Around Prediction: A case study of JFK airport
Exploring speech style spaces with language models: Emotional TTS without emotion labels
Simulating Petri nets with Boolean Matrix Logic Programming
Can Public LLMs be used for Self-Diagnosis of Medical Conditions ?
How big is Big Data?
A Model for Optimal Resilient Planning Subject to Fallible Actuators
Preparing for Black Swans: The Antifragility Imperative for Machine Learning
Adjacent Leader Decentralized Stochastic Gradient Descent
Liver Fat Quantification Network with Body Shape
Investigating KAN-Based Physics-Informed Neural Networks for EMI/EMC Simulations
Meta-Control: Automatic Model-based Control Synthesis for Heterogeneous Robot Skills
Causal Customer Churn Analysis with Low-rank Tensor Block Hazard Model
ReModels: Quantile Regression Averaging models
Large Language Models Lack Understanding of Character Composition of Words
PlantTracing: Tracing Arabidopsis Thaliana Apex with CenterTrack
Unlock the Power of Algorithm Features: A Generalization Analysis for Algorithm Selection
Cooperative Multi-agent Approach for Automated Computer Game Testing
Decision support system for Forest fire management using Ontology with Big Data and LLMs
City-Scale Multi-Camera Vehicle Tracking System with Improved Self-Supervised Camera Link Model
LinkedIn Post Embeddings: Industrial Scale Embedding Generation and Usage across LinkedIn
EyeFound: A Multimodal Generalist Foundation Model for Ophthalmic Imaging
A Unified Approach Towards Active Learning and Out-of-Distribution Detection
UPAM: Unified Prompt Attack in Text-to-Image Generation Models Against Both Textual Filters and Visual Checkers
GinAR: An End-To-End Multivariate Time Series Forecasting Model Suitable for Variable Missing
Sampling Strategies for Mitigating Bias in Face Synthesis Methods
Smooth Kolmogorov Arnold networks enabling structural knowledge representation
MediCLIP: Adapting CLIP for Few-shot Medical Image Anomaly Detection
A Dual Power Grid Cascading Failure Model for the Vulnerability Analysis
Large Neighborhood Prioritized Search for Combinatorial Optimization with Answer Set Programming
Unveiling Key Aspects of Fine-Tuning in Sentence Embeddings: A Representation Rank Analysis
Medical Image Analysis for Detection, Treatment and Planning of Disease using Artificial Intelligence Approaches
InfRS: Incremental Few-Shot Object Detection in Remote Sensing Images
MBIAS: Mitigating Bias in Large Language Models While Retaining Context
Motion Avatar: Generate Human and Animal Avatars with Arbitrary Motion
The Logic of Counterfactuals and the Epistemology of Causal Inference
Estimating the Level of Dialectness Predicts Interannotator Agreement in Multi-dialect Arabic Datasets
Cooperative Cognitive Dynamic System in UAV Swarms: Reconfigurable Mechanism and Framework
Joint Analysis of Single-Cell Data across Cohorts with Missing Modalities
Action Controlled Paraphrasing
Visible and Clear: Finding Tiny Objects in Difference Map
Predicting and Explaining Hearing Aid Usage Using Encoder-Decoder with Attention Mechanism and SHAP
Double Correction Framework for Denoising Recommendation
HR Human: Modeling Human Avatars with Triangular Mesh and High-Resolution Textures from Videos
EnviroExam: Benchmarking Environmental Science Knowledge of Large Language Models
Cross-Language Assessment of Mathematical Capability of ChatGPT
WisPerMed at "Discharge Me!": Advancing Text Generation in Healthcare with Large Language Models, Dynamic Expert Selection, and Priming Techniques on MIMIC-IV
Argumentative Causal Discovery
Advancing fNIRS Neuroimaging through Synthetic Data Generation and Machine Learning Applications
Testing the Performance of Face Recognition for People with Down Syndrome
SimAD: A Simple Dissimilarity-based Approach for Time Series Anomaly Detection
Lag Selection for Univariate Time Series Forecasting using Deep Learning: An Empirical Study
OTLP: Output Thresholding Using Mixed Integer Linear Programming
BadActs: A Universal Backdoor Defense in the Activation Space
SeBot: Structural Entropy Guided Multi-View Contrastive Learning for Social Bot Detection
Transformer based neural networks for emotion recognition in conversations
Identifying and Aligning Medical Claims Made on Social Media with Medical Evidence
MemeMQA: Multimodal Question Answering for Memes via Rationale-Based Inferencing
Real Time Monitoring and Forecasting of COVID 19 Cases using an Adjusted Holt based Hybrid Model embedded with Wavelet based ANN
Automated Text Identification Using CNN and Training Dynamics
Excess Delay from GDP: Measurement and Causal Analysis
Discovering Physics-Informed Neural Networks Model for Solving Partial Differential Equations through Evolutionary Computation
Fuse & Calibrate: A bi-directional Vision-Language Guided Framework for Referring Image Segmentation
LexGen: Domain-aware Multilingual Lexicon Generation
Adaptive Stabilization Based on Machine Learning for Column Generation
Designing NLP Systems That Adapt to Diverse Worldviews
Trustworthy Actionable Perturbations
BrainStorm @ iREL at #SMM4H 2024: Leveraging Translation and Topical Embeddings for Annotation Detection in Tweets
Biathlon: Harnessing Model Resilience for Accelerating ML Inference Pipelines
ReasonPix2Pix: Instruction Reasoning Dataset for Advanced Image Editing
Wind Power Prediction across Different Locations using Deep Domain Adaptive Learning
Towards Knowledge-Infused Automated Disease Diagnosis Assistant

All 112