Papers

New on arXiv

Sat 17 Feb 2024

119 papers

SINR-Aware Deep Reinforcement Learning for Distributed Dynamic Channel Allocation in Cognitive Interference NetworksDeep reinforcement learning methods → RL for energy, networks and operations
Turn Waste into Worth: Rectifying Top-k Router of MoEMixture-of-experts → Expert routing strategies
GraphKD: Exploring Knowledge Distillation Towards Document Object Detection with Structured Graph CreationKnowledge distillation → Detection and dense prediction distillation
k-SemStamp: A Clustering-Based Semantic Watermark for Detection of Machine-Generated TextLLM safety and security → Watermarking generated content and models
Reasoning before Comparison: LLM-Enhanced Semantic Similarity Metrics for Domain Specialized Text AnalysisLLM reasoning → Clinical and biomedical applications
Reinforcement learning to maximise wind turbine energy generationDeep reinforcement learning methods → RL for energy, networks and operations
Multi Task Inverse Reinforcement Learning for Common Sense RewardOffline RL and imitation learning from data → Inverse reinforcement learning +1
Offline Training of Language Model Agents with Functions as Learnable WeightsLLM agents and tool use → General LLM agent frameworks and benchmarks
Debiased Offline Representation Learning for Fast Online Adaptation in Non-stationary DynamicsDeep reinforcement learning methods → Deep RL algorithms and representations
Simulating Multi-Stakeholder Decision-Making with Generative Agents in Urban PlanningLLM agents and tool use → Social simulation and multi-agent debate
MMMModal -- Multi-Images Multi-Audio Multi-turn Multi-ModalMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Dissecting Human and LLM PreferencesLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
Puzzle Solving using Reasoning of Large Language Models: A SurveyLLM reasoning → Reasoning benchmarks and evaluation
Can Large Multimodal Models Uncover Deep Semantics Behind Images?Multimodal LLMs / vision-language models → MLLM training and visual instruction tuning
TC-DiffRecon: Texture coordination MRI reconstruction method based on diffusion model and modified MF-UNet methodDiffusion models → Medical imaging and segmentation
MoRAL: MoE Augmented LoRA for LLMs' Lifelong LearningMixture-of-experts → MoE large language models
Aligning Large Language Models by On-Policy Self-JudgmentLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
CoLLaVO: Crayon Large Language and Vision mOdelMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
DiffPoint: Single and Multi-view Point Cloud Reconstruction with ViT Based Diffusion ModelDiffusion models → 3D, point cloud and scene generation
A Spectrum Evaluation Benchmark for Medical Multi-Modal Large Language ModelsMultimodal LLMs / vision-language models → Medical vision-language models
Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
Direct Evaluation of Chain-of-Thought in Multi-hop Reasoning with Knowledge GraphsLLM reasoning → Knowledge- and tool-augmented reasoning
Evaluating LLMs' Mathematical Reasoning in Financial Document Question AnsweringLLM reasoning → Reasoning for agents, planning and code
GenDec: A robust generative Question-decomposition method for Multi-hop reasoningLLM reasoning → Knowledge- and tool-augmented reasoning
KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge GraphLLM reasoning → Knowledge- and tool-augmented reasoning +1
Knowledge Distillation Based on Transformed Teacher MatchingKnowledge distillation → General knowledge distillation methods
Boosting of Thoughts: Trial-and-Error Problem Solving with Large Language ModelsLLM reasoning → Prompting and chain-of-thought reasoning
Deep Reinforcement Learning Based Toolpath Generation for Thermal Uniformity in Laser Powder Bed Fusion Process
Optimizing Wireless Networks with Deep Unfolding: Comparative Study on Two Deep Unfolding Mechanisms
Detecting a Proxy for Potential Comorbid ADHD in People Reporting Anxiety Symptoms from Social Media Data
Empirical and Experimental Insights into Data Mining Techniques for Crime Prediction: A Comprehensive Survey
EEG2Rep: Enhancing Self-supervised EEG Representation Through Informative Masked Inputs
CliqueParcel: An Approach For Batching LLM Prompts That Jointly Optimizes Efficiency And Faithfulness
Learning causation event conjunction sequences
MLSTL-WSN: Machine Learning-based Intrusion Detection using SMOTETomek in WSNs
When LLMs Meets Acoustic Landmarks: An Efficient Approach to Integrate Speech into Large Language Models for Depression Detection
Implementation of a Model of the Cortex Basal Ganglia Loop
Estimating the age-conditioned average treatment effects curves: An application for assessing load-management strategies in the NBA
Primary and Secondary Factor Consistency as Domain Knowledge to Guide Happiness Computing in Online Assessment
Multi-class Temporal Logic Neural Networks
Evaluating the Stability of Deep Learning Latent Feature Spaces
An Empirical Evaluation of Neural and Neuro-symbolic Approaches to Real-time Multimodal Complex Event Detection
Random Projection Neural Networks of Best Approximation: Convergence theory and practical applications
Data-Driven Stochastic AC-OPF using Gaussian Processes
Transformer-based de novo peptide sequencing for data-independent acquisition mass spectrometry
Exploiting T-norms for Deep Learning in Autonomous Driving
A Practical Method for Generating String Counterfactuals
Probabilistic Routing for Graph-Based Approximate Nearest Neighbor Search
Understanding the Impact of Long-Term Memory on Self-Disclosure with Large Language Model-Driven Chatbots for Public Health Intervention
Language Models Don't Learn the Physical Manifestation of Language
SEE: Strategic Exploration and Exploitation for Cohesive In-Context Prompt Optimization
Variational Entropy Search for Adjusting Expected Improvement
Ransomware detection using stacked autoencoder for feature selection
Expressive Higher-Order Link Prediction through Hypergraph Symmetry Breaking
Fair Classification with Partial Feedback: An Exploration-Based Data Collection Approach
Learning by Reconstruction Produces Uninformative Features For Perception
ChatEarthNet: A Global-Scale Image-Text Dataset Empowering Vision-Language Geo-Foundation Models
EVEDIT: Event-based Knowledge Editing with Deductive Editing Boundaries
SpikeNAS: A Fast Memory-Aware Neural Architecture Search Framework for Spiking Neural Network-based Embedded AI Systems
Hysteresis Compensation of Flexible Continuum Manipulator using RGBD Sensing and Temporal Convolutional Network
BiasBuster: a Neural Approach for Accurate Estimation of Population Statistics using Biased Location Data
ICHPro: Intracerebral Hemorrhage Prognosis Classification Via Joint-attention Fusion-based 3d Cross-modal Network
On Good Practices for Task-Specific Distillation of Large Pretrained Visual Models
FViT: A Focal Vision Transformer with Gabor Filter
ReViT: Enhancing Vision Transformers Feature Diversity with Attention Residual Connections
OneBit: Towards Extremely Low-bit Large Language Models
Enhancing Surgical Performance in Cardiothoracic Surgery with Innovations from Computer Vision and Artificial Intelligence: A Narrative Review
Dense Matchers for Dense Tracking
Fair Resource Allocation in Virtualized O-RAN Platforms
Deep adaptive sampling for surrogate modeling without labeled data
Grammaticality illusion or ambiguous interpretation? Event-related potentials reveal the nature of the missing-NP effect in Mandarin centre-embedded structures
Multi-Perspective Consistency Enhances Confidence Estimation in Large Language Models
Semi-supervised Medical Image Segmentation Method Based on Cross-pseudo Labeling Leveraging Strong and Weak Data Augmentation Strategies
MONAL: Model Autophagy Analysis for Modeling Human-AI Interactions
Beyond Literal Descriptions: Understanding and Locating Open-World Objects Aligned with Human Intentions
Mirror Gradient: Towards Robust Multimodal Recommender Systems via Exploring Flat Local Minima
C-ICL: Contrastive In-context Learning for Information Extraction
LLM can Achieve Self-Regulation via Hyperparameter Aware Generation
Hierarchical Prior-based Super Resolution for Point Cloud Geometry Compression
Can Large Language Models perform Relation-based Argument Mining?
Learning with Imbalanced Noisy Data by Preventing Bias in Sample Selection
Be Persistent: Towards a Unified Solution for Mitigating Shortcuts in Deep Learning
ZeroG: Investigating Cross-dataset Zero-shot Transferability in Graphs
Adaptive Split Balancing for Optimal Random Forest
On the Role of Similarity in Detecting Masquerading Files
Neural Networks with (Low-Precision) Polynomial Approximations: New Insights and Techniques for Accuracy Improvement
HEAL: Brain-inspired Hyperdimensional Efficient Active Learning
Controlled Text Generation for Large Language Model with Dynamic Attribute Graphs
AdAdaGrad: Adaptive Batch Size Schemes for Adaptive Gradient Methods
Training-free image style alignment for self-adapting domain shift on handheld ultrasound devices
Hand Biometrics in Digital Forensics
Exploring ChatGPT for Next-generation Information Retrieval: Opportunities and Challenges
A Decoding Scheme with Successive Aggregation of Multi-Level Features for Light-Weight Semantic Segmentation
Achieving Linear Speedup in Asynchronous Federated Learning with Heterogeneous Clients
Centroid-Based Efficient Minimum Bayes Risk Decoding
Maintaining Adversarial Robustness in Continuous Learning
I Learn Better If You Speak My Language: Understanding the Superior Performance of Fine-Tuning Large Language Models with LLM-Generated Responses
Knowledge Graph Assisted Automatic Sports News Writing
Disclosure and Mitigation of Gender Bias in LLMs
LaCo: Large Language Model Pruning via Layer Collapse

All 119