Papers

New on arXiv

Sat 24 Feb 2024

122 papers

Stepwise Self-Consistent Mathematical Reasoning with Large Language ModelsLLM reasoning → Mathematical reasoning
Procedural Adherence and Interpretability Through Neuro-Symbolic Generative AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
A priori Estimates for Deep Residual Network in Continuous-time Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
Scalable Volt-VAR Optimization using RLlib-IMPALA Framework: A Reinforcement Learning ApproachDeep reinforcement learning methods → RL for energy, networks and operations
PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-RailsLLM safety and security → Jailbreaking
Multimodal Instruction Tuning with Conditional Mixture of LoRAMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Concurrent Learning of Policy and Unknown Safety Constraints in Reinforcement LearningDeep reinforcement learning methods → Safe and constrained RL
HIR-Diff: Unsupervised Hyperspectral Image Restoration Via Improved Diffusion ModelsDiffusion models → Inverse problems and image restoration
Reward Design for Justifiable Sequential Decision-MakingLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
Empowering Large Language Model Agents through Action LearningLLM agents and tool use → General LLM agent frameworks and benchmarks
Discretionary Lane-Change Decision and Control via Parameterized Soft Actor-Critic for Hybrid Action SpaceDeep reinforcement learning methods → RL for autonomous driving and traffic
Analysis of Off-Policy Multi-Step TD-Learning with Linear Function ApproximationDeep reinforcement learning methods → RL theory and sample complexity
Truly No-Regret Learning in Constrained MDPsDeep reinforcement learning methods → RL theory and sample complexity
Look Before You Leap: Problem Elaboration Prompting Improves Mathematical Reasoning in Large Language ModelsLLM reasoning → Mathematical reasoning
Res-VMamba: Fine-Grained Food Category Visual Classification Using Selective State Space Models with Deep Residual LearningState-space sequence models (S4, Mamba) → Vision Mamba backbones
Chimera: A Lossless Decoding Method for Accelerating Large Language Models Inference by Fusing all TokensEfficient LLM inference and serving → Speculative decoding
HD-Eval: Aligning Large Language Model Evaluators Through Hierarchical Criteria DecompositionLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
GAOKAO-MM: A Chinese Human-Level Benchmark for Multimodal Models EvaluationMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
How Do Humans Write Code? Large Models Do It the Same Way TooLLM reasoning → Prompting and chain-of-thought reasoning
LLMs Can Defend Themselves Against Jailbreaking in a Practical Manner: A Vision PaperLLM safety and security → Jailbreaking
Hal-Eval: A Universal and Fine-grained Hallucination Evaluation Framework for Large Vision Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
Foot In The Door: Understanding Large Language Model Jailbreaking via Cognitive PsychologyLLM safety and security → Jailbreaking
Minions: Accelerating Large Language Model Inference with Aggregated Speculative ExecutionEfficient LLM inference and serving → Speculative decoding
Exploring Failure Cases in Multimodal Reasoning About Physical DynamicsLLM reasoning → Spatial and embodied reasoning +1
Revolutionizing Retail Analytics: Advancing Inventory and Customer Insight with AI
MemeCraft: Contextual and Stance-Driven Multimodal Meme Generation
Effective Gradient Sample Size via Variation Estimation for Accelerating Sharpness aware Minimization
Abdelhak at SemEval-2024 Task 9 : Decoding Brainteasers, The Efficacy of Dedicated Models Versus ChatGPT
IPED: An Implicit Perspective for Relational Triple Extraction based on Diffusion Model
Enhancing Cloud-Based Large Language Model Processing with Elasticsearch and Transformer Models
Enhanced User Interaction in Operating Systems through Machine Learning Language Models
A New Dynamic Distributed Planning Approach: Application to DPDP Problems
Uncovering Customer Issues through Topological Natural Language Analysis
Multimodal Sleep Apnea Detection with Missing or Noisy Modalities
ByteComposer: a Human-like Melody Composition Method based on Language Model Agent
BagStacking: An Integrated Ensemble Learning Approach for Freezing of Gait Detection in Parkinson's Disease
Selective Task offloading for Maximum Inference Accuracy and Energy efficient Real-Time IoT Sensing Systems
A novel data generation scheme for surrogate modelling with deep operator networks
PRoLoRA: Partial Rotation Empowers More Parameter-Efficient LoRA
FGBERT: Function-Driven Pre-trained Gene Language Model for Metagenomics
MIM-Reasoner: Learning with Theoretical Guarantees for Multiplex Influence Maximization
Reliable Conflictive Multi-View Learning
Deep Separable Spatiotemporal Learning for Fast Dynamic Cardiac MRI
Generalization or Memorization: Data Contamination and Trustworthy Evaluation for Large Language Models
Bridging the Gap between 2D and 3D Visual Question Answering: A Fusion Approach for 3D VQA
Frustratingly Simple Prompting-based Text Denoising
Evaluating Prompting Strategies for Grammatical Error Correction Based on Language Proficiency
Certifying Knowledge Comprehension in LLMs
Large Stepsize Gradient Descent for Logistic Loss: Non-Monotonicity of the Loss Improves Optimization Efficiency
MultiContrievers: Analysis of Dense Retrieval Representations
Predicting Outcomes in Video Games with Long Short Term Memory Networks
Pretraining Strategy for Neural Potentials
Learning to See Through Dazzle
Enhanced Droplet Analysis Using Generative Adversarial Networks
Explainable Contrastive and Cost-Sensitive Learning for Cervical Cancer Classification
ESFL: Efficient Split Federated Learning over Resource-Constrained Heterogeneous Wireless Devices
Multi-Object Tracking by Hierarchical Visual Representations
Multi-graph Graph Matching for Coronary Artery Semantic Labeling
Statistical Games
Extraction Propagation
SemEval-2024 Task 8: Weighted Layer Averaging RoBERTa for Black-Box Machine-Generated Text Detection
Spec-Gaussian: Anisotropic View-Dependent Appearance for 3D Gaussian Splatting
E(3)-equivariant models cannot learn chirality: Field-based molecular generation
SportQA: A Benchmark for Sports Understanding in Large Language Models
MATHWELL: Generating Educational Math Word Problems Using Teacher Annotations
FedMM: Federated Multi-Modal Learning with Modality Heterogeneity in Computational Pathology
RAUCA: A Novel Physical Adversarial Attack on Vehicle Detectors via Robust and Accurate Camouflage Generation
NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation
Prompt Perturbation Consistency Learning for Robust Language Models
Multiple Instance Learning for Glioma Diagnosis using Hematoxylin and Eosin Whole Slide Images: An Indian Cohort Study
Parameter-efficient Prompt Learning for 3D Point Cloud Understanding
Cooperation and Control in Delegation Games
DART: Depth-Enhanced Accurate and Real-Time Background Matting
Debiased Model-based Interactive Recommendation
Linguistic Intelligence in Large Language Models for Telecommunications
A Generative Machine Learning Model for Material Microstructure 3D Reconstruction and Performance Evaluation
On Efficiently Representing Regular Languages as RNNs
Measuring Bargaining Abilities of LLMs: A Benchmark and A Buyer-Enhancement Method
OAG-Bench: A Human-Curated Benchmark for Academic Graph Mining
Optimal Zero-Shot Detector for Multi-Armed Attacks
Sequential Visual and Semantic Consistency for Semi-supervised Text Recognition
Construction and application of artificial intelligence crowdsourcing map based on multi-track GPS data
IRConStyle: Image Restoration Framework Using Contrastive Learning and Style Transfer
Cryptanalysis and improvement of multimodal data encryption by machine-learning-based system
From COBIT to ISO 42001: Evaluating Cybersecurity Frameworks for Opportunities, Risks, and Regulatory Compliance in Commercializing Large Language Models
GenCode: A Generic Data Augmentation Framework for Boosting Deep Learning-Based Code Understanding
PhyPlan: Compositional and Adaptive Physical Task Reasoning with Physics-Informed Skill Networks for Robot Manipulators
TV-SAM: Increasing Zero-Shot Segmentation Performance on Multimodal Medical Images Using GPT-4 Generated Descriptive Prompts Without Human Annotation
Batch Active Learning of Reward Functions from Human Preferences
Detection Is Tracking: Point Cloud Multi-Sweep Deep Learning Models Revisited
Dental Severity Assessment through Few-shot Learning and SBERT Fine-tuning
Sparse MeZO: Less Parameters for Better Performance in Zeroth-Order LLM Fine-Tuning
Design, Implementation and Analysis of a Compressed Sensing Photoacoustic Projection Imaging System
Intelligent Director: An Automatic Framework for Dynamic Visual Composition using ChatGPT
Traditional Transformation Theory Guided Model for Learned Image Compression
Low-Rank Bandits via Tight Two-to-Infinity Singular Subspace Recovery
Data-Efficient Operator Learning via Unsupervised Pretraining and In-Context Learning
ArEEG_Chars: Dataset for Envisioned Speech Recognition using EEG for Arabic Characters
Clustering in Dynamic Environments: A Framework for Benchmark Dataset Generation With Heterogeneous Changes
Understanding Missingness in Time-series Electronic Health Records for Individualized Representation

All 122