Papers

New on arXiv

Sun 14 Apr 2024

115 papers

Evidence from counterfactual tasks supports emergent analogical reasoning in large language modelsLLM reasoning → Reasoning benchmarks and evaluation
Towards Practical Tool Usage for Continually Learning LLMsLLM agents and tool use → Tool learning and function calling
Weight Copy and Low-Rank Adaptation for Few-Shot Distillation of Vision TransformersKnowledge distillation → General knowledge distillation methods
Mean Field Correlated Imitation LearningOffline RL and imitation learning from data → Inverse reinforcement learning
A Novel State Space Model with Local Enhancement and State Sharing for Image FusionState-space sequence models (S4, Mamba) → Vision Mamba backbones
TrafficVLM: A Controllable Visual Language Model for Traffic Video CaptioningMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
Knowledgeable Agents by Offline Reinforcement Learning from Large Language Model RolloutsLLM agents and tool use → Reinforcement learning for LLM agents +1
Arena: A Patch-of-Interest ViT Inference Acceleration System for Edge-Assisted Video AnalyticsEfficient LLM inference and serving → Token pruning and merging for ViTs
Fault Detection in Mobile Networks Using Diffusion ModelsDiffusion models → Flow matching, time series and science
DreamScape: 3D Scene Creation via Gaussian Splatting joint Correlation ModelingDiffusion models → 3D, point cloud and scene generation
Exploring and Improving Drafts in Blockwise Parallel DecodingEfficient LLM inference and serving → Speculative decoding
Compass: Large Multilingual Language Model for South-east AsiaLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
TextHawk: Exploring Efficient Fine-Grained Perception of Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
FaceCat: Enhancing Face Recognition Security with a Unified Diffusion ModelDiffusion models → Robustness, privacy and adversarial aspects
LoopAnimate: Loopable Salient Object AnimationDiffusion models → Video generation
Distilling Reasoning Ability from Large Language Models with Adaptive ThinkingLLM reasoning → Prompting and chain-of-thought reasoning +1
Fusion-Mamba for Cross-modality Object DetectionState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
RF-Diffusion: Radio Signal Generation via Time-Frequency DiffusionDiffusion models → Diffusion for compression and wireless
Generative AI Agents with Large Language Model for Satellite Networks via a Mixture of Experts TransmissionLLM agents and tool use → Agentic AI for wireless networks +1
When Hindsight is Not 20/20: Testing Limits on Reflective Thinking in Large Language ModelsLLM reasoning → Test-time compute and efficient thinking
Confidence Calibration and Rationalization for LLMs via Multi-Agent DeliberationLLM agents and tool use → General LLM agent frameworks and benchmarks +1
A data-driven approach to modeling brain activity using differential equations
Affirmative safety: An approach to risk management for high-risk AI
Ethical Framework for Responsible Foundational Models in Medical Imaging
RNA Secondary Structure Prediction Using Transformer-Based Deep Learning Models
Long-term Human Participation Assessment In Collaborative Learning Environments Using Dynamic Scene Analysis
ML-based handover prediction over a real O-RAN deployment using RAN Intelligent controller
LuminLab: An AI-Powered Building Retrofit and Energy Modelling Platform
Integrating Physiological Data with Large Language Models for Empathic Human-AI Interaction
Evaluating Fast Adaptability of Neural Networks for Brain-Computer Interface
A Survey on Multimodal Wearable Sensor-based Human Action Recognition
Evaluation and Improvement of Fault Detection for Large Language Models
Subtle Signs of Scribal Intent in the Voynich Manuscript
Model Failure or Data Corruption? Exploring Inconsistencies in Building Energy Ratings with Self-Supervised Contrastive Learning
Incremental Self-training for Semi-supervised Learning
Intelligent Message Behavioral Identification System
VideoSAGE: Video Summarization with Graph Representation Learning
Can AI Understand Our Universe? Test of Fine-Tuning GPT by Astrophysical Data
Model-based Offline Quantum Reinforcement Learning
Generative transformations and patterns in LLM-native approaches for software verification and falsification
Low-Resource Named Entity Recognition with Cross-Lingual, Character-Level Neural Conditional Random Fields
Orientation-conditioned Facial Texture Mapping for Video-based Facial Remote Photoplethysmography Estimation
textitsweet- An Open Source Modular Platform for Contactless Hand Vascular Biometric Experiments
Deceptive Patterns of Intelligent and Interactive Writing Assistants
The Effect of Data Partitioning Strategy on Model Generalizability: A Case Study of Morphological Segmentation
Understanding the Role of Temperature in Diverse Question Generation by GPT-4
Hierarchical Attention Models for Multi-Relational Graphs
Momentum-based gradient descent methods for Lie groups
Evaluation Framework for Feedback Generation Methods in Skeletal Movement Assessment
LLeMpower: Understanding Disparities in the Control and Access of Large Language Models
A Unified Combination Framework for Dependent Tests with Applications to Microbiome Association Studies
Counteracting Concept Drift by Learning with Future Malware Predictions
Machine learning-based identification of Gaia astrometric exoplanet orbits
Adversarial Robustness Limits via Scaling-Law and Human-Alignment Studies
Face-voice Association in Multilingual Environments (FAME) Challenge 2024 Evaluation Plan
Entropy Guided Extrapolative Decoding to Improve Factuality in Large Language Models
Self-Selected Attention Span for Accelerating Large Language Model Inference
SNN4Agents: A Framework for Developing Energy-Efficient Embodied Spiking Neural Networks for Autonomous Agents
Large Language Models are as persuasive as humans, but how? About the cognitive effort and moral-emotional language of LLM arguments
The intelligent prediction and assessment of financial information risk in the cloud computing model
Characterizing Soft-Error Resiliency in Arm's Ethos-U55 Embedded Machine Learning Accelerator
Text-to-Song: Towards Controllable Music Generation Incorporating Vocals and Accompaniment
In My Perspective, In My Hands: Accurate Egocentric 2D Hand Pose and Action Recognition
OWLOOP: Interfaces for Mapping OWL Axioms into OOP Hierarchies
Monte Carlo Search Algorithms Discovering Monte Carlo Tree Search Exploration Terms
High Significant Fault Detection in Azure Core Workload Insights
A Simple Strategy for Body Estimation from Partial-View Images
Reap the Wild Wind: Detecting Media Storms in Large-Scale News Corpora
Cross-Data Knowledge Graph Construction for LLM-enabled Educational Question-Answering System: A Case Study at HCMUT
Bridging Data Islands: Geographic Heterogeneity-Aware Federated Learning for Collaborative Remote Sensing Semantic Segmentation
RoofDiffusion: Constructing Roofs from Severely Corrupted Point Data via Diffusion
Artificial Intelligence enhanced Security Problems in Real-Time Scenario using Blowfish Algorithm
SyntStereo2Real: Edge-Aware GAN for Remote Sensing Image-to-Image Translation while Maintaining Stereo Constraint
VRS-NeRF: Visual Relocalization with Sparse Neural Radiance Field
PANet: A Physics-guided Parametric Augmentation Net for Image Dehazing by Hazing
Make Split, not Hijack: Preventing Feature-Space Hijacking Attacks in Split Learning
Task-Driven Exploration: Decoupling and Inter-Task Feedback for Joint Moment Retrieval and Highlight Detection
JaFIn: Japanese Financial Instruction Dataset
FedCCL: Federated Dual-Clustered Feature Contrast Under Domain Heterogeneity
GPT2MEG: Quantizing MEG for Autoregressive Generation
TEXT2TASTE: A Versatile Egocentric Vision System for Intelligent Reading Assistance Using Large Language Model
Test Code Generation for Telecom Software Systems using Two-Stage Generative Model
Generalization Error Bounds for Learning under Censored Feedback
Learning Self-Growth Maps for Fast and Accurate Imbalanced Streaming Data Clustering
MAP: Model Aggregation and Personalization in Federated Learning with Incomplete Classes
Tri-modal Confluence with Temporal Dynamics for Scene Graph Generation in Operating Rooms
Breast Cancer Image Classification Method Based on Deep Transfer Learning
DetCLIPv3: Towards Versatile Generative Open-vocabulary Object Detection
Qandle: Accelerating State Vector Simulation Using Gate-Matrix Caching and Circuit Splitting
FedDistill: Global Model Distillation for Local Model De-Biasing in Non-IID Federated Learning
DEGNN: Dual Experts Graph Neural Network Handling Both Edge and Node Feature Noise
DKE-Research at SemEval-2024 Task 2: Incorporating Data Augmentation with Generative Models and Biomedical Knowledge to Enhance Inference Robustness
Prior-agnostic Multi-scale Contrastive Text-Audio Pre-training for Parallelized TTS Frontend Modeling
Change Guiding Network: Incorporating Change Prior to Guide Change Detection in Remote Sensing Imagery
HANet: A Hierarchical Attention Network for Change Detection With Bitemporal Very-High-Resolution Remote Sensing Images
An Experimental Comparison Of Multi-view Self-supervised Methods For Music Tagging
TransformerFAM: Feedback attention is working memory
Survey on Embedding Models for Knowledge Graph and its Applications
GeMQuAD : Generating Multilingual Question Answering Datasets from Large Language Models using Few Shot Learning
Coreset Selection for Object Detection

All 115