Papers

New on arXiv

Sun 2 Jun 2024

151 papers

Towards a copilot in BIM authoring tool using a large language model-based agent for intelligent human-machine interactionLLM agents and tool use → Software engineering coding agents
Brainstorming Brings Power to Large Language Models of Knowledge ReasoningLLM reasoning → Reasoning benchmarks and evaluation
Inverse Constitutional AI: Compressing Preferences into PrinciplesLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
Distortion-free Watermarks are not Truly Distortion-free under Watermark Key CollisionsLLM safety and security → Watermarking generated content and models
Teams of LLM Agents can Exploit Zero-Day VulnerabilitiesLLM agents and tool use → Agent threats, guardrails and governance
Reservoir History Matching of the Norne field with generative exotic priors and a coupled Mixture of Experts -- Physics Informed Neural Operator Forward ModelDiffusion models → Flow matching, time series and science
Aligning Language Models with Demonstrated FeedbackLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Deep Reinforcement Learning for Sim-to-Real Policy Transfer of VTOL-UAVs Offshore Docking OperationsDeep reinforcement learning methods → RL for robot navigation and UAV control
OLIVE: Object Level In-Context Visual EmbeddingsLLM reasoning → Multimodal reasoning +1
Dual Policy Reinforcement Learning for Real-time Rebalancing in Bike-sharing SystemsDeep reinforcement learning methods → RL for energy, networks and operations
DistilDIRE: A Small, Fast, Cheap and Lightweight Diffusion Synthesized Deepfake DetectionDiffusion models → Image generation, text-to-image and editing
BoNBoN Alignment for Large Language Models and the Sweetness of Best-of-n SamplingLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Invisible Backdoor Attacks on Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
Covariance-Adaptive Sequential Black-box Optimization for Diffusion Targeted GenerationDiffusion models → Diffusion foundations and sampling
Get my drift? Catching LLM Task Drift with Activation DeltasRetrieval-augmented generation → Privacy and security of RAG +1
Diffusion Features to Bridge Domain Gap for Semantic SegmentationDiffusion models → Medical imaging and segmentation
Diffusion Tuning: Transferring Diffusion Models via Chain of ForgettingDiffusion models → Diffusion foundations and sampling
Unsupervised contrastive analysis for anomaly detection in brain MRIs via conditional diffusion modelsDiffusion models → Medical imaging and segmentation
The Embodied World Model Based on LLM with Visual Information and Prediction-Oriented PromptsWorld models → World models for navigation
Shared-unique Features and Task-aware Prioritized Sampling on Multi-task Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
Evaluating Mathematical Reasoning of Large Language Models: A Focus on Error Identification and CorrectionLLM reasoning → Mathematical reasoning
A Digital Twin Framework for Reinforcement Learning with Real-Time Self-Improvement via Human Assistive TeleoperationDeep reinforcement learning methods → RL for robot locomotion and manipulation
A Survey of Deep Learning Based Radar and Vision Fusion for 3D Object Detection in Autonomous DrivingEnd-to-end autonomous driving → End-to-end system architecture
Learning Multimodal Behaviors from Scratch with Diffusion Policy GradientDiffusion models → Diffusion and flow policies for robotics +1
Cascade-CLIP: Cascaded Vision-Language Embeddings Alignment for Zero-Shot Semantic SegmentationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
An Early Investigation into the Utility of Multimodal Large Language Models in Medical ImagingMultimodal LLMs / vision-language models → Medical vision-language models
Enhancing Zero-shot Text-to-Speech Synthesis with Human FeedbackLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
FuRL: Visual-Language Models as Fuzzy Rewards for Reinforcement LearningMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
COS-Mix: Cosine Similarity and Distance Fusion for Improved Information RetrievalRetrieval-augmented generation → RAG pipeline design and evaluation
Improving GFlowNets for Text-to-Image Diffusion AlignmentDiffusion models → Diffusion and flow policies for robotics
Diff-Mosaic: Augmenting Realistic Representations in Infrared Small Target Detection via Diffusion PriorDiffusion models → Image generation, text-to-image and editing
MGI: Multimodal Contrastive pre-training of Genomic and Medical ImagingState-space sequence models (S4, Mamba) → Mamba for medical image analysis
Compositional 4D Dynamic Scenes Understanding with Physics Priors for Video Question AnsweringMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Model Predictive Control and Reinforcement Learning: A Unified Framework Based on Dynamic ProgrammingDeep reinforcement learning methods → RL for games and combinatorial optimization
RNNs, CNNs and Transformers in Human Action Recognition: A Survey and a Hybrid Model
The Future of Aerial Communications: A Survey of IRS-Enhanced UAV Communication Technologies
A Diagnostic Model for Acute Lymphoblastic Leukemia Using Metaheuristics and Deep Learning Methods
Research on Image Processing and Vectorization Storage Based on Garage Electronic Maps
Early Detection of Misinformation for Infodemic Management: A Domain Adaptation Approach
Towards commands recommender system in BIM authoring tool using transformers
Harnessing Business and Media Insights with Large Language Models
Position: Rethinking Post-Hoc Search-Based Neural Approaches for Solving Large-Scale Traveling Salesman Problems
Physics and geometry informed neural operator network with application to acoustic scattering
LncRNA-disease association prediction method based on heterogeneous information completion and convolutional neural network
Amalgam: A Framework for Obfuscated Neural Network Training on the Cloud
Know Your Neighborhood: General and Zero-Shot Capable Binary Function Search Powered by Call Graphlets
A Novel Defense Against Poisoning Attacks on Federated Learning: LayerCAM Augmented with Autoencoder
Gated recurrent neural network with TPE Bayesian optimization for enhancing stock index prediction accuracy
D-FaST: Cognitive Signal Decoding with Disentangled Frequency-Spatial-Temporal Attention
Multimodal Deep Learning for Low-Resource Settings: A Vector Embedding Alignment Approach for Healthcare Applications
Applying Fine-Tuned LLMs for Reducing Data Needs in Load Profile Analysis
COVID-19: post infection implications in different age groups, mechanism, diagnosis, effective prevention, treatment, and recommendations
Robust Multi-Modal Speech In-Painting: A Sequence-to-Sequence Approach
YODAS: Youtube-Oriented Dataset for Audio and Speech
Phonetic Error Analysis of Raw Waveform Acoustic Models with Parametric and Non-Parametric CNNs
Pretrained Hybrids with MAD Skills
Global High Categorical Resolution Land Cover Mapping via Weak Supervision
Visual place recognition for aerial imagery: A survey
Quantum Equilibrium Propagation: Gradient-Descent Training of Quantum Systems
Evidence of Learned Look-Ahead in a Chess-Playing Neural Network
Scaffold Splits Overestimate Virtual Screening Performance
Formality Style Transfer in Persian
Streaming quanta sensors for online, high-performance imaging and vision
LinkLogic: A New Method and Benchmark for Explainable Knowledge Graph Predictions
A Tutorial on Doubly Robust Learning for Causal Inference
Eating Smart: Advancing Health Informatics with the Grounding DINO based Dietary Assistant App
Local Methods with Adaptivity via Scaling
Diffusion-Inspired Quantum Noise Mitigation in Parameterized Quantum Circuits
The Power of Summary-Source Alignments
FOCUS: Forging Originality through Contrastive Use in Self-Plagiarism for Language Models
End-to-End Hybrid Refractive-Diffractive Lens Design with Differentiable Ray-Wave Model
Harvard Undergraduate Survey on Generative AI
Collaborative Novel Object Discovery and Box-Guided Cross-Modal Alignment for Open-Vocabulary 3D Object Detection
Imitating the Functionality of Image-to-Image Models Using a Single Example
Policy Verification in Stochastic Dynamical Systems Using Logarithmic Neural Certificates
Lasso Bandit with Compatibility Condition on Optimal Arm
Expected Possession Value of Control and Duel Actions for Soccer Player's Skills Estimation
Graph Neural Preconditioners for Iterative Solutions of Sparse Linear Systems
EchoNet-Synthetic: Privacy-preserving Video Generation for Safe Medical Data Sharing
Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detection
Extrapolability Improvement of Machine Learning-Based Evapotranspiration Models via Domain-Adversarial Neural Networks
Ensemble Deep Random Vector Functional Link Neural Network Based on Fuzzy Inference System
MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization
PruNeRF: Segment-Centric Dataset Pruning via 3D Spatial Consistency
Is In-Context Learning in Large Language Models Bayesian? A Martingale Perspective
Towards Point Cloud Compression for Machine Perception: A Simple and Strong Baseline by Learning the Octree Depth Level Predictor
Developing an efficient corpus using Ensemble Data cleaning approach
Applying Intrinsic Debiasing on Downstream Tasks: Challenges and Considerations for Machine Translation
AI-Face: A Million-Scale Demographically Annotated AI-Generated Face Dataset and Fairness Benchmark
Differentiation of Multi-objective Data-driven Decision Pipeline
Bayesian Joint Additive Factor Models for Multiview Learning
Constrained Adaptive Attack: Effective Adversarial Attack Against Deep Neural Networks for Tabular Data
Automatic Instruction Evolving for Large Language Models
Scaling Tractable Probabilistic Circuits: A Systems Perspective
IENE: Identifying and Extrapolating the Node Environment for Out-of-Distribution Generalization on Graphs
Once-for-All: Controllable Generative Image Compression with Dynamic Granularity Adaptation
Evaluating Distributed Representations for Multi-Level Lexical Semantics: A Research Proposal
Freeplane: Unlocking Free Lunch in Triplane-Based Sparse-View Reconstruction Models
CCF: Cross Correcting Framework for Pedestrian Trajectory Prediction
Augmenting the FedProx Algorithm by Minimizing Convergence

All 151