Papers

New on arXiv

Mon 8 Jan 2024

179 papers

Slot Structured World ModelsWorld models → Latent predictive world models
Deep Reinforcement Learning for Multi-Truck Vehicle Routing Problems with Multi-Leg Demand RoutesDeep reinforcement learning methods → RL for games and combinatorial optimization
FADI-AEC: Fast Score Based Diffusion Model Guided by Far-end Signal for Acoustic Echo CancellationDiffusion models → Audio, speech and music
MARG: Multi-Agent Review Generation for Scientific PapersLLM agents and tool use → Web, search, and research agents
Attack-Resilient Image Watermarking Using Stable DiffusionDiffusion models → Robustness, privacy and adversarial aspects +1
Curiosity & Entropy Driven Unsupervised RL in Multiple EnvironmentsDeep reinforcement learning methods → Deep RL algorithms and representations
Dense Hopfield Networks in the Teacher-Student SettingKnowledge distillation → General knowledge distillation methods
Language-Conditioned Robotic Manipulation with Fast and Slow ThinkingLLM reasoning → Spatial and embodied reasoning
RePLan: Robotic Replanning with Perception and Language ModelsLLM reasoning → Spatial and embodied reasoning
Learn Once Plan Arbitrarily (LOPA): Attention-Enhanced Deep Reinforcement Learning Method for Global Path PlanningDeep reinforcement learning methods → RL for robot navigation and UAV control
GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D GenerationLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
Mixtral of ExpertsMixture-of-experts → MoE large language models
MoE-Mamba: Efficient Selective State Space Models with Mixture of ExpertsMixture-of-experts → MoE large language models +1
A Minimaximalist Approach to Reinforcement Learning from Human FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
Behavioural Cloning in VizDoomOffline RL and imitation learning from data → Imitation learning methods
Advancing Spatial Reasoning in Large Language Models: An In-Depth Evaluation and Enhancement Using the StepGame BenchmarkLLM reasoning → Spatial and embodied reasoning
scDiffusion: conditional generation of high-quality single-cell data using diffusion modelDiffusion models → Flow matching, time series and science
Geodesic interpolation of frame-wise speaker embeddings for the diarization of meeting scenariosKnowledge distillation → Speech and audio distillation
Guiding drones by information gainDeep reinforcement learning methods → RL for robot navigation and UAV control
SpeechAgents: Human-Communication Simulation with Multi-Modal Multi-Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
Using reinforcement learning to improve drone-based inference of greenhouse gas fluxesDeep reinforcement learning methods → RL for robot navigation and UAV control
STAIR: Spatial-Temporal Reasoning with Auditable Intermediate Results for Video Question AnsweringLLM reasoning → Multimodal reasoning
FlightLLM: Efficient Large Language Model Inference with a Complete Mapping Flow on FPGAsEfficient LLM inference and serving → Serving systems and request scheduling
Inverse Reinforcement Learning with Sub-optimal ExpertsOffline RL and imitation learning from data → Inverse reinforcement learning +1
Long-term Safe Reinforcement Learning with Binary FeedbackDeep reinforcement learning methods → Safe and constrained RL
Language Models Encode the Value of Numbers LinearlyMechanistic interpretability → Steering and interpreting LLM reasoning
The Butterfly Effect of Altering Prompts: How Small Changes and Jailbreaks Affect Large Language Model PerformanceLLM safety and security → Jailbreaking
Logits Poisoning Attack in Federated DistillationKnowledge distillation → Federated, robust and private distillation
Evaluating Brain-Inspired Modular Training in Automated Circuit Discovery for Mechanistic InterpretabilityMechanistic interpretability → Circuits and mechanistic analysis
DME-Driver: Integrating Human Decision Logic and 3D Scene Perception in Autonomous DrivingEnd-to-end autonomous driving → VLMs for autonomous driving
Why Solving Multi-agent Path Finding with Large Language Model has not Succeeded YetLLM agents and tool use → General LLM agent frameworks and benchmarks
DDM-Lag : A Diffusion-based Decision-making Model for Autonomous Vehicles with Lagrangian Safety EnhancementDiffusion models → Diffusion and flow policies for robotics +1
Comparative Analysis of Deep Convolutional Neural Networks for Detecting Medical Image Deepfakes
Deep learning based detection of collateral circulation in coronary angiographies
Connect Later: Improving Fine-tuning for Robustness with Targeted Augmentations
Catalyzing Equity in STEM Teams: Harnessing Generative AI for Inclusion and Diversity
Kronecker Product Feature Fusion for Convolutional Neural Network in Remote Sensing Scene Classification
Robustness Assessment of a Runway Object Classifier for Safe Aircraft Taxiing
Why does Prediction Accuracy Decrease over Time? Uncertain Positive Learning for Cloud Failure Prediction
LF-ViT: Reducing Spatial Redundancy in Vision Transformer for Efficient Image Recognition
Deep Learning in Physical Layer: Review on Data Driven End-to-End Communication Systems and their Enabling Semantic Applications
AI and Generative AI for Research Discovery and Summarization
Greedy Algorithm for Inference of Decision Trees from Decision Rule Systems
LightHouse: A Survey of AGI Hallucination
A Span-based Model for Extracting Overlapping PICO Entities from RCT Publications
Using Zero-shot Prompting in the Automatic Creation and Expansion of Topic Taxonomies for Tagging Retail Banking Transactions
Exploring Conversational Agents as an Effective Tool for Measuring Cognitive Biases in Decision-Making
Tree Search-Based Evolutionary Bandits for Protein Sequence Optimization
LLM4PLC: Harnessing Large Language Models for Verifiable Programming of PLCs in Industrial Control Systems
Functional Graphical Models: Structure Enables Offline Data-Driven Optimization
An adaptive network-based approach for advanced forecasting of cryptocurrency values
Autosen: improving automatic wifi human sensing through cross-modal autoencoder
Physics-informed Deep Learning to Solve Three-dimensional Terzaghi Consolidation Equation: Forward and Inverse Problems
Representation Learning for Wearable-Based Applications in the Case of Missing Data
Exploring Attack Resilience in Distributed Platoon Controllers with Model Predictive Control
Universal Consistency of Wide and Deep ReLU Neural Networks and Minimax Optimal Convergence Rates for Kolmogorov-Donoho Optimal Function Classes
Efficient Constrained Graph Search for Post-hoc Error Correction in Binary Classifiers
Predicting the structure of dynamic graphs
Attention versus Contrastive Learning of Tabular Data -- A Data-centric Benchmarking
Detecting Face Synthesis Using a Concealed Fusion Model
Explaining the Power of Topological Data Analysis in Graph Machine Learning
Scalable Normalizing Flows Enable Boltzmann Generators for Macromolecules
Spatio-Temporal Turbulence Mitigation: A Translational Perspective
Data-Agnostic Face Image Synthesis Detection Using Bayesian CNNs
A learning-based mathematical programming formulation for the automatic configuration of optimization solvers
High-precision Voice Search Query Correction via Retrievable Speech-text Embedings
SOAP: Cross-sensor Domain Adaptation for 3D Object Detection Using Stationary Object Aggregation Pseudo-labelling
Distortions in Judged Spatial Relations in Large Language Models
Towards a Machine Learning-Based Approach to Predict Space Object Density Distributions
FunnyNet-W: Multimodal Learning of Funny Moments in Videos in the Wild
Effects of Multimodal Explanations for Autonomous Driving on Driving Performance, Cognitive Load, Expertise, Confidence, and Trust
Interactive Multi-Objective Evolutionary Optimization of Software Architectures
FlopPITy: Enabling self-consistent exoplanet atmospheric retrievals with machine learning
Advancing bioinformatics with large language models: components, applications and perspectives
Efficient Selective Audio Masked Multimodal Bottleneck Transformer for Audio-Video Classification
Cross-Speaker Encoding Network for Multi-Talker Speech Recognition
Chain of LoRA: Efficient Fine-tuning of Language Models via Residual Learning
Two-stream joint matching method based on contrastive learning for few-shot action recognition
Online Test-Time Adaptation of Spatial-Temporal Traffic Flow Forecasting
Robust Calibration For Improved Weather Prediction Under Distributional Shift
Dr2Net: Dynamic Reversible Dual-Residual Networks for Memory-Efficient Finetuning
AGG: Amortized Generative 3D Gaussians for Single Image to 3D
A Priori Determination of the Pretest Probability
Improved motif-scaffolding with SE(3) flow matching
RudolfV: A Foundation Model by Pathologists for Pathologists
Fun with Flags: Robust Principal Directions via Flag Manifolds
Convex SGD: Generalization Without Early Stopping
Variance Reduction in Ratio Metrics for Efficient Online Experiments
Unveiling Bias in Fairness Evaluations of Large Language Models: A Critical Literature Review of Music and Movie Recommendation Systems
Empirical Analysis of Efficient Fine-Tuning Methods for Large Pre-Trained Language Models
FFSplit: Split Feed-Forward Network For Optimizing Accuracy-Efficiency Trade-off in Language Model Inference
IDoFew: Intermediate Training Using Dual-Clustering in Language Models for Few Labels Text Classification
Efficient Multiscale Multimodal Bottleneck Transformer for Audio-Video Classification
Weak Correlations as the Underlying Principle for Linearization of Gradient-Based Learning Systems
Generative adversarial wavelet neural operator: Application to fault detection and isolation of multivariate time series data
Simultaneous Task Allocation and Planning for Multi-Robots under Hierarchical Temporal Logic Specifications
Polynomial Precision Dependence Solutions to Alignment Research Center Matrix Completion Problems
MS-DETR: Efficient DETR Training with Mixed Supervision
A Primer on Temporal Graph Learning
Differential Equations for Continuous-Time Deep Learning

All 179