Papers
Fri 30 Jun 2023
184 papers
- Counterfactual Collaborative ReasoningLLM reasoning → Causal reasoning in LLMs
- RObotic MAnipulation Network (ROMAN) -- Hybrid Hierarchical Learning for Solving Complex Sequential TasksOffline RL and imitation learning from data → Robot manipulation imitation learning
- Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion PriorsDiffusion models → 3D, point cloud and scene generation
- Statler: State-Maintaining Language Models for Embodied ReasoningWorld models → World models for language agents +1
- Meta-Reasoning: Semantics-Symbol Deconstruction for Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
- Look, Remember and Reason: Grounded reasoning in videos with language modelsLLM reasoning → Multimodal reasoning +1
- Practical and Asymptotically Exact Conditional Sampling in Diffusion ModelsDiffusion models → Flow matching, time series and science
- Content-Preserving Diffusion Model for Unsupervised AS-OCT image DespecklingDiffusion models → Medical imaging and segmentation
- Multimodal Prompt Retrieval for Generative Visual Question AnsweringMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
- Counting Guidance for High Fidelity Text-to-Image SynthesisDiffusion models → Image generation, text-to-image and editing
- Class-Incremental Learning using Diffusion Model for Distillation and ReplayDiffusion models → Robustness, privacy and adversarial aspects
- Preference Ranking Optimization for Human AlignmentLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
- CausalVLR: A Toolbox and Benchmark for Visual-Linguistic Causal ReasoningLLM reasoning → Multimodal reasoning
- Provable Robust Watermarking for AI-Generated TextLLM safety and security → Watermarking generated content and models
- Audio Embeddings as Teachers for Music ClassificationKnowledge distillation → Speech and audio distillation
- What is the Title of this Paper? Solving logic puzzles using algorithms
- Online Job Failure Prediction in an HPC System
- Voting-based Multimodal Automatic Deception Detection
- Federated Multi-Agent Deep Reinforcement Learning for Dynamic and Flexible 3D Operation of 5G Multi-MAP Networks
- Of Spiky SVDs and Music Recommendation
- An automated method for the ontological representation of security directives
- AI and Non AI Assessments for Dementia
- Multi-Dialectal Representation Learning of Sinitic Phonology
- Still No Lie Detector for Language Models: Probing Empirical and Conceptual Roadblocks
- Multiscale Progressive Text Prompt Network for Medical Image Segmentation
- The Integer Linear Programming Inference Cookbook
- VoxWatch: An open-set speaker recognition benchmark on VoxCeleb
- U-Calibration: Forecasting for an Unknown Agent
- What Do Self-Supervised Speech Models Know About Words?
- FFPDG: Fast, Fair and Private Data Generation
- The Effect of Balancing Methods on Model Behavior in Imbalanced Classification Problems
- Stitched ViTs are Flexible Vision Backbones
- Large Language Models (GPT) for automating feedback on programming assignments
- Hierarchical Neural Coding for Controllable CAD Model Generation
- Abide by the Law and Follow the Flow: Conservation Laws for Gradient Flows
- BuildingsBench: A Large-Scale Dataset of 900K Buildings and Benchmark for Short-Term Load Forecasting
- Risk-sensitive Actor-free Policy via Convex Optimization
- SMILE: Evaluation and Domain Adaptation for Social Media Language Understanding
- Generalization Limits of Graph Neural Networks in Identity Effects Learning
- iMETRE: Incorporating Markers of Entity Types for Relation Extraction
- Machine learning for advancing low-temperature plasma modeling and simulation
- Information Extraction in Domain and Generic Documents: Findings from Heuristic-based and Data-driven Approaches
- Scalable Bayesian Structure Learning for Gaussian Graphical Models Using Marginal Pseudo-likelihood
- Accelerating Inexact HyperGradient Descent for Bilevel Optimization
- How Do Human Users Teach a Continual Learning Robot in Repeated Interactions?
- An End-to-End Review of Gaze Estimation and its Interactive Applications on Handheld Mobile Devices
- Meta-training with Demonstration Retrieval for Efficient Few-shot Learning
- Goal Representations for Instruction Following: A Semi-Supervised Language Interface to Control
- A Personalized Household Assistive Robot that Learns and Creates New Breakfast Options through Human-Robot Interaction
- Performance of ChatGPT on USMLE: Unlocking the Potential of Large Language Models for AI-Assisted Medical Education
- Ticket-BERT: Labeling Incident Management Tickets with Language Models
- Distance Functions and Normalization Under Stream Scenarios
- Obscured Wildfire Flame Detection By Temporal Analysis of Smoke Patterns Captured by Unmanned Aerial Systems
- Queer People are People First: Deconstructing Sexual Identity Stereotypes in Large Language Models
- Prompting classes: Exploring the Power of Prompt Class Learning in Weakly Supervised Semantic Segmentation
- Redeeming Data Science by Decision Modelling
- A Parts Based Registration Loss for Detecting Knee Joint Areas
- Inter-case Predictive Process Monitoring: A candidate for Quantum Machine Learning?
- Dataset balancing can hurt model performance
- GIRA: Gaussian Mixture Models for Inference and Robot Autonomy
- Transformers in Healthcare: A Survey
- Improving the Transferability of Time Series Forecasting with Decomposition Adaptation
- Qualitative Prediction of Multi-Agent Spatial Interactions
- Situated Cameras, Situated Knowledges: Towards an Egocentric Epistemology for Computer Vision
- Proximal nested sampling with data-driven priors for physical scientists
- Learned harmonic mean estimation of the marginal likelihood with normalizing flows
- DisCo: Disentangled Control for Realistic Human Dance Generation
- Towards Brain Inspired Design for Addressing the Shortcomings of ANNs
- Training-free Object Counting with Prompts
- MARF: The Medial Atom Ray Field Object Representation
- Machine learning for potion development at Hogwarts
- Parameter Identification for Partial Differential Equations with Spatiotemporal Varying Coefficients
- Application of data engineering approaches to address challenges in microbiome data for optimal medical decision-making
- Uncertainty Informed Optimal Resource Allocation with Gaussian Process based Bayesian Inference
- Hardwiring ViT Patch Selectivity into CNNs using Patch Mixing
- The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks
- SPAE: Semantic Pyramid AutoEncoder for Multimodal Generation with Frozen LLMs
- Breaking the Metric Voting Distortion Barrier
- Resetting the Optimizer in Deep RL: An Empirical Study
- Federated Ensemble YOLOv5 -- A Better Generalized Object Detection Algorithm
- On the Cause of Unfairness: A Training Sample Perspective
- Scalable tensor methods for nonuniform hypergraphs
- Act3D: 3D Feature Field Transformers for Multi-Task Robotic Manipulation
- Bayesian Optimization with Formal Safety Guarantees via Online Conformal Prediction
- A Massive Scale Semantic Similarity Dataset of Historical English
- Stay on topic with Classifier-Free Guidance
- Hierarchical Bayesian Regression for Multi-Location Sales Transaction Forecasting
- Vision Through the Veil: Differential Privacy in Federated Learning for Medical Image Classification
- Towards Improving the Performance of Pre-Trained Speech Models for Low-Resource Languages Through Lateral Inhibition
- Precision Anti-Cancer Drug Selection via Neural Ranking
- MTR++: Multi-Agent Motion Prediction with Symmetric Scene Modeling and Guided Intention Querying
- Comparing Reinforcement Learning and Human Learning using the Game of Hidden Rules
- The Shaped Transformer: Attention Models in the Infinite Depth-and-Width Limit
- Should you marginalize over possible tokenizations?
- TD Convergence: An Optimization Perspective
- Discriminatory or Samaritan -- which AI is needed for humanity? An Evolutionary Game Theory Analysis of Hybrid Human-AI populations
- Token-Event-Role Structure-based Multi-Channel Document-Level Event Extraction
- Improved NL2SQL based on Multi-layer Expert Network
- FlipNeRF: Flipped Reflection Rays for Few-shot Novel View Synthesis
- Why Deep Models Often cannot Beat Non-deep Counterparts on Molecular Property Prediction?
All 184
- Beyond Neural-on-Neural Approaches to Speaker Gender Protection
- Exploration and Exploitation of Unlabeled Data for Open-Set Semi-Supervised Learning
- A New Task and Dataset on Detecting Attacks on Human Rights Defenders
- Thompson sampling for improved exploration in GFlowNets
- Generalized Time Warping Invariant Dictionary Learning for Time Series Classification and Clustering
- X-RiSAWOZ: High-Quality End-to-End Multilingual Dialogue Datasets and Few-shot Agents
- Learning Delays in Spiking Neural Networks using Dilated Convolutions with Learnable Spacings
- Zero-shot Nuclei Detection via Visual-Language Pre-trained Models
- Accurate 2D Reconstruction for PET Scanners based on the Analytical White Image Model
- Implicit 3D Human Mesh Recovery using Consistency with Pose and Shape from Unseen-view
- Biomedical Language Models are Robust to Sub-optimal Tokenization
- Enhancing training of physics-informed neural networks using domain-decomposition based preconditioning strategies
- Feature Representation Learning for NL2SQL Generation Based on Coupling and Decoupling
- Federated Object Detection for Quality Inspection in Shared Production
- Neural 3D Scene Reconstruction from Multiple 2D Images without 3D Supervision
- Point-Based Value Iteration for POMDPs with Neural Perception Mechanisms
- Geometric Autoencoders -- What You See is What You Decode
- Achieving RGB-D level Segmentation Performance from a Single ToF Camera
- Navigating Noise: A Study of How Noise Influences Generalisation and Calibration of Neural Networks
- Design of Induction Machines using Reinforcement Learning
- Sphere2Vec: A General-Purpose Location Representation Learning over a Spherical Surface for Large-Scale Geospatial Predictions
- Polarimetric iToF: Measuring High-Fidelity Depth through Scattering Media
- Scalable method for Bayesian experimental design without integrating over posterior distribution
- Mixed Integer Programming for Time-Optimal Multi-Robot Coverage Path Planning with Efficient Heuristics
- S.T.A.R.-Track: Latent Motion Models for End-to-End 3D Object Tracking with Adaptive Spatio-Temporal Appearance Representations
- Navigation of micro-robot swarms for targeted delivery using reinforcement learning
- Razor SNN: Efficient Spiking Neural Network with Temporal Embeddings
- RBSR: Efficient and Flexible Recurrent Network for Burst Super-Resolution
- Miniaturized Graph Convolutional Networks with Topologically Consistent Pruning
- Variational principle to regularize machine-learned density functionals: the non-interacting kinetic-energy functional
- Augmenting Holistic Review in University Admission using Natural Language Processing for Essays and Recommendation Letters
- SpATr: MoCap 3D Human Action Recognition based on Spiral Auto-encoder and Transformer Network
- A Cost-aware Study of Depression Language on Social Media using Topic and Affect Contextualization
- Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting
- Towards the extraction of robust sign embeddings for low resource sign language recognition
- The most likely common cause
- Why does my medical AI look at pictures of birds? Exploring the efficacy of transfer learning across domain boundaries
- Comparative study of subset selection methods for rapid prototyping of 3D object detection algorithms
- TTSWING: a Dataset for Table Tennis Swing Analysis
- DisPlacing Objects: Improving Dynamic Vehicle Detection via Visual Place Recognition under Adverse Conditions
- Locking On: Leveraging Dynamic Vehicle-Imposed Motion Constraints to Improve Visual Localization
- MeLM, a generative pretrained language modeling framework that solves forward and inverse mechanics problems
- GPT-FinRE: In-context Learning for Financial Relation Extraction using Large Language Models
- A behaviouristic approach to representing processes and procedures in the OASIS 2 ontology
- Systematic Investigation of Sparse Perturbed Sharpness-Aware Minimization Optimizer
- Efficient uniform approximation using Random Vector Functional Link networks
- Empirical Interpretation of the Relationship Between Speech Acoustic Context and Emotion Recognition
- The Implicit Bias of Minima Stability in Multivariate Shallow ReLU Networks
- Multigrid-Augmented Deep Learning Preconditioners for the Helmholtz Equation using Compact Implicit Layers
- Detection-segmentation convolutional neural network for autonomous vehicle perception
- Landmark Guided Active Exploration with State-specific Balance Coefficient
- Graphtester: Exploring Theoretical Boundaries of GNNs on Graph Datasets
- Knowledge Base Completion for Long-Tail Entities
- Oblivious Stochastic Composite Optimization
- Manga109Dialog: A Large-scale Dialogue Dataset for Comics Speaker Detection
- MedAugment: Universal Automatic Data Augmentation Plug-in for Medical Image Analysis
- FedBone: Towards Large-Scale Federated Multi-Task Learning
- Color Learning for Image Compression
- Harnessing LLMs in Curricular Design: Using GPT-4 to Support Authoring of Learning Objectives
- GMM: Delving into Gradient Aware and Model Perceive Depth Mining for Monocular 3D Detection
- Correct Like Humans: Progressive Learning Framework for Chinese Text Error Correction
- Designing strong baselines for ternary neural network quantization through support and mass equalization
- Efficient Backdoor Removal Through Natural Gradient Fine-tuning
- STTracker: Spatio-Temporal Tracker for 3D Single Object Tracking
- Defense against Adversarial Cloud Attack on Remote Sensing Salient Object Detection
- ReLU Neural Networks, Polyhedral Decompositions, and Persistent Homolog
- Decentralized Motor Skill Learning for Complex Robotic Systems
- LMBot: Distilling Graph Knowledge into Language Model for Graph-less Deployment in Twitter Bot Detection
- QuAVF: Quality-aware Audio-Visual Fusion for Ego4D Talking to Me Challenge
- Topological Data Analysis Guided Segment Anything Model Prompt Optimization for Zero-Shot Segmentation in Biological Imaging
- Japanese Lexical Complexity for Non-Native Readers: A New Dataset
- Koopman operator learning using invertible neural networks
- EyeBAG: Accurate Control of Eye Blink and Gaze Based on Data Augmentation Leveraging Style Mixing
- SummQA at MEDIQA-Chat 2023:In-Context Learning with GPT-4 for Medical Summarization
- Global Optimality in Bivariate Gradient-based DAG Learning
- HVTSurv: Hierarchical Vision Transformer for Patient-Level Survival Prediction from Whole Slide Image
- Capturing functional connectomics using Riemannian partial least squares
- Differential Privacy May Have a Potential Optimization Effect on Some Swarm Intelligence Algorithms besides Privacy-preserving
- Spatially Varying Exposure with 2-by-2 Multiplexing: Optimality and Universality
- λ-models: Effective Decision-Aware Reinforcement Learning with Latent Models
- Improving Federated Aggregation with Deep Unfolding Networks
- iSCAN: Identifying Causal Mechanism Shifts among Nonlinear Additive Noise Models
- Shadow Generation with Decomposed Mask Prediction and Attentive Shadow Filling
- Shortest Length Total Orders Do Not Minimize Irregularity in Vector-Valued Mathematical Morphology