Papers
Sat 28 Oct 2023
135 papers
- Bird's Eye View Based Pretrained World model for Visual NavigationWorld models → World models for navigation
- Customizing 360-Degree Panoramas through Text-to-Image Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
- Successfully Applying Lottery Ticket Hypothesis to Diffusion ModelDiffusion models → Diffusion foundations and sampling
- The Synergy of Speculative Decoding and Batching in Serving Large Language ModelsEfficient LLM inference and serving → Speculative decoding
- OC-NMN: Object-centric Compositional Neural Module Network for Generative Visual Analogical ReasoningLLM reasoning → Multimodal reasoning
- Are NLP Models Good at Tracing Thoughts: An Overview of Narrative UnderstandingLLM reasoning → Reasoning benchmarks and evaluation
- Purify++: Improving Diffusion-Purification with Advanced Diffusion Models and Control of RandomnessDiffusion models → Robustness, privacy and adversarial aspects
- Robust Offline Reinforcement learning with Heavy-Tailed RewardsOffline RL and imitation learning from data → Offline RL algorithms
- Unsupervised Behavior Extraction via Random Intent PriorsOffline RL and imitation learning from data → Offline RL algorithms
- Efficient Object Detection in Optical Remote Sensing Imagery via Attention-based Feature DistillationKnowledge distillation → Detection and dense prediction distillation
- DetermLR: Augmenting LLM-based Logical Reasoning from Indeterminacy to DeterminacyLLM reasoning → Reasoning benchmarks and evaluation
- One-shot Localization and Segmentation of Medical Images with Foundation ModelsDiffusion models → Medical imaging and segmentation
- Switching Temporary Teachers for Semi-Supervised Semantic SegmentationKnowledge distillation → Detection and dense prediction distillation
- Setting the Trap: Capturing and Defeating Backdoors in Pretrained Language Models through HoneypotsLLM safety and security → Backdoor and data poisoning attacks
- Personalised Distillation: Empowering Open-Sourced LLMs with Adaptive Learning for Code GenerationKnowledge distillation → Knowledge distillation for LLMs
- Large Language Models Are Better Adversaries: Exploring Generative Clean-Label Backdoor Attacks Against Text ClassifiersLLM safety and security → Backdoor and data poisoning attacks
- Accelerating LLaMA Inference by Enabling Intermediate Layer Decoding via Instruction Tuning with LITEEfficient LLM inference and serving → Early exit and edge inference
- Breaking the Trilemma of Privacy, Utility, Efficiency via Controllable Machine UnlearningLLM safety and security → Machine unlearning
- Vision-Based Incoming Traffic Estimator Using Deep Neural Network on General Purpose Embedded Hardware
- Emotion-Oriented Behavior Model Using Deep Learning
- LLMs-Healthcare : Current Applications and Challenges of Large Language Models in various Medical Specialties
- Explaining by Imitating: Understanding Decisions by Interpretable Policy Learning
- GalliformeSpectra: A Hen Breed Dataset
- AI for Open Science: A Multi-Agent Perspective for Ethically Translating Data to Knowledge
- Exploring Data Augmentations on Self-/Semi-/Fully- Supervised Pre-trained Models
- Deep Learning-based Compressed Domain Multimedia for Man and Machine: A Taxonomy and Application to Point Cloud Classification
- INCODE: Implicit Neural Conditioning with Prior Knowledge Embeddings
- BanditPAM++: Faster k-medoids Clustering
- A randomized algorithm for nonconvex minimization with inexact evaluations and complexity guarantees
- Automating the Correctness Assessment of AI-generated Code for Security Contexts
- Responsible AI (RAI) Games and Ensembles
- Translating away Translationese without Parallel Data
- All Things Considered: Detecting Partisan Events from News Media with Cross-Article Comparison
- A Fuzzy Time Series-Based Model Using Particle Swarm Optimization and Weighted Rules
- Intrinsic Gaussian Vector Fields on Manifolds
- Adaptive Test-Time Personalization for Federated Learning
- Rethinking Semi-Supervised Federated Learning: How to co-train fully-labeled and fully-unlabeled client imaging data
- Stability of Random Forests and Coverage of Random-Forest Prediction Intervals
- UniCat: Crafting a Stronger Fusion Baseline for Multimodal Re-Identification
- Hierarchical Framework for Interpretable and Probabilistic Model-Based Safe Reinforcement Learning
- Inverse distance weighting attention
- Open Visual Knowledge Extraction via Relation-Oriented Multimodality Model Prompting
- Weakly Coupled Deep Q-Networks
- A Review on the Applications of Machine Learning for Tinnitus Diagnosis Using EEG Signals
- Sequence-Level Certainty Reduces Hallucination In Knowledge-Grounded Dialogue Generation
- "Do it my way!": Impact of Customizations on Trust perceptions in Human-Robot Collaboration
- PrObeD: Proactive Object Detection Wrapper
- A Competitive Algorithm for Agnostic Active Learning
- High-probability Convergence Bounds for Nonlinear Stochastic Gradient Descent Under Heavy-tailed Noise
- Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions
- ProMap: Effective Bilingual Lexicon Induction via Language Model Prompting
- Improving Compositional Generalization Using Iterated Learning and Simplicial Embeddings
- Reflection coupling for unadjusted generalized Hamiltonian Monte Carlo in the nonconvex stochastic gradient case
- CityRefer: Geography-aware 3D Visual Grounding Dataset on City-scale Point Cloud Data
- A Data-driven Recommendation Framework for Optimal Walker Designs
- Linear Mode Connectivity in Sparse Neural Networks
- Crossing the Aisle: Unveiling Partisan and Counter-Partisan Events in News Reporting
- Rethinking Semi-Supervised Imbalanced Node Classification from Bias-Variance Decomposition
- Reboost Large Language Model-based Text-to-SQL, Text-to-Python, and Text-to-Function -- with Real Applications in Traffic Domain
- Optimization of utility-based shortfall risk: A non-asymptotic viewpoint
- On Training Implicit Meta-Learning With Applications to Inductive Weighing in Consistency Regularization
- TLM: Token-Level Masking for Transformers
- Pre-training with Random Orthogonal Projection Image Modeling
- Curriculum Learning for Graph Neural Networks: Which Edges Should We Learn First
- Using Large Language Models to Support Thematic Analysis in Empirical Legal Studies
- Debunking Free Fusion Myth: Online Multi-view Anomaly Detection with Disentangled Product-of-Experts Modeling
- Latent class analysis by regularized spectral clustering
- The Evolution of the Interplay Between Input Distributions and Linear Regions in Networks
- WCLD: Curated Large Dataset of Criminal Cases from Wisconsin Circuit Courts
- On the Accuracy of Hotelling-Type Asymmetric Tensor Deflation: A Random Tensor Analysis
- Laplacian Canonization: A Minimalist Approach to Sign and Basis Invariant Spectral Embedding
- An Investigation of Darwiche and Pearl's Postulates for Iterated Belief Update
- Episodic Multi-Task Learning with Heterogeneous Neural Processes
- Audio-Visual Instance Segmentation
- ALERTA-Net: A Temporal Distance-Aware Recurrent Networks for Stock Movement and Volatility Prediction
- Towards Combinatorial Generalization for Catalysts: A Kohn-Sham Charge-Density Approach
- Efficient Algorithms for Generalized Linear Bandits with Heavy-tailed Rewards
- Triplet Attention Transformer for Spatiotemporal Predictive Learning
- Probing LLMs for Joint Encoding of Linguistic Categories
- Foundational Models in Medical Imaging: A Comprehensive Survey and Future Vision
- Clairvoyance: A Pipeline Toolkit for Medical Time Series
- When Reviewers Lock Horn: Finding Disagreement in Scientific Peer Reviews
- DySurv: dynamic deep learning model for survival analysis with conditional variational inference
- N-Critics: Self-Refinement of Large Language Models with Ensemble of Critics
- Energy-Based Models for Anomaly Detection: A Manifold Diffusion Recovery Approach
- Maximum Independent Set: Self-Training through Dynamic Programming
- FinBTech: Blockchain-Based Video and Voice Authentication System for Enhanced Security in Financial Transactions Utilizing FaceNet512 and Gaussian Mixture Models
- ASTormer: An AST Structure-aware Transformer Decoder for Text-to-SQL
- Foundation Models for Generalist Geospatial Artificial Intelligence
- Med-DANet V2: A Flexible Dynamic Architecture for Efficient Medical Volumetric Segmentation
- Causal discovery in a complex industrial system: A time series benchmark
- Feature Guided Masked Autoencoder for Self-supervised Learning in Remote Sensing
- EHRXQA: A Multi-Modal Question Answering Dataset for Electronic Health Records with Chest X-ray Images
- Patch-Wise Self-Supervised Visual Representation Learning: A Fine-Grained Approach
- Sleep Deprivation in the Forward-Forward Algorithm
- Predicting Agricultural Commodities Prices with Machine Learning: A Review of Current Research
- Towards Plastic and Stable Exemplar-Free Incremental Learning: A Dual-Learner Framework with Cumulative Parameter Averaging
- Electrical Impedance Tomography: A Fair Comparative Study on Deep Learning and Analytic-based Approaches
- SSL Framework for Causal Inconsistency between Structures and Representations
- Explainable Modeling for Wind Power Forecasting: A Glass-Box Approach with High Accuracy
All 135
- Benchmark Generation Framework with Customizable Distortions for Image Classifier Robustness
- Arbitrarily Scalable Environment Generators via Neural Cellular Automata
- ODM3D: Alleviating Foreground Sparsity for Semi-Supervised Monocular 3D Object Detection
- Dense Retrieval as Indirect Supervision for Large-space Decision Making
- Pessimistic Off-Policy Multi-Objective Optimization
- Temporally Disentangled Representation Learning under Unknown Nonstationarity
- Hierarchical Mutual Information Analysis: Towards Multi-view Clustering in The Wild
- Efficient kernel surrogates for neural network-based regression
- Embedding in Recommender Systems: A Survey
- Where have you been? A Study of Privacy Risk for Point-of-Interest Recommendation
- TorchDEQ: A Library for Deep Equilibrium Models
- Anaphor Assisted Document-Level Relation Extraction
- Online Decision Mediation
- MILDSum: A Novel Benchmark Dataset for Multilingual Summarization of Indian Legal Case Judgments
- Domain Generalisation via Risk Distribution Matching
- Fair Streaming Principal Component Analysis: Statistical and Algorithmic Viewpoint
- Inverse Decision Modeling: Learning Interpretable Representations of Behavior
- Using Early Readouts to Mediate Featural Bias in Distillation
- This Looks Like Those: Illuminating Prototypical Concepts Using Multiple Visualizations
- Optimal Transport for Kernel Gaussian Mixture Models
- Visual Explanations via Iterated Integrated Attributions
- Self-Supervised Multi-Modality Learning for Multi-Label Skin Lesion Classification
- A General Framework for Robust G-Invariance in G-Equivariant Networks
- Optimization-Free Test-Time Adaptation for Cross-Person Activity Recognition
- Group Robust Classification Without Any Group Information
- Improved Regret Bounds of (Multinomial) Logistic Bandits via Regret-to-Confidence-Set Conversion
- The Role of Reference Points in Machine-Learned Atomistic Simulation Models
- MultiScale Spectral-Spatial Convolutional Transformer for Hyperspectral Image Classification
- Deep Intrinsic Decomposition with Adversarial Learning for Hyperspectral Image Classification
- MEDAVET: Traffic Vehicle Anomaly Detection Mechanism based on spatial and temporal structures in vehicle traffic
- Punica: Multi-Tenant LoRA Serving
- Identifying Conspiracy Theories News based on Event Relation Graph
- Discourse Structures Guided Fine-grained Propaganda Identification
- End-to-end Feature Selection Approach for Learning Skinny Trees
- ReConTab: Regularized Contrastive Representation Learning for Tabular Data