Papers
Wed 8 Nov 2023
196 papers
- Frontier Language Models are not Robust to Adversarial Arithmetic, or "What do I need to say so you agree 2+2=5?LLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks
- ADaPT: As-Needed Decomposition and Planning with Language ModelsLLM reasoning → Reasoning for agents, planning and code
- Leveraging Speculative Sampling and KV-Cache Optimizations Together for Generative AI using OpenVINOEfficient LLM inference and serving → Speculative decoding
- Lightweight Diffusion Models with Distillation-Based Block Neural Architecture SearchDiffusion models → Diffusion foundations and sampling
- Improved DDIM Sampling with Moment Matching Gaussian MixturesDiffusion models → Diffusion foundations and sampling
- GENOME: GenerativE Neuro-symbOlic visual reasoning by growing and reusing ModulEsLLM reasoning → Multimodal reasoning
- DAMEX: Dataset-aware Mixture-of-Experts for visual understanding of mixture-of-datasetsMixture-of-experts → Vision mixture-of-experts
- Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMsLLM reasoning → Reasoning benchmarks and evaluation
- Rethinking Benchmark and Contamination for Language Models with Rephrased SamplesLLM reasoning → Reasoning benchmarks and evaluation
- MTGER: Multi-view Temporal Graph Enhanced Temporal Reasoning over Time-Involved DocumentLLM reasoning → Knowledge- and tool-augmented reasoning
- Social Motion Prediction with Cognitive HierarchiesOffline RL and imitation learning from data → Social robot navigation
- Diff-HierVC: Diffusion-based Hierarchical Voice Conversion with Robust Pitch Generation and Masked Prior for Zero-shot Speaker AdaptationDiffusion models → Audio, speech and music
- Pragmatic Reasoning Unlocks Quantifier Semantics for Foundation ModelsLLM reasoning → Reasoning benchmarks and evaluation
- TEAL: Tokenize and Embed ALL for Multi-modal Large Language ModelsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
- Weakly-supervised deepfake localization in diffusion-generated imagesDiffusion models → Image generation, text-to-image and editing
- NExT-Chat: An LMM for Chat, Detection and SegmentationMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- UAV Trajectory Planning for AoI-Minimal Data Collection in UAV-Aided IoT Networks by Transformer
- GeoTop: Advancing Image Classification with Geometric-Topological Analysis
- Deep Learning-Based Frequency Offset Estimation
- NLQxform: A Language Model-based Question to SPARQL Transformer
- Synthetic Speaking Children -- Why We Need Them and How to Make Them
- A Systematic Review on Fostering Appropriate Trust in Human-AI Interaction
- Retro-BLEU: Quantifying Chemical Plausibility of Retrosynthesis Routes through Reaction Template Sequence Analysis
- On Mergable Coresets for Polytope Distance
- Learning to Configure Separators in Branch-and-Cut
- Efficient Compression of Overparameterized Deep Models through Low-Dimensional Learning Dynamics
- Geometry-Calibrated DRO: Combating Over-Pessimism with Free Energy Implications
- Deep Learning Brasil at ABSAPT 2022: Portuguese Transformer Ensemble Approaches
- Sequential learning on a Tensor Network Born machine with Trainable Token Embedding
- DeepLearningBrasil@LT-EDI-2023: Exploring Deep Learning Techniques for Detecting Depression in Social Media Text
- On the Consistency of Maximum Likelihood Estimation of Probabilistic Principal Component Analysis
- Zero-shot Translation of Attention Patterns in VQA Models to Natural Language
- Automated Annotation of Scientific Texts for ML-based Keyphrase Extraction and Validation
- Active Transfer Learning for Efficient Video-Specific Human Pose Estimation
- Transfer learning from a sparsely annotated dataset of 3D medical images
- S3AD: Semi-supervised Small Apple Detection in Orchard Environments
- Unbiased Kinetic Langevin Monte Carlo with Inexact Gradients
- Leveraging a realistic synthetic database to learn Shape-from-Shading for estimating the colon depth in colonoscopy images
- First Tragedy, then Parse: History Repeats Itself in the New Era of Large Language Models
- DEMASQ: Unmasking the ChatGPT Wordsmith
- Towards Effective Paraphrasing for Information Disguise
- Joint Sensing and Semantic Communications with Multi-Task Deep Learning
- Interpreting Pretrained Language Models via Concept Bottlenecks
- Consensus-based adaptive sampling and approximation for high-dimensional energy landscapes
- Familiarity-Based Open-Set Recognition Under Adversarial Attacks
- GPU-Accelerated WFST Beam Search Decoder for CTC-based Speech Recognition
- Effective Restoration of Source Knowledge in Continual Test Time Adaptation
- Exploiting Inductive Biases in Video Modeling through Neural CDEs
- On the steerability of large language models toward data-driven personas
- Expressibility-induced Concentration of Quantum Neural Tangent Kernels
- Prompt Sketching for Large Language Models
- Explained anomaly detection in text reviews: Can subjective scenarios be correctly evaluated?
- Causal Inference on Investment Constraints and Non-stationarity in Dynamic Portfolio Optimization through Reinforcement Learning
- Auto deep learning for bioacoustic signals
- Edge-assisted U-Shaped Split Federated Learning with Privacy-preserving for Internet of Things
- MathNAS: If Blocks Have a Role in Mathematical Architecture Design
- CSAM: A 2.5D Cross-Slice Attention Module for Anisotropic Volumetric Medical Image Segmentation
- Interpretable Geoscience Artificial Intelligence (XGeoS-AI): Application to Demystify Image Recognition
- LooGLE: Can Long-Context Language Models Understand Long Contexts?
- Beyond Size: How Gradients Shape Pruning Decisions in Large Language Models
- How Abstract Is Linguistic Generalization in Large Language Models? Experiments with Argument Structure
- Two Complementary Perspectives to Continual Learning: Ask Not Only What to Optimize, But Also How
- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State
- Machine-learning optimized measurements of chaotic dynamical systems via the information bottleneck
- Towards Few-Annotation Learning in Computer Vision: Application to Image Classification and Object Detection tasks
- SEMQA: Semi-Extractive Multi-Source Question Answering
- Profiling Irony & Stereotype: Exploring Sentiment, Topic, and Lexical Features
- LongQLoRA: Efficient and Effective Method to Extend Context Length of Large Language Models
- Computing with Residue Numbers in High-Dimensional Representation
- Algorithms for Non-Negative Matrix Factorization on Noisy Data With Negative Values
- Are foundation models efficient for medical image segmentation?
- Incorporating temporal dynamics of mutations to enhance the prediction capability of antiretroviral therapy's outcome for HIV-1
- Bridging Dimensions: Confident Reachability for High-Dimensional Controllers
- Toward Rapid, Optimal, and Feasible Power Dispatch through Generalized Neural Mapping
- Identifying Semantic Component for Robust Molecular Property Prediction
- Self-Supervised Learning for Visual Relationship Detection through Masked Bounding Box Reconstruction
- Anonymizing medical case-based explanations through disentanglement
- Real-Time Recurrent Reinforcement Learning
- Functional Bayesian Tucker Decomposition for Continuous-indexed Tensor Data
- SODAWideNet -- Salient Object Detection with an Attention augmented Wide Encoder Decoder network without ImageNet pre-training
- Hierarchically Gated Recurrent Neural Network for Sequence Modeling
- Cross-Silo Federated Learning Across Divergent Domains with Iterative Parameter Alignment
- Decentralized Personalized Online Federated Learning
- Domain Adaptive Object Detection via Balancing Between Self-Training and Adversarial Learning
- Be Careful When Evaluating Explanations Regarding Ground Truth
- Image-Based Virtual Try-On: A Survey
- A Lightweight Architecture for Real-Time Neuronal-Spike Classification
- The PetShop Dataset -- Finding Causes of Performance Issues across Microservices
- DA-Cramming: Enhancing Cost-Effective Language Model Pretraining with Dependency Agreement Integration
- Determination of toxic comments and unintended model bias minimization using Deep learning approach
- Why Do Probabilistic Clinical Models Fail To Transport Between Sites?
- VioLA: Aligning Videos to 2D LiDAR Scans
- FetMRQC: a robust quality control system for multi-centric fetal brain MRI
- Optimal Deep Neural Network Approximation for Korobov Functions with respect to Sobolev Norms
- On the Multiple Roles of Ontologies in Explainable AI
- Lidar Annotation Is All You Need
- Towards a Unified Framework of Contrastive Learning for Disentangled Representations
- GCS-ICHNet: Assessment of Intracerebral Hemorrhage Prognosis using Self-Attention with Domain Knowledge Integration
- Vital Sign Forecasting for Sepsis Patients in ICUs
- An attention-based deep learning network for predicting Platinum resistance in ovarian cancer
All 196
- DualTalker: A Cross-Modal Dual Learning Approach for Speech-Driven 3D Facial Animation
- The voraus-AD Dataset for Anomaly Detection in Robot Applications
- Towards Open-world Cross-Domain Sequential Recommendation: A Model-Agnostic Contrastive Denoising Approach
- Intrinsic Bayesian Cram'er-Rao Bound with an Application to Covariance Matrix Estimation
- Euclidean, Projective, Conformal: Choosing a Geometric Algebra for Equivariant Transformers
- Large-scale study of human memory for meaningful narratives
- Enhancing Multi-Agent Coordination through Common Operating Picture Integration
- Robust Best-arm Identification in Linear Bandits
- Predicting Properties of Nodes via Community-Aware Features
- Training CLIP models on Data from Scientific Papers
- The Quest for Content: A Survey of Search-Based Procedural Content Generation for Video Games
- 3D Pose Estimation of Tomato Peduncle Nodes using Deep Keypoint Detection and Point Cloud
- Examining Common Paradigms in Multi-Task Learning
- Evaluating Generative Ad Hoc Information Retrieval
- Robust and Communication-Efficient Federated Domain Adaptation via Random Features
- Weakly supervised cross-modal learning in high-content screening
- Compressive Recovery of Sparse Precision Matrices
- Pre-training LLMs using human-like development data corpus
- Speech language models lack important brain-relevant semantics
- Massive Editing for Large Language Models via Meta Learning
- Hybrid Focal and Full-Range Attention Based Graph Transformers
- SKU-Patch: Towards Efficient Instance Segmentation for Unseen Objects in Auto-Store
- Object-Centric Learning with Slot Mixture Module
- Learning Linear Gaussian Polytree Models with Interventions
- VET: Visual Error Tomography for Point Cloud Completion and High-Quality Neural Rendering
- General Framework to Evaluate Unlinkability in Biometric Template Protection Systems
- Image Patch-Matching with Graph-Based Learning in Street Scenes
- LuminanceL1Loss: A loss function which measures percieved brightness and colour differences
- Byzantine-Tolerant Methods for Distributed Variational Inequalities
- Accurate Autism Spectrum Disorder prediction using Support Vector Classifier based on Federated Learning (SVCFL)
- Asynchronous Message-Passing and Zeroth-Order Optimization Based Distributed Learning with a Use-Case in Resource Allocation in Communication Networks
- A Deep Learning Based Resource Allocator for Communication Networks with Dynamic User Utility Demands
- Explainable artificial intelligence model for identifying Market Value in Professional Soccer Players
- On Characterizing the Evolution of Embedding Space of Neural Networks using Algebraic Topology
- Exploring Event-based Human Pose Estimation with 3D Event Representations
- Army of Thieves: Enhancing Black-Box Model Extraction via Ensemble based sample selection
- Deep learning as a tool for quantum error reduction in quantum image processing
- GResilience: Trading Off Between the Greenness and the Resilience of Collaborative AI Systems
- Investigating the Nature of Disagreements on Mid-Scale Ratings: A Case Study on the Abstractness-Concreteness Continuum
- CAIS-DMA: A Decision-Making Assistant for Collaborative AI Systems
- Information-Theoretic Generalization Bounds for Transductive Learning and its Applications
- Assessing Distractors in Multiple-Choice Tests
- A 3D generative model of pathological multi-modal MR images and segmentations
- Regression with Cost-based Rejection
- Large GPT-like Models are Bad Babies: A Closer Look at the Relationship between Linguistic Competence and Psycholinguistic Measures
- Local Differential Privacy for Smart Meter Data Sharing
- FEIR: Quantifying and Reducing Envy and Inferiority for Fair Recommendation of Limited Resources
- On the estimation of the number of components in multivariate functional principal component analysis
- Deep Learning Assisted Multiuser MIMO Load Modulated Systems for Enhanced Downlink mmWave Communications
- RankAug: Augmented data ranking for text classification
- Loss Masking Is Not Needed in Decoder-only Transformer for Discrete-token-based ASR
- An Unsupervised Deep Learning Approach for the Wave Equation Inverse Problem
- Bandit Learning to Rank with Position-Based Click Models: Personalized and Equal Treatments
- Validating ChatGPT Facts through RDF Knowledge Graphs and Sentence Similarity
- Long-term Time Series Forecasting based on Decomposition and Neural Ordinary Differential Equations
- Learning Robust Multi-Scale Representation for Neural Radiance Fields from Unposed Images
- Adaptive Mirror Descent Bilevel Optimization
- Towards Democratizing AI: A Comparative Analysis of AI as a Service Platforms and the Open Space for Machine Learning Approach
- High-Performance Hybrid Algorithm for Minimum Sum-of-Squares Clustering of Infinitely Tall Data
- FFINet: Future Feedback Interaction Network for Motion Forecasting
- Solution of FPK Equation for Stochastic Dynamics Subjected to Additive Gaussian Noise via Deep Learning Approach
- Learning Discriminative Features for Crowd Counting
- Conversation Understanding using Relational Temporal Graph Neural Networks with Auxiliary Cross-Modality Interaction
- NITEC: Versatile Hand-Annotated Eye Contact Dataset for Ego-Vision Interaction
- Constrained Adaptive Attacks: Realistic Evaluation of Adversarial Examples and Robust Training of Deep Neural Networks for Tabular Data
- PRED: Pre-training via Semantic Rendering on LiDAR Point Clouds
- PersonMAE: Person Re-Identification Pre-Training with Masked AutoEncoders
- Multi-label and Multi-target Sampling of Machine Annotation for Computational Stance Detection
- Non-Rigid Shape Registration via Deep Functional Maps Prior
- Explainable AI for Earth Observation: Current Methods, Open Challenges, and Opportunities
- CLearViD: Curriculum Learning for Video Description
- Twitter Sentiment Analysis of Covid Vacciness
- Emergent Communication for Rules Reasoning
- All-Optical Phase Conjugation Using Diffractive Wavefront Processing
- Autonomous Advanced Aerial Mobility -- An End-to-end Autonomy Framework for UAVs and Beyond
- RDGCN: Reinforced Dependency Graph Convolutional Network for Aspect-based Sentiment Analysis
- Solving High Frequency and Multi-Scale PDEs with Gaussian Processes
- Enhancing Few-shot CLIP with Semantic-Aware Fine-Tuning
- Improving Pacing in Long-Form Story Planning
- Retargeting video with an end-to-end framework
- Evaluating Uncertainty Quantification approaches for Neural PDEs in scientific applications
- Lewis's Signaling Game as beta-VAE For Natural Word Lengths and Segments
- Recursion in Recursion: Two-Level Nested Recursion for Length Generalization with Scalability
- SS-MAE: Spatial-Spectral Masked Auto-Encoder for Multi-Source Remote Sensing Image Classification
- MixTEA: Semi-supervised Entity Alignment with Mixture Teaching
- A Hierarchical Spatial Transformer for Massive Point Samples in Continuous Space
- Blurry Video Compression: A Trade-off between Visual Enhancement and Data Compression
- Data Factors for Better Compositional Generalization
- PepLand: a large-scale pre-trained peptide representation model for a comprehensive landscape of both canonical and non-canonical amino acids
- AI-accelerated Discovery of Altermagnetic Materials
- Evaluating Emerging AI/ML Accelerators: IPU, RDU, and NVIDIA/AMD GPUs
- Learning the What and How of Annotation in Video Object Segmentation
- Human Conditional Reasoning in Answer Set Programming
- Human-Centered Planning
- Likelihood Ratio Confidence Sets for Sequential Decision Making
- LRM: Large Reconstruction Model for Single Image to 3D