Papers
Sat 27 May 2023
165 papers
- Knowledge Distillation Performs Partial Variance ReductionKnowledge distillation → General knowledge distillation methods
- PuMer: Pruning and Merging Tokens for Efficient Vision Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
- Backdooring Neural Code SearchLLM safety and security → Backdoor and data poisoning attacks
- The Curse of Recursion: Training on Generated Data Makes Models ForgetDiffusion models → Discrete and text diffusion +1
- FERMAT: An Alternative to Accuracy for Numerical ReasoningLLM reasoning → Mathematical reasoning
- Text-to-image Editing by Image Information RemovalDiffusion models → Image generation, text-to-image and editing
- A Diffusion Model for Event Skeleton GenerationDiffusion models → Flow matching, time series and science
- CrossGET: Cross-Guided Ensemble of Tokens for Accelerating Vision-Language TransformersMultimodal LLMs / vision-language models → Visual token pruning and efficiency
- Query-Efficient Black-Box Red Teaming via Bayesian OptimizationLLM safety and security → Prompt injection and agent security
- Creating Personalized Synthetic Voices from Post-Glossectomy Speech with Guided Diffusion ModelsDiffusion models → Audio, speech and music
- Towards Consistent Video Editing with Text-to-Image Diffusion ModelsDiffusion models → Video generation
- Accelerating Text-to-Image Editing via Cache-Enabled Sparse Diffusion InferenceDiffusion models → Image generation, text-to-image and editing
- FoPro-KD: Fourier Prompted Effective Knowledge Distillation for Long-Tailed Medical Image RecognitionKnowledge distillation → Distillation for medical imaging
- One-Step Knowledge Distillation and Fine-Tuning in Using Large Pre-Trained Self-Supervised Learning Models for Speaker VerificationKnowledge distillation → Speech and audio distillation
- SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive TasksLLM reasoning → Reasoning for agents, planning and code +1
- Vision Transformers for Small Histological Datasets Learned through Knowledge DistillationKnowledge distillation → Distillation for medical imaging
- MADiff: Offline Multi-agent Learning with Diffusion ModelsDiffusion models → Diffusion and flow policies for robotics +1
- Zero-TPrune: Zero-Shot Token Pruning through Leveraging of the Attention Graph in Pre-Trained TransformersEfficient LLM inference and serving → Token pruning and merging for ViTs
- Bayesian Spike Train Inference via Non-Local Priors
- PotatoPestNet: A CTInceptionV3-RS-Based Neural Network for Accurate Identification of Potato Pests
- Cheating off your neighbors: Improving activity recognition through corroboration
- Adversarial Attack On Yolov5 For Traffic And Road Sign Detection
- Decom--CAM: Tell Me What You See, In Details! Feature-Level Interpretation via Decomposition Class Activation Map
- Optimization for truss design using Bayesian optimization
- Rapid Plug-in Defenders
- A Two-Stage Decoder for Efficient ICD Coding
- Inter Subject Emotion Recognition Using Spatio-Temporal Features From EEG Signal
- MLOps: A Step Forward to Enterprise Machine Learning
- Observation Denoising in CYRUS Soccer Simulation 2D Team For RoboCup 2023
- A Telecare System for Use in Traditional Persian Medicine
- Exploring the Practicality of Generative Retrieval on Dynamic Corpora
- Assumption Generation for the Verification of Learning-Enabled Autonomous Systems
- ColibriUAV: An Ultra-Fast, Energy-Efficient Neuromorphic Edge Processing UAV-Platform with Event-Based and Frame-Based Cameras
- Explainable Brain Age Prediction using coVariance Neural Networks
- Using VGG16 Algorithms for classification of lung cancer in CT scans Image
- What can Large Language Models do in chemistry? A comprehensive benchmark on eight tasks
- Towards Explainable Conversational Recommender Systems
- Statistically Significant Concept-based Explanation of Image Classifiers via Model Knockoffs
- Deep learning network to correct axial and coronal eye motion in 3D OCT retinal imaging
- Python Wrapper for Simulating Multi-Fidelity Optimization on HPO Benchmarks without Any Wait
- Data Minimization at Inference Time
- Approximation-Generalization Trade-offs under (Approximate) Group Equivariance
- Integrating Action Knowledge and LLMs for Task Planning and Situation Handling in Open Worlds
- Graph Inductive Biases in Transformers without Message Passing
- Diagnosing Transformers: Illuminating Feature Spaces for Clinical Decision-Making
- On Neural Networks as Infinite Tree-Structured Probabilistic Graphical Models
- ArPanEmo: An Open-Source Dataset for Fine-Grained Emotion Recognition in Arabic Online Content during COVID-19 Pandemic
- Counterfactual Formulation of Patient-Specific Root Causes of Disease
- Auditing Fairness by Betting
- Collaborative Multi-Agent Video Fast-Forwarding
- Scalable Primal-Dual Actor-Critic Method for Safe Multi-Agent RL with General Utilities
- Self-Supervised Learning of Action Affordances as Interaction Modes
- Federated Conformal Predictors for Distributed Uncertainty Quantification
- Grounding Characters and Places in Narrative Texts
- Scalable Transformer for PDE Surrogate Modeling
- Pruning at Initialization -- A Sketching Perspective
- Provably Fast Finite Particle Variants of SVGD via Virtual Particle Stochastic Approximation
- Fair Clustering via Hierarchical Fair-Dirichlet Process
- Diffeomorphic Mesh Deformation via Efficient Optimal Transport for Cortical Surface Reconstruction
- Detecting Edit Failures In Large Language Models: An Improved Specificity Benchmark
- Online Nonstochastic Model-Free Reinforcement Learning
- Translatotron 3: Speech to Speech Translation with Monolingual Data
- Faster Margin Maximization Rates for Generic and Adversarially Robust Optimization Methods
- Non-Sequential Graph Script Induction via Multimedia Grounding
- Learning from Children: Improving Image-Caption Pretraining via Curriculum
- Modeling Dynamic Environments with Scene Graph Memory
- PFNs4BO: In-Context Learning for Bayesian Optimization
- Unsupervised Selective Rationalization with Noise Injection
- Probing reaction channels via reinforcement learning
- MeetingBank: A Benchmark Dataset for Meeting Summarization
- Two Heads are Actually Better than One: Towards Better Adversarial Robustness via Transduction and Rejection
- Computing a partition function of a generalized pattern-based energy over a semiring
- A Comparative Analysis of Portfolio Optimization Using Mean-Variance, Hierarchical Risk Parity, and Reinforcement Learning Approaches on the Indian Stock Market
- Deep Learning based Fingerprint Presentation Attack Detection: A Comprehensive Survey
- USIM-DAL: Uncertainty-aware Statistical Image Modeling-based Dense Active Learning for Super-resolution
- Synthesizing a Progression of Subtasks for Block-Based Visual Programming Tasks
- A Hybrid Quantum-Classical Approach based on the Hadamard Transform for the Convolutional Layer
- CIF-PT: Bridging Speech and Text Representations for Spoken Language Understanding via Continuous Integrate-and-Fire Pre-Training
- A Model-Based Method for Minimizing CVaR and Beyond
- FACTUAL: A Benchmark for Faithful and Consistent Textual Scene Graph Parsing
- Dynamic User Segmentation and Usage Profiling
- The Implicit Regularization of Dynamical Stability in Stochastic Gradient Descent
- Federated Empirical Risk Minimization via Second-Order Method
- A Match Made in Heaven: A Multi-task Framework for Hyperbole and Metaphor Detection
- Inferring Individual Direct Causal Effects Under Heterogeneous Peer Influence
- Deep Variational Lesion-Deficit Mapping
- BASED: Benchmarking, Analysis, and Structural Estimation of Deblurring
- Toward Understanding Generative Data Augmentation
- A Comprehensive Overview and Comparative Analysis on Deep Learning Models: CNN, RNN, LSTM, GRU
- Structured model selection via ℓ1-ℓ2 optimization
- Optimization's Neglected Normative Commitments
- Pentagon-Match (PMatch): Identification of View-Invariant Planar Feature for Local Feature Matching-Based Homography Estimation
- Financial misstatement detection: a realistic evaluation
- Trustworthy Deep Learning for Medical Image Segmentation
- Analysis over vision-based models for pedestrian action anticipation
- FishEye8K: A Benchmark and Dataset for Fisheye Camera Object Detection
- Measuring Your ASTE Models in The Wild: A Diversified Multi-domain Dataset For Aspect Sentiment Triplet Extraction
- Fine-tuning Happens in Tiny Subspaces: Exploring Intrinsic Task-specific Subspaces of Pre-trained Language Models
- Weaker Than You Think: A Critical Look at Weakly Supervised Learning
- Modeling Adversarial Attack on Pre-trained Language Models as Sequential Decision Making
All 165
- On the Importance of Backbone to the Adversarial Robustness of Object Detectors
- GIMM: InfoMin-Max for Automated Graph Contrastive Learning
- On the Noise Sensitivity of the Randomized SVD
- A Unified Framework for Slot based Response Generation in a Multimodal Dialogue System
- GMSF: Global Matching Scene Flow
- Choosing the Right Weights: Balancing Value, Strategy, and Noise in Recommender Systems
- Understanding Emotion Valence is a Joint Deep Learning Task
- CCDWT-GAN: Generative Adversarial Networks Based on Color Channel Using Discrete Wavelet Transform for Document Image Binarization
- Modeling Dynamic Heterogeneous Graph and Node Importance for Future Citation Prediction
- A Practical Toolkit for Multilingual Question and Answer Generation
- Exploring Better Text Image Translation with Multimodal Codebook
- On the special role of class-selective neurons in early training
- AdaptGear: Accelerating GNN Training via Adaptive Subgraph-Level Kernels on GPUs
- Enhancing Translation for Indigenous Languages: Experiments with Multilingual Models
- Parallel Corpus for Indigenous Language Translation: Spanish-Mazatec and Spanish-Mixtec
- Source-Free Domain Adaptation for SSVEP-based Brain-Computer Interfaces
- Learning and Collusion in Multi-unit Auctions
- A Framework For Refining Text Classification and Object Recognition from Academic Articles
- Query-Policy Misalignment in Preference-Based Reinforcement Learning
- NeRO: Neural Geometry and BRDF Reconstruction of Reflective Objects from Multiview Images
- Answering Unanswered Questions through Semantic Reformulations in Spoken QA
- MPCHAT: Towards Multimodal Persona-Grounded Conversation
- Learning from Integral Losses in Physics Informed Neural Networks
- HyperFormer: Learning Expressive Sparse Feature Representations via Hypergraph Transformer
- APRIL-GAN: A Zero-/Few-Shot Anomaly Classification and Segmentation Method for CVPR 2023 VAND Workshop Challenge Tracks 1&2: 1st Place on Zero-shot AD and 4th Place on Few-shot AD
- No-Regret Online Reinforcement Learning with Adversarial Losses and Transitions
- Improving Generalization in Language Model-Based Text-to-SQL Semantic Parsing: Two Simple Semantic Boundary-Based Techniques
- DePF: A Novel Fusion Approach based on Decomposition Pooling for Infrared and Visible Images
- Attention Schema in Neural Agents
- LE2Fusion: A novel local edge enhancement module for infrared and visible image fusion
- Zero- and Few-Shot Event Detection via Prompt-Based Meta Learning
- Reinforcement Learning With Reward Machines in Stochastic Games
- Towards Better Entity Linking with Multi-View Enhanced Distillation
- Modularized Zero-shot VQA with Pre-trained Models
- Instance-based Max-margin for Practical Few-shot Recognition
- Augmenting Large Language Model Translators via Translation Memories
- An Investigation of Evaluation Metrics for Automated Medical Note Generation
- DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated Text
- CTC-based Non-autoregressive Speech Translation
- Bridging the Granularity Gap for Acoustic Modeling
- Rethinking PRL: A Multiscale Progressively Residual Learning Network for Inverse Halftoning
- Complementary and Integrative Health Lexicon (CIHLex) and Entity Recognition in the Literature
- Is Centralized Training with Decentralized Execution Framework Centralized Enough for MARL?
- Disambiguated Lexically Constrained Neural Machine Translation
- How Good is Automatic Segmentation as a Multimodal Discourse Annotation Aid?
- Condition-Invariant Semantic Segmentation
- CGELBank Annotation Manual v1.2
- Input-Aware Dynamic Timestep Spiking Neural Networks for Efficient In-Memory Computing
- Modality-Independent Teachers Meet Weakly-Supervised Audio-Visual Event Parser
- Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RL
- Improved Privacy-Preserving PCA Using Optimized Homomorphic Matrix Multiplication
- Multi-label Video Classification for Underwater Ship Inspection
- Benchmarking Diverse-Modal Entity Linking with Generative Models
- Fine-Tuning Language Models with Just Forward Passes
- Learning Capacity: A Measure of the Effective Dimensionality of a Model
- Augmentation-Adapted Retriever Improves Generalization of Language Models as Generic Plug-In
- Hierarchical Deep Counterfactual Regret Minimization
- Matrix Information Theory for Self-Supervised Learning
- Why Does Zero-Shot Cross-Lingual Generation Fail? An Explanation and a Solution
- Some Primal-Dual Theory for Subgradient Methods for Strongly Convex Optimization
- Moral Machine or Tyranny of the Majority?
- Radar Enlighten the Dark: Enhancing Low-Visibility Perception for Automated Vehicles with Camera-Radar Fusion
- Automatic Roof Type Classification Through Machine Learning for Regional Wind Risk Assessment
- Super-Resolution of License Plate Images Using Attention Modules and Sub-Pixel Convolution Layers
- Beyond Positive Scaling: How Negation Impacts Scaling Trends of Language Models