Papers

New on arXiv

Mon 29 May 2023

267 papers

BRICS: Bi-level feature Representation of Image CollectionSDiffusion models → Diffusion foundations and sampling
On Diffusion Modeling for Anomaly DetectionDiffusion models → Flow matching, time series and science
Controllable Text-to-Image Generation with GPT-4LLM reasoning → Multimodal reasoning +1
RLAD: Reinforcement Learning from Pixels for Autonomous Driving in Urban EnvironmentsEnd-to-end autonomous driving → Reinforcement learning for driving
Code Prompting: a Neural Symbolic Method for Complex Reasoning in Large Language ModelsLLM reasoning → Prompting and chain-of-thought reasoning
Provable Reward-Agnostic Preference-Based Reinforcement LearningLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement LearningWorld models → Latent dynamics models and model-based RL
Make-An-Audio 2: Temporal-Enhanced Text-to-Audio GenerationDiffusion models → Audio, speech and music
Aligning Optimization Trajectories with Diffusion Models for Constrained Design GenerationDiffusion models → Flow matching, time series and science
Membership Inference Attacks against Language Models via Neighbourhood ComparisonLLM safety and security → Membership inference attacks
Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement LearningDiffusion models → Diffusion and flow policies for robotics
Baselines for Identifying Watermarked Large Language ModelsLLM safety and security → Watermarking generated content and models
Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion ModelsDiffusion models → Diffusion foundations and sampling
Conditional Diffusion Models for Semantic 3D Brain MRI SynthesisDiffusion models → Medical imaging and segmentation
Reinforcement Learning with Human Feedback: Learning Dynamic Choices via PessimismLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
RAPHAEL: Text-to-Image Generation via Large Mixture of Diffusion PathsDiffusion models → Image generation, text-to-image and editing +1
Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
Direct Preference Optimization: Your Language Model is Secretly a Reward ModelLLM reasoning → Reinforcement learning for reasoning +1
Contextual Object Detection with Multimodal Large Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Reconstructing the Mind's Eye: fMRI-to-Image with Contrastive Learning and Diffusion PriorsDiffusion models → Medical imaging and segmentation
Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-DenoisingDiffusion models → Video generation
GlyphControl: Glyph Conditional Control for Visual Text GenerationDiffusion models → Image generation, text-to-image and editing
Leveraging Training Data in Few-Shot Prompting for Numerical ReasoningLLM reasoning → Prompting and chain-of-thought reasoning
Image Captioning with Multi-Context Synthetic DataDiffusion models → Image generation, text-to-image and editing +1
InstructEdit: Improving Automatic Masks for Diffusion-based Image Editing With User InstructionsDiffusion models → Image generation, text-to-image and editing
Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP +1
Conditional Score Guidance for Text-Driven Image-to-Image TranslationDiffusion models → Image generation, text-to-image and editing
DiffRate : Differentiable Compression Rate for Efficient Vision TransformersEfficient LLM inference and serving → Token pruning and merging for ViTs
CamoDiffusion: Camouflaged Object Detection via Conditional Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
Ask an Expert: Leveraging Language Models to Improve Strategic Reasoning in Goal-Oriented Dialogue ModelsLLM reasoning → Reasoning benchmarks and evaluation
Few-Shot Rotation-Invariant Aerial Image Semantic Segmentation
Chatbots to ChatGPT in a Cybersecurity Space: Evolution, Vulnerabilities, Attacks, Challenges, and Future Recommendations
Exploring the Compositional Generalization in Context Dependent Text-to-SQL Parsing
From Zero to Turbulence: Generative Modeling for 3D Flow Simulation
RE-centric Recommendations for the Development of Trustworthy(er) Autonomous Systems
Re-imagining health and well-being in low resource African settings using an augmented AI system and a 3D digital twin
ProcessGPT: Transforming Business Process Management with Generative Artificial Intelligence
DeepVAT: A Self-Supervised Technique for Cluster Assessment in Image Datasets
Trainable and Explainable Simplicial Map Neural Networks
Graph Exploration Matters: Improving both individual-level and system-level diversity in WeChat Feed Recommender
Brainformers: Trading Simplicity for Efficiency
Datasets for Portuguese Legal Semantic Textual Similarity: Comparing weak supervision and an annotation process approaches
Truncated Affinity Maximization: One-class Homophily Modeling for Graph Anomaly Detection
Perimeter Control Using Deep Reinforcement Learning: A Model-free Approach towards Homogeneous Flow Rate Optimization
Global Layers: Non-IID Tabular Federated Learning
Full High-Dimensional Intelligible Learning In 2-D Lossless Visualization Space
Representation Of Lexical Stylistic Features In Language Models' Embedding Space
Parity Calibration
Faith and Fate: Limits of Transformers on Compositionality
UMD: Unsupervised Model Detection for X2X Backdoor Attacks
Deep Equilibrium Models Meet Federated Learning
Enhanced Chart Understanding in Vision and Language Task via Cross-modal Pre-training on Plot Table Pairs
Short Answer Grading Using One-shot Prompting and Text Similarity Scoring Model
Graph Rewriting for Graph Neural Networks
Identification of stormwater control strategies and their associated uncertainties using Bayesian Optimization
Quantize Once, Train Fast: Allreduce-Compatible Compression with Provable Guarantees
W-procer: Weighted Prototypical Contrastive Learning for Medical Few-Shot Named Entity Recognition
Alfred: A System for Prompted Weak Supervision
Networked Time Series Imputation via Position-aware Graph Enhanced Variational Autoencoders
How Effective Are Neural Networks for Fixing Security Vulnerabilities
From `Snippet-lects' to Doculects and Dialects: Leveraging Neural Representations of Speech for Placing Audio Signals in a Language Landscape
Improving Generalization for Multimodal Fake News Detection
A Method for Studying Semantic Construal in Grammatical Constructions with Interpretable Contextual Embedding Spaces
Building Accurate Low Latency ASR for Streaming Voice Search
Exploiting Explainability to Design Adversarial Attacks and Evaluate Attack Resilience in Hate-Speech Detection Models
Coeditor: Leveraging Contextual Changes for Multi-round Code Auto-editing
Information Association for Language Model Updating by Mitigating LM-Logical Discrepancy
Quick Adaptive Ternary Segmentation: An Efficient Decoding Procedure For Hidden Markov Models
Towards Constituting Mathematical Structures for Learning to Optimize
TreeMAN: Tree-enhanced Multimodal Attention Network for ICD Coding
Search-Based Regular Expression Inference on a GPU
PaLI-X: On Scaling up a Multilingual Vision and Language Model
SHARP: Sparsity and Hidden Activation RePlay for Neuro-Inspired Continual Learning
DelBugV: Delta-Debugging Neural Network Verifiers
Evaluating 3D Shape Analysis Methods for Robustness to Rotation Invariance
Forgotten Knowledge: Examining the Citational Amnesia in NLP
Controllable Path of Destruction
Learning Linear Groups in Neural Networks
Meta-Regression Analysis of Errors in Short-Term Electricity Load Forecasting
Robust Lipschitz Bandits to Adversarial Corruptions
SlimFit: Memory-Efficient Fine-Tuning of Transformer-based Models Using Training Dynamics
A Rainbow in Deep Network Black Boxes
Contextual Bandits with Budgeted Information Reveal
On the Variance, Admissibility, and Stability of Empirical Risk Minimization
Generalization Ability of Wide Residual Networks
Generalized Disparate Impact for Configurable Fairness Solutions in ML
From Adversarial Arms Race to Model-centric Evaluation: Motivating a Unified Automatic Robustness Evaluation Framework
Escaping mediocrity: how two-layer networks learn hard generalized linear models with SGD
DoMo-AC: Doubly Multi-step Off-policy Actor-Critic Algorithm
VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset
ANPL: Towards Natural Programming with Interactive Decomposition
Collaborative Learning via Prediction Consensus
Generalized equivalences between subsampling and ridge regularization
Hardware-aware Training Techniques for Improving Robustness of Ex-Situ Neural Network Transfer onto Passive TiO2 ReRAM Crossbars
Adapting Learned Sparse Retrieval for Long Documents
Insights from the Design Space Exploration of Flow-Guided Nanoscale Localization
DMS: Differentiable Mean Shift for Dataset Agnostic Task Specific Clustering Using Side Information
Towards a Better Understanding of Representation Dynamics under TD-learning
SANE: The phases of gradient descent through Sharpness Adjusted Number of Effective parameters
A Transfer Learning and Explainable Solution to Detect mpox from Smartphones images

All 267