Papers
Sat 17 Aug 2024
112 papers
- Reinforcement Learning Compensated Model Predictive Control for Off-road Driving on Unknown Deformable TerrainEnd-to-end autonomous driving → Reinforcement learning for driving +1
- V2X-VLM: End-to-End V2X Cooperative Autonomous Driving Through Large Vision-Language ModelsMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
- FPGA: Flexible Portrait Generation ApproachDiffusion models → Image generation, text-to-image and editing
- Learning to Optimally Stop Diffusion Processes, with Financial ApplicationsDeep reinforcement learning methods → Adversarial robustness and RL in finance
- RepControlNet: ControlNet ReparameterizationDiffusion models → Image generation, text-to-image and editing
- QEDCartographer: Automating Formal Verification Using Reward-Free Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
- Scalable and Certifiable Graph Unlearning: Overcoming the Approximation Error BarrierLLM safety and security → Graph unlearning
- TC-RAG:Turing-Complete RAG's Case study on Medical LLM SystemsRetrieval-augmented generation → Medical and biomedical RAG
- Cognitive LLMs: Towards Integrating Cognitive Architectures and Large Language Models for Manufacturing Decision-makingLLM reasoning → Reasoning benchmarks and evaluation
- Are CLIP features all you need for Universal Synthetic Image Origin Attribution?Diffusion models → Image generation, text-to-image and editing
- Timestep-Aware Diffusion Model for Extreme Image RescalingDiffusion models → Inverse problems and image restoration
- Reinforcement learning-based adaptive speed controllers in mixed autonomy conditionDeep reinforcement learning methods → RL for autonomous driving and traffic
- Markov Balance Satisfaction Improves Performance in Strictly Batch Offline Imitation LearningOffline RL and imitation learning from data → Imitation learning methods
- Training Verifiably Robust Agents Using Set-Based Reinforcement LearningDeep reinforcement learning methods → Adversarial robustness and RL in finance
- Measuring Agreeableness Bias in Multimodal ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
- BaThe: Defense against the Jailbreak Attack in Multimodal Large Language Models by Treating Harmful Instruction as Backdoor TriggerLLM safety and security → Vision-language and text-to-image safety
- Direction of Arrival Estimation with Sparse Subarrays
- ADformer: A Multi-Granularity Spatial-Temporal Transformer for EEG-Based Alzheimer Detection
- Quality Assessment in the Era of Large Models: A Survey
- TimeSense: Multi-Person Device-free Indoor Localization via RTT
- Attack Anything: Blind DNNs via Universal Background Adversarial Attack
- Pupil-Adaptive 3D Holography Beyond Coherent Depth-of-Field
- Fairness-Aware Streaming Feature Selection with Causal Graphs
- Machine Learning Potentials: A Roadmap Toward Next-Generation Biomolecular Simulations
- How Susceptible are LLMs to Influence in Prompts?
- Unraveling Text Generation in LLMs: A Stochastic Differential Equation Approach
- Sentiment analysis of preservice teachers' reflections using a large language model
- Toward End-to-End Bearing Fault Diagnosis for Industrial Scenarios with Spiking Neural Networks
- Increasing transformer token length with a Maximum Entropy Principle Method
- FEDKIM: Adaptive Federated Knowledge Injection into Medical Foundation Models
- FedKBP: Federated dose prediction framework for knowledge-based planning in radiation therapy
- Benchmarking quantum machine learning kernel training for classification tasks
- An Open-Source American Sign Language Fingerspell Recognition and Semantic Pose Retrieval Interface
- Narrowing the Focus: Learned Optimizers for Pretrained Models
- A Benchmark Time Series Dataset for Semiconductor Fabrication Manufacturing Constructed using Component-based Discrete-Event Simulation Models
- CyberPal.AI: Empowering LLMs with Expert-Driven Cybersecurity Instructions
- Malacopula: adversarial automatic speaker verification attacks using a neural-based generalised Hammerstein model
- Out-of-distribution materials property prediction using adversarial learning based fine-tuning
- Multi-Camera Multi-Person Association using Transformer-Based Dense Pixel Correspondence Estimation and Detection-Based Masking
- Evaluating Usability and Engagement of Large Language Models in Virtual Reality for Traditional Scottish Curling
- Cross-Species Data Integration for Enhanced Layer Segmentation in Kidney Pathology
- ConVerSum: A Contrastive Learning-based Approach for Data-Scarce Solution of Cross-Lingual Summarization Beyond Direct Equivalents
- Enhancing Audio-Language Models through Self-Supervised Post-Training with Text-Audio Pairs
- Graph Classification with GNNs: Optimisation, Representation and Inductive Bias
- ByCAN: Reverse Engineering Controller Area Network (CAN) Messages from Bit to Byte Level
- PREMAP: A Unifying PREiMage APproximation Framework for Neural Networks
- Adaptify: A Refined Adaptation Scheme for Frame Classification in Atrophic Gastritis Videos
- Re-boosting Self-Collaboration Parallel Prompt GAN for Unsupervised Image Restoration
- Towards Effective Top-N Hamming Search via Bipartite Graph Contrastive Hashing
- Hybrid Semantic Search: Unveiling User Intent Beyond Keywords
- Reference-Guided Verdict: LLMs-as-Judges in Automatic Evaluation of Free-Form QA
- Siamese Multiple Attention Temporal Convolution Networks for Human Mobility Signature Identification
- FEDMEKI: A Benchmark for Scaling Medical Foundation Models via Federated Knowledge Injection
- Neuro-Symbolic AI for Military Applications
- Flatten: Video Action Recognition is an Image Classification task
- FQGA-single: Towards Fewer Training Epochs and Fewer Model Parameters for Image-to-Image Translation Tasks
- Generating Data with Text-to-Speech and Large-Language Models for Conversational Speech Recognition
- On the Improvement of Generalization and Stability of Forward-Only Learning via Neural Polarization
- H2PIPE: High throughput CNN Inference on FPGAs with High-Bandwidth Memory
- Architectural Foundations for the Large Language Model Infrastructures
- A Deep Neural Network Framework for Solving Forward and Inverse Problems in Delay Differential Equations
- Maintainability Challenges in ML: A Systematic Literature Review
- DRL-Based Resource Allocation for Motion Blur Resistant Federated Self-Supervised Learning in IoV
- AI Managed Emergency Documentation with a Pretrained Model
- GSLAMOT: A Tracklet and Query Graph-based Simultaneous Locating, Mapping, and Multiple Object Tracking System
- SA-GDA: Spectral Augmentation for Graph Domain Adaptation
- EEG-SCMM: Soft Contrastive Masked Modeling for Cross-Corpus EEG-Based Emotion Recognition
- PADetBench: Towards Benchmarking Physical Attacks against Object Detection
- MambaTrack: A Simple Baseline for Multiple Object Tracking with State Space Model
- Chinese Metaphor Recognition Using a Multi-stage Prompting Large Language Model
- TableBench: A Comprehensive and Complex Benchmark for Table Question Answering
- Unlocking the Power of LLM Uncertainty for Active In-Context Example Selection
- Automatic Metrics in Natural Language Generation: A Survey of Current Evaluation Practices
- Ranking Across Different Content Types: The Robust Beauty of Multinomial Blending
- Zero-Shot Object-Centric Representation Learning
- Linear Attention is Enough in Spatial-Temporal Forecasting
- On the KL-Divergence-based Robust Satisficing Model
- DSReLU: A Novel Dynamic Slope Function for Superior Model Training
- Learning Robust Treatment Rules for Censored Data
- CogLM: Tracking Cognitive Development of Large Language Models
- SSNeRF: Sparse View Semi-supervised Neural Radiance Fields with Augmentation
- Point Source Identification Using Singularity Enriched Neural Networks
- Learning to Explore for Stochastic Gradient MCMC
- StylePrompter: Enhancing Domain Generalization with Test-Time Style Priors
- Vanilla Gradient Descent for Oblique Decision Trees
- Better Python Programming for all: With the focus on Maintainability
- Thin-Plate Spline-based Interpolation for Animation Line Inbetweening
- Gaussian in the Dark: Real-Time View Synthesis From Inconsistent Dark Images Using Gaussian Splatting
- Identifying Technical Debt and Its Types Across Diverse Software Projects Issues
- DreamBarbie: Text to Barbie-Style 3D Avatars
- Dynamic Neural Dowker Network: Approximating Persistent Homology in Dynamic Directed Graphs
- MaskBEV: Towards A Unified Framework for BEV Detection and Map Segmentation
- Selective Prompt Anchoring for Code Generation
- Time Series Analysis by State Space Learning
- LOID: Lane Occlusion Inpainting and Detection for Enhanced Autonomous Driving Systems
- GoodSAM++: Bridging Domain and Capacity Gaps via Segment Anything Model for Panoramic Semantic Segmentation
- Locate Anything on Earth: Advancing Open-Vocabulary Object Detection for Remote Sensing Community
- Improved Q-learning based Multi-hop Routing for UAV-Assisted Communication
- Temporal Reversal Regularization for Spiking Neural Networks: Hybrid Spatio-Temporal Invariance for Generalization
- Fragment-Masked Diffusion for Molecular Optimization
All 112
- HybridOcc: NeRF Enhanced Transformer-based Multi-Camera 3D Occupancy Prediction
- Depth-guided Texture Diffusion for Image Semantic Segmentation
- Research on color recipe recommendation based on unstructured data using TENN
- Dynamic Graph Representation Learning for Passenger Behavior Prediction
- Segment Anything with Multiple Modalities
- Twin Sorting Dynamic Programming Assisted User Association and Wireless Bandwidth Allocation for Hierarchical Federated Learning
- Improving Rare Word Translation With Dictionaries and Attention Masking
- Gradient-Variation Online Learning under Generalized Smoothness
- Enhancing Community Detection in Networks: A Comparative Analysis of Local Metrics and Hierarchical Algorithms
- CodeTaxo: Enhancing Taxonomy Expansion with Limited Examples via Code Language Prompts
- Linking Robustness and Generalization: A k* Distribution Analysis of Concept Clustering in Latent Space for Vision Models
- MoRA: LoRA Guided Multi-Modal Disease Diagnosis with Missing Modality