Papers
Sun 25 Aug 2024
122 papers
- Path-Consistency with Prefix Enhancement for Efficient Inference in LLMsLLM reasoning → Test-time compute and efficient thinking
- Vision-Language and Large Language Model Performance in Gastroenterology: GPT, Claude, Llama, Phi, Mistral, Gemma, and Quantized ModelsLLM reasoning → Clinical and biomedical applications +1
- Unveiling the Statistical Foundations of Chain-of-Thought Prompting MethodsLLM reasoning → Prompting and chain-of-thought reasoning
- Derailer-Rerailer: Adaptive Verification for Efficient and Reliable Language Model ReasoningLLM reasoning → Test-time compute and efficient thinking
- LLMs are Superior Feedback Providers: Bootstrapping Reasoning for Lie Detection with Self-Generated FeedbackLLM reasoning → Prompting and chain-of-thought reasoning +1
- LowCLIP: Adapting the CLIP Model Architecture for Low-Resource Languages in Multimodal Image Retrieval TaskMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
- ConVis: Contrastive Decoding with Hallucination Visualization for Mitigating Hallucinations in Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
- Evaluating Attribute Comprehension in Large Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- HTS-Attack: Heuristic Token Search for Jailbreaking Text-to-Image ModelsLLM safety and security → Vision-language and text-to-image safety
- SimpleSpeech 2: Towards Simple and Efficient Text-to-Speech with Flow-based Scalar Latent Transformer Diffusion ModelsDiffusion models → Audio, speech and music
- Making Large Language Models Better Planners with Reasoning-Decision AlignmentLLM reasoning → Chain-of-thought reasoning for driving
- Enhancing SQL Query Generation with Neurosymbolic ReasoningLLM reasoning → Reasoning benchmarks and evaluation
- Safe Policy Exploration Improvement via SubgoalsDeep reinforcement learning methods → Safe and constrained RL
- Particle-Filtering-based Latent Diffusion for Inverse ProblemsDiffusion models → Inverse problems and image restoration
- CodeGraph: Enhancing Graph Reasoning of LLMs with CodeLLM reasoning → Knowledge- and tool-augmented reasoning
- Draw Like an Artist: Complex Scene Generation with Diffusion Model via Composition, Painting, and RetouchingDiffusion models → Image generation, text-to-image and editing
- Tangram: Benchmark for Evaluating Geometric Element Recognition in Large Multimodal ModelsLLM reasoning → Spatial and embodied reasoning +1
- Condensed Data Expansion Using Model Inversion for Knowledge DistillationKnowledge distillation → General knowledge distillation methods
- Bring the Power of Diffusion Model to Defect DetectionDiffusion models → Flow matching, time series and science
- Non-asymptotic bounds for forward processes in denoising diffusions: Ornstein-Uhlenbeck is hard to beatDiffusion models → Diffusion foundations and sampling
- 3D-VirtFusion: Synthetic 3D Data Augmentation through Generative Diffusion Models and Controllable EditingDiffusion models → 3D, point cloud and scene generation
- MSVM-UNet: Multi-Scale Vision Mamba UNet for Medical Image SegmentationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
- StockTime: A Time Series Specialized Large Language Model Architecture for Stock Price Prediction
- A proof of contribution in blockchain using game theoretical deep learning model
- Quantized neural network for complex hologram generation
- McGrids: Monte Carlo-Driven Adaptive Grids for Iso-Surface Extraction
- Unveiling Visual Biases in Audio-Visual Localization Benchmarks
- CF-KAN: Kolmogorov-Arnold Network-based Collaborative Filtering to Mitigate Catastrophic Forgetting in Recommender Systems
- Transformer-Enhanced Iterative Feedback Mechanism for Polyp Segmentation
- A Note On Deterministic Submodular Maximization With Bounded Curvature
- Genetic Approach to Mitigate Hallucination in Generative IR
- On-device Learning of EEGNet-based Network For Wearable Motor Imagery Brain-Computer Interface
- SPICED: Syntactical Bug and Trojan Pattern Identification in A/MS Circuits using LLM-Enhanced Detection
- Quantum-Powered Personalized Learning
- A Joint Learning Model with Variational Interaction for Multilingual Program Translation
- An Empirical Study on Improving SimCLR's Nonlinear Projection Head using Pretrained Autoencoder Embeddings
- Variational autoencoder-based neural network model compression
- LLMs as Zero-shot Graph Learners: Alignment of GNN Representations with LLM Token Embeddings
- Shifted Window Fourier Transform And Retention For Image Captioning
- Optimizing Luxury Vehicle Dealership Networks: A Graph Neural Network Approach to Site Selection
- Time Series Analysis for Education: Methods, Applications, and Future Directions
- Bidirectional Awareness Induction in Autoregressive Seq2Seq Models
- Prediction of COPD Using Machine Learning, Clinical Summary Notes, and Vital Signs
- InterTrack: Tracking Human Object Interaction without Object Templates
- Bridging the Gap between Real-world and Synthetic Images for Testing Autonomous Driving Systems
- Personalized Topology-Informed Localization of Standard 12-Lead ECG Electrode Placement from Incomplete Cardiac MRIs for Efficient Cardiac Digital Twins
- OpenNav: Efficient Open Vocabulary 3D Object Detection for Smart Wheelchair Navigation
- Learning to Move Like Professional Counter-Strike Players
- MobileQuant: Mobile-friendly Quantization for On-device Language Models
- GeoPlant: Spatial Plant Species Prediction Dataset
- FedGlu: A personalized federated learning-based glucose forecasting algorithm for improved performance in glycemic excursion regions
- Infrared Domain Adaptation with Zero-Shot Quantization
- COMPOSE: Comprehensive Portrait Shadow Editing
- Geo-Llama: Leveraging LLMs for Human Mobility Trajectory Generation with Spatiotemporal Constraints
- Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs
- TraIL-Det: Transformation-Invariant Local Feature Networks for 3D LiDAR Object Detection with Unsupervised Pre-Training
- ESG Rating Disagreement and Corporate Total Factor Productivity:Inference and Prediction
- SpeechCaps: Advancing Instruction-Based Universal Speech Models with Multi-Talker Speaking Style Captioning
- LLM with Relation Classifier for Document-Level Relation Extraction
- Neural Spacetimes for DAG Representation Learning
- Generalization of Graph Neural Networks is Robust to Model Mismatch
- Camouflaged Object Tracking: A Benchmark
- AlphaViT: A flexible game-playing AI for multiple games and variable board sizes
- Knowledge-Aware Reasoning over Multimodal Semi-structured Tables
- LaneTCA: Enhancing Video Lane Detection with Temporal Context Aggregation
- Consistent machine learning for topology optimization with microstructure-dependent neural network material models
- Exploring Reliable Matching with Phase Enhancement for Night-time Semantic Segmentation
- PAM: A Propagation-Based Model for Segmenting Any 3D Objects across Multi-Modal Medical Images
- Biomedical Large Languages Models Seem not to be Superior to Generalist Models on Unseen Medical Data
- A Low-dose CT Reconstruction Network Based on TV-regularized OSEM Algorithm
- Guardians of the Machine Translation Meta-Evaluation: Sentinel Metrics Fall In!
- Multi-SIGATnet: A multimodal schizophrenia MRI classification algorithm using sparse interaction mechanisms and graph attention networks
- RoCP-GNN: Robust Conformal Prediction for Graph Neural Networks in Node-Classification
- HER2 and FISH Status Prediction in Breast Biopsy H&E-Stained Images Using Deep Learning
- Few-Shot Histopathology Image Classification: Evaluating State-of-the-Art Methods and Unveiling Performance Insights
- Revisiting the Exit from Nuclear Energy in Germany with NLP
- On the Robustness of Kolmogorov-Arnold Networks: An Adversarial Perspective
- Towards Reliable Medical Question Answering: Techniques and Challenges in Mitigating Hallucinations in Language Models
- Prior Learning in Introspective VAEs
- TripleMixer: A 3D Point Cloud Denoising Model for Adverse Weather
- BCDNet: A Fast Residual Neural Network For Invasive Ductal Carcinoma Detection
- Selectively Dilated Convolution for Accuracy-Preserving Sparse Pillar-based Embedded 3D Object Detection
- CV-MOS: A Cross-View Model for Motion Segmentation
- Mask-Encoded Sparsification: Mitigating Biased Gradients in Communication-Efficient Split Learning
- Localization of Synthetic Manipulations in Western Blot Images
- Analyzing the Impact of Splicing Artifacts in Partially Fake Speech Signals
- Batch-FPM: Random batch-update multi-parameter physical Fourier ptychography neural network
- Towards Completeness: A Generalizable Action Proposal Generator for Zero-Shot Temporal Action Localization
- Extremely Fine-Grained Visual Classification over Resembling Glyphs in the Wild
- SAB:A Stealing and Robust Backdoor Attack based on Steganographic Algorithm against Federated Learning
- ICFRNet: Image Complexity Prior Guided Feature Refinement for Real-time Semantic Segmentation
- TranSplat: Generalizable 3D Gaussian Splatting from Sparse Multi-View Images with Transformers
- Lecture Notes on Linear Neural Networks: A Tale of Optimization and Generalization in Deep Learning
- Enhancing Robustness of Human Detection Algorithms in Maritime SAR through Augmented Aerial Images to Simulate Weather Conditions
- FMI-TAL: Few-shot Multiple Instances Temporal Action Localization by Probability Distribution Learning and Interval Cluster Refinement
- Self-Parameterization Based Multi-Resolution Mesh Convolution Networks
- Multimodal Ensemble with Conditional Feature Fusion for Dysgraphia Diagnosis in Children from Handwriting Samples
- Localization and Expansion: A Decoupled Framework for Point Cloud Few-shot Semantic Segmentation
- Improved identification of breakpoints in piecewise regression and its applications
- Multi-Agent Target Assignment and Path Finding for Intelligent Warehouse: A Cooperative Multi-Agent Deep Reinforcement Learning Perspective
All 122
- Quartered Spectral Envelope and 1D-CNN-based Classification of Normally Phonated and Whispered Speech
- DOCE: Finding the Sweet Spot for Execution-Based Code Generation
- Enhancing Adaptive Deep Networks for Image Classification via Uncertainty-aware Decision Fusion
- Literary and Colloquial Tamil Dialect Identification
- Poor-Supervised Evaluation for SuperLLM via Mutual Consistency
- Anatomical Consistency Distillation and Inconsistency Synthesis for Brain Tumor Segmentation with Missing Modalities
- 3D-RCNet: Learning from Transformer to Build a 3D Relational ConvNet for Hyperspectral Image Classification
- LogParser-LLM: Advancing Efficient Log Parsing with Large Language Models
- PhysPart: Physically Plausible Part Completion for Interactable Objects
- EMG-Based Hand Gesture Recognition through Diverse Domain Feature Enhancement and Machine Learning-Based Approach
- A prototype-based model for set classification
- Count-based Novelty Exploration in Classical Planning
- FreqINR: Frequency Consistency for Implicit Neural Representation with Adaptive DCT Frequency Loss
- TalkLoRA: Low-Rank Adaptation for Speech-Driven Animation
- Verifiable cloud-based variational quantum algorithms
- Riemann-based Multi-scale Attention Reasoning Network for Text-3D Retrieval
- SceneDreamer360: Text-Driven 3D-Consistent Scene Generation with Panoramic Gaussian Splatting
- InSpaceType: Dataset and Benchmark for Reconsidering Cross-Space Type Performance in Indoor Monocular Depth
- DHP Benchmark: Are LLMs Good NLG Evaluators?
- CNN-Transformer Rectified Collaborative Learning for Medical Image Segmentation
- ForgeLens: Data-Efficient Forgery Focus for Generalizable Forgery Image Detection
- Revisiting DNN Training for Intermittently-Powered Energy-Harvesting Micro-Computers