Papers

New on arXiv

Sun 9 Jun 2024

162 papers

An Efficient Framework for Crediting Data Contributors of Diffusion ModelsDiffusion models → Diffusion foundations and sampling
GFPack++: Improving 2D Irregular Packing by Learning Gradient Field with AttentionDiffusion models → 3D, point cloud and scene generation
Latent Diffusion Model-Enabled Low-Latency Semantic Communication in the Presence of Semantic Ambiguities and Wireless Channel NoisesDiffusion models → Diffusion for compression and wireless
Hello Again! LLM-powered Personalized Agent for Long-term DialogueLLM agents and tool use → Agent memory systems
Whose Preferences? Differences in Fairness Preferences and Their Impact on the Fairness of AI Utilizing Human FeedbackLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
Security Vulnerability Detection with Multitask Self-Instructed Fine-Tuning of Large Language ModelsSynthetic data and self-improvement for LLMs → Code and instruction data synthesis
Information Theoretic Guarantees For Policy Alignment In Large Language ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Distributional Preference Alignment of LLMs via Optimal TransportLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
STARLING: Self-supervised Training of Text-based Reinforcement Learning Agent with Large Language ModelsLLM agents and tool use → Reinforcement learning for LLM agents
Machine Against the RAG: Jamming Retrieval-Augmented Generation with Blocker DocumentsRetrieval-augmented generation → Privacy and security of RAG
II-Bench: An Image Implication Understanding Benchmark for Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Mamba YOLO: A Simple Baseline for Object Detection with State Space ModelState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
Improving Antibody Design with Force-Guided Sampling in Diffusion ModelsDiffusion models → Flow matching, time series and science
F-LMM: Grounding Frozen Large Multimodal ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
TIGeR: Unifying Text-to-Image Generation and Retrieval with Large Multimodal ModelsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
A Review of Prominent Paradigms for LLM-Based Agents: Tool Use (Including RAG), Planning, and Feedback LearningLLM agents and tool use → General LLM agent frameworks and benchmarks
RE-RAG: Improving Open-Domain QA Performance and Interpretability with Relevance Estimator in Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
CAMS: Convolution and Attention-Free Mamba-based Cardiac Image SegmentationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
TLCM: Training-efficient Latent Consistency Model for Image Generation with 2-8 StepsDiffusion models → Diffusion foundations and sampling
Vision Mamba: Cutting-Edge Classification of Alzheimer's Disease with 3D MRI ScansState-space sequence models (S4, Mamba) → Mamba for medical image analysis
EmbSpatial-Bench: Benchmarking Spatial Understanding for Embodied Tasks with Large Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Binarized Diffusion Model for Image Super-ResolutionDiffusion models → Inverse problems and image restoration
ALGO: Object-Grounded Visual Commonsense Reasoning for Open-World Egocentric Action RecognitionLLM reasoning → Spatial and embodied reasoning
Data-Driven Upper Confidence Bounds with Near-Optimal Regret for Heavy-Tailed BanditsDeep reinforcement learning methods → RL theory and sample complexity
Towards A General-Purpose Motion Planning for Autonomous Vehicles Using Fluid DynamicsEnd-to-end autonomous driving → Imitation-learning end-to-end planners
HDMba: Hyperspectral Remote Sensing Imagery Dehazing with State Space ModelState-space sequence models (S4, Mamba) → Hyperspectral image analysis with Mamba
Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal ExamplesLLM reasoning → Test-time compute and efficient thinking
Certified Robustness to Data Poisoning in Gradient-Based TrainingLLM safety and security → Backdoor and data poisoning attacks
Injecting Undetectable Backdoors in Obfuscated Neural Networks and Language ModelsLLM safety and security → Backdoor and data poisoning attacks
Do LLMs Exhibit Human-Like Reasoning? Evaluating Theory of Mind in LLMs for Open-Ended ResponsesLLM reasoning → Reasoning benchmarks and evaluation
DomainRAG: A Chinese Benchmark for Evaluating Domain-specific Retrieval-Augmented GenerationRetrieval-augmented generation → RAG pipeline design and evaluation
A Superalignment Framework in Autonomous Driving with Large Language ModelsMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +2
ICU-Sepsis: A Benchmark MDP Built from Real Medical DataDeep reinforcement learning methods → RL for clinical treatment and surgery
How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden StatesLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
PaRa: Personalizing Text-to-Image Diffusion via Parameter Rank ReductionDiffusion models → Image generation, text-to-image and editing
Ctrl-V: Higher Fidelity Video Generation with Bounding-Box Controlled Object MotionDiffusion models → Video generation
Building Artificial Intelligence with Creative Agency and Self-hood
Simplicits: Mesh-Free, Geometry-Agnostic, Elastic Simulation
Text2VP: Generative AI for Visual Programming and Parametric Modeling
Data-Driven Radio Environment Map Estimation Using Graph Neural Networks
Technical Report for CVPR 2024 WeatherProof Dataset Challenge: Semantic Segmentation on Paired Real Data
Realtime Dynamic Gaze Target Tracking and Depth-Level Estimation
Interpretable machine learning approach for electron antineutrino selection in a large liquid scintillator detector
Factor Graph Optimization of Error-Correcting Codes for Belief Propagation Decoding
Robust portfolio optimization for recommender systems considering uncertainty of estimated statistics
A Reality check of the benefits of LLM in business
A novel method for identifying rice seed purity based on hybrid machine learning algorithms
DMS: Addressing Information Loss with More Steps for Pragmatic Adversarial Attacks
TopoBench: A Framework for Benchmarking Topological Deep Learning
News and Load: Social and Economic Drivers of Regional Multi-horizon Electricity Demand Forecasting
Particle Multi-Axis Transformer for Jet Tagging
Exploring the Efficacy of Large Language Models (GPT-4) in Binary Reverse Engineering
LLM Questionnaire Completion for Automatic Psychiatric Assessment
Sparse Binarization for Fast Keyword Spotting
PairCFR: Enhancing Model Training on Paired Counterfactually Augmented Data through Contrastive Learning
Expressive Power of Graph Neural Networks for (Mixed-Integer) Quadratic Programs
Linear Causal Representation Learning from Unknown Multi-node Interventions
Semisupervised Neural Proto-Language Reconstruction
MeanSparse: Post-Training Robustness Enhancement Through Mean-Centered Feature Sparsification
Contrastive Learning from Synthetic Audio Doppelg"angers
Why Don't Prompt-Based Fairness Metrics Correlate?
Bits-to-Photon: End-to-End Learned Scalable Point Cloud Compression for Direct Rendering
BD-SAT: High-resolution Land Use Land Cover Dataset & Benchmark Results for Developing Division: Dhaka, BD
TTM-RE: Memory-Augmented Document-Level Relation Extraction
Large Language Models Memorize Sensor Datasets! Implications on Human Activity Recognition Research
Async Learned User Embeddings for Ads Delivery Optimization
InfoGaussian: Structure-Aware Dynamic Gaussians through Lightweight Information Shaping
Event prediction and causality inference despite incomplete information
GCtx-UNet: Efficient Network for Medical Image Segmentation
Feriji: A French-Zarma Parallel Corpus, Glossary & Translator
Few-Shot Load Forecasting Under Data Scarcity in Smart Grids: A Meta-Learning Approach
Are Large Language Models Actually Good at Text Style Transfer?
Training Fast Robot Policies with Slow Foundation Models
Zero-Shot End-To-End Spoken Question Answering In Medical Domain
Conserving Human Creativity with Evolutionary Generative Algorithms: A Case Study in Music Generation
OmniControlNet: Dual-stage Integration for Conditional Image Generation
An Analysis of Elo Rating Systems via Markov Chains
Procrastination Is All You Need: Exponent Indexed Accumulators for Floating Point, Posits and Logarithmic Numbers
Source -Free Domain Adaptation for Speaker Verification in Data-Scarce Languages and Noisy Channels
Self-supervised Adversarial Training of Monocular Depth Estimation against Physical-World Attacks
Self-Distilled Disentangled Learning for Counterfactual Prediction
RefGaussian: Disentangling Reflections from 3D Gaussian Splatting for Realistic Rendering
Scaling Graph Convolutions for Mobile Vision
MedREQAL: Examining Medical Knowledge Recall of Large Language Models via Question Answering
MaLa-ASR: Multimedia-Assisted LLM-Based ASR
Solution for CVPR 2024 UG2+ Challenge Track on All Weather Semantic Segmentation
BOSC: A toolbox for aerial imagery mapping
Probabilistic Approach to Black-Box Binary Optimization with Budget Constraints: Application to Sensor Placement
Multi-Stain Multi-Level Convolutional Network for Multi-Tissue Breast Cancer Image Segmentation
PSBD: Prediction Shift Uncertainty Unlocks Backdoor Detection
Symmetric Matrix Completion with ReLU Sampling
Attention as a Hypernetwork
What Can We Learn from State Space Models for Machine Learning on Graphs?
Seventeenth-Century Spanish American Notary Records for Fine-Tuning Spanish Large Language Models
ControlLoc: Physical-World Hijacking Attack on Visual Perception in Autonomous Driving
Do Prompts Really Prompt? Exploring the Prompt Understanding Capability of Whisper
Towards identifiability of micro total effects in summary causal graphs with latent confounding: extension of the front-door criterion
SAM-PM: Enhancing Video Camouflaged Object Detection using Spatio-Temporal Attention
SlowPerception: Physical-World Latency Attack against Visual Perception in Autonomous Driving
Hidden Holes: topological aspects of language models

All 162