Papers

New on arXiv

Tue 6 Aug 2024

190 papers

Mitigating Hallucinations in Large Vision-Language Models (LVLMs) via Language-Contrastive Decoding (LCD)Multimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
Can DPO Learn Diverse Human Values? A Theoretical Scaling LawLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
Communication-Aware Consistent Edge Selection for Mobile Users and Autonomous VehiclesEnd-to-end autonomous driving → Cooperative and V2X driving +1
Hybrid diffusion models: combining supervised and generative pretraining for label-efficient fine-tuning of segmentation modelsDiffusion models → Medical imaging and segmentation
Attacks and Defenses for Generative Diffusion Models: A Comprehensive SurveyDiffusion models → Robustness, privacy and adversarial aspects +1
GMAI-MMBench: A Comprehensive Multimodal Evaluation Benchmark Towards General Medical AIMultimodal LLMs / vision-language models → Medical vision-language models
Adversarial Domain Adaptation for Cross-user Activity Recognition Using Diffusion-based Noise-centred LearningDiffusion models → Diffusion foundations and sampling
LLaVA-OneVision: Easy Visual Task TransferMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model ParametersLLM reasoning → Test-time compute and efficient thinking +1
MDT-A2G: Exploring Masked Diffusion Transformers for Co-Speech Gesture GenerationDiffusion models → Audio, speech and music
KnowPO: Knowledge-aware Preference Optimization for Controllable Knowledge Selection in Retrieval-Augmented Language ModelsRetrieval-augmented generation → RAG robustness and adaptive retrieval +1
Making Long-Context Language Models Better Multi-Hop ReasonersLLM reasoning → Knowledge- and tool-augmented reasoning
IPAdapter-Instruct: Resolving Ambiguity in Image-based Conditioning using Instruct PromptsDiffusion models → Image generation, text-to-image and editing
Adversarial Safety-Critical Scenario Generation using Naturalistic Human Driving PriorsEnd-to-end autonomous driving → Adversarial scenarios and safety testing +1
RELIEF: Reinforcement Learning Empowered Graph Feature Prompt TuningDeep reinforcement learning methods → Deep RL algorithms and representations
Integrated Intention Prediction and Decision-Making with Spectrum Attention Net and Proximal Policy OptimizationDeep reinforcement learning methods → RL for autonomous driving and traffic
Iterative CT Reconstruction via Latent Variable Optimization of Shallow Diffusion ModelsDiffusion models → Medical imaging and segmentation
Stochastic Trajectory Optimization for Robotic Skill Acquisition From a Suboptimal DemonstrationOffline RL and imitation learning from data → Robot learning from demonstration
500xCompressor: Generalized Prompt Compression for Large Language ModelsEfficient LLM inference and serving → Prompt and context compression
QADQN: Quantum Attention Deep Q-Network for Financial Market PredictionDeep reinforcement learning methods → Adversarial robustness and RL in finance
Research on Autonomous Driving Decision-making Strategies based Deep Reinforcement LearningEnd-to-end autonomous driving → Reinforcement learning for driving +1
Model-free optimal controller for discrete-time Markovian jump linear systems: A Q-learning approachDeep reinforcement learning methods → RL for games and combinatorial optimization
Towards an Analysis of Discourse and Interactional Pragmatic Reasoning Capabilities of Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
OpenOmni: A Collaborative Open Source Tool for Building Future-Ready Multimodal Conversational AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
Targeted Visual Prompting for Medical Visual Question AnsweringMultimodal LLMs / vision-language models → Medical vision-language models
Training-Free Condition Video Diffusion Models for single frame Spatial-Semantic Echocardiogram SynthesisDiffusion models → Medical imaging and segmentation
A Course in Dynamic OptimizationDeep reinforcement learning methods → RL theory and sample complexity
Highly Efficient Self-Adaptive Reward Shaping for Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
DreamLCM: Towards High-Quality Text-to-3D Generation via Latent Consistency ModelDiffusion models → 3D, point cloud and scene generation
Diffusion Model Meets Non-Exemplar Class-Incremental Learning and BeyondDiffusion models → Robustness, privacy and adversarial aspects
Sample-agnostic Adversarial Perturbation for Vision-Language Pre-training ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
Data-Driven Stochastic Closure Modeling via Conditional Diffusion Model and Neural OperatorDiffusion models → Flow matching, time series and science
Scaling Trends for Data Poisoning in LLMsLLM safety and security → Backdoor and data poisoning attacks
HARMONIC: Harnessing LLMs for Tabular Data Synthesis and Privacy ProtectionSynthetic data and self-improvement for LLMs → Privacy-preserving tabular data synthesis
Intermediate direct preference optimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Pose Magic: Efficient and Temporally Consistent Human Pose Estimation with a Hybrid Mamba-GCN NetworkState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
A Taxonomy of Architecture Options for Foundation Model-based Agents: Analysis and Decision ModelLLM agents and tool use → General LLM agent frameworks and benchmarks
KOI: Accelerating Online Imitation Learning via Hybrid Key-state GuidanceOffline RL and imitation learning from data → Imitation learning methods
MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for MedicineMultimodal LLMs / vision-language models → Medical vision-language models
Compromising Embodied Agents with Contextual Backdoor AttacksLLM agents and tool use → Agent threats, guardrails and governance +1
Body of Her: A Preliminary Study on End-to-End Humanoid AgentLLM agents and tool use → Multimodal and embodied agents
Joint Image De-noising and Enhancement for Satellite-Based SAR
MicroXercise: A Micro-Level Comparative and Explainable System for Remote Physical Therapy
Analysis of Unstructured High-Density Crowded Scenes for Crowd Monitoring
SCREENER: A general framework for task-specific experiment design in quantitative MRI
OpenFactCheck: A Unified Framework for Factuality Evaluation of LLMs
FAKER: Full-body Anonymization with Human Keypoint Extraction for Real-time Video Deidentification
Online Electric Vehicle Charging Detection Based on Memory-based Transformer using Smart Meter Data
FLASH: Federated Learning-Based LLMs for Advanced Query Processing in Social Networks through RAG
Non-Determinism of "Deterministic" LLM Settings
LLMs are Not Just Next Token Predictors
LLM-based MOFs Synthesis Condition Extraction using Few-Shot Demonstrations
Dopamin: Transformer-based Comment Classifiers through Domain Post-Training and Multi-level Layer Aggregation
Citekit: A Modular Toolkit for Large Language Model Citation Generation
LumiGauss: Relightable Gaussian Splatting in the Wild
Advancing EEG-Based Gaze Prediction Using Depthwise Separable Convolution and Enhanced Pre-Processing
Effect of Kernel Size on CNN-Vision-Transformer-Based Gaze Prediction Using Electroencephalography Data
Can LLMs Serve As Time Series Anomaly Detectors?
Integrating HCI Datasets in Project-Based Machine Learning Courses: A College-Level Review and Case Study
Vision Foundation Models in Remote Sensing: A Survey
Identifying treatment response subgroups in observational time-to-event data
When does the mean network capture the topology of a sample of networks?
Probabilistic Surrogate Model for Accelerating the Design of Electric Vehicle Battery Enclosures for Crash Performance
EEGMobile: Enhancing Speed and Accuracy in EEG-Based Gaze Prediction with Advanced Mobile Architectures
Post-Mortem Human Iris Segmentation Analysis with Deep Learning
Spacecraft inertial parameters estimation using time series clustering and reinforcement learning
Simple Perturbations Subvert Ethereum Phishing Transactions Detection: An Empirical Analysis
Sequential Conditional Transport on Probabilistic Graphs for Interpretable Counterfactual Fairness
Probabilistic Scores of Classifiers, Calibration is not Enough
Logistic Regression makes small LLMs strong and explainable "tens-of-shot" classifiers
A TVD neural network closure and application to turbulent combustion
LLM-Aided Compilation for Tensor Accelerators
Deep Clustering via Distribution Learning
Combining Diverse Information for Coordinated Action: Stochastic Bandit Algorithms for Heterogeneous Agents
Set2Seq Transformer: Temporal and Position-Aware Set Representations for Sequential Multiple-Instance Learning
ULLME: A Unified Framework for Large Language Model Embeddings with Generation-Augmented Learning
RHiOTS: A Framework for Evaluating Hierarchical Time Series Forecasting Algorithms
HeTraX: Energy Efficient 3D Heterogeneous Manycore Architecture for Transformer Acceleration
Biomedical Image Segmentation: A Systematic Literature Review of Deep Learning Based Object Detection Methods
A Non-negative VAE:the Generalized Gamma Belief Network
Prioritize Alignment in Dataset Distillation
LAMPO: Large Language Models as Preference Machines for Few-shot Ordinal Classification
MLC-GCN: Multi-Level Generated Connectome Based GCN for AD Analysis
RayGauss: Volumetric Gaussian-Based Ray Casting for Photorealistic Novel View Synthesis
FastEdit: Fast Text-Guided Single-Image Editing via Semantic-Aware Diffusion Fine-Tuning
The Use of Large Language Models (LLM) for Cyber Threat Intelligence (CTI) in Cybercrime Forums
CoverBench: A Challenging Benchmark for Complex Claim Verification
ClassiFIM: An Unsupervised Method To Detect Phase Transitions
Segment Anything in Medical Images and Videos: Benchmark and Deployment
Hedge Fund Portfolio Construction Using PolyModel Theory and iTransformer
Training LLMs to Recognize Hedges in Spontaneous Narratives
Exchangeable Sequence Models Quantify Uncertainty Over Latent Concepts
Fusing Forces: Deep-Human-Guided Refinement of Segmentation Masks
Understanding How Blind Users Handle Object Recognition Errors: Strategies and Challenges
TextIM: Part-aware Interactive Motion Synthesis from Text
Static IR Drop Prediction with Attention U-Net and Saliency-Based Explainability
DopQ-ViT: Towards Distribution-Friendly and Outlier-Aware Post-Training Quantization for Vision Transformers
SARA: Singular-Value Based Adaptive Low-Rank Adaption
Malicious Internet Entity Detection Using Local Graph Inference
Biomedical SAM 2: Segment Anything in Biomedical Images and Videos

All 190