Papers

New on arXiv

Wed 11 Sep 2024

239 papers

Brain Network Diffusion-Driven fMRI Connectivity Augmentation for Enhanced Autism Spectrum Disorder DiagnosisDiffusion models → Medical imaging and segmentation
Mamba for Scalable and Efficient Personalized RecommendationsState-space sequence models (S4, Mamba) → Core SSM architectures for language
Context-Aware Membership Inference Attacks against Pre-trained Large Language ModelsLLM safety and security → Membership inference attacks
Inf-MLLM: Efficient Streaming Inference of Multimodal Large Language Models on a Single GPUMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
FlowSep: Language-Queried Sound Separation with Rectified Flow MatchingDiffusion models → Audio, speech and music
The Role of Deep Learning Regularizations on Actors in Offline RLOffline RL and imitation learning from data → Offline RL algorithms
miMamba: EEG-based Emotion Recognition with Multi-scale Inverted Mamba ModelsState-space sequence models (S4, Mamba) → Physiological signal modeling
New constructions of pseudorandom codesLLM safety and security → Watermarking generated content and models
A Comprehensive Survey on Inverse Constrained Reinforcement Learning: Definitions, Progress and ChallengesDeep reinforcement learning methods → RL for robot locomotion and manipulation
EchoDFKD: Data-Free Knowledge Distillation for Cardiac Ultrasound Segmentation using Synthetic DataKnowledge distillation → Distillation for medical imaging
Unsupervised Point Cloud Registration with Self-DistillationKnowledge distillation → Detection and dense prediction distillation
AdaPPA: Adaptive Position Pre-Fill Jailbreak Attack Approach Targeting LLMsLLM safety and security → Jailbreaking
DreamMesh: Jointly Manipulating and Texturing Triangle Meshes for Text-to-3D GenerationDiffusion models → 3D, point cloud and scene generation
Hi3D: Pursuing High-Resolution Image-to-3D Generation with Video Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
FreeEnhance: Tuning-Free Image Enhancement via Content-Consistent Noising-and-Denoising ProcessDiffusion models → Diffusion foundations and sampling
StereoCrafter: Diffusion-based Generation of Long and High-fidelity Stereoscopic 3D from Monocular VideosDiffusion models → 3D, point cloud and scene generation
SUPER: Evaluating Agents on Setting Up and Executing Tasks from Research RepositoriesLLM agents and tool use → Web, search, and research agents
Agent Workflow MemoryLLM agents and tool use → Web, search, and research agents
Hierarchical Reinforcement Learning for Temporal Abstraction of Listwise RecommendationDeep reinforcement learning methods → RL training of language and agent models
Training-Free Guidance for Discrete Diffusion Models for Molecular GenerationDiffusion models → Flow matching, time series and science
Think Together and Work Better: Combining Humans' and LLMs' Think-Aloud Outcomes for Effective Text EvaluationLLM reasoning → Reasoning benchmarks and evaluation
Securing Vision-Language Models with a Robust Encoder Against Jailbreak and Adversarial AttacksMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
Learning Robotic Manipulation Policies from Point Clouds with Conditional Flow MatchingDiffusion models → Diffusion and flow policies for robotics +1
Online Decision MetaMorphFormer: A Casual Transformer-Based Reinforcement Learning Framework of Universal Embodied IntelligenceDeep reinforcement learning methods → RL for robot locomotion and manipulation
Explanation, Debate, Align: A Weak-to-Strong Framework for Language Model GeneralizationLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
Learning to Compress Contexts for Efficient Knowledge-based Visual Question AnsweringMultimodal LLMs / vision-language models → Visual token pruning and efficiency
Efficient and Unbiased Sampling of Boltzmann Distributions via Consistency ModelsDiffusion models → Diffusion foundations and sampling
Module-wise Adaptive Adversarial Training for End-to-end Autonomous DrivingEnd-to-end autonomous driving → Adversarial scenarios and safety testing
MEDIC: Comprehensive Evaluation of Leading Indicators for LLM Safety and Utility in Clinical ApplicationsLLM safety and security → Safety alignment, refusal and guardrails
Data Augmentation via Latent Diffusion for Saliency PredictionDiffusion models → Image generation, text-to-image and editing
Exploring User-level Gradient Inversion with a Diffusion PriorDiffusion models → Robustness, privacy and adversarial aspects
Using Generative Agents to Create Tip Sheets for Investigative Data ReportingLLM agents and tool use → Web, search, and research agents
Rethinking Mamba in Speech Processing by Self-Supervised ModelsState-space sequence models (S4, Mamba) → Speech and audio SSMs
CFCPalsy: Facial Image Synthesis with Cross-Fusion Cycle Diffusion Model for Facial Paralysis IndividualsDiffusion models → Audio, speech and music
Realistic and Efficient Face Swapping: A Unified Approach with Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
Multi-Type Preference Learning: Empowering Preference-Based Reinforcement Learning with Equal PreferencesDeep reinforcement learning methods → RL training of language and agent models
MiniDrive: More Efficient Vision-Language Models with Multi-Level 2D Features as Text Tokens for Autonomous DrivingMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +2
Alignment of Diffusion Models: Fundamentals, Challenges, and FutureDiffusion models → Diffusion foundations and sampling
PiTe: Pixel-Temporal Alignment for Large Video-Language ModelMultimodal LLMs / vision-language models → Video understanding with MLLMs
Diff-VPS: Video Polyp Segmentation via a Multi-task Diffusion Network with Adversarial Temporal ReasoningDiffusion models → Medical imaging and segmentation
Behavioral Cloning Models Reality Check for Autonomous DrivingOffline RL and imitation learning from data → Imitation and offline RL for driving
Phy124: Fast Physics-Driven 4D Content Generation from a Single ImageDiffusion models → Video generation
Learning Efficient Recursive Numeral Systems via Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
Mamba Policy: Towards Efficient 3D Diffusion Policy with Hybrid Selective State ModelsDiffusion models → Diffusion and flow policies for robotics +1
Cross-Refine: Improving Natural Language Explanation Generation by Learning in TandemLLM reasoning → Test-time compute and efficient thinking
Pushing the Limits of Vision-Language Models in Remote Sensing without Human AnnotationsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
From optimal score matching to optimal samplingDiffusion models → Diffusion foundations and sampling
CPSample: Classifier Protected Sampling for Guarding Training Data During DiffusionDiffusion models → Robustness, privacy and adversarial aspects
AdvLogo: Adversarial Patch Attack against Object Detectors based on Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
Unveiling Markov Heads in Pretrained Language Models for Offline Reinforcement LearningOffline RL and imitation learning from data → Decision transformers and sequence modeling
Policy Filtration for RLHF to Mitigate Noise in Reward ModelsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
Privacy-Preserving Federated Learning with Consistency via Knowledge Distillation Using Conditional GeneratorKnowledge distillation → Federated, robust and private distillation
You Have Thirteen Hours in Which to Solve the Labyrinth: Enhancing AI Game Masters with Function CallingLLM agents and tool use → Reinforcement learning for LLM agents
Integrating SPARQL and LLMs for Question Answering over Scholarly Data Sources
Safety challenges of AI in medicine in the era of large language models
Multi-scale decomposition of sea surface height snapshots using machine learning
Autonomous Vehicle Decision-Making Framework for Considering Malicious Behavior at Unsignalized Intersections
Contextualization of ASR with LLM using phonetic retrieval-based augmentation
Mapping Biomedical Ontology Terms to IDs: Effect of Domain Prevalence on Prediction Accuracy
A Simplified Retriever to Improve Accuracy of Phenotype Normalizations by Large Language Models
Semantic Interoperability on Blockchain by Generating Smart Contracts Based on Knowledge Graphs
The Unreliability of Acoustic Systems in Alzheimer's Speech Datasets with Heterogeneous Recording Conditions
DrLLM: Prompt-Enhanced Distributed Denial-of-Service Resistance Method with Large Language Models
An Evaluation of GPT-4V for Transcribing the Urban Renewal Hand-Written Collection
Y-Drop: A Conductance based Dropout for fully connected layers
KKT-Informed Neural Network
HESSO: Towards Automatic Efficient and User Friendly Any Neural Network Training and Pruning
Distributed Convolutional Neural Network Training on Mobile and Edge Clusters
Mapping the Russian Internet Troll Network on Twitter using a Predictive Model
Passed the Turing Test: Living in Turing Futures
STAND: Self-Aware Precondition Induction for Interactive Task Learning
Gaussian Process Upper Confidence Bounds in Distributed Point Target Tracking over Wireless Sensor Networks
Foundation Models Boost Low-Level Perceptual Similarity Metrics
DiffTED: One-shot Audio-driven TED Talk Video Generation with Diffusion-based Co-speech Gestures
Feature Importance in Pedestrian Intention Prediction: A Context-Aware Review
Deep Learning of Dynamic Systems using System Identification Toolbox(TM)
SimulBench: Evaluating Language Models with Creative Simulation Tasks
Can We Count on LLMs? The Fixed-Effect Fallacy and Claims of GPT-4 Capabilities
Weather-Informed Probabilistic Forecasting and Scenario Generation in Power Systems
Learning Robust Observable to Address Noise in Quantum Machine Learning
Dividable Configuration Performance Learning
Leveraging User-Generated Reviews for Recommender Systems with Dynamic Headers
Generalization Error Bound for Quantum Machine Learning in NISQ Era -- A Survey
Object Depth and Size Estimation using Stereo-vision and Integration with SLAM
Ensemble Methods for Sequence Classification with Hidden Markov Models
Understanding Foundation Models: Are We Back in 1924?
MOSAIC: Multiple Observers Spotting AI Content
Token Turing Machines are Efficient Vision Models
When More Data Hurts: Optimizing Data Coverage While Mitigating Diversity Induced Underfitting in an Ultra-Fast Machine-Learned Potential
Survival of the Cheapest: Cost-Aware Hardware Adaptation for Adversarial Robustness
Automated Discovery of Pairwise Interactions from Unstructured Data
Deep Learning for predicting rate-induced tipping
2D bidirectional gated recurrent unit convolutional Neural networks for end-to-end violence detection In videos
Efficient Localized Adaptation of Neural Weather Forecasting: A Case Study in the MENA Region
DS-ViT: Dual-Stream Vision Transformer for Cross-Task Distillation in Alzheimer's Early Diagnosis
Minimizing Embedding Distortion for Robust Out-of-Distribution Performance
Violence detection in videos using deep recurrent and convolutional neural networks
A Novel Mathematical Framework for Objective Characterization of Ideas
Self-Masking Networks for Unsupervised Adaptation
FaVoR: Features via Voxel Rendering for Camera Relocalization

All 239