Papers

New on arXiv

Fri 27 Sep 2024

271 papers

Revisiting the Superficial Alignment HypothesisLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
DANA: Domain-Aware Neurosymbolic Agents for Consistency and AccuracyLLM agents and tool use → General LLM agent frameworks and benchmarks
Mixture of Multicenter Experts in Multimodal AI for Debiased Radiotherapy Target DelineationMixture-of-experts → Medical and biomedical MoE
Evidence Is All You Need: Ordering Imaging Studies via Language Model Alignment with the ACR Appropriateness CriteriaLLM alignment / RLHF / preference optimisation → Medical LLM alignment
HM3: Heterogeneous Multi-Class Model MergingLLM safety and security → Machine unlearning
Multimodal Pragmatic Jailbreak on Text-to-image ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
Pruning then Reweighting: Towards Data-Efficient Training of Diffusion ModelsDiffusion models → Diffusion foundations and sampling
System-Level Defense against Indirect Prompt Injection Attacks: An Information Flow Control PerspectiveLLM safety and security → Prompt injection and agent security
Meta-RTL: Reinforcement-Based Meta-Transfer Learning for Low-Resource Commonsense ReasoningLLM reasoning → Test-time compute and efficient thinking
On the Inductive Bias of Stacking Towards Improving ReasoningLLM reasoning → Test-time compute and efficient thinking
Exploring Token Pruning in Vision State Space ModelsEfficient LLM inference and serving → Token pruning and merging for ViTs
O(d/T) Convergence Theory for Diffusion Probabilistic Models under Minimal AssumptionsDiffusion models → Diffusion foundations and sampling
From Seconds to Hours: Reviewing MultiModal Large Language Models on Comprehensive Long Video UnderstandingLLM reasoning → Multimodal reasoning +1
ReviveDiff: A Universal Diffusion Model for Restoring Images in Adverse Weather ConditionsDiffusion models → Inverse problems and image restoration
Simulated patient systems powered by large language model-based AI agents offer potential for transforming medical educationLLM agents and tool use → Medical and scientific domain agents
Unsupervised Low-light Image Enhancement with Lookup Tables and Diffusion PriorsDiffusion models → Inverse problems and image restoration
Detecting Dataset Abuse in Fine-Tuning Stable Diffusion Models for Text-to-Image SynthesisDiffusion models → Robustness, privacy and adversarial aspects +1
Emu3: Next-Token Prediction is All You NeedDiffusion models → Image generation, text-to-image and editing
ARLBench: Flexible and Efficient Benchmarking for Hyperparameter Optimization in Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
Convergence of Diffusion Models Under the Manifold Hypothesis in High-DimensionsDiffusion models → Diffusion foundations and sampling
MiniVLN: Efficient Vision-and-Language Navigation by Progressive Knowledge DistillationKnowledge distillation → Multimodal distillation
A Survey on the Honesty of Large Language ModelsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
Student-Oriented Teacher Knowledge Refinement for Knowledge DistillationKnowledge distillation → General knowledge distillation methods
Learning from Demonstration with Implicit Nonlinear Dynamics ModelsOffline RL and imitation learning from data → Robot learning from demonstration
Charting the Future: Using Chart Question-Answering for Scalable Evaluation of LLM-Driven Data VisualizationsSynthetic data and self-improvement for LLMs → Self-improving MLLMs and synthetic data
Enhancing Explainability in Multimodal Large Language Models Using Ontological ContextMultimodal LLMs / vision-language models → Agricultural vision-language models
Enhancing Spectrum Efficiency in 6G Satellite Networks: A GAIL-Powered Policy Learning via Asynchronous Federated Inverse Reinforcement LearningOffline RL and imitation learning from data → Offline multi-agent RL +1
Discrete Policy: Learning Disentangled Action Space for Multi-Task Robotic ManipulationDiffusion models → Diffusion and flow policies for robotics
Toward Universal and Interpretable World Models for Open-ended Learning AgentsWorld models → World models for language agents
Speech-Mamba: Long-Context Speech Recognition with Selective State Spaces ModelsState-space sequence models (S4, Mamba) → Speech and audio SSMs
Unsupervised Fingerphoto Presentation Attack Detection With Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
Refutation of Spectral Graph Theory Conjectures with Search Algorithms)Deep reinforcement learning methods → RL for games and combinatorial optimization
Model-based Preference Optimization in Abstractive Summarization without Human FeedbackLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
TemporalPaD: a reinforcement-learning framework for temporal feature representation and dimension reductionDeep reinforcement learning methods → Deep RL algorithms and representations
Corpus-informed Retrieval Augmented Generation of Clarifying QuestionsRetrieval-augmented generation → RAG robustness and adaptive retrieval
Climate Adaptation with Reinforcement Learning: Experiments with Flooding and Transportation in CopenhagenDeep reinforcement learning methods → RL for energy, networks and operations
Harmonizing knowledge Transfer in Neural Network with Unified DistillationKnowledge distillation → General knowledge distillation methods
Align2LLaVA: Cascaded Human and Large Language Model Preference Alignment for Multi-modal Instruction CurationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
A Survey on Complex Tasks for Goal-Directed Interactive AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
Token Caching for Diffusion Transformer AccelerationDiffusion models → Diffusion foundations and sampling
Treating Brain-inspired Memories as Priors for Diffusion Model to Forecast Multivariate Time SeriesDiffusion models → Flow matching, time series and science
Underwater Image Enhancement with Physical-based Denoising Diffusion Implicit ModelsDiffusion models → Inverse problems and image restoration
FoodMLLM-JP: Leveraging Multimodal Large Language Models for Japanese Recipe GenerationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Cost-Aware Dynamic Cloud Workflow Scheduling using Self-Attention and Evolutionary Reinforcement LearningDeep reinforcement learning methods → RL for energy, networks and operations
Gradient-free Decoder Inversion in Latent Diffusion ModelsDiffusion models → Diffusion foundations and sampling
State-free Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
VickreyFeedback: Cost-efficient Data Construction for Reinforcement Learning from Human FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
SciDFM: A Large Language Model with Mixture-of-Experts for ScienceMixture-of-experts → MoE large language models
GenesisTex2: Stable, Consistent and High-Quality Text-to-Texture GenerationDiffusion models → 3D, point cloud and scene generation
Multi-hypotheses Conditioned Point Cloud Diffusion for 3D Human Reconstruction from Occluded ImagesDiffusion models → 3D, point cloud and scene generation
Generative AI for fast and accurate statistical computation of fluidsDiffusion models → Flow matching, time series and science
Volatility Forecasting in Global Financial Markets Using TimeMixer
EarthquakeNPP: A Benchmark for Earthquake Forecasting with Neural Point Processes
Analysis and Optimization of Seismic Monitoring Networks with Bayesian Optimal Experiment Design
Building a Chinese Medical Dialogue System: Integrating Large-scale Corpora and Novel Models
A GEN AI Framework for Medical Note Generation
FlashMix: Fast Map-Free LiDAR Localization via Feature Mixing and Contrastive-Constrained Accelerated Training
Looking through the mind's eye via multimodal encoder-decoder networks
Artificial intelligence-based blockchain-driven financial default prediction
Semi-Supervised Bone Marrow Lesion Detection from Knee MRI Segmentation Using Mask Inpainting Models
Learning-Based Image Compression for Machines
Artificial-Intelligence Generated Code Considered Harmful: A Road Map for Secure and High-Quality Code Generation
A comprehensive review and new taxonomy on superpixel segmentation
FLINT: Learning-based Flow Estimation and Temporal Interpolation for Scientific Ensemble Visualization
Feature Estimation of Global Language Processing in EEG Using Attention Maps
Reducing Overtreatment of Indeterminate Thyroid Nodules Using a Multimodal Deep Learning Model
bnRep: A repository of Bayesian networks from the academic literature
Calibrated Probabilistic Forecasts for Arbitrary Sequences
MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motion
Can LLMs Really Learn to Translate a Low-Resource Language from One Grammar Book?
On the Power of Decision Trees in Auto-Regressive Language Modeling
Uncovering Differences in Persuasive Language in Russian versus English Wikipedia
Bound Tightening Network for Robust Crowd Counting
Diverse Code Query Learning for Speech-Driven Facial Animation
TTT4Rec: A Test-Time Training Approach for Rapid Adaption in Sequential Recommendation
Physics-Informed Echo State Networks for Modeling Controllable Dynamical Systems
Sequencing the Neurome: Towards Scalable Exact Parameter Reconstruction of Black-Box Neural Networks
Kinematic Detection of Anomalies in Human Trajectory Data
Chebyshev Feature Neural Network for Accurate Function Approximation
Confidential Prompting: Privacy-preserving LLM Inference on Cloud
From Vision to Audio and Beyond: A Unified Model for Audio-Visual Representation and Generation
Multi-modal Cross-domain Self-supervised Pre-training for fMRI and EEG Fusion
Secure Multiparty Generative AI
Range-aware Positional Encoding via High-order Pretraining: Theory and Practice
Fusion is all you need: Face Fusion for Customized Identity-Preserving Image Synthesis
Responsible AI in Open Ecosystems: Reconciling Innovation with Risk Assessment and Disclosure
Implementing NLPs in industrial process modeling: Addressing Categorical Variables
Enhancing Robustness of Graph Neural Networks through p-Laplacian
Federated Online Prediction from Experts with Differential Privacy: Separations and Regret Speed-ups
Solving FDR-Controlled Sparse Regression Problems with Five Million Variables on a Laptop
Differential privacy enables fair and accurate AI-based analysis of speech disorders while protecting patient data
Show and Guide: Instructional-Plan Grounded Vision and Language Model
Localizing Memorization in SSL Vision Encoders
CURATE: Scaling-up Differentially Private Causal Graph Discovery
CLLMate: A Multimodal Benchmark for Weather and Climate Events Forecasting
Multimodal Markup Document Models for Graphic Design Completion
Gaussian Heritage: 3D Digitization of Cultural Heritage with Integrated Object Segmentation
Intention-aware policy graphs: answering what, how, and why in opaque agents
Self-Replicating Mechanical Universal Turing Machine
PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation

All 271