Papers

New on arXiv

Sun 29 Sep 2024

167 papers

Focus On What Matters: Separated Models For Visual-Based RL GeneralizationDeep reinforcement learning methods → RL for robot locomotion and manipulation
Hypnopaedia-Aware Machine Unlearning via Psychometrics of Artificial Mental ImageryLLM safety and security → Backdoor and data poisoning attacks
Overcoming the Machine Penalty with Imperfectly Fair AI AgentsLLM agents and tool use → Social simulation and multi-agent debate
Survey of Security and Data Attacks on Machine Unlearning In Financial and E-CommerceLLM safety and security → Machine unlearning
Counterfactual Evaluation of Ads Ranking Models through Domain AdaptationLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
Calibrating Language Models with Adaptive Temperature ScalingLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Grounded Curriculum LearningDeep reinforcement learning methods → Deep RL algorithms and representations
PALM: Few-Shot Prompt Learning for Audio Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Does RAG Introduce Unfairness in LLMs? Evaluating Fairness in Retrieval-Augmented Generation SystemsRetrieval-augmented generation → RAG robustness and adaptive retrieval
Membership Inference Attacks Cannot Prove that a Model Was Trained On Your DataLLM safety and security → Membership inference attacks
The Duke Humanoid: Design and Control For Energy Efficient Bipedal Locomotion Using Passive DynamicsDeep reinforcement learning methods → RL for robot locomotion and manipulation
Analysis on Riemann Hypothesis with Cross Entropy Optimization and ReasoningLLM reasoning → Mathematical reasoning
Adaptive Event-triggered Reinforcement Learning Control for Complex Nonlinear SystemsDeep reinforcement learning methods → RL theory and sample complexity
Balancing Cost and Effectiveness of Synthetic Data Generation Strategies for LLMsSynthetic data and self-improvement for LLMs → LLM synthetic data generation
CoTKR: Chain-of-Thought Enhanced Knowledge Rewriting for Complex Knowledge Graph Question AnsweringLLM reasoning → Knowledge- and tool-augmented reasoning +1
Learning Robust Policies via Interpretable Hamilton-Jacobi Reachability-Guided DisturbancesDeep reinforcement learning methods → Adversarial robustness and RL in finance
PEAR: Position-Embedding-Agnostic Attention Re-weighting Enhances Retrieval-Augmented Generation with Zero Inference OverheadRetrieval-augmented generation → Generation and context integration
Tailored Federated Learning: Leveraging Direction Regulation & Knowledge DistillationKnowledge distillation → Federated, robust and private distillation
Scrambled text: training Language Models to correct OCR errors using synthetic dataSynthetic data and self-improvement for LLMs → LLM synthetic data generation
T2Vs Meet VLMs: A Scalable Multimodal Dataset for Visual Harmfulness RecognitionLLM safety and security → Safety alignment, refusal and guardrails
Unified Gradient-Based Machine Unlearning with Remain Geometry EnhancementLLM safety and security → Machine unlearning
Constrained Reinforcement Learning for Safe Heat Pump ControlDeep reinforcement learning methods → RL for energy, networks and operations
Coffee-Gym: An Environment for Evaluating and Improving Natural Language Feedback on Erroneous CodeLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
A multimodal LLM for the non-invasive decoding of spoken text from brain recordingsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
DreamWaQ++: Obstacle-Aware Quadrupedal Locomotion With Resilient Multi-Modal Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
A Certified Robust Watermark For Large Language ModelsLLM safety and security → Watermarking generated content and models
Vision-Language Models are Strong Noisy Label DetectorsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Text-driven Human Motion Generation with Motion Masked Diffusion ModelDiffusion models → Video generation
MedViLaM: A multimodal large language model with advanced generalizability and explainability for medical data understanding and generationMultimodal LLMs / vision-language models → Medical vision-language models
Simple and Fast Distillation of Diffusion ModelsDiffusion models → Diffusion foundations and sampling
SemiDDM-Weather: A Semi-supervised Learning Framework for All-in-one Adverse Weather RemovalDiffusion models → Inverse problems and image restoration
Flipped Classroom: Aligning Teacher Attention with Student in Generalized Category DiscoveryKnowledge distillation → General knowledge distillation methods
Multimodal Misinformation Detection by Learning from Synthetic Data with Multimodal LLMsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
Storynizor: Consistent Story Generation via Inter-Frame Synchronized and Shuffled ID InjectionDiffusion models → Image generation, text-to-image and editing
MCDDPM: Multichannel Conditional Denoising Diffusion Model for Unsupervised Anomaly Detection in Brain MRIDiffusion models → Medical imaging and segmentation
LiRA: Light-Robust Adversary for Model-based Reinforcement Learning in Real WorldDeep reinforcement learning methods → Adversarial robustness and RL in finance
Hybrid Mamba for Few-Shot SegmentationState-space sequence models (S4, Mamba) → Vision Mamba backbones
Federated Learning from Vision-Language Foundation Models: Theoretical Analysis and MethodMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Causal Deciphering and Inpainting in Spatio-Temporal Dynamics via Diffusion ModelDiffusion models → Flow matching, time series and science
The Crucial Role of Samplers in Online Direct Preference OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
One Token to Seg Them All: Language Instructed Reasoning Segmentation in VideosLLM reasoning → Multimodal reasoning +1
DiffCP: Ultra-Low Bit Collaborative Perception via Diffusion ModelDiffusion models → Diffusion for compression and wireless
Effective Diffusion Transformer Architecture for Image Super-ResolutionDiffusion models → Inverse problems and image restoration
High Quality Human Image Animation using Regional Supervision and Motion Blur ConditionDiffusion models → Video generation
FoAM: Foresight-Augmented Multi-Task Imitation Policy for Robotic ManipulationOffline RL and imitation learning from data → Robot manipulation imitation learning
Efficient Backdoor Defense in Multimodal Contrastive Learning: A Token-Level Unlearning Method for Mitigating ThreatsLLM safety and security → Backdoor and data poisoning attacks
GenTel-Safe: A Unified Benchmark and Shielding Framework for Defending Against Prompt Injection AttacksLLM safety and security → Prompt injection and agent security
Making LLMs Better Many-to-Many Speech-to-Text Translators with Curriculum LearningMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Ads Supply Personalization via Doubly Robust Learning
Design of an Efficient Fan-Shaped Clustered Trust-Based Routing Model with QoS & Security-Aware Side-Chaining for IoV Deployments
Swap-Net: A Memory-Efficient 2.5D Network for Sparse-View 3D Cone Beam CT Reconstruction
DIIT: A Domain-Invariant Information Transfer Method for Industrial Cross-Domain Recommendation
Online Client Scheduling and Resource Allocation for Efficient Federated Edge Learning
Finetuning YOLOv9 for Vehicle Detection: Deep Learning for Intelligent Transportation Systems in Dhaka, Bangladesh
Stock Price Prediction and Traditional Models: An Approach to Achieve Short-, Medium- and Long-Term Goals
Realtime, multimodal invasive ventilation risk monitoring using language models and BoXHED
Human Bias in the Face of AI: Examining Human Judgment Against Text Labeled as AI Generated
Automated Disease Diagnosis in Pumpkin Plants Using Advanced CNN Models
Neural Decompiling of Tracr Transformers
IDEA: An Inverse Domain Expert Adaptation Based Active DNN IP Protection Method
STTM: A New Approach Based Spatial-Temporal Transformer And Memory Network For Real-time Pressure Signal In On-demand Food Delivery
Generalizability of Graph Neural Networks for Decentralized Unlabeled Motion Planning
OrganiQ: Mitigating Classical Resource Bottlenecks of Quantum Generative Adversarial Networks on NISQ-Era Machines
Tracking Everything in Robotic-Assisted Surgery
Qompose: A Technique to Select Optimal Algorithm- Specific Layout for Neutral Atom Quantum Architectures
Transforming Hidden States into Binary Semantic Features
Robust Incremental Structure-from-Motion with Hybrid Features
Can Models Learn Skill Composition from Examples?
CRScore: Grounding Automated Evaluation of Code Review Comments in Code Claims and Smells
Differentially Private Bilevel Optimization
Black-Box Segmentation of Electronic Medical Records
Gradient descent with adaptive stepsize converges (nearly) linearly under fourth-order growth
Exploring Adversarial Robustness in Classification tasks using DNA Language Models
Automatic debiasing of neural networks via moment-constrained learning
Crafting Distribution Shifts for Validation and Training in Single Source Domain Generalization
PPLNs: Parametric Piecewise Linear Networks for Event-Based Temporal Modeling and Beyond
Towards Robust Extractive Question Answering Models: Rethinking the Training Methodology
Offline Signature Verification Based on Feature Disentangling Aided Variational Autoencoder
Balancing the Scales: A Comprehensive Study on Tackling Class Imbalance in Binary Classification
AstroMLab 2: AstroLLaMA-2-70B Model and Benchmarking Specialised LLMs for Astronomy
NeuroMax: Enhancing Neural Topic Modeling via Maximizing Mutual Information and Group Topic Regularization
Natural Language Generation for Visualizations: State of the Art, Challenges and Future Directions
When Molecular GAN Meets Byte-Pair Encoding
A Systematic Review of NLP for Dementia -- Tasks, Datasets and Opportunities
Pear: Pruning and Sharing Adapters in Visual Parameter-Efficient Fine-Tuning
Investigating the Effect of Network Pruning on Performance and Interpretability
DataDRILL: Formation Pressure Prediction and Kick Detection for Drilling Rigs
Revealing Personality Traits: A New Benchmark Dataset for Explainable Personality Recognition on Dialogues
FAST: A Dual-tier Few-Shot Learning Paradigm for Whole Slide Image Classification
Evolving Multi-Scale Normalization for Time Series Forecasting under Distribution Shifts
Generating peak-aware pseudo-measurements for low-voltage feeders using metadata of distribution system operators
Posterior Conformal Prediction
Applying the Lower-Biased Teacher Model in Semi-Supervised Object Detection
RNG: Relightable Neural Gaussians
Hyperspectral Unmixing of Agricultural Images taken from UAV Using Adapted U-Net Architecture
2D-TPE: Two-Dimensional Positional Encoding Enhances Table Understanding for Large Language Models
CERD: A Comprehensive Chinese Rhetoric Dataset for Rhetorical Understanding and Generation in Essays
Neural-Polyptych: Content Controllable Painting Recreation for Diverse Genres
InfantCryNet: A Data-driven Framework for Intelligent Analysis of Infant Cries
Machine Learning for Raman Spectroscopy-based Cyber-Marine Fish Biochemical Composition Analysis

All 167