Papers

New on arXiv

Sun 20 Oct 2024

153 papers

Do RAG Systems Cover What Matters? Evaluating and Optimizing Responses with Sub-Question CoverageRetrieval-augmented generation → RAG robustness and adaptive retrieval
M-RewardBench: Evaluating Reward Models in Multilingual SettingsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
Generating Tabular Data Using Heterogeneous Sequential Feature Forest Flow MatchingDiffusion models → Flow matching, time series and science
ConTReGen: Context-driven Tree-structured Retrieval for Open-domain Long-form Text GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
Reinforcement Learning for Dynamic Memory AllocationDeep reinforcement learning methods → Deep RL algorithms and representations
"What is the value of {templates}?" Rethinking Document Information Extraction Datasets for LLMsLLM reasoning → Multimodal reasoning
Understanding Forgetting in LLM Supervised Fine-Tuning and Preference Learning -- A Convex Optimization PerspectiveLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Data Augmentation via Diffusion Model to Enhance AI FairnessDiffusion models → Flow matching, time series and science
AssemblyComplete: 3D Combinatorial Construction with Deep Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
EVA: An Embodied World Model for Future Video AnticipationWorld models → Video-generation world models and simulators
Heterogeneous Graph Reinforcement Learning for Dependency-aware Multi-task Allocation in Spatial CrowdsourcingDeep reinforcement learning methods → RL for games and combinatorial optimization
Unveiling and Consulting Core Experts in Retrieval-Augmented MoE-based LLMsRetrieval-augmented generation → RAG pipeline design and evaluation +1
MedDiff-FM: A Diffusion-based Foundation Model for Versatile Medical Image ApplicationsDiffusion models → Medical imaging and segmentation
BoostAdapter: Improving Vision-Language Test-Time Adaptation via Regional BootstrappingMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP +1
IPO: Interpretable Prompt Optimization for Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
LoRA-IR: Taming Low-Rank Experts for Efficient All-in-One Image RestorationMixture-of-experts → Vision mixture-of-experts
FrameBridge: Improving Image-to-Video Generation with Bridge ModelsDiffusion models → Video generation
Scene Graph Generation with Role-Playing Large Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Faster-GCG: Efficient Discrete Optimization Jailbreak Attacks against Aligned Large Language ModelsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
IKDP: Inverse Kinematics through Diffusion ProcessDiffusion models → Diffusion and flow policies for robotics
Diffusion-PINN SamplerDiffusion models → Diffusion foundations and sampling
Modality-Fair Preference Optimization for Trustworthy MLLM AlignmentMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
Training Language Models to Critique With Multi-agent FeedbackLLM agents and tool use → General LLM agent frameworks and benchmarks
Customized FinGPT Search Agents Using Foundation ModelsLLM agents and tool use → Financial trading and forecasting agents
LLM4AD: Large Language Models for Autonomous Driving -- Concept, Review, Benchmark, Experiments, and Future TrendsEnd-to-end autonomous driving → Large language models for driving
BRIEF: Bridging Retrieval and Inference for Multi-hop Reasoning via CompressionLLM reasoning → Knowledge- and tool-augmented reasoning +1
FIOVA: A Multi-Annotator Benchmark for Human-Aligned Video CaptioningMultimodal LLMs / vision-language models → Video understanding with MLLMs
When Machine Unlearning Meets Retrieval-Augmented Generation (RAG): Keep Secret or Forget Knowledge?Retrieval-augmented generation → RAG pipeline design and evaluation +1
HyQE: Ranking Contexts with Hypothetical Query EmbeddingsRetrieval-augmented generation → Generation and context integration
Lossless KV Cache Compression to 2%Efficient LLM inference and serving → KV cache optimization
FastSTI: A Fast Conditional Pseudo Numerical Diffusion Model for Spatio-temporal Traffic Data ImputationDiffusion models → Flow matching, time series and science
Jailbreaking and Mitigation of Vulnerabilities in Large Language ModelsLLM safety and security → Jailbreaking
Comparative Analysis of LSTM, GRU, and Transformer Models for Stock Price Prediction
log-RRIM: Yield Prediction via Local-to-global Reaction Representation Learning and Interaction Modeling
Fairness Evaluation with Item Response Theory
Slicing for AI: An Online Learning Framework for Network Slicing Supporting AI Services
An Improved Chicken Swarm Optimization Algorithm for Handwritten Document Image Enhancement
A Heterogeneous Network-based Contrastive Learning Approach for Predicting Drug-Target Interaction
Integrating Symbolic Neural Networks with Building Physics: A Study and Proposal
Non-invasive Neural Decoding in Source Reconstructed Brain Space
Upsampling DINOv2 features for unsupervised vision tasks and weakly supervised materials segmentation
Advancing Gasoline Consumption Forecasting: A Novel Hybrid Model Integrating Transformers, LSTM, and CNN
Grammatical Error Correction for Low-Resource Languages: The Case of Zarma
GRS: Generating Robotic Simulation Tasks from Real-World Images
Improving Clinical Documentation with AI: A Comparative Study of Sporo AI Scribe and GPT-4o mini
SDP4Bit: Toward 4-bit Communication Quantization in Sharded Data Parallelism for LLM Training
MIRA: A Method of Federated MultI-Task Learning for LaRge LAnguage Models
Lying mirror using structured surfaces
TrackMe:A Simple and Effective Multiple Object Tracking Annotation Tool
SceneGraMMi: Scene Graph-boosted Hybrid-fusion for Multi-Modal Misinformation Veracity Prediction
Reverse Question Answering: Can an LLM Write a Question so Hard (or Bad) that it Can't Answer?
Exploring Curriculum Learning for Vision-Language Tasks: A Study on Small-Scale Multimodal Training
Predicting adaptively chosen observables in quantum systems
Anonymising Elderly and Pathological Speech: Voice Conversion Using DDSP and Query-by-Example
Improving Voice Quality in Speech Anonymization With Just Perception-Informed Losses
RoMemes: A multimodal meme corpus for the Romanian language
Taming Mambas for Voxel Level 3D Medical Image Segmentation
SEA: State-Exchange Attention for High-Fidelity Physics Based Transformers
Structural Causality-based Generalizable Concept Discovery Models
Dynamic Intelligence Assessment: Benchmarking LLMs on the Road to AGI with a Focus on Model Confidence
Generative AI Agents in Autonomous Machines: A Safety Perspective
Event-based Sensor Fusion and Application on Odometry: A Survey
Multimodal Fusion via Self-Consistent Task-Gradient Fields
Optimizing Backward Policies in GFlowNets via Trajectory Likelihood Maximization
A Bayesian Framework for Clustered Federated Learning
Multi-Layer Feature Fusion with Cross-Channel Attention-Based U-Net for Kidney Tumor Segmentation
Generative Models, Humans, Predictive Models: Who Is Worse at High-Stakes Decision Making?
Hey GPT, Can You be More Racist? Analysis from Crowdsourced Attempts to Elicit Biased Content from Generative AI
Keep Guessing? When Considering Inference Scaling, Mind the Baselines
A Novel Interpretability Metric for Explaining Bias in Language Models: Applications on Multilingual Models from Southeast Asia
MedLogic-AQA: Enhancing Medical Question Answering with Abstractive Models Focusing on Logical Structures
Hallucination Detox: Sensitivity Dropout (SenD) for Large Language Model Training
Allegro: Open the Black Box of Commercial-Level Video Generation Model
CROPE: Evaluating In-Context Adaptation of Vision and Language Models to Culture-Specific Concepts
Concept Complement Bottleneck Model for Interpretable Medical Image Diagnosis
MDFI-Net: Multiscale Differential Feature Interaction Network for Accurate Retinal Vessel Segmentation
Exploring Social Desirability Response Bias in Large Language Models: Evidence from GPT-4 Simulations
Evaluating Consistencies in LLM responses through a Semantic Clustering of Question Answering
AttCDCNet: Attention-enhanced Chest Disease Classification using X-Ray Images
Discriminating image representations with principal distortions
Efficient Model Extraction via Boundary Sampling
Accelerated Sub-Image Search For Variable-Size Patches Identification Based On Virtual Time Series Transformation And Segmentation
Power Plays: Unleashing Machine Learning Magic in Smart Grids
Where to Build Food Banks and Pantries: A Two-Level Machine Learning Approach
CASET: Complexity Analysis using Simple Execution Traces for CS* submissions
Contrast All the Time: Learning Time Series Representation from Temporal Consistency
A Comprehensive Evaluation of Cognitive Biases in LLMs
PEAS: A Strategy for Crafting Transferable Adversarial Examples
XAI-based Feature Ensemble for Enhanced Anomaly Detection in Autonomous Driving Systems
MMDS: A Multimodal Medical Diagnosis System Integrating Image Analysis and Knowledge-based Departmental Consultation
The Best Defense is a Good Offense: Countering LLM-Powered Cyberattacks
CalibraEval: Calibrating Prediction Distribution to Mitigate Selection Bias in LLMs-as-Judges
EF-3DGS: Event-Aided Free-Trajectory 3D Gaussian Splatting
Layout-your-3D: Controllable and Precise 3D Generation with 2D Blueprint
High-dimensional prediction for count response via sparse exponential weights
Synthetic Data Generation for Residential Load Patterns via Recurrent GAN and Ensemble Method
Neural Active Structure-from-Motion in Dark and Textureless Environment
ActiveNeuS: Neural Signed Distance Fields for Active Stereo
Explainability of Point Cloud Neural Networks Using SMILE: Statistical Model-Agnostic Interpretability with Local Explanations
DynaVINS++: Robust Visual-Inertial State Estimator in Dynamic Environments by Adaptive Truncated Least Squares and Stable State Recovery

All 153