Papers

New on arXiv

Sun 2 Mar 2025

170 papers

ER-RAG: Enhance RAG with ER-Based Unified Modeling of Heterogeneous Data SourcesRetrieval-augmented generation → RAG pipeline design and evaluation
Optimizing Multi-Hop Document Retrieval Through Intermediate RepresentationsRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
Cyber for AI at SemEval-2025 Task 4: Forgotten but Not Lost: The Balancing Act of Selective Unlearning in Large Language ModelsLLM safety and security → Machine unlearning
Unnatural Languages Are Not Bugs but Features for LLMsLLM safety and security → Jailbreaking
Output Length Effect on DeepSeek-R1's Safety in Forced ThinkingLLM reasoning → Reasoning for agents, planning and code +1
Offline RLAIF: Piloting VLM Feedback for RL via SFOMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +2
Personalize Your LLM: Fake it then Align itLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
Data Unlearning in Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
Delving into Out-of-Distribution Detection with Medical Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
MedUnifier: Unifying Vision-and-Language Pre-training on Medical Data with Vision Generation Task using Discrete Visual RepresentationsMultimodal LLMs / vision-language models → Medical vision-language models
Dialogue Without Limits: Constant-Sized KV Caches for Extended Responses in LLMsEfficient LLM inference and serving → KV cache optimization
An Efficient and Uncertainty-aware Reinforcement Learning Framework for Quality Assurance in Extrusion Additive ManufacturingDeep reinforcement learning methods → RL for energy, networks and operations
Dynamical Diffusion: Learning Temporal Dynamics with Diffusion ModelsDiffusion models → Diffusion foundations and sampling
Behavior Preference Regression for Offline Reinforcement LearningLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
AMUN: Adversarial Machine UNlearningLLM safety and security → Machine unlearning
HiBench: Benchmarking LLMs Capability on Hierarchical Structure ReasoningLLM reasoning → Reasoning benchmarks and evaluation
Instruct-of-Reflection: Enhancing Large Language Models Iterative Reflection Capabilities via Dynamic-Meta InstructionLLM reasoning → Test-time compute and efficient thinking
FunBench: Benchmarking Fundus Reading Skills of MLLMsMultimodal LLMs / vision-language models → Medical vision-language models
A Simple and Effective Reinforcement Learning Method for Text-to-Image Diffusion Fine-tuningDiffusion models → Diffusion and flow policies for robotics +1
Rewarding Graph Reasoning Process makes LLMs more Generalized ReasonersLLM reasoning → Knowledge- and tool-augmented reasoning +1
A Law Reasoning Benchmark for LLM with Tree-Organized Structures including Factum Probandum, Evidence and ExperiencesLLM reasoning → Reasoning for agents, planning and code
AI Agents for Ground-Based Gamma AstronomyLLM agents and tool use → Web, search, and research agents
Minimax Optimal Reinforcement Learning with Quasi-OptimismDeep reinforcement learning methods → RL theory and sample complexity
MFM-DA: Instance-Aware Adaptor and Hierarchical Alignment for Efficient Domain Adaptation in Medical Foundation ModelsDiffusion models → Medical imaging and segmentation
On Generalization Across Environments In Multi-Objective Reinforcement LearningDeep reinforcement learning methods → RL for games and combinatorial optimization
DuoDecoding: Hardware-aware Heterogeneous Speculative Decoding with Dynamic Multi-Sequence DraftingEfficient LLM inference and serving → Speculative decoding
CARIL: Confidence-Aware Regression in Imitation Learning for Autonomous DrivingEnd-to-end autonomous driving → Imitation-learning end-to-end planners +1
Towards Efficient Educational Chatbots: Benchmarking RAG FrameworksRetrieval-augmented generation → Agentic RAG, agents and memory
AffordGrasp: In-Context Affordance Reasoning for Open-Vocabulary Task-Oriented Grasping in ClutterLLM reasoning → Spatial and embodied reasoning
Evaluating Personalized Tool-Augmented LLMs from the Perspectives of Personalization and ProactivityLLM agents and tool use → Tool learning and function calling +1
TRACE: A Self-Improving Framework for Robot Behavior Forecasting with Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
Rethinking Light Decoder-based Solvers for Vehicle Routing ProblemsDeep reinforcement learning methods → RL for games and combinatorial optimization
RAPID: Efficient Retrieval-Augmented Long Text Generation with Writing Planning and Information DiscoveryRetrieval-augmented generation → RAG pipeline design and evaluation
Geodesic Diffusion Models for Efficient Medical Image EnhancementDiffusion models → Medical imaging and segmentation
Quality-Driven Curation of Remote Sensing Vision-Language Data via Learned Scoring ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
LADDER: Self-Improving LLMs Through Recursive Problem DecompositionSynthetic data and self-improvement for LLMs → Synthetic reasoning data and bootstrapping
Robust Real-Time Endoscopic Stereo Matching under Fuzzy Tissue BoundariesState-space sequence models (S4, Mamba) → Mamba for medical image analysis
CLEA: Closed-Loop Embodied Agent for Enhancing Task Execution in Dynamic EnvironmentsLLM agents and tool use → Multimodal and embodied agents
Enhancing Monocular 3D Scene Completion with Diffusion ModelDiffusion models → 3D, point cloud and scene generation
Re-Imagining Multimodal Instruction Tuning: A Representation ViewMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
LLMDR: LLM-Driven Deadlock Detection and Resolution in Multi-Agent PathfindingLLM agents and tool use → General LLM agent frameworks and benchmarks
Spiking World Model with Multi-Compartment Neurons for Model-based Reinforcement LearningWorld models → World models for navigation +1
DualMS: Implicit Dual-Channel Minimal Surface Optimization for Heat Exchanger Design
Human-AI Interaction Design Standards
The Reliability of LLMs for Medical Diagnosis: An Examination of Consistency, Manipulation, and Contextual Awareness
CBW: Towards Dataset Ownership Verification for Speaker Verification via Clustering-based Backdoor Watermarking
Parallel Corpora for Machine Translation in Low-resource Indic Languages: A Comprehensive Review
QCS-ADME: Quantum Circuit Search for Drug Property Prediction with Imbalanced Data and Regression Adaptation
Volume-Wise Task fMRI Decoding with Deep Learning:Enhancing Temporal Resolution and Cognitive Function Analysis
TAET: Two-Stage Adversarial Equalization Training on Long-Tailed Distributions
Pruning Deep Neural Networks via a Combination of the Marchenko-Pastur Distribution and Regularization
NCL-UoR at SemEval-2025 Task 3: Detecting Multilingual Hallucination and Related Observable Overgeneration Text Spans with Modified RefChecker and Modified SeflCheckGPT
AI-Invented Tonal Languages: Preventing a Machine Lingua Franca Beyond Human Understanding
ALinFiK: Learning to Approximate Linearized Future Influence Kernel for Scalable Third-Party LLM Data Valuation
MAPS: Multi-Fidelity AI-Augmented Photonic Simulation and Inverse Design Infrastructure
Language-agnostic, automated assessment of listeners' speech recall using large language models
A Comparison of Object Detection and Phrase Grounding Models in Chest X-ray Abnormality Localization using Eye-tracking Data
Data-Efficient Kernel Methods for Learning Differential Equations and Their Solution Operators: Algorithms and Error Analysis
Variance reduction in output from generative AI
Language Models Predict Empathy Gaps Between Social In-groups and Out-groups
LLM-Fusion: A Novel Multimodal Fusion Model for Accelerated Material Discovery
Generative Motion Infilling From Imprecisely Timed Keyframes
TimeXL: Explainable Multi-modal Time Series Prediction with LLM-in-the-Loop
Solving Satisfiability Modulo Counting Exactly with Probabilistic Circuits
Underdamped Diffusion Bridges with Applications to Sampling
A Semantic Search Pipeline for Causality-driven Adhoc Information Retrieval
Evaluating Polish linguistic and cultural competency in large language models
Evidence of conceptual mastery in the application of rules by Large Language Models
Modeling Fine-Grained Hand-Object Dynamics for Egocentric Video Representation Learning
Enhancing Text Editing for Grammatical Error Correction: Arabic as a Case Study
Machine Learning for Health symposium 2024 -- Findings track
Molecule Generation for Target Protein Binding with Hierarchical Consistency Diffusion Model
SemICP: Semantic Non-Rigid Point Cloud Registration with Elastic Energy Regularization
Using Synthetic Images to Augment Small Medical Image Datasets
CAGN-GAT Fusion: A Hybrid Contrastive Attentive Graph Neural Network for Network Intrusion Detection
Layered Insights: Generalizable Analysis of Authorial Style by Leveraging All Transformer Layers
Exploiting Vulnerabilities in Speech Translation Systems through Targeted Adversarial Attacks
SemViQA: A Semantic Question Answering System for Vietnamese Information Fact-Checking
A Survey on Ordinal Regression: Applications, Advances and Prospects
Extrapolating and Decoupling Image-to-Video Generation Models: Motion Modeling is Easier Than You Think
Cross Modality Medical Image Synthesis for Improving Liver Segmentation
Can AI Model the Complexities of Human Moral Decision-Making? A Qualitative Study of Kidney Allocation Decisions
From Poses to Identity: Training-Free Person Re-Identification via Feature Centralization
Learning-Augmented Frequent Directions
IteRPrimE: Zero-shot Referring Image Segmentation with Iterative Grad-CAM Refinement and Primary Word Emphasis
Improving the Transferability of Adversarial Attacks by an Input Transpose
Parameter-Adaptive Dynamic Pricing
Revisiting CAD Model Generation by Learning Raster Sketch
Explainable Classifier for Malignant Lymphoma Subtyping via Cell Graph and Image Fusion
PABBO: Preferential Amortized Black-Box Optimization
Multimodal Distillation-Driven Ensemble Learning for Long-Tailed Histopathology Whole Slide Images Analysis
Impact of Fasteners on the Radar Cross-Section performance of Radar Absorbing Air Intake Duct
Patient-Level Anatomy Meets Scanning-Level Physics: Personalized Federated Low-Dose CT Denoising Empowered by Large Language Model
Unveiling Biases while Embracing Sustainability: Assessing the Dual Challenges of Automatic Speech Recognition Systems
DEAL: Data-Efficient Adversarial Learning for High-Quality Infrared Imaging
S4M: S4 for multivariate time series forecasting with Missing values
Riemannian Integrated Gradients: A Geometric View of Explainable AI
Estimating Blood Pressure with a Camera: An Exploratory Study of Ambulatory Patients with Cardiovascular Disease
Re-Evaluating the Impact of Unseen-Class Unlabeled Data on Semi-Supervised Learning Model
Evolving High-Quality Rendering and Reconstruction in a Unified Framework with Contribution-Adaptive Regularization

All 170