Papers

New on arXiv

Sun 27 Jul 2025

147 papers

Lessons from A Large Language Model-based Outdoor Trail Recommendation Chatbot with Retrieval Augmented GenerationRetrieval-augmented generation → RAG for recommendation
HoneyImage: Verifiable, Harmless, and Stealthy Dataset Ownership Verification for Image ModelsLLM safety and security → Watermarking generated content and models
Spatial-Temporal Reinforcement Learning for Network Routing with Non-Markovian TrafficDeep reinforcement learning methods → RL for energy, networks and operations
Beyond Neural Networks: Symbolic Reasoning over Wavelet Logic Graph SignalsLLM reasoning → Knowledge- and tool-augmented reasoning
Embeddings to Diagnosis: Latent Fragility under Agentic Perturbations in Clinical LLMsLLM agents and tool use → Medical and scientific domain agents
Contrast-CAT: Contrasting Activations for Enhanced Interpretability in Transformer-based Text ClassifiersMechanistic interpretability → Circuits and mechanistic analysis
MaPPO: Maximum a Posteriori Preference Optimization with Prior KnowledgeLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
SDD: Self-Degraded Defense against Malicious Fine-tuningLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
CONCAP: Seeing Beyond English with Concepts Retrieval-Augmented CaptioningMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning +1
Cognitive Chain-of-Thought (CoCoT): Structured Multimodal Reasoning about Social SituationsLLM reasoning → Multimodal reasoning
VESPA: Towards un(Human)supervised Open-World Pointcloud Labeling for Autonomous DrivingEnd-to-end autonomous driving → VLMs for autonomous driving
MazeEval: A Benchmark for Testing Sequential Decision-Making in Language ModelsLLM reasoning → Spatial and embodied reasoning
Bipedalism for Quadrupedal Robots: Versatile Loco-Manipulation through Risk-Adaptive Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
Advancing Shared and Multi-Agent Autonomy in Underwater Missions: Integrating Knowledge Graphs and Retrieval-Augmented GenerationRetrieval-augmented generation → Agentic RAG, agents and memory +1
Generative Pre-training for Subjective Tasks: A Diffusion Transformer-Based Framework for Facial Beauty PredictionDiffusion models → Image generation, text-to-image and editing
Detecting Visual Information Manipulation Attacks in Augmented Reality: A Multimodal Semantic Reasoning ApproachLLM reasoning → Reasoning for agents, planning and code
VLMPlanner: Integrating Visual Language Models with Motion PlanningMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
Cultivating Helpful, Personalized, and Creative AI Tutors: A Framework for Pedagogical Alignment using Reinforcement LearningLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
The Blessing and Curse of Dimensionality in Safety AlignmentLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
Fine-structure Preserved Real-world Image Super-resolution via Transfer VAE TrainingDiffusion models → Inverse problems and image restoration
SciToolAgent: A Knowledge Graph-Driven Scientific Agent for Multi-Tool IntegrationLLM agents and tool use → Web, search, and research agents
What Language(s) Does Aya-23 Think In? How Multilinguality Affects Internal Language RepresentationsLLM reasoning → Reasoning benchmarks and evaluation
MoL-RL: Distilling Multi-Step Environmental Feedback into LLMs for Feedback-Independent ReasoningLLM reasoning → Test-time compute and efficient thinking
Learning from Expert Factors: Trajectory-level Reward Shaping for Formulaic Alpha MiningDeep reinforcement learning methods → Adversarial robustness and RL in finance
A Multi-Agent System Enables Versatile Information Extraction from the Chemical LiteratureLLM agents and tool use → Medical and scientific domain agents
StepFun-Prover Preview: Let's Think and Verify Step by StepLLM reasoning → Mathematical reasoning +1
A Survey of Token Compression for Efficient Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
SAViL-Det: Semantic-Aware Vision-Language Model for Multi-Script Text DetectionMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
Diversity-Enhanced Reasoning for Subjective QuestionsLLM reasoning → Reinforcement learning for reasoning
SGPO: Self-Generated Preference Optimization based on Self-ImproverLLM alignment / RLHF / preference optimisation → LLM preference optimization methods +1
LRR-Bench: Left, Right or Rotate? Vision-Language models Still Struggle With Spatial Understanding TasksMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
AnimeColor: Reference-based Animation Colorization with Diffusion TransformersDiffusion models → Image generation, text-to-image and editing
Trust the Model: Compact VLMs as In-Context Judges for Image-Text Data QualityLLM reasoning → Multimodal reasoning +1
The Policy Cliff: A Theoretical Analysis of Reward-Policy Maps in Large Language ModelsLLM reasoning → Reinforcement learning for reasoning +1
Multi-Agent Interactive Question Generation Framework for Long Document UnderstandingLLM agents and tool use → Multimodal and embodied agents
Do Not Mimic My Voice: Speaker Identity Unlearning for Zero-Shot Text-to-SpeechLLM safety and security → Machine unlearning
Sem-DPO: Mitigating Semantic Inconsistency in Preference Optimization for Prompt EngineeringLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
Diffusion-based Symbolic Music Generation with Structured State Space ModelsDiffusion models → Audio, speech and music +1
Packet-Level DDoS Data Augmentation Using Dual-Stream Temporal-Field DiffusionDiffusion models → Diffusion and flow policies for robotics
NeuroVoxel-LM: Language-Aligned 3D Perception via Dynamic Voxelization and Meta-EmbeddingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Learning to Align Human Code PreferencesLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
Local Prompt Adaptation for Style-Consistent Multi-Object Generation in Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
Bridging AI Innovation and Healthcare Needs: Lessons Learned from Incorporating Modern NLP at The BC Cancer Registry
Benchmarking Large Language Models for Geolocating Colonial Virginia Land Grants
AI Should Be More Human, Not More Complex
Cross-Process Defect Attribution using Potential Loss Analysis
Multi-Community Spectral Clustering for Geometric Graphs
Accelerating multiparametric quantitative MRI using self-supervised scan-specific implicit neural representation with model reinforcement
ELMES: An Automated Framework for Evaluating Large Language Models in Educational Scenarios
Interpretable Anomaly-Based DDoS Detection in AI-RAN with XAI and LLMs
Exploring Adaptive Structure Learning for Heterophilic Graphs
Operator-Based Machine Intelligence: A Hilbert Space Framework for Spectral Learning and Symbolic Reasoning
Can Language Models Discover Scaling Laws?
BioNeuralNet: A Graph Neural Network based Multi-Omics Network Data Analysis Tool
When Prompts Go Wrong: Evaluating Code Model Robustness to Ambiguous, Contradictory, and Incomplete Task Descriptions
FAST: Similarity-based Knowledge Transfer for Efficient Policy Learning
ResCap-DBP: A Lightweight Residual-Capsule Network for Accurate DNA-Binding Protein Prediction Using Global ProteinBERT Embeddings
Communication-Efficient Distributed Training for Collaborative Flat Optima Recovery in Deep Learning
CodeNER: Code Prompting for Named Entity Recognition
Survey of NLU Benchmarks Diagnosing Linguistic Phenomena: Why not Standardize Diagnostics Benchmarks?
Can Foundation Models Predict Fitness for Duty?
Indian Sign Language Detection for Real-Time Translation using Machine Learning
A Multi-Stage Hybrid CNN-Transformer Network for Automated Pediatric Lung Sound Classification
Second Competition on Presentation Attack Detection on ID Card
A General Framework for Estimating Preferences Using Response Time Data
Length Representations in Large Language Models
Solving Scene Understanding for Autonomous Navigation in Unstructured Environments
ModalFormer: Multimodal Transformer for Low-Light Image Enhancement
Set-based Implicit Likelihood Inference of Galaxy Cluster Mass
Multi-Agent Reinforcement Learning for Dynamic Mobility Resource Allocation with Hierarchical Adaptive Grouping
WBHT: A Generative Attention Architecture for Detecting Black Hole Anomalies in Backbone Networks
Clustering by Attention: Leveraging Prior Fitted Transformers for Data Partitioning
MagicAnime: A Hierarchically Annotated, Multimodal and Multitasking Dataset with Benchmarks for Cartoon Animation Generation
Sequence-Aware Inline Measurement Attribution for Good-Bad Wafer Diagnosis
MH-GIN: Multi-scale Heterogeneous Graph-based Imputation Network for AIS Data (Extended Version)
Wafer Defect Root Cause Analysis with Partial Trajectory Regression
A Unified Theory of θ-Expectations
RMTBench: Benchmarking LLMs Through Multi-Turn User-Centric Role-Playing
Computational Advantages of Multi-Grade Deep Learning: Convergence Analysis and Performance Insights
From Observations to Causations: A GNN-based Probabilistic Prediction Framework for Causal Discovery
DYNARTmo: A Dynamic Articulatory Model for Visualization of Speech Movement Patterns
PIVOTS: Aligning unseen Structures using Preoperative to Intraoperative Volume-To-Surface Registration for Liver Navigation
From Gallery to Wrist: Realistic 3D Bracelet Insertion in Videos
MIPS: a Multimodal Infinite Polymer Sequence Pre-training Framework for Polymer Property Prediction
Artificial Intelligence In Patent And Market Intelligence: A New Paradigm For Technology Scouting
A Comparative Study of OpenMP Scheduling Algorithm Selection Strategies
SWIFT: A General Sensitive Weight Identification Framework for Fast Sensor-Transfer Pansharpening
Advancing Dialectal Arabic to Modern Standard Arabic Machine Translation
Towards Generalized Parameter Tuning in Coherent Ising Machines: A Portfolio-Based Approach
T3SVFND: Towards an Evolving Fake News Detector for Emergencies with Test-time Training on Short Video Platforms
Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation
Approximating Full Conformal Prediction for Neural Network Regression with Gauss-Newton Influence
Reliable Wireless Indoor Localization via Cross-Validated Prediction-Powered Calibration
EMBRACE: Shaping Inclusive Opinion Representation by Aligning Implicit Conversations with Social Norms
L-MCAT: Unpaired Multimodal Transformer with Contrastive Attention for Label-Efficient Satellite Image Classification
MIRepNet: A Pipeline and Foundation Model for EEG-Based Motor Imagery Classification
Post-Completion Learning for Language Models
Modeling Professionalism in Expert Questioning through Linguistic Differentiation
Protein-SE(3): Benchmarking SE(3)-based Generative Models for Protein Structure Design
Reframe Your Life Story: Interactive Narrative Therapist and Innovative Moment Assessment with Large Language Models

All 147