Papers

New on arXiv

Sat 12 Jul 2025

135 papers

Learning to Move in Rhythm: Task-Conditioned Motion Policies with Orbital Stability GuaranteesOffline RL and imitation learning from data → Real-world robot offline RL
LLM-Stackelberg Games: Conjectural Reasoning Equilibria and Their Applications to SpearphishingLLM reasoning → Reasoning for agents, planning and code
Adversarial Activation Patching: A Framework for Detecting and Mitigating Emergent Deception in Safety-Aligned TransformersLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
Real-Time Adaptive Motion Planning via Point Cloud-Guided, Energy-Based Diffusion and Potential FieldsDiffusion models → Diffusion and flow policies for robotics
EduFlow: Advancing MLLMs' Problem-Solving Proficiency through Multi-Stage, Multi-Perspective CritiqueLLM reasoning → Prompting and chain-of-thought reasoning +1
Constrained Style Learning from Imperfect Demonstrations under Task OptimalityOffline RL and imitation learning from data → Robot learning from demonstration
Fast3D: Accelerating 3D Multi-modal Large Language Models for Efficient 3D Scene UnderstandingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
When Developer Aid Becomes Security Debt: A Systematic Analysis of Insecure Behaviors in LLM Coding AgentsLLM agents and tool use → Agent threats, guardrails and governance
ZipVoice-Dialog: Non-Autoregressive Spoken Dialogue Generation with Flow MatchingDiffusion models → Audio, speech and music
A Fairness-Oriented Multi-Objective Reinforcement Learning approach for Autonomous Intersection ManagementDeep reinforcement learning methods → RL for autonomous driving and traffic
AlphaVAE: Unified End-to-End RGBA Image Reconstruction and Generation with Alpha-Aware Representation LearningDiffusion models → Diffusion foundations and sampling
DAA*: Deep Angular A Star for Image-based Path PlanningOffline RL and imitation learning from data → Imitation learning methods
Prompt4Trust: A Reinforcement Learning Prompt Augmentation Framework for Clinically-Aligned Confidence Calibration in Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Medical vision-language models
Cross Knowledge Distillation between Artificial and Spiking Neural NetworksKnowledge distillation → Distillation for spiking neural networks
StockSim: A Dual-Mode Order-Level Simulator for Evaluating Multi-Agent LLMs in Financial MarketsLLM agents and tool use → Financial trading and forecasting agents
TPP-SD: Accelerating Transformer Point Process Sampling with Speculative DecodingEfficient LLM inference and serving → Speculative decoding
EgoAnimate: Generating Human Animations from Egocentric top-down ViewsDiffusion models → 3D, point cloud and scene generation
Warm Starts Accelerate Conditional DiffusionDiffusion models → Diffusion foundations and sampling
Uncertainty-Driven Expert Control: Enhancing the Reliability of Medical Vision-Language ModelsMultimodal LLMs / vision-language models → Medical vision-language models
From Curated Data to Scalable Models: Continual Pre-training of Dense and MoE Large Language Models for TibetanMixture-of-experts → MoE large language models
Retrieval-Augmented Recommendation Explanation Generation with Hierarchical AggregationRetrieval-augmented generation → RAG for recommendation
MCA-LLaVA: Manhattan Causal Attention for Reducing Hallucination in Large Vision-Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
Hide-and-Shill: A Reinforcement Learning Framework for Market Manipulation Detection in Symphony-a Decentralized Multi-Agent SystemLLM agents and tool use → Financial trading and forecasting agents
Continual Reinforcement Learning by Planning with Online World ModelsWorld models → Latent dynamics models and model-based RL +1
RAMA: Retrieval-Augmented Multi-Agent Framework for Misinformation Detection in Multimodal Fact-CheckingRetrieval-augmented generation → Agentic RAG, agents and memory +1
Tactile-VLA: Unlocking Vision-Language-Action Model's Physical Knowledge for Tactile GeneralizationVision-language-action models → Tactile, force-aware and humanoid VLA
OPENXRD: A Comprehensive Benchmark Framework for LLM/MLLM XRD Question AnsweringMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
I2-World: Intra-Inter Tokenization for Efficient Dynamic 4D Scene ForecastingWorld models → World models for autonomous driving
Interactive Drawing Guidance for Anime Illustrations with Diffusion ModelDiffusion models → Image generation, text-to-image and editing
HedraRAG: Coordinating LLM Generation and Database Retrieval in Heterogeneous RAG ServingRetrieval-augmented generation → RAG pipeline design and evaluation
A Study of Value-Aware EigenoptionsDeep reinforcement learning methods → Deep RL algorithms and representations
Towards Human-level Dexterity via Robot LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
Hybrid Autoregressive-Diffusion Model for Real-Time Sign Language ProductionDiffusion models → Sign language production
CoVAE: Consistency Training of Variational AutoencodersDiffusion models → Diffusion foundations and sampling
Harnessing Text-to-Image Diffusion Models for Point Cloud Self-Supervised LearningDiffusion models → 3D, point cloud and scene generation
RadEyeVideo: Enhancing general-domain Large Vision Language Model for chest X-ray analysis with video representations of eye gazeMultimodal LLMs / vision-language models → Medical vision-language models
Temporal Misalignment Attacks against Multimodal Perception in Autonomous DrivingEnd-to-end autonomous driving → Adversarial scenarios and safety testing
DS@GT at Touch'e: Large Language Models for Retrieval-Augmented DebateRetrieval-augmented generation → RAG robustness and adaptive retrieval
Deep Reinforcement Learning with Gradient Eligibility TracesDeep reinforcement learning methods → RL theory and sample complexity
InsurTech innovation using natural language processing
Quantifying Holistic Review: A Multi-Modal Approach to College Admissions Prediction
NeuroHD-RA: Neural-distilled Hyperdimensional Model with Rhythm Alignment
From Bias to Behavior: Learning Bull-Bear Market Dynamics with Contrastive Modeling
Semi-Supervised Federated Learning via Dual Contrastive Learning and Soft Labeling for Intelligent Fault Diagnosis
Digital Twin-Assisted Explainable AI for Robust Beam Prediction in mmWave MIMO Systems
Smart Routing for Multimodal Video Retrieval: When to Search What
Butter: Frequency Consistency and Hierarchical Fusion for Autonomous Driving Object Detection
LLM-Powered Quantum Code Transpilation
AGFS-Tractometry: A Novel Atlas-Guided Fine-Scale Tractometry Approach for Enhanced Along-Tract Group Statistical Comparison Using Diffusion MRI Tractography
Emergence of Hierarchical Emotion Organization in Large Language Models
PLEX: Perturbation-free Local Explanations for LLM-Based Text Classification
Divide-Then-Rule: A Cluster-Driven Hierarchical Interpolator for Attribute-Missing Graphs
Extension OL-MDISF: Online Learning from Mix-Typed, Drifted, and Incomplete Streaming Features
Optimizing External Sources for Controlled Burning Plasma in Tokamaks with Neural Ordinary Differential Equations
On Information Geometry and Iterative Optimization in Model Compression: Operator Factorization
DATE-LM: Benchmarking Data Attribution Evaluation for Large Language Models
Domain Adaptation and Multi-view Attention for Learnable Landmark Tracking with Sparse Data
GreenCrossingAI: A Camera Trap/Computer Vision Pipeline for Environmental Science Research Groups
Scaling Laws for Optimal Data Mixtures
A Random Matrix Theory Perspective on the Learning Dynamics of Multi-head Latent Attention
Geometric Generative Modeling with Noise-Conditioned Graph Networks
Knowledge Conceptualization Impacts RAG Efficacy
Optimal Differentially Private Ranking from Pairwise Comparisons
Credit Card Fraud Detection Using RoFormer Model With Relative Distance Rotating Encoding
Fair CCA for Fair Representation Learning: An ADNI Study
Robust Spatiotemporal Epidemic Modeling with Integrated Adaptive Outlier Detection
Context-Aware Regularization with Markovian Integration for Attention-Based Nucleotide Analysis
Automated Multi-Class Crop Pathology Classification via Convolutional Neural Networks: A Deep Learning Approach for Real-Time Precision Agriculture
A Taxonomy of Omnicidal Futures Involving Artificial Intelligence
Meta-autoencoders: An approach to discovery and representation of relationships between dynamically evolving classes
Impute With Confidence: A Framework for Uncertainty Aware Multivariate Time Series Imputation
A Framework for Predictive Directional Trading Based on Volatility and Causal Inference
Unified Linear Parametric Map Modeling and Perception-aware Trajectory Planning for Mobile Robotics
Simplifying Traffic Anomaly Detection with Video Foundation Models
WellPINN: Accurate Well Representation for Transient Fluid Pressure Diffusion in Subsurface Reservoirs with Physics-Informed Neural Networks
Dynamic Inter-Class Confusion-Aware Encoder for Audio-Visual Fusion in Human Activity Recognition
Uncovering symmetric and asymmetric species associations from community and environmental data
Enhancing Interpretability in Software Change Management with Chain-of-Thought Reasoning
ProactiveVideoQA: A Comprehensive Benchmark Evaluating Proactive Interactions in Video Large Language Models
Voice Conversion for Lombard Speaking Style with Implicit and Explicit Acoustic Feature Conditioning
ViT-ProtoNet for Few-Shot Image Classification: A Multi-Benchmark Evaluation
Geo-RepNet: Geometry-Aware Representation Learning for Surgical Phase Recognition in Endoscopic Submucosal Dissection
Supercharging Floorplan Localization with Semantic Rays
Generative Latent Kernel Modeling for Blind Motion Deblurring
ClaritySpeech: Dementia Obfuscation in Speech
SAGE: Segment-Aware Gloss-Free Encoding for Token-Efficient Sign Language Translation
Overtone: Cyclic Patch Modulation for Clean, Efficient, and Flexible Physics Emulators
Psychology-Driven Enhancement of Humour Translation
Ambiguity-Aware and High-Order Relation Learning for Multi-Grained Image-Text Matching
AGCD-Net: Attention Guided Context Debiasing Network for Emotion Recognition
A CLuP algorithm to practically achieve ~ 0.76 SK--model ground state free energy
Swa-bhasha Resource Hub: Romanized Sinhala to Sinhala Transliteration Systems and Data Resources
PPJudge: Towards Human-Aligned Assessment of Artistic Painting Process
PanoDiff-SR: Synthesizing Dental Panoramic Radiographs using Diffusion and Super-resolution
MetaClimage: A novel database of visual metaphors related to Climate Change, with costs and benefits analysis
Calibrated and Robust Foundation Models for Vision-Language and Medical Image Tasks Under Distribution Shift
Online Long-term Point Tracking in the Foundation Model Era
360-Degree Full-view Image Segmentation by Spherical Convolution compatible with Large-scale Planar Pre-trained Models
Stereo-based 3D Anomaly Object Detection for Autonomous Driving: A New Dataset and Baseline
Optimizing Basis Function Selection in Constructive Wavelet Neural Networks and Its Applications

All 135