Papers

New on arXiv

Sun 29 Jun 2025

168 papers

SketchMind: A Multi-Agent Cognitive Framework for Assessing Student-Drawn Scientific SketchesLLM agents and tool use → Multimodal and embodied agents
A Representation Engineering Perspective on the Effectiveness of Multi-Turn JailbreaksLLM safety and security → Jailbreaking +1
Advanced Financial Reasoning at Scale: A Comprehensive Evaluation of Large Language Models on CFA Level IIILLM reasoning → Reasoning for agents, planning and code
Theoretical Modeling of Large Language Model Self-Improvement Training Dynamics Through Solver-Verifier GapSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training
Fractional Policy Gradients: Reinforcement Learning with Long-Term MemoryDeep reinforcement learning methods → RL theory and sample complexity
When Additive Noise Meets Unobserved Mediators: Bivariate Denoising Diffusion for Causal DiscoveryDiffusion models → Diffusion foundations and sampling
GeoProg3D: Compositional Visual Reasoning for City-Scale 3D Language FieldsLLM reasoning → Spatial and embodied reasoning
IR3D-Bench: Evaluating Vision-Language Model Scene Understanding as Agentic Inverse RenderingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
FA-Seg: A Fast and Accurate Diffusion-Based Method for Open-Vocabulary SegmentationDiffusion models → Medical imaging and segmentation
Physics informed guided diffusion for accelerated multi-parametric MRI reconstructionDiffusion models → Medical imaging and segmentation
SurgTPGS: Semantic 3D Surgical Scene Understanding with Text Promptable Gaussian SplattingMultimodal LLMs / vision-language models → Medical vision-language models
GATSim: Urban Mobility Simulation with Generative AgentsLLM agents and tool use → Multimodal and embodied agents
Exposing and Mitigating Calibration Biases and Demographic Unfairness in MLLM Few-Shot In-Context Learning for Medical Image ClassificationMultimodal LLMs / vision-language models → Medical vision-language models
DiffFit: Disentangled Garment Warping and Texture Refinement for Virtual Try-OnDiffusion models → 3D, point cloud and scene generation
Competitive Distillation: A Simple Learning Strategy for Improving Visual ClassificationKnowledge distillation → General knowledge distillation methods
MoMa: Modulating Mamba for Adapting Image Foundation Models to Video RecognitionState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
Corrupted by Reasoning: Reasoning Language Models Become Free-Riders in Public Goods GamesLLM reasoning → Reasoning for agents, planning and code
Real-Time Progress Prediction in Reasoning Language ModelsLLM reasoning → Test-time compute and efficient thinking +1
Token Activation Map to Visually Explain Multimodal LLMsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
Sub-MoE: Efficient Mixture-of-Expert LLMs Compression via Subspace Expert MergingMixture-of-experts → MoE large language models
Causal-Entity Reflected Egocentric Traffic Accident Video SynthesisDiffusion models → Diffusion and flow policies for robotics
From Prompt Injections to Protocol Exploits: Threats in LLM-Powered AI Agents WorkflowsLLM agents and tool use → Agent threats, guardrails and governance +1
PixelBoost: Leveraging Brownian Motion for Realistic-Image Super-ResolutionDiffusion models → Inverse problems and image restoration
Generalist Reward Models: Found Inside Large Language ModelsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
UrbanLLaVA: A Multi-modal Large Language Model for Urban Intelligence with Spatial Reasoning and UnderstandingLLM reasoning → Spatial and embodied reasoning +1
BridgeShape: Latent Diffusion Schr"odinger Bridge for 3D Shape CompletionDiffusion models → 3D, point cloud and scene generation
External Data-Enhanced Meta-Representation for Adaptive Probabilistic Load ForecastingMixture-of-experts → MoE for time series and graphs
Score-based Diffusion Model for Unpaired Virtual Histology StainingDiffusion models → Medical imaging and segmentation
Mirror Descent Policy Optimisation for Robust Constrained Markov Decision ProcessesDeep reinforcement learning methods → RL theory and sample complexity
AlignEvoSkill: Towards Knowledge-Aware and Task-Aligned Agent Skill EvolutionLLM agents and tool use → Agent skill learning and evolution
Forget-MI: Machine Unlearning for Forgetting Multimodal Information in Healthcare SettingsLLM safety and security → Machine unlearning
Benchmarking Deep Search over Heterogeneous Enterprise DataLLM reasoning → Knowledge- and tool-augmented reasoning +1
LLM-Assisted Question-Answering on Technical Documents Using Structured Data-Aware Retrieval Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
RoboScape: Physics-informed Embodied World ModelWorld models → Embodied and robot world models
Format-Adapter: Improving Reasoning Capability of LLMs by Adapting Suitable FormatLLM reasoning → Mathematical reasoning
Are Large Language Models Capable of Deep Relational Reasoning? Insights from DeepSeek-R1 and Benchmark ComparisonsLLM reasoning → Reasoning benchmarks and evaluation
ParticleFormer: A 3D Point Cloud World Model for Multi-Object, Multi-Material Robotic ManipulationWorld models → Embodied and robot world models
Enhancing Spatial Reasoning in Multimodal Large Language Models through Reasoning-based SegmentationLLM reasoning → Spatial and embodied reasoning +1
MoCa: Modality-aware Continual Pre-training Makes Better Bidirectional Multimodal EmbeddingsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
Region-Aware Multimodal Large Language Model via SlowFast Tokenization and Pseudo-Mask Guidance for 3D CT Report GenerationMultimodal LLMs / vision-language models → Medical vision-language models
From Individuals to Interactions: Benchmarking Gender Bias in Multimodal Large Language Models from the Lens of Social RelationshipMultimodal LLMs / vision-language models → Social bias and fairness in VLMs
Multi-task Offline Reinforcement Learning for Online Advertising in Recommender SystemsOffline RL and imitation learning from data → Decision transformers and sequence modeling
Learning Counterfactually Decoupled Attention for Open-World Model AttributionWorld models → Latent predictive world models
Curious Causality-Seeking Agents Learn Meta Causal WorldWorld models → World models for language agents +1
Empowering Small VLMs to Think with Dynamic Memorization and ExplorationLLM reasoning → Multimodal reasoning +1
Boosting LLM's Molecular Structure Elucidation with Knowledge Enhanced Tree Search ReasoningLLM reasoning → Clinical and biomedical applications
Double-Diffusion: Balancing Speed, Accuracy, and Uncertainty in Probabilistic Forecasting for Urban Sensor NetworksDiffusion models → Flow matching, time series and science
AURA: Agent for Understanding, Reasoning, and Automated Tool Use in Voice-Driven TasksLLM reasoning → Audio-language model reasoning +1
ReMem: Mutual Information-Aware Fine-tuning of Pretrained Vision Transformers for Effective Knowledge DistillationKnowledge distillation → General knowledge distillation methods
Flexibility-Conditioned Protein Structure Design with Flow Matching
Adaptive Linguistic Prompting (ALP) Enhances Phishing Webpage Detection in Multimodal Large Language Models
Multimodal image registration for effective thermographic fever screening
Strategies for Resource Allocation of Two Competing Companies using Genetic Algorithm
Bittensor Protocol: The Bitcoin in Decentralized Artificial Intelligence? A Critical and Empirical Analysis
FinAI-BERT: A Transformer-Based Model for Sentence-Level Detection of AI Disclosures in Financial Reports
Integrating Large Language Models in Financial Investments and Market Analysis: A Survey
Automated Vehicles Should be Connected with Natural Language
Online Meal Detection Based on CGM Data Dynamics
VoyagerVision: Investigating the Role of Multi-modal Information for Open-ended Learning Systems
The language of time: a language model perspective on time-series foundation models
Pipelined Decoder for Efficient Context-Aware Text Generation
DPOT: A DeepParticle method for Computation of Optimal Transport with convergence guarantee
Detecting What Matters: A Novel Approach for Out-of-Distribution 3D Object Detection in Autonomous Vehicles
Accurate Parameter-Efficient Test-Time Adaptation for Time Series Forecasting
TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs
BenchMake: Turn any scientific data set into a reproducible benchmark
Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models
A High-Throughput Platform to Bench Test Smartphone-Based Heart Rate Measurements Derived From Video
Datasets for Fairness in Language Models: An In-Depth Survey
Do LLMs Dream of Discrete Algorithms?
AICO: Feature Significance Tests for Supervised Learning
Teaching a Language Model to Speak the Language of Tools
Hierarchical Memory Organization for Wikipedia Generation
SIEDD: Shared-Implicit Encoder with Discrete Decoders
Perspective Dial: Measuring Perspective of Text and Guiding LLM Outputs
Investigating an Overfitting and Degeneration Phenomenon in Self-Supervised Multi-Pitch Estimation
You Sound a Little Tense: L2 Tailored Clear TTS Using Durational Vowel Properties
Density, asymmetry and citation dynamics in scientific literature
OmniVCus: Feedforward Subject-driven Video Customization with Multimodal Control Conditions
Federated Timeline Synthesis: Scalable and Private Methodology For Model Training and Deployment
Layer Decomposition and Morphological Reconstruction for Task-Oriented Infrared Image Enhancement
Benchmarking Generalizable Bimanual Manipulation: RoboTwin Dual-Arm Collaboration Challenge at CVPR 2025 MEIS Workshop
A case for data valuation transparency via DValCards
CycleVAR: Repurposing Autoregressive Model for Unsupervised One-Step Image Translation
Data-Driven Self-Supervised Learning for the Discovery of Solution Singularity for Partial Differential Equations
ATGen: A Framework for Active Text Generation
Information Loss in LLMs' Multilingual Translation: The Role of Training Data, Language Proximity, and Language Family
VALID-Mol: a Systematic Framework for Validated LLM-Assisted Molecular Design
Federated Breast Cancer Detection Enhanced by Synthetic Ultrasound Image Augmentation
XY-Tokenizer: Mitigating the Semantic-Acoustic Conflict in Low-Bitrate Speech Codecs
GaussMaster: An LLM-based Database Copilot System
Learning to Rank with Variable Result Presentation Lengths
SceneStreamer: Continuous Scenario Generation as Next Token Group Prediction
Ensemble BERT for Medication Event Classification on Electronic Health Records (EHRs)
Interpretable by Design: MH-AutoML for Transparent and Efficient Android Malware Detection without Compromising Performance
Endo-4DGX: Robust Endoscopic Scene Reconstruction and Illumination Correction with Gaussian Splatting
BPD-Neo: An MRI Dataset for Lung-Trachea Segmentation with Clinical Data for Neonatal Bronchopulmonary Dysplasia
Securing AI Systems: A Guide to Known Attacks and Impacts
Self-Organizing Language
DDL: A Large-Scale Dataset for Deepfake Detection and Localization in Diversified Real-World Scenarios

All 168