Papers

New on arXiv

Sun 16 Mar 2025

186 papers

State Fourier Diffusion Language Model (SFDLM): A Scalable, Novel Iterative Approach to Language ModelingDiffusion models → Discrete and text diffusion
SAUCE: Selective Concept Unlearning in Vision-Language Models with Sparse AutoencodersMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +2
Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language ModelsLLM reasoning → Reinforcement learning for reasoning +1
DDPM-Polycube: A Denoising Diffusion Probabilistic Model for Polycube-Based Hexahedral Mesh Generation and Volumetric Spline ConstructionDiffusion models → 3D, point cloud and scene generation
Dynamic Angle Selection in X-Ray CT: A Reinforcement Learning Approach to Optimal StoppingDeep reinforcement learning methods → RL for clinical treatment and surgery
AI Agents: Evolution, Architecture, and Real-World ApplicationsLLM agents and tool use → General LLM agent frameworks and benchmarks
Understanding Formal Reasoning Failures in LLMs as Abstract InterpretersLLM reasoning → Reasoning benchmarks and evaluation
RL-TIME: Reinforcement Learning-based Task Replication in Multicore Embedded SystemsDeep reinforcement learning methods → RL training of language and agent models
Logic-RAG: Augmenting Large Multimodal Models with Visual-Spatial Knowledge for Road Scene UnderstandingMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
UniVG: A Generalist Diffusion Model for Unified Image Generation and EditingDiffusion models → Image generation, text-to-image and editing
VeriLA: A Human-Centered Evaluation Framework for Interpretable Verification of LLM Agent FailuresLLM agents and tool use → General LLM agent frameworks and benchmarks
LATINO-PRO: LAtent consisTency INverse sOlver with PRompt OptimizationDiffusion models → Inverse problems and image restoration
UniBERT: Adversarial Training for Language-Universal RepresentationsKnowledge distillation → Knowledge distillation for LLMs
Multimodal Chain-of-Thought Reasoning: A Comprehensive SurveyLLM reasoning → Multimodal reasoning +1
MoECollab: Democratizing LLM Development Through Collaborative Mixture of ExpertsMixture-of-experts → MoE large language models
Personalize Anything for Free with Diffusion TransformerDiffusion models → Image generation, text-to-image and editing
Focusing Robot Open-Ended Reinforcement Learning Through Users' PurposesDeep reinforcement learning methods → Deep RL algorithms and representations
BalancedDPO: Adaptive Multi-Metric AlignmentDiffusion models → Diffusion and flow policies for robotics +1
Diffusion on Graph: Augmentation of Graph Structure for Node ClassificationDiffusion models → Flow matching, time series and science
AdaReTaKe: Adaptive Redundancy Reduction to Perceive Longer for Video-language UnderstandingMultimodal LLMs / vision-language models → Video understanding with MLLMs
PEBench: A Fictitious Dataset to Benchmark Machine Unlearning for Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
ST-Think: How Multimodal Large Language Models Reason About 4D Worlds from Ego-Centric VideosLLM reasoning → Spatial and embodied reasoning +1
EmoBipedNav: Emotion-aware Social Navigation for Bipedal Robots with Deep Reinforcement LearningDeep reinforcement learning methods → RL for robot navigation and UAV control
Debiasing Diffusion Model: Enhancing Fairness through Latent Representation Learning in Stable Diffusion ModelDiffusion models → Image generation, text-to-image and editing
Being-0: A Humanoid Robotic Agent with Vision-Language Models and Modular SkillsLLM agents and tool use → Multimodal and embodied agents
STEVE: A Step Verification Pipeline for Computer-use Agent TrainingLLM agents and tool use → GUI and mobile agents
Towards Suturing World Models: Learning Predictive Models for Robotic Surgical TasksWorld models → Medical and surgical world models +1
Basic Category Usage in Vision Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Investigating Human-Aligned Large Language Model UncertaintyLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
EXAONE Deep: Reasoning Enhanced Language ModelsLLM reasoning → Test-time compute and efficient thinking
Segment Any-Quality Images with Generative Latent Space EnhancementDiffusion models → Medical imaging and segmentation
MPBench: A Comprehensive Multimodal Reasoning Benchmark for Process Errors IdentificationLLM reasoning → Multimodal reasoning
PTFA: An LLM-based Agent that Facilitates Online Consensus Building through Parallel ThinkingLLM reasoning → Reasoning for agents, planning and code +1
Does Your Vision-Language Model Get Lost in the Long Video Sampling Dilemma?Multimodal LLMs / vision-language models → Video understanding with MLLMs
CAKE: Cascading and Adaptive KV Cache Eviction with Layer PreferencesEfficient LLM inference and serving → KV cache optimization
GeoRSMLLM: A Multimodal Large Language Model for Vision-Language Tasks in Geoscience and Remote SensingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
SING: Semantic Image Communications using Null-Space and INN-Guided Diffusion ModelsDiffusion models → Diffusion for compression and wireless
MoT: Modularization-of-Thought Prompting for Effective Code GenerationLLM reasoning → Reasoning for agents, planning and code
Modality-Composable Diffusion Policy via Inference-Time Distribution-level CompositionDiffusion models → Diffusion and flow policies for robotics
LazyMAR: Accelerating Masked Autoregressive Models via Feature CachingEfficient LLM inference and serving → Fast autoregressive visual generation
BREEN: Bridge Data-Efficient Encoder-Free Multimodal Learning with Learnable QueriesMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
A Survey on the Optimization of Large Language Model-based AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
MExD: An Expert-Infused Diffusion Model for Whole-Slide Image ClassificationDiffusion models → Image generation, text-to-image and editing +1
TERL: Large-Scale Multi-Target Encirclement Using Transformer-Enhanced Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
Beyond Final Code: A Process-Oriented Error Analysis of Software Development Agents in Real-World GitHub ScenariosLLM agents and tool use → Software engineering coding agents
IPCGRL: Language-Instructed Reinforcement Learning for Procedural Level GenerationDeep reinforcement learning methods → RL training of language and agent models
Localized Concept Erasure for Text-to-Image Diffusion Models Using Training-Free Gated Low-Rank AdaptationDiffusion models → Robustness, privacy and adversarial aspects +1
SPIN-Bench: How Well Do LLMs Plan Strategically and Reason Socially?LLM reasoning → Reasoning for agents, planning and code
A Closer Look at Adversarial Suffix Learning for Jailbreaking LLMs: Augmented Adversarial Trigger LearningLLM safety and security → Jailbreaking
VideoMAP: Toward Scalable Mamba-based Video Autoregressive PretrainingState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
Leveraging Vision Capabilities of Multimodal LLMs for Automated Data Extraction from PlotsMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
Will Pre-Training Ever End? A First Step Toward Next-Generation Foundation MLLMs via Self-Improving Systematic CognitionSynthetic data and self-improvement for LLMs → Self-improving MLLMs and synthetic data
One Goal, Many Challenges: Robust Preference Optimization Amid Content-Aware and Multi-Source NoiseLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
EQ-TAA: Equivariant Traffic Accident Anticipation via Diffusion-Based Accident Video Synthesis
GenShin: Guiding Rational Liposome Design by Ranking Liposomal Protein Corona through a Docking-Pose-Free GNN
Semantic Matters: Multimodal Features for Affective Analysis
Unequal Opportunities: Examining the Bias in Geographical Recommendations by Large Language Models
Scalable Min-Max Optimization via Primal-Dual Exact Pareto Optimization
What Can 240,000 New Credit Transactions Tell Us About the Impact of NGEU Funds?
Fragile Mastery: Are Domain-Specific Trade-Offs Undermining On-Device Language Models?
A graph neural network surrogate model for mesh-based crashworthiness prediction of vehicle panel components
Uncertainty Quantification for Data-Driven Machine Learning Models in Nuclear Engineering Applications: Where We Are and What Do We Need?
Advancing Human-Machine Teaming: Concepts, Challenges, and Applications
From G-Factor to A-Factor: Establishing a Psychometric Framework for AI Literacy
Using LLMs for Automated Privacy Policy Analysis: Prompt Engineering, Fine-Tuning and Explainability
Highlighting Case Studies in LLM Literature Review of Interdisciplinary System Science
Data-Driven Approximation of Binary-State Network Reliability Function: Algorithm Selection and Reliability Thresholds for Large-Scale Systems
Feasibility study for reconstruction of knee MRI from one corresponding X-ray via CNN
LLMs' Leaning in European Elections
LLM-Mediated Guidance of MARL Systems
Towards Privacy-Preserving Data-Driven Education: The Potential of Federated Learning
A Showdown of ChatGPT vs DeepSeek in Solving Programming Tasks
Fuzzy Rule-based Differentiable Representation Learning
CNCast: Leveraging 3D Swin Transformer and DiT for Enhanced Regional Weather Forecasting
Optimization on black-box function by parameter-shift rule
Decision by Supervised Learning with Deep Ensembles: A Practical Framework for Robust Portfolio Optimization
Enhancing Visual Representation with Textual Semantics: Textual Semantics-Powered Prototypes for Heterogeneous Federated Learning
HAR-DoReMi: Optimizing Data Mixture for Self-Supervised Human Activity Recognition Across Heterogeneous IMU Datasets
MSCMHMST: A traffic flow prediction model based on Transformer
AnyCalib: On-Manifold Learning for Model-Agnostic Single-View Camera Calibration
A Continual Learning-driven Model for Accurate and Generalizable Segmentation of Clinically Comprehensive and Fine-grained Whole-body Anatomies in CT
MagicID: Hybrid Preference Optimization for ID-Consistent and Dynamic-Preserved Video Customization
Algebraic Adversarial Attacks on Explainability Models
Discovering uncertainty: Gaussian constitutive neural networks with correlated weights
Domain Generalization for Improved Human Activity Recognition in Office Space Videos Using Adaptive Pre-processing
ZO2: Scalable Zeroth-Order Fine-Tuning for Extremely Large Language Models with Limited GPU Memory
Plausibility Vaccine: Injecting LLM Knowledge for Event Plausibility
TuneNSearch: a hybrid transfer learning and local search approach for solving vehicle routing problems
FW-Merging: Scaling Model Merging with Frank-Wolfe Optimization
Realized Volatility Forecasting for New Issues and Spin-Offs using Multi-Source Transfer Learning
Understanding Gradient Orthogonalization for Deep Learning via Non-Euclidean Trust-Region Optimization
COVID-19 Pneumonia Diagnosis Using Medical Images: Deep Learning-Based Transfer Learning Approach
Understanding Driver Cognition and Decision-Making Behaviors in High-Risk Scenarios: A Drift Diffusion Perspective
Hybrid Learners Do Not Forget: A Brain-Inspired Neuro-Symbolic Approach to Continual Learning
Clustered random forests with correlated data for optimal estimation and inference under potential covariate shift
Fast filtering of non-Gaussian models using Amortized Optimal Transport Maps
Online Misinformation Detection in Live Streaming Videos
Automated Planning for Optimal Data Pipeline Instantiation
MAVEN: Multi-modal Attention for Valence-Arousal Emotion Network
Real-Time Cell Sorting with Scalable In Situ FPGA-Accelerated Deep Learning

All 186