Papers

New on arXiv

Sat 1 Mar 2025

203 papers

Addressing Cold-start Problem in Click-Through Rate Prediction via Supervised Diffusion ModelingDiffusion models → Diffusion recommenders
EXCLAIM: An Explainable Cross-Modal Agentic System for Misinformation Detection with Hierarchical RetrievalLLM agents and tool use → Web, search, and research agents
Echo: Efficient Co-Scheduling of Hybrid Online-Offline Tasks for Large Language Model ServingEfficient LLM inference and serving → Serving systems and request scheduling
Sentence-level Reward Model can Generalize Better for Aligning LLM from Human PreferenceLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
Adaptive Entanglement Routing with Deep Q-Networks in Quantum NetworksDeep reinforcement learning methods → Quantum reinforcement learning
Reinforcement learning with combinatorial actions for coupled restless banditsDeep reinforcement learning methods → RL theory and sample complexity
Discrete Codebook World Models for Continuous ControlWorld models → Latent dynamics models and model-based RL +1
Efficiently Editing Mixture-of-Experts Models with Compressed ExpertsMixture-of-experts → MoE large language models
Multimodal Large Language Models Predict Urban Safety Perception but Encode Non-Neutral Demographic PriorsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Semantic Integrity Constraints: Declarative Guardrails for AI-Augmented Data Processing SystemsLLM safety and security → Safety alignment, refusal and guardrails
BadJudge: Backdoor Vulnerabilities of LLM-as-a-JudgeLLM safety and security → Backdoor and data poisoning attacks
SolidMark: Evaluating Image Memorization in Generative ModelsDiffusion models → Diffusion foundations and sampling
AesthetiQ: Enhancing Graphic Layout Design via Aesthetic-Aware Preference Alignment of Multi-modal Large Language ModelsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG +1
Actor-Critic Cooperative Compensation to Model Predictive Control for Off-Road Autonomous Vehicles Under Unknown DynamicsEnd-to-end autonomous driving → Reinforcement learning for driving +1
ToolDial: Multi-turn Dialogue Generation Method for Tool-Augmented Language ModelsLLM agents and tool use → Tool learning and function calling
Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less ReasonableLLM reasoning → Reasoning for agents, planning and code +1
Streaming Video Question-Answering with In-context Video KV-Cache RetrievalEfficient LLM inference and serving → Visual token pruning in multimodal models
Distributionally Robust Reinforcement Learning with Human FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
Scalable Reinforcement Learning for Virtual Machine SchedulingDeep reinforcement learning methods → RL for energy, networks and operations
What Makes a Good Diffusion Planner for Decision Making?Diffusion models → Diffusion and flow policies for robotics +1
GaussianSeal: Rooting Adaptive Watermarks for 3D Gaussian Generation ModelLLM safety and security → Watermarking generated content and models
End-To-End Learning of Gaussian Mixture Priors for Diffusion SamplerDiffusion models → Diffusion foundations and sampling
Periodic Materials Generation using Text-Guided Joint Diffusion ModelDiffusion models → Flow matching, time series and science
2DMCG:2DMambawith Change Flow Guidance for Change Detection in Remote SensingState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
Inst3D-LMM: Instance-Aware 3D Scene Understanding with Multi-modal Instruction TuningMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
HGDiffuser: Efficient Task-Oriented Grasp Generation via Human-Guided Grasp Diffusion ModelsDiffusion models → Diffusion and flow policies for robotics
Interact, Instruct to Improve: A LLM-Driven Parallel Actor-Reasoner Framework for Enhancing Autonomous Vehicle InteractionsLLM reasoning → Chain-of-thought reasoning for driving +1
Shaping Laser Pulses with Reinforcement LearningDeep reinforcement learning methods → RL for energy, networks and operations
Flying on Point Clouds with Reinforcement LearningDeep reinforcement learning methods → RL for robot navigation and UAV control
Tutorial Proposal: Speculative Decoding for Efficient LLM InferenceEfficient LLM inference and serving → Speculative decoding
Interacting with AI Reasoning Models: Harnessing "Thoughts" for AI-Driven Software EngineeringLLM reasoning → Reasoning for agents, planning and code
Challenges in Testing Large Language Model Based Software: A Faceted TaxonomyLLM agents and tool use → Software engineering coding agents
CL-MoE: Enhancing Multimodal Large Language Model with Dual Momentum Mixture-of-Experts for Continual Visual Question AnsweringMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP +1
Smoothing Grounding and Reasoning for MLLM-Powered GUI Agents with Query-Oriented Pivot TasksLLM agents and tool use → GUI and mobile agents
Progressive Sparse Attention: Algorithm and System Co-design for Efficient Attention in LLM ServingEfficient LLM inference and serving → KV cache optimization
Octopus: Alleviating Hallucination via Dynamic Contrastive DecodingMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
Structured Reasoning for Fairness: A Multi-Agent Approach to Bias Detection in Textual DataLLM reasoning → Reasoning benchmarks and evaluation +1
U-NIAH: Unified RAG and LLM Evaluation for Long Context Needle-In-A-HaystackRetrieval-augmented generation → RAG pipeline design and evaluation
Towards Understanding the Benefit of Multitask Representation Learning in Decision ProcessDeep reinforcement learning methods → Deep RL algorithms and representations
Falcon: Fast Visuomotor Policies via Partial DenoisingDiffusion models → Diffusion and flow policies for robotics
Remasking Discrete Diffusion Models with Inference-Time ScalingLLM reasoning → Diffusion reasoning and test-time scaling +1
Robust Multi-Objective Preference Alignment with Online DPOLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Passivity-Centric Safe Reinforcement Learning for Contact-Rich Robotic TasksDeep reinforcement learning methods → Safe and constrained RL
Maintaining Plasticity in Reinforcement Learning: A Cost-Aware Framework for Aerial Robot Control in Non-stationary EnvironmentsDeep reinforcement learning methods → RL for robot navigation and UAV control
Flow Matching for Medical Image Synthesis: Bridging the Gap Between Speed and QualityDiffusion models → Medical imaging and segmentation
Traffic Priority-Aware 5G NR-U/Wi-Fi Coexistence with Deep Reinforcement LearningDeep reinforcement learning methods → RL for energy, networks and operations
A Modern Approach to Real-Time Air Traffic Management System
A Review of Brain-Computer Interface Technologies: Signal Acquisition Methods and Interaction Paradigms
Simulation of prosthetic vision with PRIMA system and enhancement of face representation
Psychological Counseling Ability of Large Language Models
MedSimAI: Simulation and Formative Feedback Generation to Enhance Deliberate Practice in Medical Education
Cross-linguistic disagreement as a conflict of semantic alignment norms in multilingual AI~Linguistic Diversity as a Problem for Philosophy, Cognitive Science, and AI~
Quantum Geometry insights in Deep Learning
Multi-models with averaging in feature domain for non-invasive blood glucose estimation
Steer LLM Latents for Hallucination Detection
QDCNN: Quantum Deep Learning for Enhancing Safety and Reliability in Autonomous Transportation Systems
Conceptual Contrastive Edits in Textual and Vision-Language Retrieval
dyAb: Flow Matching for Flexible Antibody Design with AlphaFold-driven Pre-binding Antigen
The Role, Trends, and Applications of Machine Learning in Undersea Communication: A Bangladesh Perspective
Development of an Unpaired Deep Neural Network for Synthesizing X-ray Fluoroscopic Images from Digitally Reconstructed Tomography in Image Guided Radiotherapy
Generative Artificial Intelligence for Academic Research: Evidence from Guidance Issued for Researchers by Higher Education Institutions in the United States
A new practical and effective source-independent full-waveform inversion with a velocity-distribution supported deep image prior: Applications to two real datasets
Artificially Generated Visual Scanpath Improves Multi-label Thoracic Disease Classification in Chest X-Ray Images
The Hidden Cost of Waiting for Accurate Predictions
T-cell receptor specificity landscape revealed through de novo peptide design
Deep Change Monitoring: A Hyperbolic Representative Learning Framework and a Dataset for Long-term Fine-grained Tree Change Detection
Self-supervision via Controlled Transformation and Unpaired Self-conditioning for Low-light Image Enhancement
How to Probe: Simple Yet Effective Techniques for Improving Post-hoc Explanations
Asymptotic Theory of Eigenvectors for Latent Embeddings with Generalized Laplacian Matrices
Synergy Between Sufficient Changes and Sparse Mixing Procedure for Disentangled Representation Learning
Learning Automata of PLCs in Production Lines Using LSTM
Dissecting the Impact of Model Misspecification in Data-driven Optimization
Perceptual Visual Quality Assessment: Principles, Methods, and Future Directions
An evaluation of DeepSeek Models in Biomedical Natural Language Processing
PinLanding: Content-First Keyword Landing Page Generation via Multi-Modal AI for Web-Scale Discovery
Statistical Mechanics of Semantic Compression
Modeling Arbitrarily Applicable Relational Responding with the Non-Axiomatic Reasoning System: A Machine Psychology Approach
Near-Optimal Real-Time Personalization with Simple Transformers
GenVDM: Generating Vector Displacement Maps From a Single Image
Large Engagement Networks for Classifying Coordinated Campaigns and Organic Twitter Trends
Zero-Shot Keyphrase Generation: Investigating Specialized Instructions and Multi-Sample Aggregation on Large Language Models
Cross-Attention Fusion of MRI and Jacobian Maps for Alzheimer's Disease Diagnosis
Space-Time Graphs of Convex Sets for Multi-Robot Motion Planning
Brain Foundation Models: A Survey on Advancements in Neural Signal Processing and Brain Discovery
Channel-Attentive Graph Neural Networks
Polyconvex Physics-Augmented Neural Network Constitutive Models in Principal Stretches
LoR2C : Low-Rank Residual Connection Adaptation for Parameter-Efficient Fine-Tuning
Communication-Efficient Device Scheduling for Federated Learning Using Lyapunov Optimization
Instructor-Worker Large Language Model System for Policy Recommendation: a Case Study on Air Quality Analysis of the January 2025 Los Angeles Wildfires
Batched Single-Index Global Multi-Armed Bandits with Covariates
A Guide to Failure in Machine Learning: Reliability and Robustness from Foundations to Practice
Heatwave increases nighttime light intensity in hyperdense cities of the Global South: A double machine learning study
The Uncertainty of Machine Learning Predictions in Asset Pricing
Unbiased Video Scene Graph Generation via Visual and Semantic Dual Debiasing
Performance Heterogeneity in Graph Neural Networks: Lessons for Architecture Design and Preprocessing
RFWNet: A Lightweight Remote Sensing Object Detector Integrating Multiscale Receptive Fields and Foreground Focus Mechanism
BodyGen: Advancing Towards Efficient Embodiment Co-Design
Trajectory Inference with Smooth Schr"odinger Bridges
Efficient Prompting for Continual Adaptation to Missing Modalities
Never too Prim to Swim: An LLM-Enhanced RL-based Adaptive S-Surface Controller for AUVs under Extreme Sea Conditions

All 203