Papers
Thu 2 Oct 2025
430 papers
- AURA: Adaptive Unified Reasoning and Automation with LLM-Guided MARL for NextG Cellular NetworksLLM reasoning → Reasoning for agents, planning and code
- Cluster-based Adaptive Retrieval: Dynamic Context Selection for RAG ApplicationsRetrieval-augmented generation → RAG pipeline design and evaluation
- Diagnosing Bottlenecks in Data Visualization Understanding by Vision-Language ModelsMultimodal LLMs / vision-language models → Chart understanding and anomaly detection +1
- Chronological Thinking in Full-Duplex Spoken Dialogue Language ModelsLLM reasoning → Audio-language model reasoning
- Every Step Counts: Decoding Trajectories as Authorship Fingerprints of dLLMsDiffusion models → Discrete and text diffusion
- Adaptive Reinforcement Learning for Dynamic Configuration Allocation in Pre-Production TestingDeep reinforcement learning methods → RL training of language and agent models
- Efficient Tree-Structured Deep Research with Adaptive Resource AllocationLLM agents and tool use → Web, search, and research agents
- On Architectures for Combining Reinforcement Learning and Model Predictive Control with Runtime ImprovementsDeep reinforcement learning methods → RL for autonomous driving and traffic
- Inference-Time Search Using Side Information for Diffusion-Based Image ReconstructionDiffusion models → Inverse problems and image restoration
- AgentCaster: Reasoning-Guided Tornado ForecastingLLM reasoning → Time series reasoning
- Learning Pareto-Optimal Pandemic Intervention Policies with MORLDeep reinforcement learning methods → RL for clinical treatment and surgery
- Matching the Optimal Denoiser in Point Cloud Diffusion with (Improved) Rotational AlignmentDiffusion models → Diffusion foundations and sampling
- Input-Aware Sparse Attention for Real-Time Co-Speech Video GenerationDiffusion models → Audio, speech and music
- UMI-on-Air: Embodiment-Aware Guidance for Embodiment-Agnostic Visuomotor PoliciesDiffusion models → Diffusion and flow policies for robotics
- ElasticMoE: An Efficient Auto Scaling Method for Mixture-of-Experts ModelsMixture-of-experts → Efficient MoE training and inference systems
- On the Role of Temperature Sampling in Test-Time ScalingLLM reasoning → Test-time compute and efficient thinking
- RedCodeAgent: Automatic Red-teaming Agent against Diverse Code AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
- Mitigating Modal Imbalance in Multimodal ReasoningLLM reasoning → Multimodal reasoning +1
- PEO: Training-Free Aesthetic Quality Enhancement in Pre-Trained Text-to-Image Diffusion Models with Prompt Embedding OptimizationDiffusion models → Image generation, text-to-image and editing
- Multimodal Large Language Model Framework for Safe and Interpretable Grid-Integrated EVsMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
- Use the Online Network If You Can: Towards Fast and Stable Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
- A Benchmark Study of Deep Reinforcement Learning Algorithms for the Container Stowage Planning ProblemDeep reinforcement learning methods → RL for robot navigation and UAV control
- Agentic Additive Manufacturing Alloy EvaluationLLM agents and tool use → Medical and scientific domain agents
- Oracle-RLAIF: An Improved Fine-Tuning Framework for Multi-modal Video Models using Reinforcement Learning from Ranking FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- Orchestrating Human-AI Teams: The Manager Agent as a Unifying Research ChallengeLLM agents and tool use → Software engineering coding agents
- ToolTweak: An Attack on Tool Selection in LLM-based AgentsLLM agents and tool use → Agent threats, guardrails and governance
- Knowledge-Graph Based RAG System Evaluation FrameworkRetrieval-augmented generation → RAG pipeline design and evaluation
- Exploring OCR-augmented Generation for Bilingual VQAMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- A Recipe for Efficient Sim-to-Real Transfer in Manipulation with Online Imitation-Pretrained World ModelsWorld models → Embodied and robot world models +1
- Multimodal Function Vectors for Visual RelationsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- Self-supervised diffusion model fine-tuning for costate initialization using Markov chain Monte CarloDiffusion models → Diffusion and flow policies for robotics
- Graph Generation with Spectral Geodesic Flow MatchingDiffusion models → Flow matching, time series and science
- Beyond Linear Diffusions: Improved Representations for Rare Conditional Generative ModelingDiffusion models → Diffusion foundations and sampling
- Beyond Imitation: Recovering Dense Rewards from DemonstrationsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +2
- Improved Robustness of Deep Reinforcement Learning for Control of Time-Varying Systems by Bounded Extremum SeekingDeep reinforcement learning methods → RL theory and sample complexity
- From Pixels to Factors: Learning Independently Controllable State Variables for Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
- Controlling the Risk of Corrupted Contexts for Language Models via Early-ExitingEfficient LLM inference and serving → Early exit and edge inference
- SIMSplat: Language-Aligned 4D Gaussian Splatting for Driving Scenario GenerationEnd-to-end autonomous driving → Generative simulation for driving
- Dynamic Jailbreaking AttackLLM safety and security → Jailbreaking
- BrowserArena: Evaluating LLM Agents on Real-World Web Navigation TasksLLM agents and tool use → Web, search, and research agents
- OpenTSLM: Time-Series Language Models for Reasoning over Multivariate Medical Text- and Time-Series DataLLM reasoning → Time series reasoning
- FOCUS: Optimal Control for Multi-Entity World Modeling in Text-to-Image GenerationWorld models → Video-generation world models and simulators +1
- KaVa: Latent Reasoning via Compressed KV-Cache DistillationLLM reasoning → Test-time compute and efficient thinking +1
- NoiseShift: Resolution-Aware Noise Recalibration for Better Low-Resolution Image GenerationDiffusion models → Diffusion foundations and sampling
- Drawing Conclusions from Draws: Rethinking Preference Semantics in Arena-Style LLM EvaluationLLM reasoning → Reasoning for agents, planning and code
- Diffusion Models and the Manifold Hypothesis: Log-Domain Smoothing is Geometry AdaptiveDiffusion models → Diffusion foundations and sampling
- Knowledge Distillation Detection for Open-weights ModelsKnowledge distillation → General knowledge distillation methods
- ARMADA: Autonomous Online Failure Detection and Human Shared Control Empower Scalable Real-world Deployment and AdaptationOffline RL and imitation learning from data → Language-conditioned policies and VLAs
- Continual Personalization for Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
- VideoNSA: Native Sparse Attention Scales Video UnderstandingMultimodal LLMs / vision-language models → Video understanding with MLLMs
- From Behavioral Performance to Internal Competence: Interpreting Vision-Language Models with VLM-LensMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- Test-Time Anchoring for Discrete Diffusion Posterior SamplingDiffusion models → Discrete and text diffusion
- MultiModal Action Conditioned Video GenerationWorld models → Embodied and robot world models
- Tree-based Dialogue Reinforced Policy Optimization for Red-Teaming AttacksLLM safety and security → Prompt injection and agent security
- Learning to Generate Rigid Body Interactions with Video Diffusion ModelsDiffusion models → Video generation
- Self-Forcing++: Towards Minute-Scale High-Quality Video GenerationDiffusion models → Video generation
- VidGuard-R1: AI-Generated Video Detection and Explanation via Reasoning MLLMs and RLLLM reasoning → Multimodal reasoning +1
- Parallel Scaling Law: Unveiling Reasoning Generalization through A Cross-Linguistic PerspectiveLLM reasoning → Reasoning benchmarks and evaluation
- InfoMosaic-Bench: Evaluating Multi-Source Information Seeking in Tool-Augmented AgentsLLM agents and tool use → Web, search, and research agents
- microCLIP: Unsupervised CLIP Adaptation via Coarse-Fine Token Fusion for Fine-Grained Image ClassificationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Do You Know Where Your Camera Is? View-Invariant Policy Learning with Camera ConditioningOffline RL and imitation learning from data → Robot manipulation imitation learning
- How to Combat Reactive and Dynamic Jamming Attacks with Reinforcement LearningDeep reinforcement learning methods → RL for energy, networks and operations
- DragFlow: Unleashing DiT Priors with Region Based Supervision for Drag EditingDiffusion models → Image generation, text-to-image and editing
- Scaling Agents for Computer UseLLM agents and tool use → GUI and mobile agents
- Explore Briefly, Then Decide: Mitigating LLM Overthinking via Cumulative Entropy RegulationLLM reasoning → Test-time compute and efficient thinking
- ExGRPO: Learning to Reason from ExperienceLLM reasoning → Reinforcement learning for reasoning
- AccurateRAG: A Framework for Building Accurate Retrieval-Augmented Question-Answering ApplicationsRetrieval-augmented generation → RAG robustness and adaptive retrieval
- RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement LearningLLM reasoning → Multimodal reasoning +1
- The Reasoning Boundary Paradox: How Reinforcement Learning Constrains Language ModelsLLM reasoning → Reinforcement learning for reasoning
- More Than One Teacher: Adaptive Multi-Guidance Policy Optimization for Diverse ExplorationLLM reasoning → Reinforcement learning for reasoning
- Diffusion Transformers for Imputation: Statistical Efficiency and Uncertainty QuantificationDiffusion models → Flow matching, time series and science
- DiFFPO: Training Diffusion LLMs to Reason Fast and Furious via Reinforcement LearningLLM reasoning → Diffusion reasoning and test-time scaling +1
- StockBench: Can LLM Agents Trade Stocks Profitably In Real-world Markets?LLM agents and tool use → Financial trading and forecasting agents
- MACS: Measurement-Aware Consistency Sampling for Inverse ProblemsDiffusion models → Inverse problems and image restoration
- Say One Thing, Do Another? Diagnosing Reasoning-Execution Gaps in VLM-Powered Mobile-Use AgentsLLM reasoning → Reasoning for agents, planning and code +1
- UpSafe^circC: Upcycling for Controllable Safety in Large Language ModelsMixture-of-experts → Expert routing strategies +1
- Dr. Bench: A Multidimensional Evaluation for Deep Research Agents, from Answers to ReportsLLM agents and tool use → Web, search, and research agents
- GeoPurify: A Data-Efficient Geometric Distillation Framework for Open-Vocabulary 3D SegmentationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
- FalseCrashReducer: Mitigating False Positive Crashes in OSS-Fuzz-Gen Using Agentic AILLM agents and tool use → Software engineering coding agents
- Uncovering Semantic Selectivity of Latent Groups in Higher Visual Cortex with Mutual Information-Guided DiffusionDiffusion models → Medical imaging and segmentation
- GRACE: A Language Model Framework for Explainable Inverse Reinforcement LearningLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
- DisCo-Layout: Disentangling and Coordinating Semantic and Physical Refinement in a Multi-Agent Framework for 3D Indoor Layout SynthesisLLM agents and tool use → Multimodal and embodied agents
- Learning to Reason for Hallucination Span DetectionLLM reasoning → Hallucination detection and mitigation
- RESTRAIN: From Spurious Votes to Signals -- Self-Driven RL with Self-PenalizationLLM reasoning → Reinforcement learning for reasoning
- Agentic Reasoning and Refinement through Semantic InteractionLLM reasoning → Reasoning for agents, planning and code +1
- Unlocking Vision-Language Models for Video Anomaly Detection via Fine-Grained PromptingMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
- Reinforcement Learning with Action-Triggered ObservationsDeep reinforcement learning methods → RL theory and sample complexity
- Policy Gradient Guidance Enables Test Time ControlDiffusion models → Diffusion and flow policies for robotics +1
- BioinfoMCP: A Unified Platform Enabling MCP Interfaces in Agentic BioinformaticsLLM agents and tool use → Medical and scientific domain agents
- The Disparate Impacts of Speculative DecodingEfficient LLM inference and serving → Speculative decoding
- Do AI Models Perform Human-like Abstract Reasoning Across Modalities?LLM reasoning → Multimodal reasoning
- Demystifying the Roles of LLM Layers in Retrieval, Knowledge, and ReasoningLLM reasoning → Reasoning benchmarks and evaluation
- VGDM: Vision-Guided Diffusion Model for Brain Tumor Detection and SegmentationDiffusion models → Medical imaging and segmentation
- Fine-Tuning Flow Matching via Maximum Likelihood Estimation of ReconstructionsDiffusion models → Flow matching, time series and science
- Chain-of-Thought Reasoning in Streaming Full-Duplex End-to-End Spoken Dialogue SystemsLLM reasoning → Audio-language model reasoning
- MSRepaint: Multiple Sclerosis Repaint with Conditional Denoising Diffusion Implicit Model for Bidirectional Lesion Filling and SynthesisDiffusion models → Medical imaging and segmentation
- Stream RAG: Instant and Accurate Spoken Dialogue Systems with Streaming Tool UsageRetrieval-augmented generation → Conversational and speech RAG
- Zero-shot Human Pose Estimation using Diffusion-based Inverse solversDiffusion models → 3D, point cloud and scene generation
- Fine-Grained GRPO for Precise Preference Alignment in Flow ModelsLLM reasoning → Reinforcement learning for reasoning +1
- ZK-WAGON: Imperceptible Watermark for Image Generation Models using ZK-SNARKsLLM safety and security → Watermarking generated content and models
All 430
- Exploring Resolution-Wise Shared Attention in Hybrid Mamba-U-Nets for Improved Cross-Corpus Speech EnhancementState-space sequence models (S4, Mamba) → Speech and audio SSMs
- Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
- Veri-R1: Toward Precise and Faithful Claim Verification via Online Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning +1
- Enhancing Large Language Model Reasoning with Reward Models: An Analytical SurveyLLM reasoning → Reinforcement learning for reasoning +1
- To Mask or to Mirror: Human-AI Alignment in Collective ReasoningLLM reasoning → Reasoning benchmarks and evaluation
- Flow-Matching Guided Deep Unfolding for Hyperspectral Image ReconstructionDiffusion models → Inverse problems and image restoration
- Are LLMs Better GNN Helpers? Rethinking Robust Graph Learning under Deficiencies with Iterative RefinementLLM reasoning → Knowledge- and tool-augmented reasoning +1
- Learning Reasoning Rewards from Expert Demonstrations with Inverse Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning +1
- Leveraging Prior Knowledge of Diffusion Model for Person SearchDiffusion models → Image generation, text-to-image and editing
- Plan Then Action:High-Level Planning Guidance Reinforcement Learning for LLM ReasoningLLM reasoning → Reinforcement learning for reasoning
- SCRIBES: Web-Scale Script-Based Semi-Structured Data Extraction with Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
- Black-Box Combinatorial Optimization with Order-Invariant Reinforcement LearningDeep reinforcement learning methods → RL for games and combinatorial optimization
- Nav-EE: Navigation-Guided Early Exiting for Efficient Vision-Language Models in Autonomous DrivingMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +2
- Octax: Accelerated CHIP-8 Arcade Environments for Reinforcement Learning in JAXDeep reinforcement learning methods → RL training of language and agent models
- MetaboT: An LLM-based Multi-Agent Frameworkfor Interactive Analysis of Mass SpectrometryMetabolomics Knowledge GraphsLLM agents and tool use → Medical and scientific domain agents
- Finite-Time Convergence of Single-Trajectory Chi-Square Robust Q-Learning With Linear Function ApproximationDeep reinforcement learning methods → RL theory and sample complexity
- What MLLMs Learn about When they Learn about Multimodal ReasoningLLM reasoning → Multimodal reasoning
- Contrastive Representation Regularization for Vision-Language-Action ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
- VaPR -- Vision-language Preference alignment for ReasoningLLM reasoning → Multimodal reasoning +2
- MedQ-Bench: Evaluating and Exploring Medical Image Quality Assessment Abilities in MLLMsLLM reasoning → Clinical and biomedical applications
- Look Less, Reason More: Rollout-Guided Adaptive Pixel-Space ReasoningLLM reasoning → Multimodal reasoning +1
- FOR-Prompting: From Objection to Revision via an Asymmetric Prompting ProtocolLLM reasoning → Prompting and chain-of-thought reasoning
- Just Do It!? Computer-Use Agents Exhibit Blind Goal-DirectednessLLM agents and tool use → Agent threats, guardrails and governance
- UniVerse: Unleashing the Scene Prior of Video Diffusion Models for Robust Radiance Field ReconstructionDiffusion models → 3D, point cloud and scene generation
- GuruAgents: Emulating Wise Investors with Prompt-Guided LLM AgentsLLM agents and tool use → Financial trading and forecasting agents
- Asymmetric Proximal Policy Optimization: mini-critics boost LLM reasoningLLM reasoning → Reinforcement learning for reasoning
- SoK: Measuring What Matters for Closed-Loop Security AgentsLLM agents and tool use → Agent threats, guardrails and governance
- Machine Learning for Detection and Analysis of Novel LLM JailbreaksLLM safety and security → Jailbreaking
- FailSafe: Reasoning and Recovery from Failures in Vision-Language-Action ModelsLLM reasoning → Spatial and embodied reasoning +2
- FideDiff: Efficient Diffusion Model for High-Fidelity Image Motion DeblurringDiffusion models → Inverse problems and image restoration
- Understanding the Geospatial Reasoning Capabilities of LLMs: A Trajectory Recovery PerspectiveLLM reasoning → Spatial and embodied reasoning
- Detecting Post-generation Edits to Watermarked LLM Outputs via Combinatorial WatermarkingLLM safety and security → Watermarking generated content and models
- Demystifying Synthetic Data in LLM Pre-training: A Systematic Study of Scaling Laws, Benefits, and PitfallsSynthetic data and self-improvement for LLMs → LLM synthetic data generation
- Quagmires in SFT-RL Post-Training: When High SFT Scores Mislead and What to Use InsteadLLM reasoning → Reinforcement learning for reasoning
- VLA-R1: Enhancing Reasoning in Vision-Language-Action ModelsVision-language-action models → Reinforcement learning and post-training
- AMAS: Adaptively Determining Communication Topology for LLM-based Multi-Agent SystemLLM agents and tool use → General LLM agent frameworks and benchmarks
- Efficient Training of Robust Traditional Chinese LLaMA-1B on a Single Consumer GPU: Continual Pre-training, SFT, and DPOLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
- RAG-BioQA: A Retrieval-Augmented Generation Framework for Long-Form Biomedical Question AnsweringRetrieval-augmented generation → Medical and biomedical RAG
- AgentRec: Next-Generation LLM-Powered Multi-Agent Collaborative Recommendation with Adaptive IntelligenceLLM agents and tool use → Agentic recommender systems
- A Comparison of Independent and Joint Fine-tuning Strategies for Retrieval-Augmented GenerationRetrieval-augmented generation → RAG pipeline design and evaluation
- AdvEvo-MARL: Shaping Internalized Safety through Adversarial Co-Evolution in Multi-Agent Reinforcement LearningLLM agents and tool use → Agent threats, guardrails and governance +1
- ReSSFormer: A Recursive Sparse Structured Transformer for Scalable and Long-Context ReasoningLLM reasoning → Test-time compute and efficient thinking
- ImageNet-Think-250K: A Large-Scale Synthetic Dataset for Multimodal Reasoning for Vision Language ModelsLLM reasoning → Multimodal reasoning +2
- Think Right: Learning to Mitigate Under-Over Thinking via Adaptive, Attentive CompressionLLM reasoning → Test-time compute and efficient thinking
- Guiding Multimodal Large Language Models with Blind and Low Vision People Visual Questions for Proactive Visual InterpretationsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- InvThink: Premortem Reasoning for Safer Language ModelsLLM reasoning → Reasoning for agents, planning and code
- TetriServe: Efficiently Serving Mixed DiT WorkloadsDiffusion models → Diffusion foundations and sampling
- CardioRAG: A Retrieval-Augmented Generation Framework for Multimodal Chagas Disease DetectionRetrieval-augmented generation → Medical and biomedical RAG
- Rethinking KL Regularization in RLHF: From Value Estimation to Gradient OptimizationLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- MIRA: Towards Mitigating Reward Hacking in Inference-Time Alignment of T2I Diffusion ModelsDiffusion models → Diffusion and flow policies for robotics +1
- Growing Visual Generative Capacity for Pre-Trained MLLMsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
- Advancing Reasoning in Diffusion Language Models with Denoising Process RewardsLLM reasoning → Diffusion reasoning and test-time scaling +1
- Towards Better Optimization For Listwise Preference in Diffusion ModelsDiffusion models → Diffusion and flow policies for robotics +1
- Executable Counterfactuals: Improving LLMs' Causal Reasoning Through CodeLLM reasoning → Causal reasoning in LLMs
- TimeSeriesScientist: A General-Purpose AI Agent for Time Series AnalysisLLM agents and tool use → Financial trading and forecasting agents
- LOGicalThought: Logic-Based Ontological Grounding of LLMs for High-Assurance ReasoningLLM reasoning → Reasoning benchmarks and evaluation
- Towards Interpretable and Inference-Optimal COT Reasoning with Sparse Autoencoder-Guided GenerationLLM reasoning → Mathematical reasoning +1
- Causal Intervention Sequence Analysis for Fault Tracking in Radio Access Networks
- Adaptive Guided Upsampling for Low-light Image Enhancement
- Next-Generation LLM for UAV: From Natural Language to Autonomous Flight
- Neurotremor: A wearable Supportive Device for Supporting Upper Limb Muscle Function
- Multi-Agent Design Assistant for the Simulation of Inertial Fusion Energy
- Dynamic Stress Detection: A Study of Temporal Progression Modelling of Stress in Speech
- Stacked Regression using Off-the-shelf, Stimulus-tuned and Fine-tuned Neural Networks for Predicting fMRI Brain Responses to Movies (Algonauts 2025 Report)
- User to Video: A Model for Spammer Detection Inspired by Video Classification Technology
- Can AI Truly Represent Your Voice in Deliberations? A Comprehensive Study of Large-Scale Opinion Aggregation with LLMs
- An Algorithmic Information-Theoretic Perspective on the Symbol Grounding Problem
- A Single Character can Make or Break Your LLM Evals
- Exploring Large Language Models for Financial Applications: Techniques, Performance, and Challenges with FinMA
- Percepta: High Performance Stream Processing at the Edge
- Understanding Transformers for Time Series: Rank Structure, Flow-of-ranks, and Compressibility
- Learned Display Radiance Fields with Lensless Cameras
- High Cycle S-N curve prediction for Al 7075-T6 alloy using Recurrent Neural Networks (RNNs)
- Sonar Image Datasets: A Comprehensive Survey of Resources, Challenges, and Applications
- Interpretable Neuropsychiatric Diagnosis via Concept-Guided Graph Neural Networks
- Monocular Visual Odometry without Calibration or Test-time Optimization
- KVComm: Enabling Efficient LLM Communication through Selective KV Sharing
- Pilot selection in the era of Virtual reality: algorithms for accurate and interpretable machine learning models
- Assessing the impact of contact time on leachate chemistry from recycled concrete aggregates
- Defining a Strategic Action Plan for AI in Higher Education
- OpusAnimation: Code-Based Dynamic Chart Generation
- Pool Me Wisely: On the Effect of Pooling in Transformer-Based Models
- Error correction in multiclass image classification of facial emotion on unbalanced samples
- Linguistic and Audio Embedding-Based Machine Learning for Alzheimer's Dementia and Mild Cognitive Impairment Detection: Insights from the PROCESS Challenge
- Semantic-Aware Scheduling for GPU Clusters with Large Language Models
- MINERVA: Mutual Information Neural Estimation for Supervised Feature Selection
- Towards CONUS-Wide ML-Augmented Conceptually-Interpretable Modeling of Catchment-Scale Precipitation-Storage-Runoff Dynamics
- Ego-Exo 3D Hand Tracking in the Wild with a Mobile Multi-Camera Rig
- FLOWR.root: A flow matching based foundation model for joint multi-purpose structure-aware 3D ligand generation and affinity prediction
- Geospatial Machine Learning Libraries
- How Confident are Video Models? Empowering Video Models to Express their Uncertainty
- Unlocking the power of partnership: How humans and machines can work together to improve face recognition
- Transcribe, Translate, or Transliterate: An Investigation of Intermediate Representations in Spoken Language Models
- PhysHMR: Learning Humanoid Control Policies from Vision for Physically Plausible Human Motion Reconstruction
- On The Expressive Power of GNN Derivatives
- AttentiveGRUAE: An Attention-Based GRU Autoencoder for Temporal Clustering and Behavioral Characterization of Depression from Wearable Data
- Even Faster Kernel Matrix Linear Algebra via Density Estimation
- Hierarchical Semantic Retrieval with Cobweb
- PHORECAST: Enabling AI Understanding of Public Health Outreach Across Populations
- Learning Multi-Index Models with Hyper-Kernel Ridge Regression
- Unraveling Syntax: Language Modeling and the Substructure of Grammars
- Model-brain comparison using inter-animal transforms
- In-memory Training on Analog Devices with Limited Conductance States via Multi-tile Residual Learning
- Learning a distance measure from the information-estimation geometry of data
- Adaptive randomized pivoting and volume sampling
- Litespark Technical Report: High-Throughput, Energy-Efficient LLM Training Framework
- Uncertainty-Guided Model Selection for Tabular Foundation Models in Biomolecule Efficacy Prediction
- Heterogeneous Graph Representation of Stiffened Panels with Non-Uniform Boundary Conditions and Loads
- Predictive inference for time series: why is split conformal effective despite temporal dependence?
- SAGE: Streaming Agreement-Driven Gradient Sketches for Representative Subset Selection
- CLARITY: Clinical Assistant for Routing, Inference, and Triage
- Assessing the Potential for Catastrophic Failure in Dynamic Post-Training Quantization
- Market-Driven Subset Selection for Budgeted Training
- How to Train Your Advisor: Steering Black-Box LLMs with Advisor Models
- Words That Make Language Models Perceive
- Adaptive Deception Framework with Behavioral Analysis for Enhanced Cybersecurity Defense
- RefineShot: Rethinking Cinematography Understanding with Foundational Skill Evaluation
- Higher-arity PAC learning, VC dimension and packing lemma
- NEURODNAAI: Neural pipeline approaches for the advancing dna-based information storage as a sustainable digital medium using deep learning framework
- Cross-Platform DNA Methylation Classifier for the Eight Molecular Subtypes of Group 3 & 4 Medulloblastoma
- The Equilibrium Response of Atmospheric Machine-Learning Models to Uniform Sea Surface Temperature Warming
- RainSeer: Fine-Grained Rainfall Reconstruction via Physics-Guided Modeling
- Extreme value forecasting using relevance-based data augmentation with deep learning models
- Optimal Post-processing of Synthetic Data for Pearson Correlation Matching
- StealthAttack: Robust 3D Gaussian Splatting Poisoning via Density-Guided Illusions
- Clink! Chop! Thud! -- Learning Object Sounds from Real-World Interactions
- Inferring Dynamic Physical Properties from Video Foundation Models
- Robust Tangent Space Estimation via Laplacian Eigenvector Gradient Orthogonalization
- Equilibrium Matching: Generative Modeling with Implicit Energy-Based Models
- Interactive Training: Feedback-Driven Neural Network Optimization
- F2LLM Technical Report: Matching SOTA Embedding Performance with 6 Million Open-Source Data
- Addressing Pitfalls in the Evaluation of Uncertainty Estimation Methods for Natural Language Generation
- Metropolis-Scale Road Network Datasets for Fine-Grained Urban Traffic Modeling
- BioX-Bridge: Model Bridging for Unsupervised Cross-Modal Knowledge Transfer across Biosignals
- Diffusion^2: Turning 3D Environments into Radio Frequency Heatmaps
- NeuroSwift: A Lightweight Cross-Subject Framework for fMRI Visual Reconstruction of Complex Scenes
- Paving the Way Towards Kinematic Assessment Using Monocular Video: A Preclinical Benchmark of State-of-the-Art Deep-Learning-Based 3D Human Pose Estimators Against Inertial Sensors in Daily Living Activities
- RLAD: Training LLMs to Discover Abstractions for Solving Reasoning Problems
- From Frames to Clips: Training-free Adaptive Key Clip Selection for Long-Form Video Understanding
- Transformers Discover Molecular Structure Without Graph Priors
- Study on LLMs for Promptagator-Style Dense Retriever Training
- Drop-Muon: Update Less, Converge Faster
- PUL-Inter-slice Defender: An Anomaly Detection Solution for Distributed Slice Mobility Attacks
- Enhanced Arabic-language cyberbullying detection: deep embedding and transformer (BERT) approaches
- xLSTM Scaling Laws: Competitive Performance with Linear Time-Complexity
- TempoControl: Temporal Attention Guidance for Text-to-Video Models
- Efficiently Generating Correlated Sample Paths from Multi-step Time Series Foundation Models
- Quantum Fisher information matrices from R'enyi relative entropies
- Improving Large-Scale Recommender Systems with Auxiliary Learning
- Getting the Numbers Rightunicodex2014Modelling Multi-Class Object Counting in Dense and Varied Scenes
- Poolformer: Recurrent Networks with Pooling for Long-Sequence Modeling
- Detection of Chagas Disease from the ECG: The George B. Moody PhysioNet Challenge 2025
- ARUQULA -- An LLM based Text2SPARQL Approach using ReAct and Knowledge Graph Exploration Utilities
- Cross-Breed Pig Identification Using Auricular Vein Pattern Recognition: A Machine Learning Approach for Small-Scale Farming Applications
- Hybrid Physics-ML Framework for Pan-Arctic Permafrost Infrastructure Risk at Record 2.9-Million Observation Scale
- High-Fidelity Speech Enhancement via Discrete Audio Tokens
- EvolveCaptions: Empowering DHH Users Through Real-Time Collaborative Captioning
- Flatness-Aware Stochastic Gradient Langevin Dynamics
- Go witheFlow: Real-time Emotion Driven Audio Effects Modulation
- SIEVE: Towards Verifiable Certification for Code-datasets
- NoMod: A Non-modular Attack on Module Learning With Errors
- Comparing Contrastive and Triplet Loss: Variance Analysis and Optimization Behavior
- Human-Robo-advisor collaboration in decision-making: Evidence from a multiphase mixed methods experimental study
- How to Find Fantastic AI Papers: Self-Rankings as a Powerful Predictor of Scientific Impact Beyond Peer Review
- Catalyst GFlowNet for electrocatalyst design: A hydrogen evolution reaction case study
- FlexDoc: Parameterized Sampling for Diverse Multilingual Synthetic Documents for Training Document Understanding Models
- VarCoNet: A variability-aware self-supervised framework for functional connectome extraction from resting-state fMRI
- Non-Asymptotic Analysis of Data Augmentation for Precision Matrix Estimation
- DAG DECORation: Continuous Optimization for Structure Learning under Hidden Confounding
- Ensemble Threshold Calibration for Stable Sensitivity Control
- Hybrid Deep Learning Modeling Approach to Predict Natural Gas Consumption of Home Subscribers on Limited Data
- FRIEREN: Federated Learning with Vision-Language Regularization for Segmentation
- SoundReactor: Frame-level Online Video-to-Audio Generation
- SpurBreast: A Curated Dataset for Investigating Spurious Correlations in Real-world Breast MRI Classification
- Unlocking Symbol-Level Precoding Efficiency Through Tensor Equivariant Neural Network
- PENEX: AdaBoost-Inspired Neural Network Regularization
- When Tracking Fails: Analyzing Failure Modes of SAM2 for Point-Based Tracking in Surgical Videos
- Mapping Historic Urban Footprints in France: Balancing Quality, Scalability and AI Techniques
- Learning Model Representations Using Publicly Available Model Hubs
- KAIROS: Unified Training for Universal Non-Autoregressive Time Series Forecasting
- Inferring Optical Tissue Properties from Photoplethysmography using Hybrid Amortized Inference
- Spec-Gloss Surfels and Normal-Diffuse Priors for Relightable Glossy Objects
- Adaptive Kernel Selection for Stein Variational Gradient Descent
- ReTabAD: A Benchmark for Restoring Semantic Context in Tabular Anomaly Detection
- Adaptive Heterogeneous Mixtures of Normalising Flows for Robust Variational Inference
- Multidata Causal Discovery for Statistical Hurricane Intensity Forecasting
- Mathematical Modeling and Convergence Analysis of Deep Neural Networks with Dense Layer Connectivities in Deep Learning
- Variational Secret Common Randomness Extraction
- A Multicentric Dataset for Training and Benchmarking Breast Cancer Segmentation in H&E Slides
- The Current State of AI Bias Bounties: An Overview of Existing Programmes and Research
- SemMorph3D: Unsupervised Semantic-Aware 3D Morphing via Mesh-Guided Gaussians
- kabr-tools: Automated Framework for Multi-Species Behavioral Monitoring
- LiLa-Net: Lightweight Latent LiDAR Autoencoder for 3D Point Cloud Reconstruction
- Zero-shot reasoning for simulating scholarly peer-review
- Style over Story: Measuring LLM Narrative Preferences via Structured Selection
- FairContrast: Enhancing Fairness through Contrastive learning and Customized Augmenting Methods on Tabular Data
- Normality Calibration in Semi-supervised Graph Anomaly Detection
- ShapeGen3DCP: A Deep Learning Framework for Layer Shape Prediction in 3D Concrete Printing
- Generating Findings for Jaw Cysts in Dental Panoramic Radiographs Using a GPT-Based VLM: A Preliminary Study on Building a Two-Stage Self-Correction Loop with Structured Output (SLSO) Framework
- Pure-Pass: Fine-Grained, Adaptive Masking for Dynamic Token-Mixing Routing in Lightweight Image Super-Resolution
- LLM-Based Multi-Task Bangla Hate Speech Detection: Type, Severity, and Target
- Clarifying Semantics of In-Context Examples for Unit Test Generation
- 4DGS-Craft: Consistent and Interactive 4D Gaussian Splatting Editing
- TriAlignXA: An Explainable Trilemma Alignment Framework for Trustworthy Agri-product Grading
- Exploring Database Normalization Effects on SQL Generation
- PepCompass: Navigating peptide embedding spaces using Riemannian Geometry
- Private Federated Multiclass Post-hoc Calibration
- ROI-GS: Interest-based Local Quality 3D Gaussian Splatting
- Taking a SEAT: Predicting Value Interpretations from Sentiment, Emotion, Argument, and Topic Annotations
- Moon: A Modality Conversion-based Efficient Multivariate Time Series Anomaly Detection
- Lower Bounds on Adversarial Robustness for Multiclass Classification with General Loss Functions
- Multi-bit Audio Watermarking
- Bias beyond Borders: Global Inequalities in AI-Generated Music
- ClustViT: Clustering-based Token Merging for Semantic Segmentation
- Uniform-in-time convergence bounds for Persistent Contrastive Divergence algorithms
- Smooth Quasar-Convex Optimization with Constraints
- StelLA: Subspace Learning in Low-rank Adaptation using Stiefel Manifold
- Foundation Visual Encoders Are Secretly Few-Shot Anomaly Detectors
- Precise Dynamics of Diagonal Linear Networks: A Unifying Analysis by Dynamical Mean-Field Theory
- Inverse Language Modeling towards Robust and Grounded LLMs
- GFSR-Net: Guided Focus via Segment-Wise Relevance Network for Interpretable Deep Learning in Medical Imaging
- Predictively Oriented Posteriors
- Automated Defect Detection for Mass-Produced Electronic Components Based on YOLO Object Detection Models
- A Methodology for Transparent Logic-Based Classification Using a Multi-Task Convolutional Tsetlin Machine
- Constrained Adaptive Rejection Sampling
- Multimodal Foundation Models for Early Disease Detection
- Multi-marginal temporal Schr"odinger Bridge Matching from unpaired data
- HRTFformer: A Spatially-Aware Transformer for Individual HRTF Upsampling in Immersive Audio Rendering
- Small is Sufficient: Reducing the World AI Energy Consumption Through Model Selection
- FINCH: Financial Intelligence using Natural language for Contextualized SQL Handling
- REPAIR: Robust Editing via Progressive Adaptive Intervention and Reintegration
- Geometrically Principled Randomized Optimization for Efficient LLM Training
- Deep Hedging Under Non-Convexity: Limitations and a Case for AlphaZero
- Ranking Items from Discrete Ratings: The Cost of Unknown User Thresholds
- TACOS: Task Agnostic COordinator of a multi-drone System
- Universal Dynamic Regret and Constraint Violation Bounds for Constrained Online Convex Optimization
- A Modular Theory of Subjective Consciousness for Natural and Artificial Minds
- Microscaling Floating Point Formats for Large Language Models
- Compositional meta-learning through probabilistic task inference
- Explicit Discovery of Nonlinear Symmetries from Dynamic Data
- Learning Representations Through Contrastive Neural Model Checking
- NGGAN: Noise Generation GAN Based on the Practical Measurement Dataset for Narrowband Powerline Communications
- Model Merging to Maintain Language-Only Performance in Developmentally Plausible Multimodal Models
- Pre-Hoc Predictions in AutoML: Leveraging LLMs to Enhance Model Selection and Benchmarking for Tabular datasets
- A reproducible comparative study of categorical kernels for Gaussian process regression, with new clustering-based nested kernels
- Syntactic Blind Spots: How Misalignment Leads to LLMs Mathematical Errors
- Calibrating the Full Predictive Class Distribution of 3D Object Detectors for Autonomous Driving
- Sparse Query Attention (SQA): A Computationally Efficient Attention Mechanism with Query Heads Reduction
- Human-AI Teaming Co-Learning in Military Operations
- SingMOS-Pro: An Comprehensive Benchmark for Singing Quality Assessment
- Detecting LLM-Generated Spam Reviews by Integrating Language Model Embeddings and Graph Neural Network
- REBot: From RAG to CatRAG with Semantic Enrichment and Graph Routing
- PRESOL: a web-based computational setting for feature-based flare forecasting
- Rethinking the shape convention of an MLP
- Sensitivity, Specificity, and Consistency: A Tripartite Evaluation of Privacy Filters for Synthetic Data Generation
- Comparison of Unsupervised Metrics for Evaluating Judicial Decision Extraction
- Neural non-canonical Hamiltonian dynamics for long-time simulations
- Pack and Force Your Memory: Long-form and Consistent Video Generation
- Can LLMs Refuse Questions They Do Not Know? Measuring Knowledge-Aware Refusal in Factual Tasks
- Secure Multi-Modal Data Fusion in Federated Digital Health Systems via MCP
- Scalable Asynchronous Federated Modeling for Spatial Data
- LoBE-GS: Load-Balanced and Efficient 3D Gaussian Splatting for Large-Scale Scene Reconstruction
- Unsupervised Dynamic Feature Selection for Robust Latent Spaces in Vision Tasks
- Learning Regularization Functionals for Inverse Problems: A Comparative Study
- A cybersecurity AI agent selection and decision support framework
- Towards Photonic Band Diagram Generation with Transformer-Latent Diffusion Models
- Private and Fair Machine Learning: Revisiting the Disparate Impact of Differentially Private SGD
- Machine-interpretable Engineering Design Standards for Valve Specification
- Reducing Simulation Dependence in Neutrino Telescopes with Masked Point Transformers
- Workplace Location Choice Model based on Deep Neural Network
- Emotional Text-To-Speech Based on Mutual-Information-Guided Emotion-Timbre Disentanglement
- Accelerating Attention with Basis Decomposition
- Latency-aware Multimodal Federated Learning over UAV Networks
- PyramidStyler: Transformer-Based Neural Style Transfer with Pyramidal Positional Encoding and Reinforcement Learning
- ActiNet: An Open-Source Tool for Activity Intensity Classification of Wrist-Worn Accelerometry Using Self-Supervised Deep Learning
- PolySim: Bridging the Sim-to-Real Gap for Humanoid Control via Multi-Simulator Dynamics Randomization
- Representational Alignment Across Model Layers and Brain Regions with Multi-Level Optimal Transport
- Holistic Order Prediction in Natural Scenes
- PASTA: A Unified Framework for Offline Assortment Learning
- Format Inertia: A Failure Mechanism of LLMs in Medical Pre-Consultation
- Improving AGI Evaluation: A Data Science Perspective
- FreeViS: Training-free Video Stylization with Inconsistent References
- How Do Language Models Compose Functions?
- Uncovering Overconfident Failures in CXR Models via Augmentation-Sensitivity Risk Scoring
- An Efficient Deep Template Matching and In-Plane Pose Estimation Method via Template-Aware Dynamic Convolution
- Beyond Simple Fusion: Adaptive Gated Fusion for Robust Multimodal Sentiment Analysis
- Evaluating the Robustness of a Production Malware Detection System to Transferable Adversarial Attacks
- A Locally Executable AI System for Improving Preoperative Patient Communication: A Multi-Domain Clinical Evaluation
- Median2Median: Zero-shot Suppression of Structured Noise in Images
- Non-Rigid Structure-from-Motion via Differential Geometry with Recoverable Conformal Scale
- Shift-Invariant Attribute Scoring for Kolmogorov-Arnold Networks via Shapley Value
- Discrete Facial Encoding: : A Framework for Data-driven Facial Display Discovery
- VirDA: Reusing Backbone for Unsupervised Domain Adaptation with Visual Reprogramming
- MDSEval: A Meta-Evaluation Benchmark for Multimodal Dialogue Summarization
- Learning Time-Series Representations by Hierarchical Uniformity-Tolerance Latent Balancing
- Learning to Look at the Other Side: A Semantic Probing Study of Word Embeddings in LLMs with Enabled Bidirectional Attention
- LadderMoE: Ladder-Side Mixture of Experts Adapters for Bronze Inscription Recognition
- The Unseen Frontier: Pushing the Limits of LLM Sparsity with Surrogate-Free ADMM
- Source-Free Cross-Domain Continual Learning
- Position: Privacy Is Not Just Memorization!
- Support Basis: Fast Attention Beyond Bounded Entries
- Joint Deblurring and 3D Reconstruction for Macrophotography
- Towards Human-Centered RegTech: Unpacking Professionals' Strategies and Needs for Using LLMs Safely
- CAT: Curvature-Adaptive Transformers for Geometry-Aware Learning
- BioBlobs: Unsupervised Discovery of Functional Substructures for Protein Function Prediction
- LLM4Rec: Large Language Models for Multimodal Generative Recommendation with Causal Debiasing
- Posterior Collapse as a Phase Transition in Variational Autoencoders
- Learning to Decide with Just Enough: Information-Theoretic Context Summarization for CMDPs
- MPMAvatar: Learning 3D Gaussian Avatars with Accurate and Robust Physics-Based Dynamics
- Automated Genomic Interpretation via Concept Bottleneck Models for Medical Robotics
- PsychCounsel-Bench: Evaluating the Psychology Intelligence of Large Language Models
- NPN: Non-Linear Projections of the Null-Space for Imaging Inverse Problems
- ActiveUMI: Robotic Manipulation with Active Perception from Robot-Free Human Demonstrations
- Bridging Collaborative Filtering and Large Language Models with Dynamic Alignment, Multimodal Fusion and Evidence-grounded Explanations
- Securing generative artificial intelligence with parallel magnetic tunnel junction true randomness
- CLUE: Non-parametric Verification from Experience via Hidden-State Clustering
- Enhancing Noise Robustness of Parkinson's Disease Telemonitoring via Contrastive Feature Augmentation
- Gradient Shaping Beyond Clipping: A Functional Perspective on Update Magnitude Control
- Synthetic Prefixes to Mitigate Bias in Real-Time Neural Query Autocomplete
- From Supervision to Exploration: What Does Protein Language Model Learn During Reinforcement Learning?
- Large-Scale Bayesian Causal Discovery with Interventional Data
- AI Foundation Model for Time Series with Innovations Representation
- Consistent Assistant Domains Transformer for Source-free Domain Adaptation
- POLAR: Automating Cyber Threat Prioritization through LLM-Powered Assessment
- Robust Classification of Oral Cancer with Limited Training Data
- Predictive Preference Learning from Human Interventions
- NVIDIA AI Aerial: AI-Native Wireless Communications
- MATCH: Multi-faceted Adaptive Topo-Consistency for Semi-Supervised Histopathology Segmentation
- Information Seeking for Robust Decision Making under Partial Observability
- Bypassing Prompt Guards in Production with Controlled-Release Prompting