Wispr Flow - Don’t type, just speak
Mini toolsPapers
Filter by company
-
Deterministic Fuzzy Triage for Legal Compliance Classification and Evidence Retrieval
-
Can Large Language Models Keep Up? Benchmarking Online Adaptation to Continual Knowledge StreamsKorea Advanced Institute of Science & Technology, New York University, University of North Carolina at Chapel Hill
-
AQuA: Toward Strategic Response Generation for Ambiguous Visual QuestionsPohang University of Science and Technology
-
Interpretable Aneurysm Classification via 3D Concept Bottleneck Models: Integrating Morphological and Hemodynamic Clinical FeaturesArab Academy for Science and Technology, Zewail City of Science and Technology
-
VIVECaption: A Split Approach to Caption Quality Improvement
-
Generalizing Linear Autoencoder Recommenders with Decoupled Expected Quadratic LossAuburn University, Kent State University
-
Prompt-Based Caption Generation for Single-Tooth Dental Images Using Vision-Language ModelsMarshall University, West Virginia State University
-
Adaptive Capacity Allocation for Vision Language Action Fine-tuningSeoul National University, Sungkyunkwan University
-
UnSCAR: Universal, Scalable, Controllable, and Adaptable Image RestorationUniversity of California, University of North Carolina at Chapel Hill
-
Safety Under Scaffolding: How Evaluation Conditions Shape Measured SafetyHarvard University
-
Machine Learning for the Internet of Underwater Things: From Fundamentals to ImplementationUniversity of Glasgow
-
QdaVPR: A novel query-based domain-agnostic model for visual place recognitionNational University of Defense Technology
-
Context Channel Capacity: An Information-Theoretic Framework for Understanding Catastrophic Forgetting
-
DualSpec: Accelerating Deep Research Agents via Dual-Process Action SpeculationPeking University
-
Dynamic Vehicle Routing Problem with Prompt Confirmation of Advance Requests
-
AutoControl Arena: Synthesizing Executable Test Environments for Frontier AI Risk Evaluation
-
Disentangled Textual Priors for Diffusion-based Image Super-ResolutionNanjing University
-
OrthoFormer: Instrumental Variable Estimation in Transformer Hidden States via Neural Control FunctionsMetro State University
-
Generalization in Online Reinforcement Learning for Mobile AgentsConcordia University, McMaster University, Mila–Quebec AI Institute, Université de Montréal, University of Toronto
-
Data Agent: Learning to Select Data via End-to-End Dynamic OptimizationNanjing University, Nanyang Technological University, National University of Singapore
-
RPG-SAM: Reliability-Weighted Prototypes and Geometric Adaptive Threshold Selection for Training-Free One-Shot Polyp SegmentationEast China Normal University
-
Cost-Driven Representation Learning for Linear Quadratic Gaussian Control: Part IIMassachusetts Institute of Technology, Technical University of Munich, University of Maryland
-
Machine Learning for Stress Testing: Uncertainty Decomposition in Causal Panel PredictionCalifornia State University, Hong Kong University of Science and Technology
-
DogWeave: High-Fidelity 3D Canine Reconstruction from a Single Image via Normal Fusion and Conditional InpaintingUniversity of Wisconsin-Madison
-
Med-Evo: Test-time Self-evolution for Medical Multimodal Large Language ModelsThe Chinese University of Hong Kong
-
HLER: Human-in-the-Loop Economic Research via Multi-Agent Pipelines for Empirical DiscoveryChina Agricultural University
-
Few Tokens, Big Leverage: Preserving Safety Alignment by Constraining Safety Tokens during Fine-tuningCase Western Reserve University
-
Discrete Tokenization Unlocks Transformers for Calibrated Tabular Forecasting
-
Dial: A Knowledge-Grounded Dialect-Specific NL2SQL SystemHong Kong University of Science and Technology, Shanghai Jiao Tong University, Tsinghua University
-
Backdoor4Good: Benchmarking Beneficial Uses of Backdoors in LLMsFudan University, Singapore Management University, The University of Melbourne
-
SLNet: A Super-Lightweight Geometry-Adaptive Network for 3D Point Cloud RecognitionClemson University, Sirjan University of Technology
-
Image Generation Models: A Technical History
-
"Better Ask for Forgiveness than Permission": Practices and Policies of AI Disclosure in Freelance WorkEmory University, University of Southern California
-
Where Do LLM-based Systems Break? A System-Level Security Framework for Risk Assessment and TreatmentNorthern Arizona University, Tallinn University of Technology
-
The Dual-Stream Transformer: Channelized Architecture for Interpretable Language ModelingGeorgia Tech Research Institute
-
Do Machines Fail Like Humans? A Human-Centred Out-of-Distribution Spectrum for Mapping Error AlignmentFudan University, The University of Osaka, University College London
-
SIGMAE: A Spectral-Index-Guided Foundation Model for Multispectral Remote SensingHelmholtz-Zentrum Dresden-Rossendorf, Wuhan University, Wuhan University of Science and Technology
-
Selective Transfer Learning of Cross-Modality Distillation for Monocular 3D Object DetectionXi'an Jiaotong University
-
Classifying Novel 3D-Printed Objects without Retraining: Towards Post-Production Automation in Additive ManufacturingKU Leuven
-
Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AIVirginia Tech, Washington University
-
Probabilistic Inference and Learning with Stein's MethodUniversity of Texas
-
FedEU: Evidential Uncertainty-Driven Federated Fine-Tuning of Vision Foundation Models for Remote Sensing Image SegmentationWuhan University, Wuhan University of Science and Technology
-
Towards Lightweight Adaptation of Speech Enhancement Models in Real-World EnvironmentsETH Zurich
-
Contact-Guided 3D Genome Structure Generation of E. coli via Diffusion TransformersThe University of Tokyo, University of Michigan, Waseda University
-
Give Them an Inch and They Will Take a Mile:Understanding and Measuring Caller Identity Confusion in MCP-Based AI SystemsCity University of Hong Kong, Shandong University
-
Cross-Modal Taxonomic Generalization in (Vision-) Language ModelsUniversity of Texas
-
Skip to the Good Part: Representation Structure & Inference-Time Layer Skipping in Diffusion vs. Autoregressive LLMs
-
EVLF: Early Vision-Language Fusion for Generative Dataset DistillationHokkaido University, University of Fukui, University of Toyama
-
Interpretable-by-Design Transformers via Architectural Stream IndependenceGeorgia Tech Research Institute
-
Multi-Modal Decouple and Recouple Network for Robust 3D Object DetectionHong Kong University of Science and Technology, Multimodal Experiences Research Lab, Dolby Laboratories
