Wispr Flow - Don’t type, just speak
Mini toolsPapers
Filter by company
-
Nonparametric Variational Differential Privacy via Embedding Parameter Clipping
-
Memorization capacity of deep ReLU neural networks characterized by width and depth
-
Build, Borrow, or Just Fine-Tune? A Political Scientist's Guide to Choosing NLP Models
-
Symbolic Discovery of Stochastic Differential Equations with Genetic Programming
-
Detecting Miscitation on the Scholarly Web through LLM-Augmented Text-Rich Graph Learning
-
A Variational Latent Equilibrium for Learning in Neuronal CircuitsUniversity of Bern
-
MM-algorithms for traditional and convex NMF with Tweedie and Negative Binomial cost functions and empirical evaluationAarhus University
-
Digging Deeper: Learning Multi-Level Concept HierarchiesUniversity of Cambridge, University of Oxford
-
Learning the Hierarchical Organization in Brain Network for Brain Disorder DiagnosisAiShiWeiLai AI Research, Northeastern University, China, Shandong Normal University, University of Alberta
-
ParTY: Part-Guidance for Expressive Text-to-Motion SynthesisKyung Hee University
-
A Saccade-inspired Approach to Image Classification using Vision Transformer Attention MapsAix-Marseille Université, Université Côte d’Azur
-
Surgical Repair of Collapsed Attention Heads in ALiBi Transformers
-
Context Engineering: From Prompts to Corporate Multi-Agent ArchitectureHSE University
-
Physics-Driven 3D Gaussian Rendering for Zero-Shot MRI Super-ResolutionAgency for Science, Technology and Research, Singapore, Sichuan University
-
Decoder-Free Distillation for Quantized Image Restoration
-
Grounding Synthetic Data Generation With Vision and Language ModelsMiddle East Technical University
-
X-GS: An Extensible Open Framework for Perceiving and Thinking via 3D Gaussian SplattingFudan University, Shanghai Academy of Artificial Intelligence for Science
-
Tracking Cancer Through Text: Longitudinal Extraction From Radiology Reports Using Open-Source Large Language ModelsRadboud University Medical Center
-
PRECEPT: Planning Resilience via Experience, Context Engineering & Probing Trajectories A Unified Framework for Test-Time Adaptation with Compositional Rule Learning and Pareto-Guided Prompt Evolution
-
Multi-DNN Inference of Sparse Models on Edge SoCsUniversity of St Andrews
-
MM-tau-p$^2$: Persona-Adaptive Prompting for Robust Multi-Modal Agent Evaluation in Dual-Control Settings
-
Evolution of Photonic Quantum Machine Learning under NoiseUniversity of Moratuwa
-
Well Log-Guided Synthesis of Subsurface Images from Sparse Petrography Data Using cGANsUniversity of Leeds
-
MiniAppBench: Evaluating the Shift from Text to Interactive HTML Responses in LLM-Powered Assistants
-
OTPL-VIO: Robust Visual-Inertial Odometry with Optimal Transport Line Association and Adaptive UncertaintyThe Institute of Electrical and Electronics Engineers
-
Understanding the Interplay between LLMs' Utilisation of Parametric and Contextual Knowledge: A keynote at ECIR 2025University of Copenhagen
-
When to Lock Attention: Training-Free KV Control in Video DiffusionJimei University, Peking University, Shanghai Jiao Tong University, Tongji University, Tsinghua University
-
FreqCycle: A Multi-Scale Time-Frequency Analysis Method for Time Series ForecastingShanghai Jiao Tong University
-
No evaluation without fair representation : Impact of label and selection bias on the evaluation, performance and mitigation of classification modelsUniversité catholique de Louvain, Universiteit Antwerpen
-
DiffWind: Physics-Informed Differentiable Modeling of Wind-Driven Object DynamicsAntGroup / Shenzhen University, State Key Laboratory of General Artificial Intelligence, Zhejiang University
-
VarSplat: Uncertainty-aware 3D Gaussian Splatting for Robust RGB-D SLAMGeorge Mason University
-
KernelSkill: A Multi-Agent Framework for GPU Kernel OptimizationBeihang University, Nanyang Technological University, Zhejiang Lab
-
GNNs for Time Series Anomaly Detection: An Open-Source Framework and a Critical EvaluationUniversidad de la República Montevideo
-
Logics-Parsing-Omni Technical Report
-
EsoLang-Bench: Evaluating Genuine Reasoning in Large Language Models via Esoteric Programming LanguagesLossfunk
-
Improving 3D Foot Motion Reconstruction in Markerless Monocular Human Motion CaptureLeibniz Universität Hannover
-
On Catastrophic Forgetting in Low-Rank Decomposition-Based Parameter-Efficient Fine-TuningUniversity of British Columbia
-
Automatic Cardiac Risk Management Classification using large-context Electronic Patients Health RecordsUniversità Campus Bio-Medico di Roma, University Medical Center Utrecht
-
Fusing Semantic, Lexical, and Domain Perspectives for Recipe Similarity EstimationJožef Stefan Institute, Ss. Cyril and Methodius University in Skopje, University of Ljubljana
-
AutoViVQA: A Large-Scale Automatically Constructed Dataset for Vietnamese Visual Question AnsweringVietnam National University Hanoi
-
ESAinsTOD: A Unified End-to-End Schema-Aware Instruction-Tuning Framework for Task-Oriented Dialog ModelingCentral South University, Research Center for Social Computing and Information
-
ActiveUltraFeedback: Efficient Preference Data Generation using Active LearningETH Zurich
-
Physics-informed neural operator for predictive parametric phase-field modellingTongji University
-
DRIFT: Dual-Representation Inter-Fusion Transformer for Automated Driving Perception with 4D Radar Point Clouds
-
TemporalDoRA: Temporal PEFT for Robust Surgical Video Question AnsweringIstituto di Ricovero e Cura a Carattere Scientifico, Politecnico di Milano, The University of Manchester, University College London
-
Mousse: Rectifying the Geometry of Muon with Curvature-Aware PreconditioningFudan University, Shanghai AI Lab, Shanghai Jiao Tong University
-
TriFusion-SR: Joint Tri-Modal Medical Image Fusion and SRMehran University of Engineering and Technology, Sejong University, University of Würzburg
-
ProGS: Towards Progressive Coding for 3D Gaussian SplattingThe Institute of Electrical and Electronics Engineers
-
Evaluation of LLMs in retrieving food and nutritional context for RAG systemsJožef Stefan Institute
-
OOD-MMSafe: Advancing MLLM Safety from Harmful Intent to Hidden Consequences
