Wispr Flow - Don’t type, just speak
Mini toolsPapers
Filter by company
-
Recursive Inference Machines for Neural ReasoningGerman Research Center for Artificial Intelligence, Hessian.ai, Technical University of Darmstadt, University of Texas
-
Reclaiming Lost Text Layers for Source-Free Cross-Domain Few-Shot LearningHuazhong University of Science and Technology, Peking University
-
GCAgent: Enhancing Group Chat Communication through Dialogue Agents SystemUniversity of Science and Technology of China, Zhejiang University
-
ICHOR: A Robust Representation Learning Approach for ASL CBF Maps with Self-Supervised Masked AutoencodersUniversity of Maryland, University of Pennsylvania
-
CATNet: Collaborative Alignment and Transformation Network for Cooperative PerceptionTianjin University
-
Wiki-R1: Incentivizing Multimodal Reasoning for Knowledge-based VQA via Data and Sampling CurriculumLingang Laboratory, Shanghai Engineering Research Center of Intelligent Vision and Imaging, ShanghaiTech University
-
VietJobs: A Vietnamese Job Advertisement DatasetVinUniversity
-
A Behaviour-Aware Federated Forecasting Framework for Distributed Stand-Alone Wind TurbinesIT University of Copenhagen, Technical University of Denmark
-
Beyond Word Error Rate: Auditing the Diversity Tax in Speech Recognition through Dataset CartographyTechnical University of Denmark, University of Copenhagen
-
Visual-Informed Speech Enhancement Using Attention-Based BeamformingThe Institute of Electrical and Electronics Engineers
-
Oral to Web: Digitizing 'Zero Resource'Languages of BangladeshJahangirnagar University
-
SarcasmMiner: A Dual-Track Post-Training Framework for Robust Audio-Visual Sarcasm ReasoningUniversity of Groningen
-
Whispering to a Blackbox: Bootstrapping Frozen OCR with Visual Prompts
-
Layer by layer, module by module: Choose both for optimal OOD probing of ViTInstitut de recherche en informatique et systèmes aléatoires, National Institute for Research in Digital Science and Technology, Université Rennes 2
-
Bayesian Supervised Causal ClusteringUniversity of Edinburgh
-
X-RAY: Mapping LLM Reasoning Capability via Formalized and Calibrated ProbesNational University of Singapore
-
Knowledge Divergence and the Value of Debate for Scalable OversightUniversity of Cambridge
-
STRUCTUREDAGENT: Planning with AND/OR Trees for Long-Horizon Web Tasks
-
WebChain: A Large-Scale Human-Annotated Dataset of Real-World Web Interaction Traces
-
Latent Policy Steering through One-Step Flow Policies
-
WavSLM: Single-Stream Speech Language Modeling via WavLM DistillationConcordia University, Université Laval
-
UniSTOK: Uniform Inductive Spatio-Temporal KrigingCity University of Hong Kong, Renmin University of China
-
Fusion4CA: Boosting 3D Object Detection via Comprehensive Image ExploitationShanghai Jiao Tong University
-
Med-V1: Small Language Models for Zero-shot and Scalable Biomedical Evidence AttributionNational Institutes of Health, University of Virginia, Weill Cornell Medicine
-
Latent-Mark: An Audio Watermark Robust to Neural ResynthesisMoonShine Studio / CyCraft AI Lab, National Taiwan University, RIKEN Center for Computational Science
-
PersianPunc: A Large-Scale Dataset and BERT-Based Approach for Persian Punctuation RestorationInstitute for Research in Fundamental Sciences, University of Tehran
-
Frequency-Aware Error-Bounded Caching for Accelerating Diffusion Transformers
-
How important are the genes to explain the outcome - the asymmetric Shapley value as an honest importance metric for high-dimensional featuresAmsterdam University Medical Centers, Norwegian Computing Center
-
GALACTIC: Global and Local Agnostic Counterfactuals for Time-series ClusteringAthena Research Center, Université Paris Cité, University of Ioannina
-
Machine Learning for analysis of Multiple Sclerosis cross-tissue bulk and single-cell transcriptomics dataConsorzio Interuniversitario Nazionale per l’Informatica, University of Bologna, University of Pisa, University of Turin
-
FairFinGAN: Fairness-aware Synthetic Financial Data GenerationBanking Academy of Vietnam, Hanoi University of Science and Technology, The University of Sheffield, Universität Koblenz
-
Dark3R: Learning Structure from Motion in the DarkSony Group Corporation (AIBO) / Harvard University, Purdue University, University of Toronto, Vector Institute, York University
-
Bayes with No Shame: Admissibility Geometries of Predictive InferenceUniversity of Chicago, University of South Florida
-
Why Depth Matters in Parallelizable Sequence Models: A Lie Algebraic ViewHarvard Medical School, Harvard University
-
On the Statistical Optimality of Optimal Decision TreesNational University of Singapore
-
Preserving Continuous Symmetry in Discrete Spaces: Geometric-Aware Quantization for SO(3)-Equivariant GNNsNanjing University, Suzhou Lab
-
Building Effective AI Coding Agents for the Terminal: Scaffolding, Harness, Context Engineering, and Lessons Learned
-
A Multilingual Human Annotated Corpus of Original and Easy-to-Read Texts to Support Access to Democratic Participatory ProcessesPlena Inclusión Madrid, Universitat Pompeu Fabra, University of Leeds
-
Ailed: A Psyche-Driven Chess Engine with Dynamic Emotional Modulation
-
InfoFlow KV: Information-Flow-Aware KV Recomputation for Long ContextDuke University, Mohamed bin Zayed University of Artificial Intelligence, New York University
-
Exploring the potential and limitations of Model Merging for Multi-Domain Adaptation in ASRThe Instituto de Engenharia de Sistemas e Computadores - Investigação e Desenvolvimento, Universidade de Lisboa
-
DiSCTT: Consensus-Guided Self-Curriculum for Efficient Test-Time Adaptation in ReasoningConcordia University
-
PACE: A Personalized Adaptive Curriculum Engine for 9-1-1 Call-taker TrainingVanderbilt University
-
Progressive Residual Warmup for Language Model PretrainingNVIDIA / Hong Kong University of Science and Technology, The University of Hong Kong, University of Surrey
-
Learning Causal Structure of Time Series using Best Order Score SearchUniversity of Potsdam
-
Embedded Inter-Subject Variability in Adversarial Learning for Inertial Sensor-Based Human Activity RecognitionGerman Research Center for Artificial Intelligence, Kyushu University, Orebro University, Rheinland-Pfälzische Technische Universität Kaiserslautern-Landau
-
Robust Node Affinities via Jaccard-Biased Random Walks and Rank AggregationMedical University Graz
-
OpenFrontier: General Navigation with Visual-Language Grounded Frontiers
-
PRISM: Personalized Refinement of Imitation Skills for Manipulation via Human InstructionsEurecat Centre Tecnològic
-
Prediction-Powered Conditional InferenceUniversity of California
