Wispr Flow - Don’t type, just speak
Mini toolsPapers
Filter by company
-
Cheap Thrills: Effective Amortized Optimization Using Inexpensive LabelsMassachusetts Institute of Technology, Technical University of Denmark
-
POET-X: Memory-efficient LLM Training by Scaling Orthogonal TransformationHuawei / Max Planck Institute for Intelligent Systems, The Chinese University of Hong Kong, University of Cambridge
-
Accelerating Text-to-Video Generation with Calibrated Sparse Attention
-
RoboPocket: Improve Robot Policies Instantly with Your Phone
-
FaceCam: Portrait Video Camera Control via Scale-Aware Conditioning
-
Transformer-Based Inpainting for Real-Time 3D Streaming in Sparse Multi-Camera SetupsUniversity of Bonn
-
Thinking with Spatial Code for Physical-World Video ReasoningJohns Hopkins University, Stanford University
-
On the Value of Tokeniser Pretraining in Physics Foundation ModelsFlatiron Institute, New York University, Princeton University, University of Cambridge
-
From Decoupled to Coupled: Robustness Verification for Learning-based Keypoint Detection with Joint SpecificationsCarnegie Mellon University
-
DreamCAD: Scaling Multi-modal CAD Generation using Differentiable Parametric SurfacesHuawei / German Research Center for Artificial Intelligence, Imperial College London, Rheinland-Pfälzische Technische Universität Kaiserslautern-Landau
-
Behavior-dLDS: A decomposed linear dynamical systems model for neural activity partially constrained by behaviorHoward Hughes Medical Institute, Johns Hopkins University, University of North Carolina
-
Real-Time AI Service Economy: A Framework for Agentic Computing Across the ContinuumThe Institute of Electrical and Electronics Engineers
-
NOTAI.AI: Explainable Detection of Machine-Generated Text via Curvature and Feature AttributionUniversity of Luxembourg
-
Safer Reasoning Traces: Measuring and Mitigating Chain-of-Thought Leakage in LLMsTechnical University of Munich
-
RACAS: Controlling Diverse Robots With a Single Agentic SystemAGH University of Kraków, Istituto Dalle Molle di studi sull'intelligenza artificiale, King Abdullah University of Science and Technology (KAUST), Scuola universitaria professionale della Svizzera italiana, Universita della Svizzera italiana
-
Adversarial Batch Representation Augmentation for Batch Correction in High-Content Cellular Screening
-
Post Fusion Bird's Eye View Feature Stabilization for Robust Multimodal 3D DetectionUniversity of South Florida
-
Identifying Adversary Characteristics from an Observed AttackAmherst College, Vanderbilt University
-
Rethinking Concept Bottleneck Models: From Pitfalls to SolutionsHelmholtz Munich, Max Planck Institute for Informatics, Middle East Technical University, Munich Center for Machine Learning, Munich Data Science Institute, RTG Neuroexplicit Models, Technical University of Munich
-
Making Reconstruction FID Predictive of Diffusion Generation FIDKuaishou Technology, Tsinghua University, University of Cambridge
-
Relational Semantic Reasoning on 3D Scene Graphs for Open World Interactive Object Search
-
Mining Beyond the Bools: Learning Data Transformations and Temporal SpecificationsColumbia University, Yale University
-
The Fragility Of Moral Judgment In Large Language ModelsUniversity of California
-
The DSA's Blind Spot: Algorithmic Audit of Advertising and Minor Profiling on TikTokComenius University Bratislava, Kempelen Institute of Intelligent Technologies
-
When Rubrics Fail: Error Enumeration as Reward in Reference-Free RL Post-Training for Virtual Try-On
-
Uncertainty-Aware Solar Flare RegressionGeorgia State University, Texas Christian University
-
Keeping the Evidence Chain: Semantic Evidence Allocation for Training-Free Token Pruning in Video Temporal GroundingUniversity of Amsterdam, University of Warwick
-
Scaling Agentic Capabilities, Not Context: Efficient Reinforcement Finetuning for Large Toolspaces
-
The Value of Graph-based Encoding in NBA Salary PredictionBrigham Young University
-
Reinforcement Learning for Power-Flow Network AnalysisGeorgia Tech, University of Texas
-
Gabor Primitives for Accelerated Cardiac Cine MRI ReconstructionHarvard Medical School, Imperial College London, Institute of Machine Learning in Biomedical Imaging, King’s College London, Technical University of Munich
-
OWL: A Novel Approach to Machine Perception During MotionFlorida Atlantic University
-
SecureRAG-RTL: A Retrieval-Augmented, Multi-Agent, Zero-Shot LLM-Driven Framework for Hardware Vulnerability Detection
-
FreeTxt-Vi: A Benchmarked Vietnamese-English Toolkit for Segmentation, Sentiment, and SummarisationCardiff University, Lancaster University, VinUniversity
-
Improved Scaling Laws via Weak-to-Strong Generalization in Random Feature Ridge RegressionInstitute of Science and Technology Austria, Yale University
-
Parallelization Strategies for Dense LLM Deployment: Navigating Through Application-Specific Tradeoffs and Bottlenecks
-
Longitudinal Lesion Inpainting in Brain MRI via 3D Region Aware Diffusion
-
Warm Starting State-Space Models with Automata LearningColumbia University, Yale University
-
Autonomous Algorithm Discovery for Ptychography via Evolutionary LLM ReasoningArgonne National Laboratory, Rice University
-
MultiHaystack: Benchmarking Multimodal Retrieval and Reasoning over 40K Images, Videos, and DocumentsHeriot-Watt University, King Abdullah University of Science and Technology (KAUST), Lanzhou University, Monash University, Sofia University, University College Dublin
-
Towards Robust Retrieval-Augmented Generation Based on Knowledge Graph: A Comparative AnalysisInstitut national de la recherche scientifique, Université du Québec en Outaouais
-
Tureis: Transformer-based Unified Resilience for IoT Devices in Smart Homes
-
Random Dot Product Graphs as Dynamical Systems: Limitations and Opportunities
-
Reasoning Models Struggle to Control their Chains of Thought
-
Interpretable Perception and Reasoning for Audiovisual GeolocationMichigan State University
-
The Rise of AI in Weather and Climate Information and its Impact on Global InequalityBarcelona Supercomputing Center, Catalan Institution for Research and Advanced Studies, Imperial College London
-
Any to Full: Prompting Depth Anything for Depth Completion in One StageHong Kong University of Science and Technology, JD Logistics, Michigan State University, Rutgers University
-
Unsupervised domain adaptation for radioisotope identification in gamma spectroscopyPacific Northwest National Laboratory, University of Washington
-
Cultural Perspectives and Expectations for Generative AI: A Global Survey Approach
-
Interpretable Motion Artificat Detection in structural Brain MRIHarvard Medical School, Indian Institute of Technology
