Wispr Flow - Don’t type, just speak
Mini toolsPapers
Filter by company
-
Machine Translation in the Wild: User Reaction to Xiaohongshu's Built-In Translation Feature
-
Learning to Recall with Transformers Beyond Orthogonal Embeddings
-
Generative Inverse Design with Abstention via Diagonal Flow Matching
-
Evaluating Causal Discovery Algorithms for Path-Specific Fairness and Utility in Healthcare
-
Discovery of interaction and diffusion kernels in particle-to-mean-field multi-agent systems
-
Semi-Autonomous Formalization of the Vlasov-Maxwell-Landau Equilibrium
-
Nodule-Aligned Latent Space Learning with LLM-Driven Multimodal Diffusion for Lung Nodule Progression Prediction
-
Embodied Foundation Models at the Edge: A Survey of Deployment Constraints and Mitigation Strategies
-
CTG-DB: An Ontology-Based Transformation of ClinicalTrials.gov to Enable Cross-Trial Drug Safety Analyses
-
Data-Local Autonomous LLM-Guided Neural Architecture Search for Multiclass Multimodal Time-Series Classification
-
Do Not Leave a Gap: Hallucination-Free Object Concealment in Vision-Language Models
-
Towards Fair and Robust Volumetric CT Classification via KL-Regularised Group Distributionally Robust Optimisation
-
Analytically tractable model of synaptic crowding explains emergent small-world structure and network dynamics
-
Argumentative Human-AI Decision-Making: Toward AI Agents That Reason With Us, Not For Us
-
BANGLASOCIALBENCH: A Benchmark for Evaluating Sociopragmatic and Cultural Alignment of LLMs in Bangladeshi Social Interaction
-
POLAR:A Per-User Association Test in Embedding Space
-
Protein Design with Agent Rosetta: A Case Study for Specialized Scientific Agents
-
A Family of LLMs Liberated from Static Vocabularies
-
MobileLLM-Flash: Latency-Guided On-Device LLM Design for Industry Scale Deployment
-
ExpertGen: Scalable Sim-to-Real Expert Policy Learning from Imperfect Behavior Priors
-
GASP: Guided Asymmetric Self-Play For Coding LLMs
-
Deriving Hyperparameter Scaling Laws via Modern Optimization Theory
-
Optimizing Hospital Capacity During Pandemics: A Dual-Component Framework for Strategic Patient Relocation
-
MoLoRA: Composable Specialization via Per-Token Adapter Routing
-
A Comprehensive Benchmark of Histopathology Foundation Models for Kidney Digital Pathology Images
-
MAC: Multi-Agent Constitution Learning
-
Robust Language Identification for Romansh Varieties
-
100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight Proxy Models
-
Safety is Non-Compositional: A Formal Framework for Capability-Based AI Systems
-
UMO: Unified In-Context Learning Unlocks Motion Foundation Model Priors
-
An Agentic Evaluation Framework for AI-Generated Scientific Code in PETSc
-
From Workflow Automation to Capability Closure: A Formal Framework for Safe and Revenue-Aware Customer Service AI
-
Standardizing Medical Images at Scale for AI
-
Aligning Paralinguistic Understanding and Generation in Speech LLMs via Multi-Task Reinforcement Learning
-
Determinism in the Undetermined: Deterministic Output in Charge-Conserving Continuous-Time Neuromorphic Systems with Temporal Stochasticity
-
Something from Nothing: Data Augmentation for Robust Severity Level Estimation of Dysarthric Speech
-
W2T: LoRA Weights Already Know What They Can Do
-
The Midas Touch in Gaze vs. Hand Pointing: Modality-Specific Failure Modes and Implications for XR Interfaces
-
Selective Memory for Artificial Intelligence: Write-Time Gating with Hierarchical Archiving
-
Visual Set Program Synthesizer
-
NLP Occupational Emergence Analysis: How Occupations Form and Evolve in Real Time -- A Zero-Assumption Method Demonstrated on AI in the US Technology Workforce, 2022-2026
-
Mostly Text, Smart Visuals: Asymmetric Text-Visual Pruning for Large Vision-Language Models
-
RadAnnotate: Large Language Models for Efficient and Reliable Radiology Report Annotation
-
Evaluating Agentic Optimization on Large Codebases
-
The Importance of Being Smoothly Calibrated
-
FlatLands: Generative Floormap Completion From a Single Egocentric View
-
Understanding Moral Reasoning Trajectories in Large Language Models: Toward Probing-Based Explainability
-
IRAM-Omega-Q: A Computational Architecture for Uncertainty Regulation in Artificial Agents
-
\texttt{BayesBreak}: Generalized Hierarchical Bayesian Segmentation with Irregular Designs, Multi-Sample Hierarchies, and Grouped/Latent-Group Designs
-
E2EGS: Event-to-Edge Gaussian Splatting for Pose-Free 3D Reconstruction
