Wispr Flow - Don’t type, just speak
Mini toolsPapers
Filter by company
-
LLM as a Meta-Judge: Synthetic Data for NLP Evaluation Metric Validation
-
Stochastic Port-Hamiltonian Neural Networks: Universal Approximation with Passivity Guarantees
-
YOLO-NAS-Bench: A Surrogate Benchmark with Self-Evolving Predictors for YOLO Architecture Search
-
RiO-DETR: DETR for Real-time Oriented Object Detection
-
Reconstructing Movement from Sparse Samples: Enhanced Spatio-Temporal Matching Strategies for Low-Frequency Data
-
Large Spikes in Stochastic Gradient Descent: A Large-Deviations View
-
PromptDLA: A Domain-aware Prompt Document Layout Analysis Framework with Descriptive Knowledge as a Cue
-
From Flow to One Step: Real-Time Multi-Modal Trajectory Policies via Implicit Maximum Likelihood Estimation-based Distribution Distillation
-
Investigating Gender Stereotypes in Large Language Models via Social Determinants of Health
-
CIGPose: Causal Intervention Graph Neural Network for Whole-Body Pose Estimation
-
MetaDAT: Generalizable Trajectory Prediction via Meta Pre-training and Data-Adaptive Test-Time Updating
-
Open-World Motion Forecasting
-
CERES: A Probabilistic Early Warning System for Acute Food Insecurity
-
Amnesia: Adversarial Semantic Layer Specific Activation Steering in Large Language Models
-
Impact of Markov Decision Process Design on Sim-to-Real Reinforcement Learning
-
Common Sense vs. Morality: The Curious Case of Narrative Focus Bias in LLMs
-
AI Act Evaluation Benchmark: An Open, Transparent, and Reproducible Evaluation Dataset for NLP and RAG Systems
-
From Weighting to Modeling: A Nonparametric Estimator for Off-Policy Evaluation
-
GIIM: Graph-based Learning of Inter- and Intra-view Dependencies for Multi-view Medical Image Diagnosis
-
A Guideline-Aware AI Agent for Zero-Shot Target Volume Auto-Delineation
-
CyberThreat-Eval: Can Large Language Models Automate Real-World Threat Research?
-
Variational Routing: A Scalable Bayesian Framework for Calibrated Mixture-of-Experts Transformers
-
Declarative Scenario-based Testing with RoadLogic
-
An Empirical Study and Theoretical Explanation on Task-Level Model-Merging Collapse
-
EvoDriveVLA: Evolving Autonomous Driving Vision-Language-Action Model via Collaborative Perception-Planning Distillation
-
TopoOR: A Unified Topological Scene Representation for the Operating Room
-
The Patrologia Graeca Corpus: OCR, Annotation, and Open Release of Noisy Nineteenth-Century Polytonic Greek Editions
-
OmniEarth: A Benchmark for Evaluating Vision-Language Models in Geospatial Tasks
-
Telogenesis: Goal Is All U Need
-
Prune Redundancy, Preserve Essence: Vision Token Compression in VLMs via Synergistic Importance-Diversity
-
GenePlan: Evolving Better Generalized PDDL Plans using Large Language Models
-
Component-Aware Sketch-to-Image Generation Using Self-Attention Encoding and Coordinate-Preserving Fusion
-
Vibe-Creation: The Epistemology of Human-AI Emergent Cognition
-
Temporal-Conditioned Normalizing Flows for Multivariate Time Series Anomaly Detection
-
Evolving Prompt Adaptation for Vision-Language Models
-
SurgFed: Language-guided Multi-Task Federated Learning for Surgical Video Understanding
-
Modelling the Diachronic Emergence of Phoneme Frequency Distributions
-
Context-Nav: Context-Driven Exploration and Viewpoint-Aware 3D Spatial Reasoning for Instance Navigation
-
TrainDeeploy: Hardware-Accelerated Parameter-Efficient Fine-Tuning of Small Transformer Models at the Extreme Edge
-
Probing the Reliability of Driving VLMs: From Inconsistent Responses to Grounded Temporal Reasoning
-
Mitigating Frequency Learning Bias in Quantum Models via Multi-Stage Residual Learning
-
You Didn't Have to Say It like That: Subliminal Learning from Faithful Paraphrases
-
Efficiently Aligning Draft Models via Parameter- and Data-Efficient Adaptation
-
RESBev: Making BEV Perception More Robust
-
DCAU-Net: Differential Cross Attention and Channel-Spatial Feature Fusion for Medical Image Segmentation
-
Association of Radiologic PPFE Change with Mortality in Lung Cancer Screening Cohorts
-
What Do We Care About in Bandits with Noncompliance? BRACE: Bandits with Recommendations, Abstention, and Certified Effects
-
Enhancing Debunking Effectiveness through LLM-based Personality Adaptation
-
Towards Unified Multimodal Interleaved Generation via Group Relative Policy Optimization
-
Memory-Guided View Refinement for Dynamic Human-in-the-loop EQA
