Wispr Flow - Don’t type, just speak
Mini toolsPapers
Filter by company
-
Completeness of Unbounded Best-First Minimax and Descent Minimax
-
Towards Training-Free Scene Text Editing
-
VFIG: Vectorizing Complex Figures in SVG with Vision-Language Models
-
Chameleon: Episodic Memory for Long-Horizon Robotic Manipulation
-
EndoVGGT: GNN-Enhanced Depth Estimation for Surgical 3D Reconstruction
-
Vision-Language Models vs Human: Perceptual Image Quality Assessment
-
MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination
-
Retrieval Improvements Do Not Guarantee Better Answers: A Study of RAG for AI Policy QA
-
When Consistency Becomes Bias: Interviewer Effects in Semi-Structured Clinical Interviews
-
Demystifying When Pruning Works via Representation Hierarchies
-
Latent-WAM: Latent World Action Modeling for End-to-End Autonomous Driving
-
The Stochastic Gap: A Markovian Framework for Pre-Deployment Reliability and Oversight-Cost Auditing in Agentic Artificial Intelligence
-
TAG: Target-Agnostic Guidance for Stable Object-Centric Inference in Vision-Language-Action Models
-
Comparing Developer and LLM Biases in Code Evaluation
-
DreamerAD: Efficient Reinforcement Learning via Latent World Model for Autonomous Driving
-
Polynomial Speedup in Diffusion Models with the Multilevel Euler-Maruyama Method
-
From Weights to Concepts: Data-Free Interpretability of CLIP via Singular Vector Decomposition
-
Spectral methods: crucial for machine learning, natural for quantum computers?
-
When Is Collective Intelligence a Lottery? Multi-Agent Scaling Laws for Memetic Drift in LLMs
-
ReDiPrune: Relevance-Diversity Pre-Projection Token Pruning for Efficient Multimodal LLMs
-
KitchenTwin: Semantically and Geometrically Grounded 3D Kitchen Digital Twins
-
UniICL: Systematizing Unified Multimodal In-context Learning through a Capability-Oriented Taxonomy
-
BCMDA: Bidirectional Correlation Maps Domain Adaptation for Mixed Domain Semi-Supervised Medical Image Segmentation
-
Reconstructing Spiking Neural Networks Using a Single Neuron with Autapses
-
Amplified Patch-Level Differential Privacy for Free via Random Cropping
-
LLaVA-LE: Large Language-and-Vision Assistant for Lunar Exploration
-
Conformal Selective Prediction with General Risk Control
-
Amortized Inference for Correlated Discrete Choice Models via Equivariant Neural Networks
-
Training LLMs for Multi-Step Tool Orchestration with Constrained Data Synthesis and Graduated Rewards
-
Lookalike3D: Seeing Double in 3D
-
Can an Actor-Critic Optimization Framework Improve Analog Design Optimization?
-
Accurate Point Measurement in 3DGS -- A New Alternative to Traditional Stereoscopic-View Based Measurements
-
Scalable Object Relation Encoding for Better 3D Spatial Reasoning in Large Language Models
-
Is Geometry Enough? An Evaluation of Landmark-Based Gaze Estimation
-
Confidence-Based Mesh Extraction from 3D Gaussians
-
A Framework for Generating Semantically Ambiguous Images to Probe Human and Machine Perception
-
OpenCap Monocular: 3D Human Kinematics and Musculoskeletal Dynamics from a Single Smartphone Video
-
AutoSAM: an Agentic Framework for Automating Input File Generation for the SAM Code with Multi-Modal Retrieval-Augmented Generation
-
Decentralized Task Scheduling in Distributed Systems: A Deep Reinforcement Learning Approach
-
Trust as Monitoring: Evolutionary Dynamics of User Trust and AI Developer Behaviour
-
GaloisSAT: Differentiable Boolean Satisfiability Solving via Finite Field Algebra
-
Contrastive Learning Boosts Deterministic and Generative Models for Weather Data
-
Grokking as a Falsifiable Finite-Size Transition
-
A-SelecT: Automatic Timestep Selection for Diffusion Transformer Representation Learning
-
Formal Semantics for Agentic Tool Protocols: A Process Calculus Approach
-
TIGeR: A Unified Framework for Time, Images and Geo-location Retrieval
-
Pseudo Label NCF for Sparse OHC Recommendation: Dual Representation Learning and the Separability Accuracy Trade off
-
Autotuning T-PaiNN: Enabling Data-Efficient GNN Interatomic Potential Development via Classical-to-Quantum Transfer Learning
-
Light Cones For Vision: Simple Causal Priors For Visual Hierarchy
-
SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks
