Wispr Flow - Don’t type, just speak
Mini toolsPapers
Filter by company
-
Structure-Dependent Regret and Constraint Violation Bounds for Online Convex Optimization with Time-Varying Constraints
-
Early Failure Detection and Intervention in Video Diffusion Models
-
Personalized Cell Segmentation: Benchmark and Framework for Reference-Guided Cell Type Segmentation
-
How Do Medical MLLMs Fail? A Study on Visual Grounding in Medical Images
-
Learning-to-Defer with Expert-Conditioned Advice
-
ECG-Reasoning-Benchmark: A Benchmark for Evaluating Clinical Reasoning Capabilities in ECG Interpretation
-
AvatarForcing: One-Step Streaming Talking Avatars via Local-Future Sliding-Window Denoising
-
Data-Driven Physics Embedded Dynamics with Predictive Control and Reinforcement Learning for Quadrupeds
-
UAVBench and UAVIT-1M: Benchmarking and Enhancing MLLMs for Low-Altitude UAV Vision-Language Understanding
-
On the Nature of Attention Sink that Shapes Decoding Strategy in MLLMs
-
State-Dependent Safety Failures in Multi-Turn Language Model Interaction
-
Generation of Human Comprehensible Access Control Policies from Audit Logs
-
AgroNVILA: Perception-Reasoning Decoupling for Multi-view Agricultural Multimodal Large Language Models
-
Localizing and Editing Knowledge in Large Audio-Language Models
-
Motivation in Large Language Models
-
Refold: Refining Protein Inverse Folding with Efficient Structural Matching and Fusion
-
Deconfounded Lifelong Learning for Autonomous Driving via Dynamic Knowledge Spaces
-
Exposing Long-Tail Safety Failures in Large Language Models through Efficient Diverse Response Sampling
-
M$^2$RNN: Non-Linear RNNs with Matrix-Valued States for Scalable Language Modeling
-
BROTHER: Behavioral Recognition Optimized Through Heterogeneous Ensemble Regularization for Ambivalence and Hesitancy
-
AerialVLA: A Vision-Language-Action Model for UAV Navigation via Minimalist End-to-End Control
-
Representation Alignment for Just Image Transformers is not Easier than You Think
-
HomeGuard: VLM-based Embodied Safeguard for Identifying Contextual Risk in Household Task
-
From Specification to Architecture: A Theory Compiler for Knowledge-Guided Machine Learning
-
OxyGen: Unified KV Cache Management for Vision-Language-Action Models under Multi-Task Parallelism
-
Contests with Spillovers: Incentivizing Content Creation with GenAI
-
The Pulse of Motion: Measuring Physical Frame Rate from Visual Dynamics
-
LoCAtion: Long-time Collaborative Attention Framework for High Dynamic Range Video Reconstruction
-
SPARQ: Spiking Early-Exit Neural Networks for Energy-Efficient Edge AI
-
StAR: Segment Anything Reasoner
-
Label Noise Cleaning for Supervised Classification via Bernoulli Random Sampling
-
From $\boldsymbol{\logπ}$ to $\boldsymbolπ$: Taming Divergence in Soft Clipping via Bilateral Decoupled Decay of Probability Gradient Weight
-
WestWorld: A Knowledge-Encoded Scalable Trajectory World Model for Diverse Robotic Systems
-
Extending Minimal Pairs with Ordinal Surprisal Curves and Entropy Across Applied Domains
-
OCRA: Object-Centric Learning with 3D and Tactile Priors for Human-to-Robot Action Transfer
-
ES-Merging: Biological MLLM Merging via Embedding Space Signals
-
Graph-Based Deep Learning for Intelligent Detection of Energy Losses, Theft, and Operational Inefficiencies in Oil & Gas Production Networks
-
Towards One-for-All Anomaly Detection for Tabular Data
-
PGcGAN: Pathological Gait-Conditioned GAN for Human Gait Synthesis
-
BiT-MCTS: A Theme-based Bidirectional MCTS Approach to Chinese Fiction Generation
-
G-ZAP: A Generalizable Zero-Shot Framework for Arbitrary-Scale Pansharpening
-
Histo-MExNet: A Unified Framework for Real-World, Cross-Magnification, and Trustworthy Breast Cancer Histopathology
-
Questionnaire Responses Do not Capture the Safety of AI Agents
-
Deep EM with Hierarchical Latent Label Modelling for Multi-Site Prostate Lesion Segmentation
-
Data Darwinism Part II: DataEvolve -- AI can Autonomously Evolve Pretraining Data Curation
-
MBD: A Model-Based Debiasing Framework Across User, Content, and Model Dimensions
-
GenState-AI: State-Aware Dataset for Text-to-Video Retrieval on AI-Generated Videos
-
Creative Convergence or Imitation? Genre-Specific Homogeneity in LLM-Generated Chinese Literature
-
End-to-End Spatial-Temporal Transformer for Real-time 4D HOI Reconstruction
-
DASH: Dynamic Audio-Driven Semantic Chunking for Efficient Omnimodal Token Compression
