Speechmatics - API for Voice AI Agents
Mini toolsPapers
Filter by company
-
GLASS: Geometry-aware Local Alignment and Structure Synchronization Network for 2D-3D Registration
-
DRUM: Diffusion-based Raydrop-aware Unpaired Mapping for Sim2Real LiDAR Segmentation
-
Topology-Aware Graph Reinforcement Learning for Energy Storage Systems Optimal Dispatch in Distribution Networks
-
GUIDE: Resolving Domain Bias in GUI Agents through Real-Time Web Video Retrieval and Plug-and-Play Annotation
-
Knowdit: Agentic Smart Contract Vulnerability Detection with Auditing Knowledge Summarization
-
PhysVid: Physics Aware Local Conditioning for Generative Video Models
-
findsylls: A Language-Agnostic Toolkit for Syllable-Level Speech Tokenization and Embedding
-
Preference-Aligned LoRA Merging: Preserving Subspace Coverage and Addressing Directional Anisotropy
-
D-GATNet: Interpretable Temporal Graph Attention Learning for ADHD Identification Using Dynamic Functional Connectivity
-
Semi-structured multi-state delinquency model for mortgage default
-
SALMUBench: A Benchmark for Sensitive Association-Level Multimodal Unlearning
-
Label-Free Cross-Task LoRA Merging with Null-Space Compression
-
STN-GPR: A Singularity Tensor Network Framework for Efficient Option Pricing
-
DFM-VLA: Iterative Action Refinement for Robot Manipulation via Discrete Flow Matching
-
From Human Cognition to Neural Activations: Probing the Computational Primitives of Spatial Reasoning in LLMs
-
PRISMA: Toward a Normative Information Infrastructure for Responsible Pharmaceutical Knowledge Management
-
Making Multi-Axis Models Robust to Multiplicative Noise: How, and Why?
-
Verify Claimed Text-to-Image Models via Boundary-Aware Prompt Optimization
-
Mitigating the Reasoning Tax in Vision-Language Fine-Tuning with Input-Adaptive Depth Aggregation
-
Stringological sequence prediction I: efficient algorithms for predicting highly repetitive sequences
-
CALRK-Bench: Evaluating Context-Aware Legal Reasoning in Korean Law
-
From Pixels to Privacy: Temporally Consistent Video Anonymization via Token Pruning for Privacy Preserving Action Recognition
-
Curvature-aware Expected Free Energy as an Acquisition Function for Bayesian Optimization
-
HINT: Composed Image Retrieval with Dual-path Compositional Contextualized Network
-
A Power-Weighted Noncentral Complex Gaussian Distribution
-
Reflect to Inform: Boosting Multimodal Reasoning via Information-Gain-Driven Verification
-
Generative Score Inference for Multimodal Data
-
DuSCN-FusionNet: An Interpretable Dual-Channel Structural Covariance Fusion Framework for ADHD Classification Using Structural MRI
-
Only Whats Necessary: Pareto Optimal Data Minimization for Privacy Preserving Video Anomaly Detection
-
From Pen to Pixel: Translating Hand-Drawn Plots into Graphical APIs via a Novel Benchmark and Efficient Adapter
-
MPDiT: Multi-Patch Global-to-Local Transformer Architecture For Efficient Flow Matching and Diffusion Model
-
Automated near-term quantum algorithm discovery for molecular ground states
-
HandVQA: Diagnosing and Improving Fine-Grained Spatial Reasoning about Hands in Vision-Language Models
-
A Formal Framework for Uncertainty Analysis of Text Generation with Large Language Models
-
Dynamic Token Compression for Efficient Video Understanding through Reinforcement Learning
-
Generative Modeling in Protein Design: Neural Representations, Conditional Generation, and Evaluation Standards
-
Switch Attention: Towards Dynamic and Fine-grained Hybrid Transformers
-
Restore, Assess, Repeat: A Unified Framework for Iterative Image Restoration
-
Maintaining Difficulty: A Margin Scheduler for Triplet Loss in Siamese Networks Training
-
Adapting Frozen Mono-modal Backbones for Multi-modal Registration via Contrast-Agnostic Instance Optimization
-
SHANDS: A Multi-View Dataset and Benchmark for Surgical Hand-Gesture and Error Recognition Toward Medical Training
-
Word Alignment-Based Evaluation of Uniform Meaning Representations
-
AFSS: Artifact-Focused Self-Synthesis for Mitigating Bias in Audio Deepfake Detection
-
Why Models Know But Don't Say: Chain-of-Thought Faithfulness Divergence Between Thinking Tokens and Answers in Open-Weight Reasoning Models
-
KMM-CP: Practical Conformal Prediction under Covariate Shift via Selective Kernel Mean Matching
-
Kantorovich--Kernel Neural Operators: Approximation Theory, Asymptotics, and Neural Network Interpretation
-
A Hierarchical Sheaf Spectral Embedding Framework for Single-Cell RNA-seq Analysis
-
CPUBone: Efficient Vision Backbone Design for Devices with Low Parallelization Capabilities
-
Analysing Calls to Order in German Parliamentary Debates
-
Reconstructing Quantum Dot Charge Stability Diagrams with Diffusion Models
