Wispr Flow - Don’t type, just speak
Mini toolsPapers
Filter by company
-
SAVeS: Steering Safety Judgments in Vision-Language Models via Semantic Cues
-
DaPT: A Dual-Path Framework for Multilingual Multi-hop Question Answering
-
TAU-R1: Visual Language Model for Traffic Anomaly Understanding
-
LuMamba: Latent Unified Mamba for Electrode Topology-Invariant and Efficient EEG Modeling
-
FedTrident: Resilient Road Condition Classification Against Poisoning Attacks in Federated Learning
-
How Uncertainty Estimation Scales with Sampling in Reasoning Models
-
CustomTex: High-fidelity Indoor Scene Texturing via Multi-Reference Customization
-
Revisiting Autoregressive Models for Generative Image Classification
-
Exploring the Agentic Frontier of Verilog Code Generation
-
On Optimizing Multimodal Jailbreaks for Spoken Language Models
-
From Inference Efficiency to Embodied Efficiency: Revisiting Efficiency Metrics for Vision-Language-Action Models
-
Adaptive Regime-Aware Stock Price Prediction Using Autoencoder-Gated Dual Node Transformers with Reinforcement Learning Control
-
GSMem: 3D Gaussian Splatting as Persistent Spatial Memory for Zero-Shot Embodied Exploration and Reasoning
-
Implicit Patterns in LLM-Based Binary Analysis
-
Hierarchical Latent Structure Learning through Online Inference
-
SHAPCA: Consistent and Interpretable Explanations for Machine Learning Models on Spectroscopy Data
-
Anatomical Heterogeneity in Transformer Language Models
-
UGID: Unified Graph Isomorphism for Debiasing Large Language Models
-
A Mathematical Theory of Understanding
-
Enhancing Pretrained Model-based Continual Representation Learning via Guided Random Projection
-
D5P4: Partition Determinantal Point Process for Diversity in Parallel Discrete Diffusion Decoding
-
Fast and Effective Computation of Generalized Symmetric Matrix Factorization
-
Optimal Splitting of Language Models from Mixtures to Specialized Domains
-
VEPO: Variable Entropy Policy Optimization for Low-Resource Language Foundation Models
-
ADAPT: Attention Driven Adaptive Prompt Scheduling and InTerpolating Orthogonal Complements for Rare Concepts Generation
-
Adaptive Auxiliary Prompt Blending for Target-Faithful Diffusion Generation
-
GraphiContact: Pose-aware Human-Scene Robust Contact Perception for Interactive Systems
-
cuGenOpt: A GPU-Accelerated General-Purpose Metaheuristic Framework for Combinatorial Optimization
-
Rigorous Error Certification for Neural PDE Solvers: From Empirical Residuals to Solution Guarantees
-
Meanings and Measurements: Multi-Agent Probabilistic Grounding for Vision-Language Navigation
-
Evaluating Counterfactual Strategic Reasoning in Large Language Models
-
ARIADNE: A Perception-Reasoning Synergy Framework for Trustworthy Coronary Angiography Analysis
-
DyMoE: Dynamic Expert Orchestration with Mixed-Precision Quantization for Efficient MoE Inference on Edge
-
SOL-ExecBench: Speed-of-Light Benchmarking for Real-World GPU Kernels Against Hardware Limits
-
Few-shot Acoustic Synthesis with Multimodal Flow Matching
-
Box Maze: A Process-Control Architecture for Reliable LLM Reasoning
-
MIDST Challenge at SaTML 2025: Membership Inference over Diffusion-models-based Synthetic Tabular data
-
Improving RCT-Based Treatment Effect Estimation Under Covariate Mismatch via Calibrated Alignment
-
OS-Themis: A Scalable Critic Framework for Generalist GUI Rewards
-
Reconstruction Matters: Learning Geometry-Aligned BEV Representation through 3D Gaussian Splatting
-
How Auditory Knowledge in LLM Backbones Shapes Audio Language Models: A Holistic Evaluation
-
A Novel Solution for Zero-Day Attack Detection in IDS using Self-Attention and Jensen-Shannon Divergence in WGAN-GP
-
The Exponentially Weighted Signature
-
FASTER: Rethinking Real-Time Flow VLAs
-
kRAIG: A Natural Language-Driven Agent for Automated DataOps Pipeline Generation
-
Tinted Frames: Question Framing Blinds Vision-Language Models
-
Robustness, Cost, and Attack-Surface Concentration in Phishing Detection
-
RPiAE: A Representation-Pivoted Autoencoder Enhancing Both Image Generation and Editing
-
Do VLMs Need Vision Transformers? Evaluating State Space Models as Vision Encoders
-
$R$-equivalence on Cubic Surfaces I: Existing Cases with Non-Trivial Universal Equivalence
