Wispr Flow - Don’t type, just speak
Mini toolsPapers
Filter by company
-
ORMOT: A Dataset and Framework for Omnidirectional Referring Multi-Object TrackingHuazhong University of Science and Technology
-
Fusion-CAM: Integrating Gradient and Region-Based Class Activation Maps for Robust Visual ExplanationsL'Unité Expérimentale d'AgroEcologie et de Phénotypage des Cultures, Université de Toulouse Jean Jaurès, Université Toulouse Capitole
-
Legal interpretation and AI: from expert systems to argumentation and LLMs
-
On the Necessity of Learnable Sheaf Laplacians
-
Harnessing Synthetic Data from Generative AI for Statistical InferenceHarvard T.H. Chan School of Public Health, Harvard University
-
Loop Closure via Maximal Cliques in 3D LiDAR-Based SLAMUniversidad Politecnica de Madrid, University of Bonn
-
Judge Reliability Harness: Stress Testing the Reliability of LLM Judges
-
An Exploration-Analysis-Disambiguation Reasoning Framework for Word Sense Disambiguation with Low-Parameter LLMsSwansea University
-
Koopman Regularized Deep Speech Disentanglement for Speaker VerificationThe Institute of Electrical and Electronics Engineers
-
Video-based Locomotion Analysis for Fish Health MonitoringFraunhofer Institute for Telecommunications, Humboldt-Universität zu Berlin
-
Dissociating Direct Access from Inference in AI IntrospectionUniversity of Texas
-
The Spatial and Temporal Resolution of Motor Intention in Multi-Target PredictionRuhr West University of Applied Science
-
MobileFetalCLIP: Selective Repulsive Knowledge Distillation for Mobile Fetal Ultrasound AnalysisMohamed bin Zayed University of Artificial Intelligence
-
An interpretable prototype parts-based neural network for medical tabular dataPoznan University of Technology
-
Tool-Genesis: A Task-Driven Tool Creation Benchmark for Self-Evolving Language AgentThe University of Hong Kong, University of Electronic Science and Technology of China
-
RelaxFlow: Text-Driven Amodal 3D GenerationNational University of Singapore, Zhejiang University
-
A Novel Hybrid Heuristic-Reinforcement Learning Optimization Approach for a Class of Railcar Shunting ProblemsTexas A&M University
-
Ensembling Language Models with Sequential Monte CarloCanadian Institute for Advanced Research, ETH Zurich, McGill University, Mila–Quebec AI Institute
-
SAIL: Similarity-Aware Guidance and Inter-Caption Augmentation-based Learning for Weakly-Supervised Dense Video CaptioningHanyang University
-
Planning in 8 Tokens: A Compact Discrete Tokenizer for Latent World ModelRLWRLD / Korea Advanced Institute of Science & Technology, Pohang University of Science and Technology
-
Latent Wasserstein Adversarial Imitation LearningUniversity of Illinois Urbana-Champaign
-
NaiLIA: Multimodal Nail Design Retrieval Based on Dense Intent Descriptions and Palette QueriesKeio University
-
Residual RL--MPC for Robust Microrobotic Cell Pushing Under Time-Varying FlowUniversity of Delaware
-
RealWonder: Real-Time Physical Action-Conditioned Video GenerationStanford University, University of Southern California
-
Distributed Partial Information Puzzles: Examining Common Ground Construction Under Epistemic AsymmetryBrandeis University, Colorado State University
-
FlashAttention-4: Algorithm and Kernel Pipelining Co-Design for Asymmetric Hardware Scaling
-
Beyond Scattered Acceptance: Fast and Coherent Inference for DLMs via Longest Stable Prefixes
-
DEBISS: a Corpus of Individual, Semi-structured and Spoken DebatesFederal University of Campina Grande, Federal University of Paraíba
-
NCTB-QA: A Large-Scale Bangla Educational Question Answering Dataset and Benchmarking PerformanceUniversity of Dhaka
-
EdgeDAM: Real-time Object Tracking for Mobile DevicesNeubility / Kumoh National Institute of Technology, The University of Melbourne, The University of Western Australia
-
HALP: Detecting Hallucinations in Vision-Language Models without Generating a Single TokenStony Brook University, Toyota Technological Institute at Chicago
-
Kraus Constrained Sequence Learning For Quantum Trajectories from Continuous Measurement
-
Leveraging LLM Parametric Knowledge for Fact Checking without RetrievalAXXX, École Polytechnique Fédérale de Lausanne, Mohamed bin Zayed University of Artificial Intelligence, Stanford Natural Language Processing Group
-
Towards 3D Scene Understanding of Gas Plumes in LWIR Hyperspectral Images Using Neural Radiance FieldsLos Alamos National Laboratory, Utah State University
-
Spatiotemporal Heterogeneity of AI-Driven Traffic Flow Patterns and Land Use Interaction: A GeoAI-Based Analysis of Multimodal Urban MobilityTechnical University of Denmark
-
Thermodynamic Response Functions in Singular Bayesian Models
-
SurvHTE-Bench: A Benchmark for Heterogeneous Treatment Effect Estimation in Survival AnalysisCarnegie Mellon University, National Institutes of Health
-
Towards Multimodal Lifelong Understanding: A Dataset and Agentic BaselineNVIDIA / Nanjing University, Shanghai Jiao Tong University, The University of Tokyo, Zhejiang University
-
Towards Provably Unbiased LLM Judges via Bias-Bounded Evaluation
-
Bias In, Bias Out? Finding Unbiased Subnetworks in Vanilla ModelsFondazione Istituto Italiano di Tecnologia, Institut Polytechnique de Paris, University of Genoa
-
Reasoning Theater: Disentangling Model Beliefs from Chain-of-Thought
-
Censored LLMs as a Natural Testbed for Secret Knowledge ElicitationHarvard University, Warsaw University of Technology
-
Cheap Thrills: Effective Amortized Optimization Using Inexpensive LabelsMassachusetts Institute of Technology, Technical University of Denmark
-
POET-X: Memory-efficient LLM Training by Scaling Orthogonal TransformationHuawei / Max Planck Institute for Intelligent Systems, The Chinese University of Hong Kong, University of Cambridge
-
Accelerating Text-to-Video Generation with Calibrated Sparse Attention
-
RoboPocket: Improve Robot Policies Instantly with Your Phone
-
FaceCam: Portrait Video Camera Control via Scale-Aware Conditioning
-
Transformer-Based Inpainting for Real-Time 3D Streaming in Sparse Multi-Camera SetupsUniversity of Bonn
-
Thinking with Spatial Code for Physical-World Video ReasoningJohns Hopkins University, Stanford University
-
On the Value of Tokeniser Pretraining in Physics Foundation ModelsFlatiron Institute, New York University, Princeton University, University of Cambridge
