Wispr Flow - Don’t type, just speak
Mini toolsPapers
Filter by company
-
FrameDiT: Diffusion Transformer with Frame-Level Matrix Attention for Efficient Video Generation
-
RbtAct: Rebuttal as Supervision for Actionable Review Feedback GenerationNew York University, TCS Research, Yale University
-
ES-dLLM: Efficient Inference for Diffusion Large Language Models by Early-SkippingPolar Bear Tech, Tsinghua University
-
A Multi-Prototype-Guided Federated Knowledge Distillation Approach in AI-RAN Enabled Multi-Access Edge Computing SystemKyung Hee University, Noakhali Science and Technology University, Sungkyunkwan University
-
EXPLORE-Bench: Egocentric Scene Prediction with Long-Horizon Reasoning
-
FetalAgents: A Multi-Agent System for Fetal Ultrasound Image and Video AnalysisSichuan University, Tsinghua University, University of California
-
$M^2$-Occ: Resilient 3D Semantic Occupancy Prediction for Autonomous Driving with Incomplete Camera InputsHunan University, Karlsruhe Institute of Technology, Sofia University
-
Let's Reward Step-by-Step: Step-Aware Contrastive Alignment for Vision-Language Navigation in Continuous EnvironmentsZhejiang University
-
ENIGMA-360: An Ego-Exo Dataset for Human Behavior Understanding in Industrial ScenariosUniversity of Catania
-
Upper Generalization Bounds for Neural OscillatorsCalifornia Institute of Technology, Leibniz Universität Hannover, The Hong Kong Polytechnic University, University of Liverpool
-
LAP: A Language-Aware Planning Model For Procedure Planning In Instructional VideosOrebro University
-
Beyond Fine-Tuning: Robust Food Entity Linking under Ontology Drift with FoodOntoRAGJožef Stefan Institute, Jožef Stefan International Postgraduate School
-
LogoDiffuser: Training-Free Multilingual Logo Generation and Stylization via Letter-Aware Attention ControlHanyang University
-
PanoAffordanceNet: Towards Holistic Affordance Grounding in 360° Indoor EnvironmentsHunan University
-
Ego: Embedding-Guided Personalization of Vision-Language Models
-
VCR: Variance-Driven Channel Recalibration for Robust Low-Light EnhancementEnergy Digital Intelligence Technology Development, University of Science and Technology of China
-
Removing the Trigger, Not the Backdoor: Alternative Triggers and Latent BackdoorsDelft University of Technology, Radboud University, University of Bergen, University of Zagreb
-
Global universality via discrete-time signatures
-
World2Mind: Cognition Toolkit for Allocentric Spatial Reasoning in Foundation Models
-
First Estimation of Model Parameters for Neutrino-Induced Nucleon Knockout Using Simulation-Based InferenceFermi National Accelerator Laboratory, University of Chicago
-
EPIC-EuroParl-UdS: Information-Theoretic Perspectives on Translation and InterpretingUniversity of Hildesheim
-
Quantifying the Necessity of Chain of Thought through Opaque Serial Depth
-
What is Missing? Explaining Neurons Activated by Absent ConceptsHessian.ai, Johannes Gutenberg University Mainz, Leibniz Institute for Resilience Research, Max Planck Institute for Informatics, Technical University of Darmstadt, University Medical Center Mainz
-
A Hybrid Quantum-Classical Framework for Financial Volatility Forecasting Based on Quantum Circuit Born Machines
-
Exploiting Label-Aware Channel Scoring for Adaptive Channel Pruning in Split LearningThe Institute of Electrical and Electronics Engineers
-
Information Theoretic Bayesian Optimization over the Probability SimplexKTH Royal Institute of Technology, Universita degli Studi di Milano
-
Test-time Ego-Exo-centric Adaptation for Action Anticipation via Multi-Label Prototype Growing and Dual-Clue ConsistencyUniversity of Electronic Science and Technology of China
-
MITRA: An AI Assistant for Knowledge Retrieval in Physics CollaborationsUniversity of Wisconsin-Madison
-
A Survey of Weight Space Learning: Understanding, Representation, and GenerationNVIDIA / Technion – Israel Institute of Technology, University of California, University of Notre Dame, University of St. Gallen, University of Surrey, University of Virginia
-
Good Reasoning Makes Good Demonstrations: Implicit Reasoning Quality Supervision via In-Context Reinforcement LearningFudan University, Tianjin University, University of Chinese Academy of Sciences
-
RA-SSU: Towards Fine-Grained Audio-Visual Learning with Region-Aware Sound Source UnderstandingThe Institute of Electrical and Electronics Engineers
-
Multi-Stream Perturbation Attack: Breaking Safety Alignment of Thinking LLMs Through Concurrent Task InterferenceJinan University
-
Correction of Transformer-Based Models with Smoothing Pseudo-Projector
-
ConfCtrl: Enabling Precise Camera Control in Video Diffusion via Confidence-Aware InterpolationHuawei / Ludwig Maximilian University of Munich, Technical University of Munich, University of Freiburg
-
One-Eval: An Agentic System for Automated and Traceable LLM EvaluationBeijing Institute of Technology, Beijing University of Posts and Telecommunications, Peking University, Zhongguancun Academy
-
BrainSTR: Spatio-Temporal Contrastive Learning for Interpretable Dynamic Brain Network ModelingAiShiWeiLai AI Research, Nanjing Medical University, Northeastern University, Shandong Normal University, University of Alberta, Waseda University
-
VLM-Loc: Localization in Point Cloud Maps via Vision-Language ModelsChinese Academy of Sciences Institute of Automation, Munich Center for Machine Learning, Nankai University, National University of Defense Technology, Technical University of Munich, Wuhan University
-
MA-EgoQA: Question Answering over Egocentric Videos from Multiple Embodied AgentsSamsung Electronics / Electronics and Telecommunications Research Institute, Korea Advanced Institute of Science & Technology, New York University
-
Execution Is the New Attack Surface: Survivability-Aware Agentic Crypto Trading with OpenClaw-Style Local Executors
-
Chow-Liu Ordering for Long-Context Reasoning in Chain-of-Agents
-
CycleULM: A unified label-free deep learning framework for ultrasound localisation microscopyEscuela Superior Politécnica del Litoral, Imperial College London
-
Equivariant Asynchronous Diffusion: An Adaptive Denoising Schedule for Accelerated Molecular Conformation GenerationFudan University, Shanghai Academy of Artificial Intelligence for Science
-
A Unified Hierarchical Multi-Task Multi-Fidelity Framework for Data-Efficient Surrogate Modeling in ManufacturingUniversity of Illinois Urbana-Champaign, University of Michigan
-
SCENEBench: An Audio Understanding Benchmark Grounded in Assistive and Industrial Use CasesCornell Tech, Stanford University
-
A Graph-Based Approach to Spectrum Demand Prediction Using Hierarchical Attention NetworksCarleton University, Communications Research Centre Canada
-
GAST: Gradient-aligned Sparse Tuning of Large Language Models with Data-layer SelectionAntGroup / Cleveland Clinic Lerner Research Institution, Cornell University, Sichuan University, University of Liverpool
-
Rethinking Adam for Time Series Forecasting: A Simple Heuristic to Improve Optimization under Distribution ShiftsGuilin University of Electronic Technology, University of Chile
-
CarbonBench: A Global Benchmark for Upscaling of Carbon Fluxes Using Zero-Shot LearningUniversity of Minnesota
-
N-gram-like Language Models Predict Reading Time BestMassachusetts Institute of Technology
-
MissBench: Benchmarking Multimodal Affective Analysis under Imbalanced Missing ModalitiesVNU University of Engineering and Technology
