Wispr Flow - Don’t type, just speak
Mini toolsPapers
Filter by company
-
Mitigating Homophily Disparity in Graph Anomaly Detection: A Scalable and Adaptive ApproachNanjing University, Peking University
-
DARC: Disagreement-Aware Alignment via Risk-Constrained Decoding
-
Training event-based neural networks with exact gradients via Differentiable ODE Solving in JAXBielefeld University, University of London
-
MV-Fashion: Towards Enabling Virtual Try-On and Size Estimation with Multi-View Paired DataComputer Vision Center, Universitat Autònoma de Barcelona, Universitat de Barcelona
-
Gradually Excavating External Knowledge for Implicit Complex Question Answering
-
Edged USLAM: Edge-Aware Event-Based SLAM with Learning-Based Depth PriorsPaderborn University, University of Copenhagen
-
Gender Bias in MT for a Genderless Language: New Benchmarks for BasqueUniversity of the Basque Country
-
C$^2$FG: Control Classifier-Free Guidance via Score Discrepancy AnalysisShanghai Jiao Tong University, vivo BlueImage Lab
-
Are We Winning the Wrong Game? Revisiting Evaluation Practices for Long-Term Time Series ForecastingRajamangala University of Technology Tawan-ok Thailand, Shizuoka University
-
Outlier-robust Autocovariance Least Square Estimation via Iteratively Reweighted Least SquareThe Institute of Electrical and Electronics Engineers
-
Learning Hierarchical Knowledge in Text-Rich Networks with Taxonomy-Informed Representation Learning
-
Covenant-72B: Pre-Training a 72B LLM with Trustless Peers Over-the-Internet
-
An explainable hybrid deep learning-enabled intelligent fault detection and diagnosis approach for automotive software systems validationTechnische Universität Clausthal
-
RexDrug: Reliable Multi-Drug Combination Extraction through Reasoning-Enhanced LLMsDalian University of Technology
-
Evidence-Driven Reasoning for Industrial Maintenance Using Heterogeneous Data
-
Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models
-
MERLIN: Building Low-SNR Robust Multimodal LLMs for Electromagnetic SignalsArtificial Intelligence Institute of China Electronics Technology Group Corporation, Beihang University, Beijing Information Science and Technology University, Beijing University of Posts and Telecommunications, Hong Kong University of Science and Technology, Institute of Microelectronics of the Chinese Academy of Sciences, National University of Defense Technology, Tianjin University, Tsinghua University
-
Is continuous CoT better suited for multi-lingual reasoning?Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme, Lamarr Institute, University of Bonn
-
Privacy-Preserving End-to-End Full-Duplex Speech Dialogue ModelsHuawei / Agency for Science, Technology and Research, Singapore, Nanyang Technological University, The Chinese University of Hong Kong, The Hong Kong Polytechnic University
-
ALOOD: Exploiting Language Representations for LiDAR-based Out-of-Distribution Object Detection
-
AutoAdapt: An Automated Domain Adaptation Framework for LLMs
-
TildeOpen LLM: Leveraging Curriculum Learning to Achieve Equitable Language Representation
-
SERQ: Saliency-Aware Low-Rank Error Reconstruction for LLM QuantizationKyung Hee University, Yonsei University
-
Sequential Service Region Design with Capacity-Constrained Investment and Spillover EffectTongji University, University Paris-Saclay
-
Supporting Workflow Reproducibility by Linking Bioinformatics Tools across Papers and Executable CodeHumboldt-Universität zu Berlin, Laboratoire Interdisciplinaire des Sciences du Num´erique, University Paris-Saclay
-
Fusion-Poly: A Polyhedral Framework Based on Spatial-Temporal Fusion for 3D Multi-Object TrackingHarbin Institute of Technology
-
MM-TS: Multi-Modal Temperature and Margin Schedules for Contrastive Learning with Long-Tail DataMassachusetts Institute of Technology, Southeastern Illinois College, University of Bonn, University of Tübingen
-
Distributional Regression with Tabular Foundation Models: Evaluating Probabilistic Predictions via Proper Scoring Rules
-
The Conundrum of Trustworthy Research on Attacking Personally Identifiable Information Removal TechniquesRuhr University Bochum, Technical University of Darmstadt, Trustworthy Human Language Technologies
-
Alignment-Aware and Reliability-Gated Multimodal Fusion for Unmanned Aerial Vehicle Detection Across Heterogeneous Thermal-Visual SensorsBhopal University, Kuwait College of Science and Technology, Manipal Academy of Higher Education, Qatar Foundation, Qatar University, Shahjalal University of Science & Technology, University of Aberdeen, Vels Institute of Sciences, Technology, and Advanced Studies
-
Multi-Objective Evolutionary Optimization of Chance-Constrained Multiple-Choice Knapsack Problems with Implicit Probability DistributionsCentral China Normal University, Nanyang Technological University, Southern University of Science and Technology
-
Video2LoRA: Unified Semantic-Controlled Video Generation via Per-Reference-Video LoRADalian University of Technology, Hong Kong University of Science and Technology
-
Revisiting Gradient Staleness: Evaluating Distance Metrics for Asynchronous Federated Learning AggregationTechnische Universitat Berlin
-
DualTurn: Learning Turn-Taking from Dual-Channel Generative Speech Pretraining
-
Wiener Chaos Expansion based Neural Operator for Singular Stochastic Partial Differential EquationsChinese Academy of Sciences, The University of Sydney, University of Cambridge
-
SplitAgent: A Privacy-Preserving Distributed Architecture for Enterprise-Cloud Agent CollaborationMohamed bin Zayed University of Artificial Intelligence
-
SAVE: Speech-Aware Video Representation Learning for Video-Text RetrievalRenmin University of China
-
SRNeRV: A Scale-wise Recursive Framework for Neural Video RepresentationThe Institute of Electrical and Electronics Engineers
-
GarmentPainter: Efficient 3D Garment Texture Synthesis with Character-Guided Diffusion Model
-
Disentangling Reasoning in Large Audio-Language Models for Ambiguous Emotion PredictionThe University of Auckland, The University of Melbourne, University of Birmingham
-
Quantifying Cross-Lingual Transfer in Paralinguistic Speech TasksBarcelona Supercomputing Center, Universitat Politècnica de Catalunya
-
The Struggle Between Continuation and Refusal: A Mechanistic Analysis of the Continuation-Triggered Jailbreak in LLMsBeijing Institute of Technology
-
Exploring Deep Learning and Ultra-Widefield Imaging for Diabetic Retinopathy and Macular EdemaUniversidad Autónoma de Madrid
-
Fibration Policy OptimizationCarleton University
-
SiMO: Single-Modality-Operable Multimodal Collaborative PerceptionShanghaiTech University, Tongji University
-
Sensivity of LLMs' Explanations to the Training Randomness:Context, Class & Task DependenciesUniversité catholique de Louvain
-
Optimising antibiotic switching via forecasting of patient physiologyUniversity College London, University of Copenhagen
-
Topologically Stable Hough TransformGraz University of Technology, Salzburg University of Applied Sciences
-
Bootstrapping Audiovisual Speech Recognition in Zero-AV-Resource Scenarios with Synthetic Visual DataBarcelona Supercomputing Center, Universitat Politècnica de Catalunya
-
Not All Queries Need Deep Thought: CoFiCot for Adaptive Coarse-to-fine Stateful RefinementChinese Academy of Sciences, The Chinese University of Hong Kong, Xi'an Jiaotong University, Zhejiang University
