Qingsong Wen

Principal Researcher@Squirrel Ai Learning·美国·OpenReview

研究方向

time series · edtech · anomaly detection · AIOps · XAI · LLM · Agent · graph algorithms · graph computing · graph mining · signal processing · wireless communications · FPGA

Qingsong Wen

Causal Time Series Generation via Diffusion Models

AudioTrust: Benchmarking The Multifaceted Trustworthiness of Audio Large Language Models

Quadratic Direct Forecast for Training Multi-Step Time-Series Forecast Models

DistDF: Time-series Forecasting Needs Joint-distribution Wasserstein Alignment

EIP: Weighted Ranking of LLMs by Quantifying Question Difficulty

From Images to Signals: Are Large Vision Models Useful for Time Series Analysis?

DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language Models

Multi-Order Wavelet Derivative Transform for Deep Time Series Forecasting

CultureVLM: Characterizing and Improving Cultural Understanding of Vision-Language Models

TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Models

PriceFM: Foundation Model for Probabilistic Electricity Price Forecasting

Backdoor Attribution: Elucidating and Controlling Backdoor in Language Models

Graph Attribute Imputation via Generalized Wasserstein Balancing

Unraveling Hallucination in Large Reasoning Models: A Topological Perspective

Differential-Integral Neural Operator for Long-Term Turbulence Forecasting

OrderFusion: Encoding Orderbook for End-to-End Probabilistic Intraday Electricity Price Forecasting

Stable-SPAM: How to Stably Train Large Language Models in 4-Bit

VISION: Prompting Ocean Vertical Velocity Reconstruction from Incomplete Observations

On the Necessity of Step-Specific Representation Learning for Multi-Step Forecasting

League: Leaderboard Generation on Demand

Res-Bench: Reasoning Skill-Aware Reasoning Diagnostic evaluation benchmark for math reasoning

Beyond Extrapolation: Knowledge Utilization with Bidirectional Inference for Time Series Forecasting

BACKDOOR COLLAPSE: ELIMINATING UNKNOWN THREATS VIA KNOWN BACKDOOR AGGREGATION IN LANGUAGE MODELS

Improving Bilinear RNN with Closed-loop Control

Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts

ShapeX: Shapelet-Driven Post Hoc Explanations for Time Series Classification Models

MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?

Multi-Scale Finetuning for Encoder-based Time Series Foundation Models

OneForecast: A Universal Framework for Global and Regional Weather Forecasting

Open-CK: A Large Multi-Physics Fields Coupling benchmarks in Combustion Kinetics

SAEMark: Steering Personalized Multilingual LLM Watermarks with Sparse Autoencoders

SPARK: Physics-Guided Quantitative Augmentation for Dynamical System Modeling

ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detection

CaPulse: Detecting Anomalies by Tuning in to the Causal Rhythms of Time Series

Time-VLM: Exploring Multimodal Vision-Language Models for Augmented Time Series Forecasting

PDETime: Rethinking Long-term Multivariate Time Series Forecasting from the Perspective of Partial Differential Equations

Toward Physics-guided Time Series Embedding

Evolving Multi-Scale Normalization for Time Series Forecasting under Distribution Shifts

Benchmarks and Custom Package for Energy Forecasting

P-Align: Self-Alignment in Physical Dynamical System Modeling

NuwaTS: a Foundation Model Mending Every Incomplete Time Series

FoundTS: Comprehensive and Unified Benchmarking of Foundation Models for Time Series Forecasting

TSI-Bench: Benchmarking Time Series Imputation

MIND SCRAMBLE: UNVEILING LARGE LANGUAGE MODEL PSYCHOLOGY VIA TYPOGLYCEMIA