Time-Series-Works-Conferences

Time-Series Works and Conferences

About Me (Du Yin)

I am a Ph.D. student in the School of Computer Science and Engineering (CSE) at UNSW Sydney, Australia, where I am fortunate to be co-supervised by Prof. Flora Salim and Dr. Hao Xue.

My research is driven by a strong passion for Time-Series Research and Deep Learning. Currently, my work focuses on developing next-generation Time-Series Foundation Models (TSFMs), generative modeling, and scalable frameworks for complex temporal and spatio-temporal data mining.

Prior to joining UNSW, I received my Master’s degree, during which I had the privilege of being advised by Prof. Xuan Song, Dr. Quanjun Chen, and Prof. Renhe Jiang.

Backlog (To do):

Recent Time Series Works Grouped by Task

• Multivariat Time Series Forecasting
• Multivariat Probabilistic Time Series Forecasting
• Time Series Imputation
• Time Series Anomaly Detection
• Demand Prediction
• Time Series Generation
• Travel Time Estimation
• Traffic Location Prediction
• Event Prediction
• Stock Prediction
• Other Forecasting

Multivariat Time Series Forecasting

Task	Data	Model	Paper	Code	Publication
Foundation Multivariat	TimesNet	Olivia	Olivia: Harmonizing Time Series Foundation Models with Power Spectral Density	None	ICML 2026
Foundation Multivariat	TimesNet	Time-PEFT	Time-PEFT: Temporal and Multichannel Complexity-Based Fine-Tuning for Time-Series Foundation Models	None	ICML 2026
Foundation Multivariat	TimesNet		Universal Redundancies in Time Series Foundation Models	Code	ICML 2026
LLM Reasoning	TimesNet	VeriTime	Time Series Reasoning via Process-Verifiable Thinking Data Synthesis and Scheduling for Tailored LLM Reasoning	None	ICML 2026
LLM Medical	HAR-CoT Sleep-CoT ECG-QA MIMIC	OpenTSLM	OpenTSLM: Time-Series Language Models for Reasoning over Multivariate Medical Text- and Time-Series Data	Code	ICML 2026
LLM Benchmark	Health TS	HEARTS	HEARTS: Benchmarking LLM Reasoning on Health Time Series	Code	ICML 2026
Position	TimesNet		Position: Time-Series Foundation Models Require Explicit Domain-Level Benchmarks	None	ICML 2026
Foundation Benchmark	ZTF	StarEmbed	StarEmbed: Benchmarking Time Series Foundation Models on Astronomical Observations of Variable Stars	Code	ICML 2026
Physiological	MIMIC PhysioNet		Self-Supervised Dynamical System Representations for Physiological Time-Series	Code	ICML 2026
Dataset Condensat	TimesNet		One Batch Is Enough: A Unified Dataset Condensation Framework for General Time Series Analysis	None	ICML 2026
Foundation Multivariat	TimesNet	Zeus	Zeus: Towards Tuning-Free Foundation Model for Time Series Analysis	None	ICML 2026
Dataset Multimodal	TelecomTS		TelecomTS: A Multi-Modal Observability Dataset for Time Series and Language Analysis	Code	ICML 2026
Multimodal Alignment	TimesNet		Time Series, Vision, and Language: Exploring the Limits of Alignment in Contrastive Representation Spaces	None	ICML 2026
Multivariat	TimesNet	L-Drive	L-Drive: Beyond a Single Mapping—Latent Context Drives Time Series Forecasting	Code	ICML 2026
Multivariat	TimesNet	ConFlux	ConFlux: Multivariate Time Series in Flux, One Unified Forecast in Confluence	None	ICML 2026
Multivariat	TimesNet	PESD-TSF	PESD-TSF: A Period-Aware and Explicit Structured Decomposition Framework for Long-Term Time Series Forecasting	None	ICML 2026
Multivariat	TimesNet		Parameter Decorrelation via Transition-Variance Alignment for Multivariate Time-series Forecasting	None	ICML 2026
Benchmark	TimesNet	TIME	It’s TIME: Towards the Next Generation of Time Series Forecasting Benchmarks	Code	ICML 2026
Robust Multivariat	TimesNet	DropoutTS	DropoutTS: Sample-Adaptive Dropout for Robust Time Series Forecasting	Code	ICML 2026
Multivariat	TimesNet		Time-series forecasting through the lens of dynamics	Code	ICML 2026
Weather Benchmark	WEATHER-5K		Benchmarking Physics-Informed Time-Series Models for Operational Global Station Weather Forecasting	Code	ICML 2026
Efficient Multivariat	TimesNet	BPE	Byte Pair Encoding for Efficient Time Series Forecasting	None	ICML 2026
Backdoor Defense	TimesNet	TimeGuard	TimeGuard: Channel-wise Pool Training for Backdoor Defense in Time Series Forecasting	Code	ICML 2026
Counterfac	TimesNet		What if Tomorrow is the World Cup Final? Counterfactual Time Series Forecasting with Textual Conditions	None	ICML 2026
Distillation	TimesNet		Beyond Point Predictions: Manifold Expansion and Dual Alignment for Robust Time Series Distillation	None	ICML 2026
Foundation Multivariat	TimesNet		Channel Adapter for Time Series Foundation Models in Zero-Shot Multivariate Forecasting	None	ICML 2026
Multivariat	TimesNet		Beyond Extrapolation: Knowledge Utilization Paradigm with Bidirectional Inspiration for Time Series Forecasting	None	ICML 2026
Source-Free Multivariat	TimesNet	TimePD	Invariant Representation Learning for Source-Free Time Series Forecasting with LLM-Centric Proxy Denoising	Code	ICML 2026
Multivariat	TimesNet	FIPN	FIPN: Forward Self-Organizing Interpretable Polynomial Networks for Time Series Forecasting	None	ICML 2026
Multivariat	TimesNet	DMANet	Anti-Aliasing Matters: A Dynamic Network for Time Series Forecasting	Code	ICML 2026
Non-stationary Multivariat	TimesNet	DSENet	DSENet: A Novel Dual-Stream Enhancement Network for Multi-Scale Non-Stationary Time Series Forecasting	None	ICML 2026
Multivariat	TimesNet	Crisp	Crisp: A Spectral-Based Interaction Strategy for Multivariate Time Series Forecasting	None	ICML 2026
Analysis	TimesNet		Beyond Model Ranking: Predictability-Aligned Evaluation for Time Series Forecasting	Code	ICML 2026
Multivariat	TimesNet	KITE	KITE: Knowledge-Guided Probabilistic Modeling for Time Series Forecasting with Exogenous Variables	None	ICML 2026
LLM Multivariat	TimesNet	TsLLM	TsLLM: Augmenting LLMs for General Time Series Understanding and Prediction	None	ICML 2026
Multivariat	TimesNet	ReNF	ReNF: Rethinking the Principles of Neural Long-Term Time Series Forecasters	Code	ICML 2026
Multivariat	TimesNet		Reviving Error Correction in Modern Deep Time-Series Forecasting	Code	ICML 2026
Multivariat	TimesNet	MemCast	MemCast: Memory-Driven Time Series Forecasting with Experience-Conditioned Reasoning	Code	ICML 2026
Adversarial Multivariat	TimesNet	TSFAdv	TSFAdv: Frequency-Guided Black-Box Adversarial Attacks on Time Series Forecasting	None	ICML 2026
Non-stationary Multivariat	TimesNet	Dynamic TMoE	Dynamic TMoE: A Drift-Aware Dynamic Mixture of Experts Framework for Non-Stationary Time Series Forecasting	Code	ICML 2026
Multivariat	TimesNet	Fern	Ellipsoidal Time Series Forecasting	None	ICML 2026
Generative Multivariat	TimesNet	CoGenCast	CoGenCast: A Coupled Autoregressive–Flow Generative Framework for Time Series Forecasting	Code	ICML 2026
Multivariat	TimesNet	StretchTime	StretchTime: Adaptive Time Series Forecasting via Symplectic Attention	None	ICML 2026
Robust Multivariat	TimesNet		Robust Inter-Series Dependency Modeling for Time Series Forecasting via Information-Theoretic Alignment	None	ICML 2026
Analysis	TimesNet	CombiTS	CombinationTS: A Modular Framework for Understanding Time-Series Forecasting Models	Code	ICML 2026
Foundation Multivariat	TimesNet		See More, Forecast Better and Faster: Enhancing Time Series Foundation Models via Inference-Time Plug-and-Play Downsampling	Code	ICML 2026
Robust Multivariat	TimesNet	TameR	Taming the Recent-Data Bias: Towards Robust Time Series Forecasting with Global Context	Code	ICML 2026
Multivariat	TimesNet	KineFlow	KineFlow: Kinematic Second-Order Flow Matching for Time-Series Forecasting	None	ICML 2026
Multivariat	TimesNet	LatentTSF	From Observations to States: Latent Time Series Forecasting	Code	ICML 2026
Foundation Multivariat	TimesNet	Baguan-TS	Baguan-TS: dual in-context learning model for time series forecasting with covariates	None	ICML 2026
Position	TimesNet		Position: Current Benchmarking Hinders Real Progress in Deep Learning for Time Series Forecasting	Code	ICML 2026
LLM Multivariat	TimesNet	TimeMRA	TimeMRA: LLM-Empowered Time Series Forecasting via Multi-Scale Retrieval-Augmented Representations	None	ICML 2026
Multimodal Evaluation	TimesNet		Rethinking Multimodal Time-Series Forecasting Evaluation	None	ICML 2026
Irregular Multivariat	TimesNet	TFMixer	Bridging Time and Frequency: A Joint Modeling Framework for Irregular Multivariate Time Series Forecasting	None	ICML 2026
Multivariat	TimesNet	DAG	DAG: A Dual Correlation Network for Time Series Forecasting with Exogenous Variables	Code	ICML 2026
Robust Multivariat	TimesNet	SEER	SEER: Transformer-based Robust Time Series Forecasting via Automated Patch Enhancement and Replacement	None	ICML 2026
Multivariat	TimesNet	TimeSeed	TimeSeed: Effective Time Series Forecasting with Sparse Endogenous Variables	None	ICML 2026
Multivariat	TimesNet		Information Geometry Loss for Time Series Forecasting	None	ICML 2026
Multivariat	TimesNet	KUMA	KUMA: A Novel Framework with Koopman Separation and Efficient Multilevel Extraction in Time Series Forecasting	None	ICML 2026
Scaling Multivariat	TimesNet		Revealing Scaling Behavior in Large-scale Time Series Models: Implications for More Efficient and Accurate Forecasting	None	ICML 2026
Non-stationary Multivariat	TimesNet	PULSE	PULSE: Generative Phase Evolution for Non-Stationary Time Series Forecasting	Code	ICML 2026
Diffusion Multivariat	TimesNet		Not All Frequencies Are Equal: Energy-Adaptive Diffusion for Time Series Forecasting	None	ICML 2026
Irregular Medical	MIMIC	MoRGEN	MoRGEN: Mixture-of-Resolutions Generative Forecasting for Irregularly Sampled Medical Time-Series Data	None	ICML 2026
Multivariat	TimesNet	MixLinear	MixLinear: Extreme Low Resource Multivariate Time Series Forecasting with Parameters	Code	ICLR 2026
Multivariat	TimesNet	CoRA	CoRA: Boosting Time Series Foundation Models for Multivariate Forecasting through Correlation-aware Adapter	Code	ICLR 2026
Multivariat	TimesNet	PHAT	PHAT: Modeling Period Heterogeneity for Multivariate Time Series Forecasting	Code	ICLR 2026
Multivariat	TimesNet	Numerion	Numerion: A Multi-Hypercomplex Model for Time Series Forecasting	None	ICLR 2026
Multivariat	TimesNet	COSA	COSA: Context-aware Output-Space Adapter for Test-Time Adaptation in Time Series Forecasting	Code	ICLR 2026
Multivariat	TimesNet	CPiRi	CPiRi: Channel Permutation-Invariant Relational Interaction for Multivariate Time Series Forecasting	Code	ICLR 2026
Multivariat	TimesNet	GTR	Enhancing Multivariate Time Series Forecasting with Global Temporal Retrieval	Code	ICLR 2026
Multivariat	TimesNet	TimeAli	Bridging Past and Future: Distribution-Aware Alignment for Time Series Forecasting	Code	ICLR 2026
Multivariat	TimesNet		Are Global Dependencies Necessary? Scalable Time Series Forecasting via Local Cross-Variate Modeling	Code	ICLR 2026
Multivariat	TimesNet	GCGNet	GCGNet: Graph-Consistent Generative Network for Time Series Forecasting with Exogenous Variables	Code	ICLR 2026
Multivariat	TimesNet		Test-Time Efficient Pretrained Model Portfolios for Time Series Forecasting	None	ICLR 2026
Multivariat	TimesNet	MMPD	MMPD: Diverse Time Series Forecasting via Multi-Mode Patch Diffusion Loss	Code	ICLR 2026
Robust Multivariat	TimesNet		Local Geometry Attention for Time Series Forecasting under Realistic Corruptions	Code	ICLR 2026
Multivariat	TimesNet	FACT	FACT: Fine-grained Across-variable Convolution for Multivariate Time Series Forecasting	Code	ICLR 2026
Multivariat	TimesNet		Unlocking the Value of Text: Event-Driven Reasoning and Multi-Level Alignment for Time Series Forecasting	Code	ICLR 2026
Foundation Multivariat		Aurora	Aurora: Towards Universal Generative Multimodal Time Series Forecasting	Code	ICLR 2026
Multivariat	TimesNet		The Forecast After the Forecast: A Post-Processing Shift in Time Series	Code	ICLR 2026
Multivariat	TimesNet	ADAPT-Z	Online time series prediction using feature adjustment	Code	ICLR 2026
Robust Multivariat	ETT Weather EPA-Air	CTF	Towards Robust Real-World Multivariate Time Series Forecasting: A Unified Framework for Dependency, Asynchrony, and Missingness	Code	ICLR 2026
Multivariat	TimesNet	xCPD	Routing Channel-Patch Dependencies in Time Series Forecasting with Graph Spectral Decomposition	Code	ICLR 2026
Irregular Multivariat		ASTGI	ASTGI: Adaptive Spatio-Temporal Graph Interactions for Irregular Multivariate Time Series Forecasting	Code	ICLR 2026
Multivariat	TimesNet	ProtoTS	ProtoTS: Learning Hierarchical Prototypes for Explainable Time Series Forecasting	Code	ICLR 2026
Multivariat	TimesNet	PhaseFormer	PhaseFormer: From Patches to Phases for Efficient and Effective Time Series Forecasting	Code	ICLR 2026
Irregular Multivariat		ReIMTS	Learning Recursive Multi-Scale Representations for Irregular Multivariate Time Series Forecasting	Code	ICLR 2026
Multivariat	TimesNet		Characteristic Root Analysis and Regularization for Linear Time Series Forecasting	Code	ICLR 2026
Multivariat	TimesNet	SE-LLM	Semantic-Enhanced Time-Series Forecasting via Large Language Models	Code	ICLR 2026
Analysis	TimesNet	TimeRecipe	TimeRecipe: A Time-Series Forecasting Recipe via Benchmarking Module Level Effectiveness	Code	ICLR 2026
Multivariat	TimesNet	ShifTS	Tackling Time-Series Forecasting Generalization via Mitigating Concept Drift	Code	ICLR 2026
Multivariat	TimesNet	QDF	Quadratic Direct Forecast for Training Multi-Step Time-Series Forecast Models	Code	ICLR 2026
Multivariat	TimesNet	DistDF	DistDF: Time-series Forecasting Needs Joint-distribution Wasserstein Alignment	Code	ICLR 2026
Traffic	NGSIM HighD		Micro-Macro Coupled Koopman Modeling on Graph for Traffic Flow Prediction	None	ICLR 2026
Evolve Traffic	METR-LA PEMS	STBP	A General Spatio-Temporal Backbone with Scalable Contextual Pattern Bank for Urban Continual Forecasting	Code	ICLR 2026
Analysis	TimesNet		Beyond Accuracy: Are Time Series Foundation Models Well-Calibrated?	Code	ICLR 2026
Foundation Multivariat	TimesNet	UniCA	UniCA: Unified Covariate Adaptation for Time Series Foundation Model	Code	ICLR 2026
Multivariat	TimesNet	TimeOmni-1	TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Models	Code	ICLR 2026
Foundation Multivariat	TimesNet		Rating Quality of Diverse Time Series Data by Meta-learning from LLM Judgment	Code	ICLR 2026
Foundation Multivariat	TimesNet		Adapt Data to Model: Adaptive Transformation Optimization for Domain-shared Time Series Foundation Models	Code	ICLR 2026
FL Foundation	TimesNet	FeDaL	FeDaL: Federated Dataset Learning for General Time Series Foundation Models	Code	ICLR 2026
Foundation Multivariat	TimesNet	SwiftTS	SwiftTS: A Swift Selection Framework for Time Series Pre-trained Models via Multi-task Meta-Learning	Code	ICLR 2026
Foundation Multivariat	TimesNet	SFF	Lost in the Non-convex Loss Landscape: How to Fine-tune the Large Time Series Model?	Code	ICLR 2026
Foundation Multivariat	TimesNet	GTM	GTM: A General Time-series Model for Enhanced Representation Learning of Time-Series data	Code	ICLR 2026
Multivariat	TimesNet		Multi-Scale Hypergraph Meets LLMs: Aligning Large Language Models for Time Series Analysis	Code	ICLR 2026
Multivariat	TimesNet	AutoDA	AutoDA-Timeseries: Automated Data Augmentation for Time Series	Code	ICLR 2026
Foundation Multivariat	TimesNet	TS-Memory	TS-Memory: Plug-and-Play Memory for Time Series Foundation Models	Code	KDD 2026
Multivariat			Eliciting Frequency-Conditioned Spatial Dynamics for Long-Term Spatio-Temporal Forecasting	Code	KDD 2026
Multivariat	TimesNet	CCD	CCD: Capturing Cross-Correlations with Deformable Convolutional Networks for Multivariate Time Series Forecasting	Code	KDD 2026
Multivariat	TimesNet	STM3	STM3: Mixture of Multiscale Mamba for Long-Term Spatio-Temporal Time-Series Prediction	Code	KDD 2026
Multivariat	TimesNet	CAST-Norm	CAST-Norm: Coupled Adaptive Spatio-Temporal Normalization for Multivariate Time Series Forecasting	Code	KDD 2026
Multivariat	TimesNet	RePatch	RePatch: Learning Entropy-Guided Patch Structures with Quantized Representations for Time Series Forecasting	Code	KDD 2026
Traffic	LargeST	STUNet	Unified Spatio-Temporal Tokens are Bases for Generalizable Traffic Forecasting	Code	KDD 2026
Traffic	PEMS	HURST	HURST: Heterogeneity-Adaptive Urban Foundation Models for Spatiotemporal Prediction via Self-Partitional Mixture-of-Spatial-Experts	None	KDD 2026
Multivariat	TimesNet	SARAF	Stationarity-Aware Retrieval-Augmented Time Series Forecasting	Code	KDD 2026
Multivariat	TimesNet	TS-MTM	TS-MTM: Temporal-Spectral Masked Time-Series Modeling for Forecasting	Code	KDD 2026
Traffic	PEMS		Beyond Language Processing: LLMs Rules-Injected Instruction Tuning for Traffic Prediction	Code	KDD 2026
Multivariat			Orbit-Adaptive Zero-Shot Forecasting on Spatio-Temporal Graph	Code	KDD 2026
Multivariat	TimesNet		One Step Closer to Ground Truth: A Multi-Scale Residual-Aware Representation Learning Pipeline for Predicting Time Series Data	None	KDD 2026
Multivariat		GODM	GODM: Graph Orthogonal Diffusion Models for Spatio-Temporal Forecasting	Code	KDD 2026
Multivariat	TimesNet	FAiT	FAiT: Frequency-Aware Inverted Transformer for Multivariate Time Series Forecasting	Code	KDD 2026
Multivariat			Invariant Structure Learning with Pre-trained Language Models for Spatio-temporal Graph	Code	KDD 2026
Traffic	NYC Washington DC Chicago	FreMo	Frequency-Domain Multi-Modality Transportation Modeling	Code	KDD 2026
Multivariat	TimesNet	PatchCLE	PatchCLE: Breaking the Linear Representation Bottleneck in Time Series Forecasting via Soft Contrastive Learning	Code	KDD 2026
Foundation Multivariat	TimesNet	MEMTS	MEMTS: Internalizing Domain Knowledge via Parameterized Memory for Retrieval-Free Domain Adaptation of Time Series Foundation Models	None	KDD 2026
Multivariat	TimesNet		Beyond Linear Dynamics: Neural Bilinear Dynamical Models for Time Series Forecasting	Code	KDD 2026
Traffic	PeMSD4 PeMSD8 FT-AED HK-Traffic	FedTT	FedTT: A Federated Spatio-Temporal Learning Framework for Cross-City Traffic Knowledge Transfer	Code	KDD 2026
Multivariat	TimesNet		Forecasting as Rendering: A 2D Gaussian Splatting Framework for Time Series Forecasting	Code	KDD 2026
Multivariat	TimesNet		Efficient Test-Time Scaling for LLM-based Time Series Forecasting	Code	KDD 2026
Domain Forecasting	TimesNet	Aura	Aura: Universal Multi-dimensional Exogenous Integration for Aviation Time Series	None	KDD 2026
Foundation Multivariat	EpiRecipe US disease surveillance	CAPE	Lightweight Wrappers for Adapting Time Series Foundation Models to Regional Drought Forecasting	Code	KDD 2026
Multivariat	TimesNet	DSPR	DSPR: Dual-Stream Physics-Residual Networks for Trustworthy Industrial Time Series Forecasting	None	KDD 2026
Domain Forecasting			Fourier Geometric Wind Power Forecasting with Numerical Weather Prediction	Code	KDD 2026
Foundation Multivariat	Meteorology Carbon flux Soil moisture Energy grid	Guard	When to Trust, How to Distill: Multi-Foundation Model Guidance for Lightweight, Robust Scientific Time Series Forecasting	Code	KDD 2026
Foundation Multivariat		UrbanFM	UrbanFM: Scaling Urban Spatio-Temporal Foundation Models	None	KDD 2026
Traffic	CHITaxi WSHTaxi CHIBike PeMS	CSSG	CSSG: A Continuous Spatio-temporal Graph Learning Framework with Scalable Spatial Granularity	Code	KDD 2026
Traffic	PEMS	MoST	MoST: A Foundation Model for Multi-modality Spatio-temporal Traffic Prediction	Code	KDD 2026
Multivariat		FaST	FaST: Efficient and Effective Long-Horizon Forecasting for Large-Scale Spatial-Temporal Graphs via Mixture-of-Experts	Code	KDD 2026
Traffic	PEMS		Incident-Guided Spatiotemporal Traffic Forecasting	Code	KDD 2026
Multivariat	TimesNet	TimeDistill	TimeDistill: Efficient Long-Term Time Series Forecasting with MLP via Cross-Architecture Distillation	Code	KDD 2026
Multivariat	TimesNet	LoFT-LLM	LoFT-LLM: Low-Frequency Time-series Forecasting with Large Language Models	Code	KDD 2026
Multivariat	TimesNet		Neural Predictive Control to Coordinate Discrete- and Continuous-Time Models for Time-Series Analysis with Control-Theoretical Improvements	None	KDD 2026
Multivariat	TimesNet		How to Train Your Mamba for Time Series Forecasting	None	KDD 2026
Traffic	PEMS		Towards Resilient Transportation: A Conditional Transformer for Accident-Informed Traffic Forecasting	Code	KDD 2026
Multivariat	TimesNet		From Tokenizer Bias to Backbone Capability: A Controlled Study of LLMs for Time Series Forecasting	Code	KDD 2026
Traffic	PEMS	ChannelMTS	ChannelMTS: A Multi-modal Time-Series Framework for High-Speed Railway Channel Prediction	None	KDD 2026
Foundation Multivariat			Toward Green Computing: General Carbon Intensity Forecasting via Dual Graph Empowered Time Series Foundation Model	None	WWW 2026
Multivariat	TimesNet		Cross-city Time Series Forecasting with Retrieval-Augmented Large Language Models	None	WWW 2026
Multivariat	TimesNet		Automated Model Selection for Multivariate Time Series Forecasting	None	WWW 2026
Multivariat	TimesNet	GFMixer	GFMixer: Decoupled Temporal Gradient and Fourier-Aware Attention for Time Series Forecasting	Code	WWW 2026
Multivariat	TimesNet	CRAFT	Efficient High-Dimensional Time Series Forecasting with Transformers: A Channel Reordering Perspective	None	WWW 2026
Multivariat	TimesNet	DynaME	Dynamic Multi-period Experts for Online Time Series Forecasting	Code	WWW 2026
Multivariat	TimesNet	Re-Diffusion	[Re-Diffusion: Modeling Latent Residuals wi

README 内容过长，已截取前 64 KB。完整内容请前往 GitHub 仓库查看。