247 citations · 278 across the 15 of their papers we have counts for
17 papers
Position: Universal Time Series Foundation Models Rest on a Category Error
Xilin Dai, Wanxu Cai, Zhijian Xu +1
This position paper argues that the pursuit of "Universal Foundation Models for Time Series" rests on a fundamental category error, mistaking a structural Container for a semantic…
Reasoning Scaffolding: Distilling the Flow of Thought from LLMs
Xiangyu Wen, Junhua Huang, Zeju Li +6
The prevailing approach to distilling reasoning from Large Language Models (LLMs)-behavioral cloning from textual rationales-is fundamentally limited. It teaches Small Language Mod…
Reinforcement Learning on Pre-Training Data
Siheng Li, Kejiao Li, Zenan Xu +33
The growing disparity between the exponential scaling of computational resources and the finite growth of high-quality text data now constrains conventional scaling approaches for…
Fidel-TS: A High-Fidelity Multimodal Benchmark for Time Series Forecasting
Zhijian Xu, Wanxu Cai, Xilin Dai +2
The evaluation of time series forecasting models is hindered by a lack of high-quality benchmarks, leading to overestimated assessments of progress. Existing datasets suffer from i…
From Samples to Scenarios: A New Paradigm for Probabilistic Forecasting
Xilin Dai, Zhijian Xu, Wanxu Cai +1
Most state-of-the-art probabilistic time series forecasting models rely on sampling to represent future uncertainty. However, this paradigm suffers from inherent limitations, such…
Making Slow Thinking Faster: Compressing LLM Chain-of-Thought via Step Entropy
Zeju Li, Jianyuan Zhong, Ziyang Zheng +5
Large Language Models (LLMs) using Chain-of-Thought (CoT) prompting excel at complex reasoning but generate verbose thought processes with considerable redundancy, leading to incre…
Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs
Xumeng Wen, Zihan Liu, Shun Zheng +9
Recent advancements in long chain-of-thought (CoT) reasoning, particularly through the Group Relative Policy Optimization algorithm used by DeepSeek-R1, have led to significant int…
Solve-Detect-Verify: Inference-Time Scaling with Flexible Generative Verifier
Jianyuan Zhong, Zeju Li, Zhijian Xu +3
Large Language Model (LLM) reasoning for complex tasks inherently involves a trade-off between solution accuracy and computational efficiency. The subsequent step of verification,…
Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thought
Tencent Hunyuan Team, Ao Liu, Botong Zhou +248
As Large Language Models (LLMs) rapidly advance, we introduce Hunyuan-TurboS, a novel large hybrid Transformer-Mamba Mixture of Experts (MoE) model. It synergistically combines Mam…
Dyve: Thinking Fast and Slow for Dynamic Process Verification
Jianyuan Zhong, Zeju Li, Zhijian Xu +2
We present Dyve, a dynamic process verifier that enhances reasoning error detection in large language models by integrating fast and slow thinking, inspired by Kahneman's Systems T…
DSPO: An End-to-End Framework for Direct Sorted Portfolio Construction
Jianyuan Zhong, Zhijian Xu, Saizhuo Wang +3
In quantitative investment, constructing characteristic-sorted portfolios is a crucial strategy for asset allocation. Traditional methods transform raw stock data of varying freque…
Intervention-Aware Forecasting: Breaking Historical Limits from a System Perspective
Zhijian Xu, Hao Wang, Qiang Xu
Traditional time series forecasting methods predominantly rely on historical data patterns, neglecting external interventions that significantly shape future dynamics. Through cont…
Multi-Patch Prediction: Adapting LLMs for Time Series Representation Learning
Yuxuan Bian, Xuan Ju, Jiangtong Li +3
In this study, we present aLLM4TS, an innovative framework that adapts Large Language Models (LLMs) for time-series representation learning. Central to our approach is that we reco…
Preliminary Study on Incremental Learning for Large Language Model-based Recommender Systems
Tianhao Shi, Yang Zhang, Zhijian Xu +4
Adapting Large Language Models for Recommendation (LLM4Rec) has shown promising results. However, the challenges of deploying LLM4Rec in real-world scenarios remain largely unexplo…
FITS: Modeling Time Series with Parameters
Zhijian Xu, Ailing Zeng, Qiang Xu
In this paper, we introduce FITS, a lightweight yet powerful model for time series analysis. Unlike existing models that directly process raw time-domain data, FITS operates on the…
FrAug: Frequency Domain Augmentation for Time Series Forecasting
Muxi Chen, Zhijian Xu, Ailing Zeng +1
Data augmentation (DA) has become a de facto solution to expand training data size for deep learning. With the proliferation of deep models for time series analysis, various time s…
SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction
Minhao Liu, Ailing Zeng, Muxi Chen +4
One unique property of time series is that the temporal relations are largely preserved after downsampling into two sub-sequences. By taking advantage of this property, we propose…