activity
20242026
collaborators

6 papers

cs.CL2026

Neuro-Symbolic Synergy for World Modeling

Hongyu Zhao, Siyu Zhou, Haolin Yang +2

Large language models (LLMs) exhibit strong general-purpose reasoning capabilities, yet they frequently hallucinate when used as world models (WMs), where strict compliance with de…

cs.AI2026

TSRBench: A Comprehensive Multi-task Multi-modal Time Series Reasoning Benchmark for Generalist Models

Fangxu Yu, Xingang Guo, Lingzhi Yuan +6

Time series are ubiquitous in real-world scenarios and crucial for applications ranging from energy management to traffic control. Consequently, the ability to reason over time ser…

cs.CL2025

TS-Reasoner: Aligning Time Series Foundation Models with LLM Reasoning

Fangxu Yu, Hongyu Zhao, Tianyi Zhou

Time series reasoning is crucial to decision-making in diverse domains, including finance, energy, and scientific discovery. While existing time series foundation models (TSFMs) ca…

cs.CL2024

BenTo: Benchmark Task Reduction with In-Context Transferability

Hongyu Zhao, Ming Li, Lichao Sun +1

Evaluating large language models (LLMs) is costly: it requires the generation and examination of LLM outputs on a large-scale benchmark of various tasks. This paper investigates ho…

cs.CL2024

Mosaic-IT: Cost-Free Compositional Data Synthesis for Instruction Tuning

Ming Li, Pei Chen, Chenguang Wang +5

Finetuning large language models with a variety of instruction-response pairs has enhanced their capability to understand and follow instructions. Current instruction tuning primar…

cs.CL2024

Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning

Ming Li, Yong Zhang, Shwai He +5

Instruction tuning is critical to improve LLMs but usually suffers from low-quality and redundant data. Data filtering for instruction tuning has proved important in improving both…