14 papers
Bringing Stability to Diffusion: Decomposing and Reducing Variance of Training Masked Diffusion Models
Mengni Jia, Mengyu Zhou, Yihao Liu +2
Masked diffusion models (MDMs) are a promising alternative to autoregressive models (ARMs), but they suffer from inherently much higher training variance. High variance leads to no…
From Task to Tutorial: An Automated GUI Framework for Excel Tutorial Document and Video Creation
Yuhang Xie, Jian Mu, Xiaojun Ma +9
Excel is one of the most widely used productivity tools across domains, offering rich functionality but also overwhelming users with its complexity. This creates a persistent deman…
Not All Tokens Matter: Towards Efficient LLM Reasoning via Token Significance in Reinforcement Learning
Hanbing Liu, Lang Cao, Yuanyi Ren +5
Large language models (LLMs) show strong reasoning abilities but often produce unnecessarily long explanations that reduce efficiency. Although reinforcement learning (RL) has been…
Formula-R1: Incentivizing LLM Reasoning over Complex Tables with Numerical Computation via Formula-Driven Reinforcement Learning
Lang Cao, Jingxian Xu, Hanbing Liu +5
Tables are a fundamental medium for organizing and analyzing data, making table reasoning a critical capability for intelligent systems. Although large language models (LLMs) exhib…
Table-LLM-Specialist: Language Model Specialists for Tables using Iterative Generator-Validator Fine-tuning
Junjie Xing, Yeye He, Mengyu Zhou +4
Language models such as GPT and Llama have shown remarkable ability on diverse natural language tasks, yet their performance on complex table tasks (e.g., NL-to-Code and data clean…
MMTU: A Massive Multi-Task Table Understanding and Reasoning Benchmark
Junjie Xing, Yeye He, Mengyu Zhou +6
Tables and table-based use cases play a crucial role in many important real-world applications, such as spreadsheets, databases, and computational notebooks, which traditionally re…