9 citations · 17 across the 6 of their papers we have counts for
6 papers
Exact values and exact upper bounds for families of integers with arithmetic progression intersections (Erdős Problem #272)
Zhanfu Yang
Let be the largest for which there exist distinct sets such that is a nonempty arithmetic progression for all $i \…
Why Retrying Fails: Context Contamination in LLM Agent Pipelines
Zhanfu Yang
When an LLM agent fails a multi-step tool-augmented task and retries, the failed attempt typically remains in its context window -- contaminating the next attempt and elevating the…
MHB: Multimodal Handshape-aware Boundary Detection for Continuous Sign Language Recognition
Mingyu Zhao, Zhanfu Yang, Yang Zhou +4
This paper employs a multimodal approach for continuous sign recognition by first using ML for detecting the start and end frames of signs in videos of American Sign Language (ASL)…
Graph Neural Reasoning May Fail in Certifying Boolean Unsatisfiability
Ziliang Chen, Zhanfu Yang
It is feasible and practically-valuable to bridge the characteristics between graph neural networks (GNNs) and logical reasoning. Despite considerable efforts and successes witness…
Multivariate-Information Adversarial Ensemble for Scalable Joint Distribution Matching
Ziliang Chen, Zhanfu Yang, Xiaoxi Wang +4
A broad range of cross--domain generation researches boil down to matching a joint distribution by deep generative models (DGMs). Hitherto algorithms excel in pairwise domains w…
Graph Neural Reasoning for 2-Quantified Boolean Formula Solvers
Zhanfu Yang, Fei Wang, Ziliang Chen +2
In this paper, we investigate the feasibility of learning GNN (Graph Neural Network) based solvers and GNN-based heuristics for specified QBF (Quantified Boolean Formula) problems.…