6 papers
TRL-Bench: Standardizing Cross-Paradigm Representation-Level Evaluation of Tabular Encoders
Wei Pang, Xiangru Jian, Hehan Li +10
Tabular encoders are usually evaluated inside task-specific end-to-end pipelines, so models from different training paradigms are difficult to compare directly even when they opera…
FORGE: Fine-grained Multimodal Evaluation for Manufacturing Scenarios
Xiangru Jian, Hao Xu, Wei Pang +13
The manufacturing sector is increasingly adopting Multimodal Large Language Models (MLLMs) to transition from simple perception to autonomous execution, yet current evaluations fai…
GraphOmni: A Comprehensive and Extensible Benchmark Framework for Large Language Models on Graph-theoretic Tasks
Hao Xu, Xiangru Jian, Xinjian Zhao +9
This paper introduces GraphOmni, a comprehensive benchmark designed to evaluate the reasoning capabilities of LLMs on graph-theoretic tasks articulated in natural language. GraphOm…
LazyVLM: Neuro-Symbolic Approach to Video Analytics
Xiangru Jian, Wei Pang, Zhengyuan Dong +2
Current video analytics approaches face a fundamental trade-off between flexibility and efficiency. End-to-end Vision Language Models (VLMs) often struggle with long-context proces…
Enhancing Graph Self-Supervised Learning with Graph Interplay
Xinjian Zhao, Wei Pang, Xiangru Jian +3
Graph self-supervised learning (GSSL) has emerged as a compelling framework for extracting informative representations from graph-structured data without extensive reliance on labe…
Rethinking Spectral Augmentation for Contrast-based Graph Self-Supervised Learning
Xiangru Jian, Xinjian Zhao, Wei Pang +4
The recent surge in contrast-based graph self-supervised learning has prominently featured an intensified exploration of spectral cues. Spectral augmentation, which involves modify…