6 papers
Hy-MT2: A Family of Fast, Efficient and Powerful Multilingual Translation Models in the Wild
Mao Zheng, Zheng Li, Tao Chen +10
Hy-MT2 is a family of fast-thinking multilingual translation models designed for complex real-world scenarios. It includes three model sizes: 1.8B, 7B, and 30B-A3B (MoE), all of wh…
FlyMirage: A Fully Automated Generation Pipeline for Diverse and Scalable UAV Flight Data via Generative World Model
Jinhan Li, Xijie Huang, Zhaoqi Wang +7
In the field of Vision-Language Navigation (VLN), aerial datasets remain limited in their ability to combine scale, diversity, and realism, often relying on either costly real-worl…
SSKG Hub: An Expert-Guided Platform for LLM-Empowered Sustainability Standards Knowledge Graphs
Chaoyue He, Xin Zhou, Xinjia Yu +10
Sustainability disclosure standards (e.g., GRI, SASB, TCFD, IFRS S2) are comprehensive yet lengthy, terminology-dense, and highly cross-referential, hindering structured analysis a…
SP^2DPO: An LLM-assisted Semantic Per-Pair DPO Generalization
Chaoyue He, Xin Zhou, Di Wang +3
Direct Preference Optimization (DPO) controls the trade-off between fitting preference labels and staying close to a reference model using a single global temperature beta, implici…
ESGenius: Benchmarking LLMs on Environmental, Social, and Governance (ESG) and Sustainability Knowledge
Chaoyue He, Xin Zhou, Yi Wu +9
We introduce ESGenius, a comprehensive benchmark for evaluating and enhancing the proficiency of Large Language Models (LLMs) in Environmental, Social, and Governance (ESG) and sus…
MMESGBench: Pioneering Multimodal Understanding and Complex Reasoning Benchmark for ESG Tasks
Lei Zhang, Xin Zhou, Chaoyue He +5
Environmental, Social, and Governance (ESG) reports are essential for evaluating sustainability practices, ensuring regulatory compliance, and promoting financial transparency. How…