Conversational Image Search von Nie, Liqiang, Jiao, Fangkai, Wang, Wenjie, Wang, Yinglong, Tian, Qi

Volltext

UNK-VQA: A Dataset and a Probe Into the Abstention Ability of Multi-Modal Large Models von Guo, Yangyang, Jiao, Fangkai, Shen, Zhiqi, Nie, Liqiang, Kankanhalli, Mohan

Volltext

Enhanced Multi-Domain Dialogue State Tracker With Second-Order Slot Interactions von Jiao, Fangkai, Guo, Yangyang, Huang, Minlie, Nie, Liqiang

Volltext

The VLLM Safety Paradox: Dual Ease in Jailbreak Attack and Defense von Guo, Yangyang, Jiao, Fangkai, Nie, Liqiang, Kankanhalli, Mohan

Volltext bestellen

Describe-then-Reason: Improving Multimodal Mathematical Reasoning through Visual Comprehension Training von Jia, Mengzhao, Zhang, Zhihan, Yu, Wenhao, Jiao, Fangkai, Jiang, Meng

Volltext bestellen

UNK-VQA: A Dataset and a Probe into the Abstention Ability of Multi-modal Large Models von Guo, Yangyang, Jiao, Fangkai, Shen, Zhiqi, Nie, Liqiang, Kankanhalli, Mohan

Volltext bestellen

Panda LLM: Training Data and Evaluation for Open-Sourced Chinese Instruction-Following Large Language Models von Jiao, Fangkai, Ding, Bosheng, Luo, Tianze, Mo, Zhanfeng

Volltext bestellen

Preference Optimization for Reasoning with Pseudo Feedback von Jiao, Fangkai, Guo, Geyang, Zhang, Xingxing, Chen, Nancy F, Joty, Shafiq, Wei, Furu

Volltext bestellen

Can We Further Elicit Reasoning in LLMs? Critic-Guided Planning with Retrieval-Augmentation for Solving Challenging Tasks von Li, Xingxuan, Xu, Weiwen, Zhao, Ruochen, Jiao, Fangkai, Joty, Shafiq, Bing, Lidong

Volltext bestellen

Relevant or Random: Can LLMs Truly Perform Analogical Reasoning? von Qin, Chengwei, Xia, Wenhan, Wang, Tan, Jiao, Fangkai, Hu, Yuchen, Ding, Bosheng, Chen, Ruirui, Joty, Shafiq

Volltext bestellen

Learning Planning-based Reasoning by Trajectories Collection and Process Reward Synthesizing von Jiao, Fangkai, Qin, Chengwei, Liu, Zhengyuan, Chen, Nancy F, Joty, Shafiq

Volltext bestellen

Improving In-context Learning via Bidirectional Alignment von Qin, Chengwei, Xia, Wenhan, Jiao, Fangkai, Chen, Chen, Hu, Yuchen, Ding, Bosheng, Joty, Shafiq

Volltext bestellen

ChatGPT's One-year Anniversary: Are Open-Source Large Language Models Catching up? von Chen, Hailin, Jiao, Fangkai, Li, Xingxuan, Qin, Chengwei, Ravaut, Mathieu, Zhao, Ruochen, Xiong, Caiming, Joty, Shafiq

Volltext bestellen

MERIt: Meta-Path Guided Contrastive Learning for Logical Reasoning von Jiao, Fangkai, Guo, Yangyang, Song, Xuemeng, Nie, Liqiang

Volltext bestellen

SeaEval for Multilingual Foundation Models: From Cross-Lingual Alignment to Cultural Reasoning von Wang, Bin, Liu, Zhengyuan, Huang, Xin, Jiao, Fangkai, Ding, Yang, Aw, AiTi, Chen, Nancy F

Volltext bestellen

Exploring Self-supervised Logic-enhanced Training for Large Language Models von Jiao, Fangkai, Teng, Zhiyang, Ding, Bosheng, Liu, Zhengyuan, Chen, Nancy F, Joty, Shafiq

Volltext bestellen

How Much are Large Language Models Contaminated? A Comprehensive Survey and the LLMSanitize Library von Ravaut, Mathieu, Ding, Bosheng, Jiao, Fangkai, Chen, Hailin, Li, Xingxuan, Zhao, Ruochen, Qin, Chengwei, Xiong, Caiming, Joty, Shafiq

Volltext bestellen

The VLLM Safety Paradox: Dual Ease in Jailbreak Attack and Defense von Guo, Yangyang, Jiao, Fangkai, Nie, Liqiang, Kankanhalli, Mohan

Volltext

UNK-VQA: A Dataset and a Probe into the Abstention Ability of Multi-modal Large Models von Guo, Yangyang, Jiao, Fangkai, Shen, Zhiqi, Nie, Liqiang, Kankanhalli, Mohan

Volltext

Describe-then-Reason: Improving Multimodal Mathematical Reasoning through Visual Comprehension Training von Jia, Mengzhao, Zhang, Zhihan, Yu, Wenhao, Jiao, Fangkai, Jiang, Meng

Volltext