works on

From the 1 of 65 linked papers with an AI index.

activity
20242026
most citedLLM Agents for Education: Advances and Applications

7 citations · 7 across the 25 of their papers we have counts for

collaborators
Showing cs.CLShow all

28 papers · 1 filter

cs.CL2026

Should Missing Modalities Always Be Necessary to Repair for Multi-modal Sentiment Analysis?

Yubo Gao, Haotian Wu, Xiaoyu Xu +9

Existing methods for multimodal sentiment analysis (MSA) under missing modalities usually follow a repair-first paradigm. We revisit this assumption and ask: \emph{should every mis…

cs.CL2026

Thinking Economically: A Hierarchical Framework for Adaptive-Complexity Reasoning in LLMs

Yubo Gao, Haotian Wu, Hong Chen +8

Chain-of-Thought (CoT) has significantly enhanced LLM reasoning, yet often incurs substantial computational overhead due to "overthinking": generating excessively long rationales w…

cs.CL2026

Sculpting the Vector Space: Towards Efficient Multi-Vector Visual Document Retrieval via Prune-then-Merge Framework

Yibo Yan, Mingdong Ou, Yi Cao +5

Visual Document Retrieval (VDR), which aims to retrieve relevant pages within vast corpora of visually-rich documents, is of significance in current multimodal retrieval applicatio…

cs.CL2026

Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning

Yibo Yan, Shen Wang, Jiahao Huo +7

Scientific reasoning, the process through which humans apply logic, evidence, and critical thinking to explore and interpret scientific phenomena, is essential in advancing knowled…

cs.CL2026

ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detection

Yibo Yan, Shen Wang, Jiahao Huo +13

As the field of Multimodal Large Language Models (MLLMs) continues to evolve, their potential to revolutionize artificial intelligence is particularly promising, especially in addr…

cs.CL2026

CausalEmbed: Auto-Regressive Multi-Vector Generation in Latent Space for Visual Document Embedding

Jiahao Huo, Yu Huang, Yibo Yan +7

Although Multimodal Large Language Models (MLLMs) have shown remarkable potential in Visual Document Retrieval (VDR) through generating high-quality multi-vector embeddings, the su…