Large Multilingual Models Pivot Zero-Shot Multimodal Learning across Languages (2023 · 43 citations)
Most large multimodal systems for image understanding and image generation work well only in English. Other languages lack the huge image-text collections such training needs: BLIP-2 used over 100M pairs, and Stable Diffusion used over 2B. The authors propose MPM, a training paradigm that uses a multilingual LLM as a…
Quantifying the Impact of Structured Output Format on Large Language Models through Causal Inference (2026 · 2 citations)
Earlier studies disagree on whether forcing LLMs to answer in structured formats helps or hurts output quality.
CoAct: Co-Active LLM Preference Learning with Human-AI Synergy (2026 · 1 citation)
Preference-based alignment of LLMs depends on human-labelled response pairs, which are costly to collect. Self-rewarding pipelines produce such pairs cheaply, but they can amplify the model's own mistakes. Active preference learning keeps labels trustworthy, yet it leaves most of the unlabeled pool unused. CoAct…
Topology Matters: Measuring Memory Leakage in Multi-Agent LLMs (2026)
LLM agents increasingly work in teams that exchange messages over a communication graph. This paper asks how the shape of that graph affects how easily private data stored in one agent's memory can be extracted by a malicious teammate. The authors build MAMA (Multi-Agent Memory Attack), a controlled benchmark.

All works

5 works of theirs in our library, the most cited first; 4 with a page here, the others link their original until we summarise them.

Large Multilingual Models Pivot Zero-Shot Multimodal Learning across LanguagesarXiv:2308.12038Jinyi Hu, Yuan Yao, Chongyi Wang, et al.2023 · 43 citations
Quantifying the Impact of Structured Output Format on Large Language Models through Causal InferenceFindings of the Association for Computational LinguisticsHan Yuan, Yue Zhao, Li Zhang, et al.2026 · 2 citations
CoAct: Co-Active LLM Preference Learning with Human-AI SynergyAnnual Meeting of the Association for Computational Linguistics (ACL)Ruiyao Xu, Mihir Parmar, Tiankai Yang, et al.2026 · 1 citation
Topology Matters: Measuring Memory Leakage in Multi-Agent LLMsFindings of the Association for Computational LinguisticsJinbo Liu, Defu Cao, Yifei Wei, et al.2026
Self-EmoQ: Plutchik-Guided Value-based Planning to Drive Streaming Emotional TTS ↗Findings of the Association for Computational Linguistics: ACL 2026 · no summary yetYue Zhao et al.2026

Co-authors here

12 of 18 co-authors with a page, the most papers together first.

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 31 times (of the 149,439 papers whose bibliographies we read); 7 citing papers with a page here →.

Updated 1 November 2026