HL
Hongzhan Lin
cs.CLcs.AIcs.SDeess.AScs.CVcs.MMcs.LGcs.SEcs.CRcs.CY
On Valency
published · living versionsW_5mfbyv64·v1 · currentpublished
The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents
with Weidong Tang, Ruiheng Wang, Jingxuan Zhang, Hexin Wang +15
1 version
Preprints & journals
38 papers in the corpus · 2021–2026Which Speech Representation Better Matches Text-Native Reasoning? A Study of Speech-Text Alignment on Frame Rate and Representation2606.12199v1 · Zhen Ye, Xu Tan, Yiming Li et al.2026 · 0 citationsarXiv
Talker-T2AV: Joint Talking Audio-Video Generation with Autoregressive Diffusion Modeling2604.23586v2 · Zhen Ye, Xu Tan, Aoxiong Yin et al.2026 · 0 citationsarXiv
A Graph-Enhanced Defense Framework for Explainable Fake News Detection with LLM2604.06666v1 · Bo Wang, Jing Ma, Hongzhan Lin et al.2026 · 1 citationarXiv
Towards Comprehensive Stage-wise Benchmarking of Large Language Models in Fact-Checking2601.02669v1 · Hongzhan Lin, Zixin Chen, Zhiqi Shen et al.2026 · 0 citationsarXiv
Reconstructing KV Caches with Cross-layer Fusion For Enhanced Transformers2512.03870v3 · Hongzhan Lin, Zhiqi Bai, Xinmiao Zhang et al.2025 · 0 citationsarXiv
MM-CRITIC: A Holistic Evaluation of Large Multimodal Models as Multimodal Critique2511.09067v1 · Gailun Zeng, Ziyang Luo, Hongzhan Lin et al.2025 · 0 citationsarXiv
MemeArena: Automating Context-Aware Unbiased Evaluation of Harmfulness Understanding for Multimodal Large Language Models2510.27196v1 · Zixin Chen, Hongzhan Lin, Kaixin Li et al.2025 · 0 citationsarXiv
EvolProver: Advancing Automated Theorem Proving by Evolving Formalized Problems via Symmetry and Difficulty2510.00732v1 · Yuchen Tian, Ruiyuan Huang, Xuanwu Wang et al.2025 · 0 citationsarXiv
AdamMeme: Adaptively Probe the Reasoning Capacity of Multimodal Large Language Models on Harmfulness2507.01702v1 · Zixin Chen, Hongzhan Lin, Kaixin Li et al.2025 · 1 citationarXiv
ScreenSpot-Pro: GUI Grounding for Professional High-Resolution Computer Use2504.07981v1 · Kaixin Li, Ziyang Meng, Hongzhan Lin et al.2025 · 27 citationsarXiv
FACT-AUDIT: An Adaptive Multi-Agent Framework for Dynamic Fact-Checking Evaluation of Large Language Models2502.17924v2 · Hongzhan Lin, Yang Deng, Yuxuan Gu et al.2025 · 4 citationsarXiv
ProMedTS: A Self-Supervised, Prompt-Guided Multimodal Approach for Integrating Medical Text and Time Series2502.13509v2 · Shuai Niu, Jing Ma, Hongzhan Lin et al.2025 · 1 citationarXiv
LLM-Enhanced Multiple Instance Learning for Joint Rumor and Stance Detection with Social Context Information2502.08888v1 · Ruichao Yang, Jing Ma, Wei Gao et al.2025 · 9 citationsarXiv
Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis2502.04128v2 · Zhen Ye, Xinfa Zhu, Chi-Min Chan et al.2025 · 0 citationsarXiv
Meme Trojan: Backdoor Attacks Against Hateful Meme Detection via Cross-Modal Triggers2412.15503v1 · Ruofei Wang, Hongzhan Lin, Ziyuan Luo et al.2024 · 3 citationsarXiv
ClarityEthic: Explainable Moral Judgment Utilizing Contrastive Ethical Insights from Large Language Models2412.12848v2 · Yuxi Sun, Wei Gao, Jing Ma et al.2024 · 0 citationsarXiv
Knowledge-Augmented Multimodal Clinical Rationale Generation for Disease Diagnosis with Small Language Models2411.07611v5 · Shuai Niu, Jing Ma, Hongzhan Lin et al.2024 · 3 citationsThis paper is accpeted by ACL2025(Main)
Towards Low-Resource Harmful Meme Detection with LMM Agents2411.05383v1 · Jianzhao Huang, Hongzhan Lin, Ziyan Liu et al.2024 · 8 citationsarXiv
AMR-Evol: Adaptive Modular Response Evolution Elicits Better Knowledge Distillation for Large Language Models in Code Generation2410.00558v1 · Ziyang Luo, Xin Li, Hongzhan Lin et al.2024 · 1 citationarXiv
PEAR: Position-Embedding-Agnostic Attention Re-weighting Enhances Retrieval-Augmented Generation with Zero Inference Overhead2409.19745v2 · Tao Tan, Yining Qian, Ang Lv et al.2024 · 0 citationsarXiv
Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model2408.17175v3 · Zhen Ye, Peiwen Sun, Jiahe Lei et al.2024 · 20 citationsarXiv
CodeJudge-Eval: Can Large Language Models be Good Judges in Code Understanding?2408.10718v2 · Yuwei Zhao, Ziyang Luo, Yuchen Tian et al.2024 · 0 citationsarXiv
MFC-Bench: Benchmarking Multimodal Fact-Checking with Large Vision-Language Models2406.11288v3 · Shengkang Wang, Hongzhan Lin, Ziyang Luo et al.2024 · 0 citationsarXiv
Reinforcement Tuning for Detecting Stances and Debunking Rumors Jointly with Large Language Models2406.02143v1 · Ruichao Yang, Wei Gao, Jing Ma et al.2024 · 7 citationsarXiv
Explainable Fake News Detection With Large Language Model via Defense Among Competing Wisdom2405.03371v3 · Bo Wang, Jing Ma, Hongzhan Lin et al.2024 · 65 citationsarXiv
CofiPara: A Coarse-to-fine Paradigm for Multimodal Sarcasm Target Identification with Large Multimodal Models2405.00390v2 · Hongzhan Lin, Zixin Chen, Ziyang Luo et al.2024 · 14 citationsarXiv
Towards Explainable Harmful Meme Detection through Multimodal Debate between Large Language Models2401.13298v1 · Hongzhan Lin, Ziyang Luo, Wei Gao et al.2024 · 59 citationsThe ACM Web Conference 2024
GOAT-Bench: Safety Insights to Large Multimodal Models through Meme-Based Social Abuse2401.01523v4 · Hongzhan Lin, Ziyang Luo, Bo Wang et al.2024 · 15 citationsarXiv
Collaborative Synthesis of Patient Records through Multi-Visit Health State Inference2312.14646v1 · Hongda Sun, Hongzhan Lin, Rui Yan2023 · 4 citationsarXiv
Beneath the Surface: Unveiling Harmful Memes with Multimodal Reasoning Distilled from Large Language Models2312.05434v1 · Hongzhan Lin, Ziyang Luo, Jing Ma et al.2023 · 23 citationsThe 2023 Conference on Empirical Methods in Natural Language Processing
WSDMS: Debunk Fake News via Weakly Supervised Detection of Misinforming Sentences with Contextualized Social Wisdom2310.16579v1 · Ruichao Yang, Wei Gao, Jing Ma et al.2023 · 3 citationsThe 2023 Conference on Empirical Methods in Natural Language Processing
Dual-Scale Interest Extraction Framework with Self-Supervision for Sequential Recommendation2310.10025v1 · Liangliang Chen, Hongzhan Lin, Jinshan Ma et al.2023 · 0 citations26th European Conference on Artificial Intelligence ECAI 2023
A Unified Contrastive Transfer Framework with Propagation Structure for Boosting Low-Resource Rumor Detection2304.01492v5 · Hongzhan Lin, Jing Ma, Ruichao Yang et al.2023 · 2 citationsarXiv
Zero-Shot Rumor Detection with Propagation Structure via Prompt Learning2212.01117v5 · Hongzhan Lin, Pengyao Yi, Jing Ma et al.2022 · 57 citationsarXiv
A Coarse-to-fine Cascaded Evidence-Distillation Neural Network for Explainable Fake News Detection2209.14642v1 · Zhiwei Yang, Jing Ma, Hechang Chen et al.2022 · 16 citationsarXiv
Detect Rumors in Microblog Posts for Low-Resource Domains via Adversarial Contrastive Learning2204.08143v2 · Hongzhan Lin, Jing Ma, Liangliang Chen et al.2022 · 60 citations2022 Annual Conference of the North American Chapter of the Association for Computational Linguistics
A Weakly Supervised Propagation Model for Rumor Verification and Stance Detection with Multiple Instance Learning2204.02626v2 · Ruichao Yang, Jing Ma, Hongzhan Lin et al.2022 · 41 citationsarXiv
Rumor Detection on Twitter with Claim-Guided Hierarchical Graph Attention Networks2110.04522v2 · Hongzhan Lin, Jing Ma, Mingfei Cheng et al.2021 · 64 citationsarXiv
Career total: 49 works. 38 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.