Papers by Yibo Zhang

PhysicsArena: The First Multimodal Physics Reasoning Benchmark Exploring Variable, Process, and Solution Dimensions (2025.findings-emnlp)

Challenge:	Test-time computing approaches that leverage additional computational resources during inference have been proven effective in enhancing large language model performance.
Approach:	They propose a linearly scaling approach that leverages local consistency of neighboring unlabeled data to improve test-time predictions.
Outcome:	The proposed approach outperforms baseline methods such as prompting and self-consistency across eight datasets and performs robustly across embedding models.

Copied to clipboard

Song Dai, Yibo Yan, Jiamin Su, Zihao Dongfang, Yubo Gao, Yonghua Hei, Jungang Li, Junyan Zhang, Sicheng Tao, Zhuoran Gao, Xuming Hu

Reasoning

Challenge:	Current physics benchmarks focus on text-only inputs or only on problem-solving . current physics reasoning benchmarks neglect critical intermediate steps of variable identification and process formulation.
Approach:	a new benchmark evaluates multimodal large language models in physics reasoning . the benchmark measures variables, process formulations, and solution derivation .
Outcome:	PhysicsArena is the first multimodal physics reasoning benchmark . it evaluates MLLMs across three critical dimensions: variable identification, process formulation, and solution derivation.

LLMs Assist NLP Researchers: Critique Paper (Meta-)Reviewing (2024.emnlp-main)

Copied to clipboard

Jiangshu Du, Yibo Wang, Wenting Zhao, Zhongfen Deng, Shuaiqi Liu, Renze Lou, Henry Zou, Pranav Narayanan Venkit, Nan Zhang, Mukund Srinath, Haoran Zhang, Vipul Gupta, Yinghui Li, Tao Li, Fei Wang, Qin Liu, Tianlin Liu, Pengzhi Gao, Congying Xia, Chen Xing, Cheng Jiayang, Zhaowei Wang, Ying Su, Raj Shah, Ruohao Guo, Jing Gu, Haoran Li, Kangda Wei, Zihao Wang, Lu Cheng, Surangika Ranathunga, Meng Fang, Jie Fu, Fei Liu, Ruihong Huang, Eduardo Blanco, Yixin Cao, Rui Zhang, Philip Yu, Wenpeng Yin

Challenge:	a comparative analysis of paper (meta-)reviews by large language models (LLMs) aims to identify and distinguish LLMs from human activities .
Approach:	They present a comparative analysis to identify and distinguish LLM activities from human activities.
Outcome:	The proposed analysis aims to improve recognition of instances when someone implicitly uses LLMs for reviewing activities.

CodeArena: Evaluating and Aligning CodeLLMs on Human Preference (2025.emnlp-main)

Copied to clipboard

Jian Yang, Jiaxi Yang, Wei Zhang, Jin Ke, Yibo Miao, Lei Zhang, Liqun Yang, Zeyu Cui, Yichang Zhang, Zhoujun Li, Binyuan Hui, Junyang Lin

PositionID: LLMs can Control Lengths, Copy and Paste with Explicit Positional Awareness (2024.findings-emnlp)

Challenge:	Code large language models (codeLLMs) focus on synthesizing the correct code snippet, ignoring the alignment with human preferences.
Approach:	They propose a benchmark code-based on 40 categories and 44 programming languages to emulate real-world coding tasks.
Outcome:	The proposed benchmarks show that open-source code LLMs perform better than open-sourced ones.

Copied to clipboard

Noah Wang, Feiyu Duan, Yibo Zhang, Wangchunshu Zhou, Ke Xu, Wenhao Huang, Jie Fu

AdaMoE: Token-Adaptive Routing with Null Experts for Mixture-of-Experts Language Models (2024.findings-emnlp)

Challenge:	Large Language Models (LLMs) have impressive capabilities across various domains, including role-playing, creative writing, mathematical reasoning, and coding.
Approach:	They propose two methods to improve the model’s adherence to length constraints and copy-paste accuracy without compromising response quality.
Outcome:	The proposed methods improve the model’s adherence to length constraints and copy-paste accuracy without compromising response quality.

Copied to clipboard

Zihao Zeng, Yibo Miao, Hongcheng Gao, Hao Zhang, Zhijie Deng

D-Artemis: A Deliberative Cognitive Framework for Mobile GUI Multi-Agents (2026.findings-acl)

Challenge:	Existing MoE methods require a constant top-k routing for all tokens, which is restrictive because of the number of experts required for feature abstraction.
Approach:	They propose a token-adaptive routing method that allows different tokens to select a different number of experts.
Outcome:	a new method can reduce average expert load while achieving superior performance.

Copied to clipboard

Hongze Mi, Yibo Feng, WenJie Lu, Yuqi Wang, Jinyuan Li, Song Cao, He Cui, Tengfei Tian, Xuelin Zhang, Haotian Luo, Di Sun, Jun Fang, Hua Chai, Naiqiang Tan, Gang Pan

Challenge:	Graphical User Interface (GUI) agents aim to automate a wide spectrum of human tasks by emulating user interaction.
Approach:	They propose a deliberative framework that leverages a fine-grained tip retrieval mechanism to inform its decision-making process.
Outcome:	The proposed framework achieves SOTA among open-source general models on AndroidWorld and ScreenSpot-V2 . it leverages a fine-grained, app-specific tip retrieval mechanism to inform its decision-making process .

Can Public Large Language Models Help Private Cross-device Federated Learning? (2024.findings-naacl)

Copied to clipboard

Boxin Wang, Yibo Zhang, Yuan Cao, Bo Li, Hugh McMahan, Sewoong Oh, Zheng Xu, Manzil Zaheer

ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detection (2026.findings-acl)

Challenge:	Recent studies have shown that public data can be used to improve privacy-utility trade-offs for large and small language models.
Approach:	They propose to use large-scale public data to help differentially private FL training . they propose a distribution matching algorithm with theoretical grounding to sample public data close to private data distribution .
Outcome:	The proposed method is efficient and effective for training private models by taking advantage of public data.

Copied to clipboard

Yibo Yan, Shen Wang, Jiahao Huo, Hang Li, Boyan Li, Jiamin Su, Xiong Gao, YiFan Zhang, Tianlong Xu, Zhendong Chu, Aoxiao Zhong, Kun Wang, Hui Xiong, Philip S. Yu, Xuming Hu, Qingsong Wen

Reasoning

Challenge:	Current mathematical benchmarks focus on evaluating MLLMs’ problem-solving ability, yet there is a crucial gap in addressing more complex scenarios such as error detection.
Approach:	They propose to evaluate multimodal error detection by evaluating two sub-tasks error step identification and error categorization.
Outcome:	The proposed task evaluates MLLMs' ability to handle multimodal questions compared to text-only models.

RSA-Bench: Benchmarking Audio Large Models in Real-World Acoustic Scenarios (2026.findings-acl)

Copied to clipboard

Yibo Zhang, Kaiwen Luo, Liang Lin, Shilinlu Yan, Jin Wang, Yaoqi Guo, Yitian Chen, Yalan Qin, Zhenhong Zhou, Kun Wang, Li Sun

Unifying Language Agent Algorithms with Graph-based Orchestration Engine for Reproducible Agent Research (2025.acl-demo)

Challenge:	Existing evaluations rely on synthetic Gaussian noise or simplistic single-source interference, failing to capture the intricate, multi-layered acoustic dynamics that characterize authentic physical environments.
Approach:	They propose a robustness benchmark to stress-test Audio Large Models (ALLMs) using high-fidelity auditory scene simulations.
Outcome:	The proposed model performs well on a wide range of tasks, including automatic speech recognition, speech translation, and audio-based reasoning.

Copied to clipboard

Qianqian Zhang, Jiajia Liao, Heting Ying, Yibo Ma, Haozhan Shen, Jingcheng Li, Peng Liu, Lu Zhang, Chunxin Fang, Kyusong Lee, Ruochen Xu, Tiancheng Zhao

Measuring Bargaining Abilities of LLMs: A Benchmark and A Buyer-Enhancement Method (2024.findings-acl)

Challenge:	Language agents powered by large language models (LLMs) have demonstrated remarkable capabilities in understanding, reasoning, and executing complex tasks.
Approach:	They propose a flexible framework that addresses engineering overhead and insufficient evaluation frameworks for fair comparison.
Outcome:	The proposed framework simplifies language agent development and establishes a foundation for reproducible agent research.

Copied to clipboard

Tian Xia, Zhiwei He, Tong Ren, Yibo Miao, Zhuosheng Zhang, Yang Yang, Rui Wang

Challenge:	Using a novel approach, we can evaluate an agent’s bargaining abilities as an asymmetric incomplete information game.
Approach:	They propose an approach that integrates a deterministic Offer Generator and an LLM Narrator to create natural language sentences for generated offers.
Outcome:	The proposed approach improves the buyer’s deal rates from 26.67% to 88.88% and brings a ten times multiplication of profits on all baselines, even a model that has not been aligned.

EssayJudge: A Multi-Granular Benchmark for Assessing Automated Essay Scoring Capabilities of Multimodal Large Language Models (2025.findings-acl)

Copied to clipboard

Jiamin Su, Yibo Yan, Fangteng Fu, Zhang Han, Jingheng Ye, Xiang Liu, Jiahao Huo, Huiyu Zhou, Xuming Hu

SimpleOCR: Rendering Visual Questions to Teach MLLMs to Read (2026.findings-acl)

Challenge:	Automated Essay Scoring (AES) systems face three major challenges: reliance on handcrafted features that limit generalizability, difficulty in capturing fine-grained traits like coherence and argumentation, and inability to handle multimodal contexts.
Approach:	They propose a multimodal benchmark to evaluate AES capabilities across lexical-, sentence-, and discourse-level traits without manual feature engineering.
Outcome:	The proposed system can evaluate AES capabilities across lexical-, sentence-, and discourse-level traits without manual feature engineering.

Copied to clipboard

Yibo Peng, Peng Xia, Ding Zhong, Kaide Zeng, Siwei Han, Yiyang Zhou, Jiaqi Liu, Ruiyi Zhang, Huaxiu Yao

Visual Data in NLP

Challenge:	MLLMs lack visual grounding mechanism to read text embedded in images, or rely on parametric shortcuts . despite strong OCR capabilities, models suffer performance degradation of 12.7% in the VQ setting .
Approach:	They propose a plug-and-play training strategy that invalidates shortcuts in text prompts . they propose 'vq' setting where text queries are rendered directly onto images .
Outcome:	The proposed training strategy surpasses the base model by 5.4% and GRPO based on original images by 2.7% on four representative OOD benchmarks.

SEE: Signal Embedding Energy for Quantifying Noise Interference in Large Audio Language Models (2026.acl-long)

Copied to clipboard

Yuanhe Zhang, Jiayu Tian, Yibo Zhang, Shilinlu Yan, Liang Lin, Zhenhong Zhou, Li Sun, Sen Su

Thinking Economically: A Hierarchical Framework for Adaptive-Complexity Reasoning in LLMs (2026.findings-acl)

Challenge:	Existing studies on noise lack quantitative analysis and rely on intuition and empirical observation, thus failing to understand practical robustness.
Approach:	They propose a method for quantifying the impact of noise intensity on LALM inputs by using a structured activation subspace derived from the model's internal representations.
Outcome:	The proposed method outperforms existing denoising methods and demonstrates that noise is perceived more accurately than raw audio features.

Copied to clipboard

Yubo Gao, Haotian Wu, Hong Chen, Junquan Huang, Yibo Yan, Jungang Li, Zihao Dongfang, Sicheng Tao, PS Tan, Jie Zhang, Xuming Hu

Green & Sustainable NLP

Challenge:	Existing efficiency methods for Chain-of-Thought (CoT) generate excessively long rationales without commensurate accuracy gains.
Approach:	They propose a training framework that operationalizes this principle through coarse-to-fine budgeting.
Outcome:	Experiments on GSM8K and MATH500 show that HAB surpasses standard CoT in accuracy and reduces token usage, achieving stronger performance-efficiency trade-off than baselines.

A Survey of Large Language Models for Text-Guided Molecular Discovery: From Molecule Generation to Optimization (2026.acl-long)

Copied to clipboard

Ziqing Wang, Kexin Zhang, Zihan Zhao, Yibo Wen, Abhishek Pandey, Han Liu, Kaize Ding

Text Detoxification: Data Efficiency, Semantic Preservation and Model Generalization (2025.emnlp-main)

Challenge:	Large language models (LLMs) are introducing a paradigm shift in molecular discovery by enabling text-guided interaction with chemical spaces through natural language and symbolic notations.
Approach:	They analyze the current LLM learning paradigms to tackle four critical evaluation dimensions that have emerged as critical dimensions in recent studies.
Outcome:	The proposed models are able to interact with chemical spaces through natural language and symbolic notations, and have emerging extensions to incorporate multi-modal inputs.

Copied to clipboard

Jing Yu, Yibo Zhao, Jiapeng Zhu, Wenming Shao, Bo Pang, Zhao Zhang, Xiang Li

OmAgent: A Multi-modal Agent Framework for Complex Video Understanding with Task Divide-and-Conquer (2024.emnlp-main)

Challenge:	Existing methods for detoxification of text often rely on manually annotated data . xiangli: "detoxification of texts is a powerful way to remove toxic content"
Approach:	They propose a reinforcement learning framework that optimizes detoxification and semantic preservation without annotating large amounts of data.
Outcome:	The proposed method overcomes major limitations and surpasses humanannotated references across multiple benchmarks.

Copied to clipboard

Lu Zhang, Tiancheng Zhao, Heting Ying, Yibo Ma, Kyusong Lee

Robustness in NLP

Challenge:	Large Language Models (LLMs) have expanded their capabilities to multimodal contexts, including comprehensive video understanding.
Approach:	They propose to store and retrieve relevant video frames for specific queries and a Divide-and-Conquer loop capable of autonomous reasoning.
Outcome:	The proposed model efficiently stores and retrieves relevant video frames for specific queries, preserving the detailed content of videos.

UORA: Uniform Orthogonal Reinitialization Adaptation in Parameter Efficient Fine-Tuning of Large Models (2025.acl-long)

Copied to clipboard

Xueyan Zhang, Jinman Zhao, Zhifei Yang, Yibo Zhong, Shuhao Guan, Linbo Cao, Yining Wang

TextFusion: Privacy-Preserving Pre-trained Model Inference via Token Fusion (2022.emnlp-main)

Challenge:	Existing methods such as LoRA and VeRA use a low-rank approximation method that reduces the number of trainable parameters without compromising performance.
Approach:	They propose a parameter-efficient fine-tuning approach that leverages a low-rank approximation method that reduces the number of trainable parameters without compromising performance.
Outcome:	The proposed approach outperforms existing methods on GLUE and E2E benchmarks and is effective in instruction-tuning large language models and image classification models.

Copied to clipboard

Xin Zhou, Jinzhu Lu, Tao Gui, Ruotian Ma, Zichu Fei, Yuran Wang, Yong Ding, Yibo Cheung, Qi Zhang, Xuanjing Huang

MIO: A Foundation Model on Multimodal Tokens (2025.emnlp-main)

Challenge:	Existing methods to preserve inference privacy are available as cloud services . however, the risk of privacy leakage remains, according to recent studies .
Approach:	They propose a method to preserve inference privacy by fusing token representations in the cloud.
Outcome:	The proposed method preserves inference privacy without sacrificing performance on different scenarios.

Copied to clipboard

Zekun Moore Wang, King Zhu, Chunpu Xu, Wangchunshu Zhou, Jiaheng Liu, Yibo Zhang, Jessie Wang, Ning Shi, Siyu Li, Yizhi Li, Haoran Que, Zhaoxiang Zhang, Yuanxing Zhang, Ge Zhang, Ke Xu, Jie Fu, Wenhao Huang

Detecting AI-Generated Content on Social Media with Multi-modal Language Models (2026.acl-industry)

Challenge:	Existing models lack multimodal understanding capabilities, resulting in closed-source model that does not support multimodal interleaved sequences.
Approach:	They propose a foundation model built on multimodal tokens capable of understanding and generating speech, text, images, and videos in an end-to-end, autoregressive manner.
Outcome:	The proposed model is able to understand speech, text, images, and videos in an end-to-end, autoregressive manner.

Copied to clipboard

Chenyang Yang, Shen Yan, Yibo Yang, Litao Hu, Yuchen Liu, Yuan Zeng, Hanchao Yu, Yinan Zhu, Sumedha Singla, Brian Vanover, Huijun Qian, Zihao Wang, Fujun Liu, Aashu Singh, Jianyu Wang, Xuewen Zhang

Qwen2.5-xCoder: Multi-Agent Collaboration for Multilingual Code Instruction Tuning (2025.acl-long)

Challenge:	Existing methods for AI-generated content detection face poor generalization to newer models, reliance on single modalities, and lack of interpretable explanations.
Approach:	They propose a model that curates diverse social media data and trains a vision-language model for detection and explanation.
Outcome:	The proposed model achieves state-of-the-art detection performance on public benchmarks and observes positive downstream impacts on user engagement.

Copied to clipboard

Jian Yang, Wei Zhang, Yibo Miao, Shanghaoran Quan, Zhenhe Wu, Qiyao Peng, Liqun Yang, Tianyu Liu, Zeyu Cui, Binyuan Hui, Junyang Lin

Inference Compute-Optimal Video Vision Language Models (2025.acl-long)

Challenge:	Existing methods to train code LLMs view each programming language in isolation . experimental results show that Qwen2.5-xCoder can bridge the gap between different programming languages .
Approach:	They propose a framework that allows agents to collaborate to enhance multilingual instruction tuning for code LLMs.
Outcome:	Experimental results show that Qwen2.5-xCoder can transfer knowledge efficiently and effectively between languages.

Copied to clipboard

Peiqi Wang, ShengYun Peng, Xuewen Zhang, Hanchao Yu, Yibo Yang, Lifu Huang, Fujun Liu, Qifan Wang

Visual Data in NLP

Challenge:	Using video vision language models, inference costs are often more expensive than finetuning.
Approach:	They investigate the optimal allocation of inference compute across three key scaling factors in video vision language models.
Outcome:	The proposed model configurations are based on three key scaling factors . the results can be applied to real-world tasks and tasks with fixed inference budgets.

Unlocking Speech Instruction Data Potential with Query Rewriting (2025.findings-acl)

Copied to clipboard

Yonghua Hei, Yibo Yan, Shuliang Liu, Huiyu Zhou, Linfeng Zhang, Xuming Hu

Text Generation

Challenge:	Existing LLMs lack datasets and biased training tasks to follow speech instructions.
Approach:	They propose a query rewriting framework that uses multiple agents to annotate and validate the synthesized speech.
Outcome:	The proposed framework can transform text instructions into distributions more suitable for TTS models for speech synthesis without human annotation.

Learning to Collaborate for Question Answering and Asking (N18-1)

Copied to clipboard

Duyu Tang, Nan Duan, Zhao Yan, Zhirui Zhang, Yibo Sun, Shujie Liu, Yuanhua Lv, Ming Zhou

Natural Language Interfaces

Challenge:	Question answering (QA) and question generation (QG) are closely related tasks.
Approach:	They propose a training algorithm that generalizes both Generative Adversarial Network and Generating Domain-Adaptive Nets under the question answering scenario.
Outcome:	The proposed training algorithm generalizes both Generative Adversarial Network (GAN) and Generating Domain-Adaptive Nets (GDAN) under the question answering scenario.

Efficient Detection of LLM-generated Texts with a Bayesian Surrogate Model (2024.findings-acl)

Copied to clipboard

Yibo Miao, Hongcheng Gao, Hao Zhang, Zhijie Deng

From Bottom to Top: Extending the Potential of Parameter Efficient Fine-Tuning (2024.emnlp-main)

Challenge:	Large language models can be used to produce text that is coherent, well-written, and persuasive . some individuals have misused LLMs for nefarious purposes, such as creating fake news articles or engaging in cheating .
Approach:	They propose to incorporate a Bayesian surrogate model to improve query efficiency . they propose to select typical samples based on Bayes' uncertainty and interpolate scores .
Outcome:	The proposed method significantly outperforms existing approaches under a low query budget.

Copied to clipboard

Jihao Gu, Zelin Wang, Yibo Zhang, Ziji Zhang, Ping Gong

Scaling Law for Multimodal Large Language Model Supervised Fine-Tuning (2026.acl-long)

Challenge:	Existing methods to fine-tune large language models primarily focus on the interaction between different layers, ignoring the fact that different layers store different information.
Approach:	They propose a Parameter Efficient Fine-Tuning method which freeze pre-trained parameters and fine-tunes only a few task-specific parameters.
Outcome:	The proposed methods reduce parameter count to nearly half by omitting fine-tuning in the middle layers.

Copied to clipboard

YiFan Zhang, Tao Yu, Feng Li, Chaoyou Fu, Yibo Hu, Kun Wang, Qingsong Wen, Zhang Zhang, Liang Wang, Rong Jin

TextObfuscator: Making Pre-trained Language Model a Privacy Protector via Obfuscating Word Representations (2023.findings-acl)

Challenge:	supervised fine-tuning (SFT) is crucial for multimodal large language models, yet a comprehensive scaling law is lacking . et al.: scaling laws focus on model size, pre-training tokens, and MLLM SFT data volumes .
Approach:	They propose two scaling laws to guide optimal model-data configuration . they propose one applicable when training data volumes are well defined by researchers .
Outcome:	The proposed scaling laws provide valuable recommendations for optimal resource allocation . they show that the proposed laws are more accurate than existing models .

Copied to clipboard

Xin Zhou, Yi Lu, Ruotian Ma, Tao Gui, Yuran Wang, Yong Ding, Yibo Zhang, Qi Zhang, Xuanjing Huang

Unlocking the Black Box of Latent Reasoning: An Interpretability-Guided Approach to Intervention (2026.acl-long)

Challenge:	Existing inference services are plagued by privacy concerns, such as sharing sensitive data with service providers.
Approach:	They propose a framework for protecting inference privacy by applying random perturbations to clustered representations.
Outcome:	The proposed framework protects inference privacy by applying random perturbations to clustered representations.

Copied to clipboard

Shuochen Chang, Tong Bai, Xiaofeng Zhang, Qianli Ma, Qingyang Liu, Zhaohe Liao, Yibo Miao, Li Niu