Papers by Zheng Cai

Look Twice before You Leap: A Rational Framework for Localized Adversarial Text Anonymization (2026.findings-acl)

Challenge:	Existing datasets are too challenging for direct model learning or suffer from misalignment between text and images.
Approach:	They propose a pipeline that leverages GPT-4 and GPT4V to generate geometry problems with aligned text and images, facilitating model learning.
Outcome:	The proposed pipeline generates 4.9K geometry problems with aligned text and images, facilitating model learning.

Copied to clipboard

Donghang Duan, Xu Zheng, Yuefeng He, Chong Mu, Leyi Cai, Lizong Zhang

ReCon: Active Defense against Large Vision-Language Model Jailbreaks via Reverse Safety Concept Injection (2026.findings-acl)

Challenge:	Existing LLMs rely on remote API services, which creates privacy paradoxes and suboptimal solutions with severe utility collapse.
Approach:	They propose a localized and training-free framework with an Attacker-Arbitrator-Anonymizer architecture that allows attackers to filter out ghost leaks.
Outcome:	The proposed framework achieves superior privacy-utility trade-off compared to strong baselines.

Copied to clipboard

Zheng He, Yiwei Wang, Hongxing Wang, Yujun Cai

SimGRAG: Leveraging Similar Subgraphs for Knowledge Graphs Driven Retrieval-Augmented Generation (2025.findings-acl)

Challenge:	Existing defense strategies neglect visual threats and lack of fine-grained specificity regarding specific attack semantics.
Approach:	They propose a black-box defense framework that maps unsafe concepts to fine-grained, constructive Safe Concepts.
Outcome:	a new black-box defense framework enhances robustness against jailbreak attacks . it maps detected unsafe concepts to fine-grained, constructive Safe Concepts . the proposed framework is available for free at http://www.epa.org/recon/ .

Copied to clipboard

Yuzheng Cai, Zhenyue Guo, YiWen Pei, WanRui Bian, Weiguo Zheng

ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch (2026.acl-long)

Challenge:	Recent advances in large language models (LLMs) have shown impressive versatility across various tasks.
Approach:	They propose a retrieval-augmented generation method that integrates LLMs with external knowledge sources to produce grounded outputs.
Outcome:	The proposed method outperforms state-of-the-art KG-driven methods in question answering and fact verification.

Copied to clipboard

Zheng Liu, Honglin Lin, Xiaoyang Wang, Xin Gao, Yu Li, Mengzhang Cai, Yun Zhu, Zhanping Zhong, Qizhi Pei, Zhuoshi Pan, Xiaoran Shang, Conghui He, Bin Cui, Wentao Zhang, Lijun Wu

Spatial AMR: Expanded Spatial Annotation in the Context of a Grounded Minecraft Corpus (2020.lrec-1)

Challenge:	Existing open-source vision language models lack high-quality training data for chart reasoning . current models are simplistic and repetitive, while associated QA pairs are prone to hallucinations .
Approach:	They propose a framework to synthesize complex charts and reliable reasoning data from scratch.
Outcome:	Experimental results show that ChartVerse-8B surpasses existing models in QA and difficulty . lack of high-quality training data hampers development of open-source models .

Copied to clipboard

Julia Bonn, Martha Palmer, Zheng Cai, Kristin Wright-Bettner

A Boundary-aware Neural Model for Nested Named Entity Recognition (D19-1)

Challenge:	Existing annotation tools for spatial relations capture fine-grained semantics and pragmatics derived from spatial information.
Approach:	They propose an extension to the Abstract Meaning Representation annotation schema that captures fine-grained spatial information in grounded corpora.
Outcome:	The proposed tool can handle fine-grained spatial relationships grounded in quantized space.

Copied to clipboard

Changmeng Zheng, Yi Cai, Jingyun Xu, Ho-fung Leung, Guandong Xu

Information Extraction & Text Mining

Challenge:	Existing methods for named entity recognition ignore nested entities . a boundary-aware neural model can locate entities precisely by detecting boundaries .
Approach:	They propose a boundary-aware neural model for nested named entity recognition which leverages entity boundaries to predict entity categorical labels.
Outcome:	The proposed model outperforms state-of-the-art methods on GENIA dataset . it captures dependencies of entity boundaries and categorical labels, which helps to improve identifying entities.

SciAssess: Benchmarking LLM Proficiency in Scientific Literature Analysis (2025.findings-naacl)

Copied to clipboard

Hengxing Cai, Xiaochen Cai, Junhan Chang, Sihang Li, Lin Yao, Wang Changxin, Zhifeng Gao, Hongshuai Wang, Li Yongge, Mujie Lin, Shuwen Yang, Jiankun Wang, Mingjun Xu, Jin Huang, Xi Fang, Jiaxi Zhuang, Yuqi Yin, Yaqi Li, Changhong Chen, Zheng Cheng, Zifeng Zhao, Linfeng Zhang, Guolin Ke

Challenge:	Existing benchmarks fail to adequately evaluate the proficiency of Large Language Models (LLMs) Existing standards do not cover the skills needed to evaluate LLMs in scientific literature analysis.
Approach:	They propose a benchmark to evaluate the proficiency of large language models in scientific literature analysis.
Outcome:	SciAssess evaluates 11 LLMs on multiple tasks across scientific fields.

Improving Empathetic Dialogue Generation by Dynamically Infusing Commonsense Knowledge (2023.findings-acl)

Copied to clipboard

Hua Cai, Xuli Shen, Qing Xu, Weilin Shen, Xiaomei Wang, Weifeng Ge, Xiaoqing Zheng, Xiangyang Xue

Dialogue Systems & Conversational Agents

Challenge:	Existing work on generating empathetic responses by utilizing the speaker's emotion has not been successful.
Approach:	They propose an approach which incorporates an adaptive module for commonsense knowledge selection to ensure consistency between the generated empathetic responses and the speaker’s situation.
Outcome:	The proposed approach outperforms baseline models in both automatic and human evaluations, exhibiting the generation of more coherent and empathetic responses.

Heterogeneous Adaptive Policy Optimization: Tailoring Optimization to Every Token’s Nature (2026.acl-long)

Copied to clipboard

Zheng Liu, Mengjie Liu, Siwei Wen, Mengzhang Cai, Bin Cui, Conghui He, Wentao Zhang

LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language Feedback (2025.findings-acl)

Challenge:	Existing methods that use entropy as a discrete filter or post-hoc regulator are limited in their ability to optimize for reasoning tasks.
Approach:	They propose a token-aware algorithm that continuously adapts optimization dynamics based on token-level entropy throughout the entire training process.
Outcome:	Extensive experiments on mathematical reasoning, code, and logic tasks across multiple models demonstrate HAPO’s consistent superiority over DAPO.

Copied to clipboard

Bofei Gao, Zefan Cai, Runxin Xu, Peiyi Wang, Ce Zheng, Runji Lin, Keming Lu, Dayiheng Liu, Chang Zhou, Wen Xiao, Tianyu Liu, Baobao Chang

Can LLMs Learn From Mistakes? An Empirical Study on Reasoning Tasks (2024.findings-emnlp)

Challenge:	Existing mathematical verifiers are trained with binary classification labels, which are not informative enough for the model to accurately assess the solutions.
Approach:	They propose a natural language feedback-enhanced verifier that can validate the correctness of response generated by policy models by constructing automatically generated training data and a two-stage training paradigm.
Outcome:	The proposed verifier significantly improves in verification and reinforcement learning and alleviates data-demanding problems of the reward model.

Copied to clipboard

Shengnan An, Zexiong Ma, Siqi Cai, Zeqi Lin, Nanning Zheng, Jian-Guang Lou, Weizhu Chen

Empowering Large Language Model for Continual Video Question Answering with Collaborative Prompting (2024.emnlp-main)

Challenge:	Existing work has shown that simple learning can enhance the chain-of-thought (CoT) reasoning of large language models.
Approach:	They construct mistake-correction datasets to identify and correct mistakes in CoTs . they conclude that LLMs can learn from mistakes to enhance their CoT reasoning .
Outcome:	The proposed datasets show that LLMs can learn from mistakes to enhance their CoT reasoning performance.

Copied to clipboard

Chen Cai, Zheng Wang, Jianjun Gao, Wenyang Liu, Ye Lu, Runzhong Zhang, Kim-Hui Yap

Multi-Programming Language Sandbox for LLMs (2025.acl-demo)

Challenge:	Existing VideoQA models struggle to adapt to new questions or tasks posed by newly available content.
Approach:	They propose a continual learning framework that fine-tunes a large language model for a sequence of tasks and integrates specific question constraint prompting, knowledge acquisition prompting and visual temporal awareness prompting.
Outcome:	The proposed model achieves 55.14% accuracy on both NExT-QA and DramaQA datasets and 71.24% accuracy for DramaQA.

Copied to clipboard

Shihan Dou, Jiazheng Zhang, Jianxiang Zang, Yunbo Tao, Weikang Zhou, Haoxiang Jia, Shichun Liu, Yuming Yang, Shenxi Wu, Zhiheng Xi, Muling Wu, Rui Zheng, Changze Lv, Limao Xiong, Shaoqing Zhang, Lin Zhang, Wenyu Zhan, Rongxiang Weng, Jingang Wang, Xunliang Cai, Yueming Wu, Ming Wen, Yixin Cao, Tao Gui, Xipeng Qiu, Qi Zhang, Xuanjing Huang

STAR: SQL Guided Pre-Training for Context-dependent Text-to-SQL Parsing (2022.findings-emnlp)

Challenge:	MPLSandbox is an out-of-the-box multi-programming language sandbox designed to provide unified and comprehensive feedback from compiler and analysis tools for Large Language Models (LLMs).
Approach:	They propose a multi-programming language sandbox that provides unified feedback from compilers and analysis tools for Large Language Models.
Outcome:	The proposed multi-language sandbox can provide comprehensive feedback from compilers and analysis tools for large language models (LLMs).

Copied to clipboard

Zefeng Cai, Xiangyu Li, Binyuan Hui, Min Yang, Bowen Li, Binhua Li, Zheng Cao, Weijie Li, Fei Huang, Luo Si, Yongbin Li

Programming Languages in NLP

Challenge:	Extensive experiments show that STAR outperforms previous pre-training methods and ranks first on the leaderboard . text-to-SQL parsing aims to translate natural language (NL) questions into executable SQL queries .
Approach:	They propose a SQL guided pre-training framework STAR for context-dependent text-to-SQL parsing . they propose two objectives that explore context-dependence of NL utterances and SQL queries .
Outcome:	The proposed framework outperforms existing methods on two downstream benchmarks and ranks first on the leaderboard.

Not All Contexts Are Equal: Teaching LLMs Credibility-aware Generation (2024.emnlp-main)

Copied to clipboard

Ruotong Pan, Boxi Cao, Hongyu Lin, Xianpei Han, Jia Zheng, Sirui Wang, Xunliang Cai, Le Sun

Information Retrieval

Challenge:	Existing RAG paradigms suffer from the impact of flawed information introduced during the retrieval phrase, thereby diminishing the reliability and correctness of the generated output.
Approach:	They propose a framework that empowers models to discern and process information based on its credibility.
Outcome:	The proposed framework outperforms existing models with retrieval augmentation and exhibits robustness despite increasing noise in the context.

From Spatial Relations to Spatial Configurations (2020.lrec-1)

Copied to clipboard

Soham Dan, Parisa Kordjamshidi, Julia Bonn, Archna Bhatia, Zheng Cai, Martha Palmer, Dan Roth

Towards Near-imperceptible Steganographic Text (P19-1)

Challenge:	Existing spatial representations are not sufficient for describing complex spatial configurations.
Approach:	They propose to integrate existing spatial representation languages with an annotation schema to extend the capabilities of existing ones.
Outcome:	The proposed language can represent a large set of spatial concepts crucial for reasoning . it integrates with the Abstract Meaning Representation (AMR) annotation schema and annotates text from diverse datasets .

Copied to clipboard

Falcon Dai, Zheng Cai

DRK: Discriminative Rule-based Knowledge for Relieving Prediction Confusions in Few-shot Relation Extraction (2022.coling-1)

Challenge:	Existing methods for linguistic steganography are vulnerable to automated detection.
Approach:	They propose an encoding algorithm with improved near-imperceptible guarantees based on implicit assumptions on statistical behaviors of fluent text.
Outcome:	The proposed algorithm improves on existing steganographic systems with near-imperceptible guarantees.

Copied to clipboard

Mengru Wang, Jianming Zheng, Fei Cai, Taihua Shao, Honghui Chen

DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments (2025.emnlp-main)

Challenge:	Existing methods to identify relation type in low-resource scenario fall into prediction confusions owing to the limited inference ability over shallow text features.
Approach:	They propose a discriminative rule-based knowledge method to identify the relation type between entities in a given text in the low-resource scenario.
Outcome:	The proposed method improves on four types of meta tasks with a 6.0% accuracy gain on average.

Copied to clipboard

Yuxiang Zheng, Dayuan Fu, Xiangkun Hu, Xiaojie Cai, Lyumanshan Ye, Pengrui Lu, Pengfei Liu

MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning (2026.acl-long)

Challenge:	Large Language Models (LLMs) with web search capabilities show significant potential for deep research.
Approach:	They introduce a framework for end-to-end training of LLM-based deep research agents . they implement a specialized multi-agent architecture where browsing agents extract relevant information from various webpage structures.
Outcome:	The proposed framework improves on open-domain research tasks by 28.9 points over prompt engineering and 7.2 points over RAG-based RL agents.

Copied to clipboard

Xiaoliang Fu, Jiaye Lin, Yangyi Fang, Binbin Zheng, Chaowen Hu, Zekai Shao, Cong Qin, Lu Pan, Ke Zeng, Xunliang Cai

SWE-QA-Pro: A Representative Benchmark and Scalable Training Recipe for Repository-Level Code Understanding (2026.findings-acl)

Challenge:	Existing RLVR algorithms rely on rigid, uniform, and symmetric trust region mechanisms . current algorithms lack robustness, asymmetric signal reliability and inefficient gradient utilization .
Approach:	They propose a framework to harmonize three dimensions of RLVR algorithms, a paper argues . a binary cutoff is used to discard valuable reinforcement signals, they argue .
Outcome:	The proposed framework outperforms baselines in evaluating a robust RLVR solution.

Copied to clipboard

Songcheng Cai, Zhiheng Lyu, Yuansheng Ni, Xiangchao Chen, Baichuan Zhou, Shenzhe Zhu, Yi Lu, Haozhe Wang, Chi Ruan, Benjamin Schneider, Weixu Zhang, Xiang Li, Andy Zheng, Yuyu Zhang, Ping Nie, Wenhu Chen

AMoPO: Adaptive Multi-objective Preference Optimization without Reward Models and Reference Models (2025.findings-acl)

Challenge:	Existing benchmarks for agentic repository-level code understanding overlook long tail topics and rely on memorized knowledge.
Approach:	They propose a repository-level agentic code understanding benchmark that uses long-tail repositories with executable environments to enforce topical balance.
Outcome:	Empirically, a Qwen3-8B model trained with the proposed benchmark outperforms GPT-4o by 2.3 points.

Copied to clipboard

Qi Liu, Jingqing Ruan, Hao Li, Haodong Zhao, Desheng Wang, Jiansong Chen, Wan Guanglu, Xunliang Cai, Zhi Zheng, Tong Xu

Heterogeneous Graph Neural Networks to Predict What Happen Next (2020.coling-main)

Challenge:	Existing multi-objective preference alignment methods for large language models face limitations such as auxiliary reward/reference models and computational complexity.
Approach:	They propose a framework that achieves dynamic balance across preference dimensions by using dimension-aware generation metrics as implicit rewards.
Outcome:	Empirical results show that AMoPO outperforms state-of-the-art methods by 28.5% .

Copied to clipboard

Jianming Zheng, Fei Cai, Yanxiang Ling, Honghui Chen

Structured Data in NLP

Challenge:	Existing work on event representation cannot capture discontinuous event segments . Existing models cannot represent heterogeneous relations and discontinuous events .
Approach:	They propose a heterogeneous-event graph network to model missing events . they employ each unique word and individual event as nodes in the graph .
Outcome:	The proposed model outperforms baseline models on one-step and multi-step inference tasks.

Reverse Chain: A Generic-Rule for LLMs to Master Multi-API Planning (2024.findings-naacl)

Copied to clipboard

Yinger Zhang, Hui Cai, Xierui Song, Yicheng Chen, Rui Sun, Jing Zheng

The World is Not Binary: Learning to Rank with Grayscale Data for Dialogue Response Selection (2020.emnlp-main)

Challenge:	Existing approaches to enable large language models to implement function calling are limited in their tool-use capabilities.
Approach:	They propose a controllable, target-driven approach to empower LLMs to operate external APIs only via prompts.
Outcome:	The proposed approach limits LLMs to executing simple tasks, e.g., API Selection and Argument Completion.

Copied to clipboard

Zibo Lin, Deng Cai, Yan Wang, Xiaojiang Liu, Haitao Zheng, Shuming Shi

Information Retrieval

Challenge:	Existing approaches to learning-to-rank response selection are suboptimal due to ignorance of diversity of response quality.
Approach:	They propose to use off-the-shelf response retrieval models as automatic grayscale data generators to train response selection models.
Outcome:	The proposed approach can be automated without human effort on grayscale data.

Aligned Dual Channel Graph Convolutional Network for Visual Question Answering (2020.acl-main)

Copied to clipboard

Qingbao Huang, Jielong Wei, Yi Cai, Changmeng Zheng, Junying Chen, Ho-fung Leung, Qing Li

SegTune: Structured and Fine-Grained Control for Song Generation (2026.acl-long)

Challenge:	Existing graph-based methods focus only on relations between objects in an image and neglect the importance of syntactic dependency relations between words.
Approach:	They propose a dual channel graph convolutional network to capture relations between objects in an image and syntactic dependency relations between words in a question.
Outcome:	The proposed model achieves comparable performance with the state-of-the-art approaches.

Copied to clipboard

Yuejiao Wang, Zihao Ji, Pengfei Cai, Xu Li, Haorui Zheng, Zewen Song, Zhongliang Liu, Chen Zhang, Pengfei Wan

FanChuan: A Multilingual and Graph-Structured Benchmark For Parody Detection and Analysis (2025.findings-acl)

Challenge:	Recent advances in neural song generation have enabled high-quality synthesis from lyrics and global textual prompts.
Approach:	They propose a framework that allows users to specify local musical descriptions aligned to song segments.
Outcome:	The proposed framework outperforms baselines in musicality and controllability.

Copied to clipboard

Yilun Zheng, Sha Li, Fangkun Wu, Yang Ziyi, Lin Hongchao, Zhichao Hu, Cai Xinjun, Ziming Wang, Jinxuan Chen, Sitao Luan, Jiahao Xu, Lihui Chen

Can Multimodal LLMs See Materials Clearly? A Multimodal Benchmark on Materials Characterization (2025.findings-emnlp)

Challenge:	Parody is an emerging phenomenon on social media, where individuals imitate a role or position opposite to their own . limited available data and deficient diversity in current datasets hinder study of parody .
Approach:	They build a dataset of parody users and annotated comments from both English and Chinese corpora to test parody detection and comment sentiment analysis.
Outcome:	The proposed datasets provide richer contextual information, which is lacking in existing datasets.

Copied to clipboard

Zhengzhao Lai, Youbin Zheng, Zhenyang Cai, Haonan Lyu, Jingpu Yang, Hong-Qing Liang, Yan Hu, Benyou Wang

COIG-P: A High-Quality and Large-Scale Chinese Preference Dataset for Alignment with Human Values (2026.findings-eacl)

Challenge:	characterization imaging data is fundamental to acquiring materials information.
Approach:	a team of researchers develop a benchmark for materials characterization imaging data . the goal is to bridge this gap by addressing 1,500 questions that require expert-level expertise.
Outcome:	a new benchmark for materials characterization imaging data is presented . the benchmark reveals that MLLMs perform poorly when addressing higher-level questions .

Copied to clipboard

Siwei Wu, JinCheng Ren, Xeron Du, Shuyue Guo, Xingwei Qu, Yiming Liang, Jie Liu, Yunwen Li, Tyler Loakman, Tianyu Zheng, Boyu Feng, Huaqing Yuan, Zili Wang, Jiaheng Liu, Wenhao Huang, Chenglin Cai, Haoran Que, Jian Yang, Yuelin Bai, Zekun Moore Wang, Zhouliang Yu, Qunshu Lin, Ding Pan, Yuchen Eleanor Jiang, Tiannan Wang, Wangchunshu Zhou, Shenzhi Wang, Xingyuan Bu, Minghao Liu, Guoyin Wang, Ge Zhang, Chenghua Lin

MavenCoder: Competitive Code Generation via Model Adaptive Planning Strategies and Multi-Perspective Verification Enhancement (2026.acl-long)

Challenge:	Existing Chinese preference datasets suffer from limited scale, restricted domain coverage, and insufficiently rigorous data validation.
Approach:	They propose an LLM-based data annotation pipeline with no human intervention to annotate Chinese preference datasets.
Outcome:	The proposed pipeline outperforms existing Chinese preference datasets on AlignBench and Chinese Reward Benchmark.

Copied to clipboard

ZhenChun Xu, Yi Cai, Dajun Zheng, li Yuan, Mengchen Zhao, Qixiang Wang, Jiexin Wang

Programming Languages in NLP

Challenge:	Recent advances in large language models (LLMs) have significantly enhanced automated program synthesis.
Approach:	They propose a model-adaptive and verification–enhanced framework for competition-level code generation that leverages adaptive assessment aligned with the model’s capabilities to select planning strategies while providing timely feedback and correction via multi-perspective verification.
Outcome:	The proposed framework outperforms existing state-of-the-art approaches on livecodebench, humanEval+, MBPP+, and codecontests, and achieves pass@1 results exceeding 3%–40%.

ELBA-Bench: An Efficient Learning Backdoor Attacks Benchmark for Large Language Models (2025.acl-long)

Copied to clipboard

Xuxu Liu, Siyuan Liang, Mengya Han, Yong Luo, Aishan Liu, Xiantao Cai, Zheng He, Dacheng Tao

Many Faces of Feature Importance: Comparing Built-in and Post-hoc Feature Importance in Text Classification (D19-1)

Challenge:	Existing backdoor models are limited in coverage of attack, system integrity and backdoor alignment . ELBA-Bench provides over 1300 experiments encompassing 12 attack methods, 18 datasets, and 12 LLMs.
Approach:	They propose a framework that allows attackers to inject backdoor through parameter efficient fine-tuning or without fine-uning techniques.
Outcome:	ELBA-Bench provides over 1300 experiments encompassing 12 attack methods, 18 datasets, and 12 LLMs.

Copied to clipboard

Vivian Lai, Zheng Cai, Chenhao Tan

Text Classification

Challenge:	Feature importance is commonly used to explain machine predictions . however, the consistency of feature importance via different methods remains understudied .
Approach:	They compare feature importance from built-in mechanisms and post-hoc methods that approximate model behavior to find similarities between models.
Outcome:	The proposed methods show that features from traditional models are more similar with each other than with deep learning models.

Massive End-to-end Speech Recognition Models with Time Reduction (2024.naacl-long)

Copied to clipboard

Weiran Wang, Rohit Prabhavalkar, Haozhe Shan, Zhong Meng, Dongseong Hwang, Qiujia Li, Khe Chai Sim, Bo Li, James Qin, Xingyu Cai, Adam Stooke, Chengjian Zheng, Yanzhang He, Tara Sainath, Pedro Moreno Mengibar

Rethinking Multimodal Entity and Relation Extraction from a Translation Point of View (2023.acl-long)

Challenge:	Using the neural architecture of Google’s universal speech model, we reduce the frame rate and speed up training and inference.
Approach:	They propose to use the neural architecture of Google’s universal speech model with additional funnel pooling layers to significantly reduce the frame rate and speed up training and inference.
Outcome:	The proposed methods work with both connectionist temporal classification (CTC) and RNN-Transducer (RNN-T) and over two domains.

Copied to clipboard

Changmeng Zheng, Junhao Feng, Yi Cai, Xiaoyong Wei, Qing Li

Multilinguality

Challenge:	Special attention is paid to the cross-modal misalignment in text-image datasets which may mislead the learning.
Approach:	They propose a multimodal back-translation method which uses diffusion-based generative models for pseudo-paralleled pairs and a divergence estimator to construct a high-resource corpora as a bridge for low-ressource learners.
Outcome:	The proposed method outperforms 14 state-of-the-art methods in both entity and relation extraction tasks.

Look and Think: Efficient Multimodal Reasoning via Modality-Decoupled Compression (2026.findings-acl)

Copied to clipboard

Xidi Cai, Junhao Zheng, Jingye Li, Boyuan Li, Shaowei Zhang, Qianli Ma

Watermarking PLMs on Classification Tasks by Combining Contrastive Learning with Weight Perturbation (2023.findings-emnlp)

Challenge:	Multimodal large language models have strong performance on visual question answering benchmarks . however, their inference efficiency is severely constrained by the rapidly growing context .
Approach:	They propose a modality-decoupled compression method that enables efficient multimodal inference . they propose to evict visual tokens whenever visual grounding is unnecessary .
Outcome:	The proposed method reduces the average context length by up to 57% while maintaining comparable performance to the standard MLLM baseline.

Copied to clipboard

Chenxi Gu, Xiaoqing Zheng, Jianhan Xu, Muling Wu, Cenyuan Zhang, Chengsong Huang, Hua Cai, Xuanjing Huang

OneRec-Think: In-Text Reasoning for Generative Recommendation (2026.acl-long)

Challenge:	Large pre-trained language models (PLMs) are highly valuable intellectual property due to their expensive training costs.
Approach:	They propose to embed backdoors that can be triggered by specific inputs into models by model watermarking.
Outcome:	The proposed method can be used to protect the intellectual property of large pre-trained language models without knowledge about downstream tasks.

Copied to clipboard

Zhanyu Liu, Shiyao Wang, Xingmei Wang, Rongzhou Zhang, Jiaxin Deng, Honghui Bao, Jinghao Zhang, Wuchao Li, PengFei Zheng, Xiangyu Wu, Yifei Hu, Qigen Hu, Xinchen Luo, Lejian Ren, Zhang Zixing, Qianqian Wang, Kuo Cai, Yunfan Wu, Hongtao Cheng, Zexuan Cheng, Lu Ren, Huanjie Wang, Yi Su, Ruiming Tang, Kun Gai, Guorui Zhou

Improving Named Entity Recognition via Bridge-based Domain Adaptation (2023.findings-acl)

Challenge:	Existing generative models lack the capacity for explicit and controllable reasoning, a key advantage of LLMs.
Approach:	They propose a framework that integrates dialogue, reasoning, and personalized recommendation.
Outcome:	Experiments across public benchmarks show state-of-the-art performance.

Copied to clipboard

Jingyun Xu, Changmeng Zheng, Yi Cai, Tat-Seng Chua