Papers by Ziyang Wang

SAC: Neural Speech Codec with Semantic-Acoustic Dual-Stream Quantization (2026.acl-long)

Challenge:	Knowledge distillation is an effective method for model acceleration and compression.
Approach:	They propose to use parameters to distill knowledge from large neural networks to small ones . they propose to do this by using a parameter generator to transfer the knowledge to a small neural network .
Outcome:	The proposed method learns a small network 1.88 2.94x faster than the large network but with competitive BLEU points.

Copied to clipboard

Wenxi Chen, Ruiqi Yan, Yushen Chen, Zhikang Niu, Ziyang Ma, Xiquan Li, Yuzhe Liang, null Wenhanlin, Shunshun Yin, Ming Tao, Xinsheng Wang, Xie Chen

F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching (2025.acl-long)

Challenge:	Existing speech codecs struggle to balance high-quality reconstruction with semantically rich representations, limiting their effectiveness in both generative and understanding tasks.
Approach:	They propose a neural speech codec with semantic-acoustic dual-stream quantization that disentangles semantic and acousian modeling into two dedicated streams.
Outcome:	The proposed codec outperforms state-of-the-art speech tokenizers in auto-propagating text-to-speech models.

Copied to clipboard

Yushen Chen, Zhikang Niu, Ziyang Ma, Keqi Deng, Chunhui Wang, JianZhao JianZhao, Kai Yu, Xie Chen

Beyond Noise: Characterizing Creative Potential in Unverifiable LLM Hallucinations (2026.acl-long)

Challenge:	Recent research in Text-to-Speech (TTS) has experienced great advancement . current models can synthesize speech for any given text and mimic the speaker of audio prompt.
Approach:	They propose a fully non-autoregressive text-to-speech system based on flow matching with Diffusion Transformer (DiT) without complex designs such as duration model, text encoder, and phoneme alignment, the text input is simply padded with filler tokens to the same length as input speech, and then denoising is performed for speech generation.
Outcome:	The proposed system achieves an inference RTF of 0.15, which is greatly improved compared to state-of-the-art diffusion-based models.

Copied to clipboard

Yu Yan, Chunhong Zhang, Haiyu Zhao, Ziyang Zeng, Zihao Liu, Yongkang Wu, Jianzhou Diao, YiJie Chen, Shujie Wang, Zheng Hu

Reasoning

Challenge:	Large Language Models generate outputs that extend beyond established knowledge . prior work does not characterize the unverifiable space as a whole .
Approach:	They propose a novelty-verifiability characterization that distinguishes Creative Synthesis from Groundless Fabrication by a conceptual creation task.
Outcome:	The proposed model distinguishes Creative Synthesis (Region A) from Groundless Fabrication (Regium B) it shows that Region A is non-negligible and robust, persisting across generation strategies, models, domains, and embedding choices.

MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing (2026.acl-industry)

Copied to clipboard

Junbo Niu, Zheng Liu, Zhuangcheng Gu, Bin Wang, Linke Ouyang, Zhiyuan Zhao, Tao Chu, Tianyao He, Fan Wu, Qintong Zhang, Zhenjiang Jin, Guang Liang, Rui Zhang, Wenzheng Zhang, Yuan Qu, Zhifei Ren, Yuefeng Sun, Zirui Tang, Boyu Niu, Yuanhong Zheng, Dongsheng Ma, Ziyang Miao, Hejun Dong, Siyi Qian, Junyuan Zhang, Fangdong Wang, Jingzhou Chen, Xiaomeng Zhao, Liqun Wei, Wei Li, Shasha Wang, RuiLiang Xu, Yuanyuan Cao, Lu Chen, Qianqian Wu, Huaiyu Gu, Lindong Lu, Dechen Lin, null Shenguanlin, Xuanhe Zhou, Linfeng Zhang, Yuhang Zang, Xiaoyi Dong, Jiaqi Wang, Bo Zhang, Lei Bai, Pei Chu, Weijia Li, Jiang Wu, Lijun Wu, Zhenxiang Li, Guangyu Wang, Zhongying Tu, Chao Xu, Kai Chen, Bowen Zhou, Dahua Lin, Wentao Zhang, Conghui He

Green & Sustainable NLP

Challenge:	Document images are characterized by higher resolutions, denser content, and more complex structural layouts.
Approach:	They propose a 1.2B-parameter document parsing vision-language model that decouples layout analysis from local content recognition.
Outcome:	The proposed model surpasses general-purpose and domain-specific models on multiple benchmarks while maintaining significantly lower computational overhead.

Towards Reliable Large Audio Language Model (2025.findings-acl)

Copied to clipboard

Ziyang Ma, Xiquan Li, Yakun Song, Wenxi Chen, Chenpeng Du, Jian Wu, Yuanzhe Chen, Zhuo Chen, Yuping Wang, Yuxuan Wang, Xie Chen

Knowledge Distillation based Contextual Relevance Matching for E-commerce Product Search (2022.emnlp-industry)

Challenge:	Recent advances in large audio language models (LALMs) have demonstrated impressive results and promising prospects in universal understanding and reasoning across speech, music, and general sound.
Approach:	They propose to use training-free and training-based methods to enhance LALM reliability to different extents.
Outcome:	The proposed methods improve the reliability of large audio language models to different extents.

Copied to clipboard

Ziyang Liu, Chaokun Wang, Hao Feng, Lingfei Wu, Liqun Yang

Towards Fine-Grained and Multi-Granular Contrastive Language-Speech Pre-training (2026.acl-long)

Challenge:	Existing approaches to e-commerce relevance matching ignore bipartite graphs in logs . experimental results show that proposed method improves human relevance judgment .
Approach:	They propose an efficient knowledge distillation framework for e-commerce relevance matching to exploit the advantages of Transformer-style and classical relevance matching models.
Outcome:	The proposed method significantly improves human relevance judgment on large-scale real-world data.

Copied to clipboard

Yifan Yang, Bing Han, Hui Wang, Wei Wang, Ziyang Ma, Long Zhou, Zengrui Jin, Guanrou Yang, Tianrui Wang, Xu Tan, Xie Chen

Video-RTS: Rethinking Reinforcement Learning and Test-Time Scaling for Efficient and Enhanced Video Reasoning (2025.emnlp-main)

Challenge:	Existing models for fine-grained speaking styles are limited in terms of accuracy, coverage, and naturalness.
Approach:	They propose a model that pre-trains with coarse captions and annotates with a pipeline that grounds captions in audio.
Outcome:	The proposed model outperforms existing models with fine-grained style annotations . it integrates global and fine-granular supervision, enabling unified representations based on the proposed model .

Copied to clipboard

Ziyang Wang, Jaehong Yoon, Shoubin Yu, Md Mohaiminul Islam, Gedas Bertasius, Mohit Bansal

Visual Data in NLP

Challenge:	Despite advances in reinforcement learning, data collection and fine-tuning remain costly and hard to scale.
Approach:	They propose a video-adaptive test-time scaling strategy that combines RL with a supervised fine-tuning strategy to improve video reasoning capability.
Outcome:	The proposed method surpasses existing models by 2.4% in accuracy using only 3.6% training samples.

Mitigating Posterior Salience Attenuation in Long-Context LLMs with Positional Contrastive Decoding (2025.acl-short)

Copied to clipboard

Zikai Xiao, Ziyang Wang, Wen Ma, Yan Zhang, Wei Shen, WangYan WangYan, Luqi Gong, Zuozhu Liu

Challenge:	Current solutions incur prohibitive training costs, leaving statistical behaviors and cost-effective approaches underexplored.
Approach:	They propose a positional contrast decoding technique that contrasts long-aware attention with designed local-awn attention.
Outcome:	The proposed model achieves state-of-the-art performance on long-context benchmarks.

UltraEval-Audio: A Unified Framework for Comprehensive Evaluation of Audio Foundation Models (2026.acl-demo)

Copied to clipboard

Qundong Shi, Jie Zhou, Biyuan Lin, Junbo Cui, Guoyang Zeng, Yixuan Zhou, Ziyang Wang, Xin Liu, Zhen Luo, Yudong Wang, Zhiyuan Liu

Unleashing Large Language Models’ Proficiency in Zero-shot Essay Scoring (2024.findings-emnlp)

Challenge:	Existing evaluation frameworks for audio foundation models are heavily reliant on English, making it difficult to objectively assess models’ performance on Chinese.
Approach:	They propose a unified framework that supports 10 languages, 14 task categories, 24 models, and 36 benchmarks with one-command evaluation and real-time leaderboards.
Outcome:	The proposed framework supports 10 languages, 14 task categories, 24 models, and 36 benchmarks with one-command evaluation and real-time leaderboards.

Copied to clipboard

Sanwoo Lee, Yida Cai, Desong Meng, Ziyang Wang, Yunfang Wu

Efficient Prior-Guided Reasoning for Robust Retrieval-Augmented Generation under Conflicts (2026.acl-long)

Challenge:	Recent advances in automated essay scoring (AES) have relied on labeled essays, requiring tremendous cost and expertise for their acquisition.
Approach:	They propose a zero-shot prompting framework that automatically decomposes writing proficiency into distinct traits and generates scoring criteria for each trait.
Outcome:	The proposed framework outperforms straightforward prompting (Vanilla) on TOEFL11 and ASAP, while the small-sized Llama2-13b-chat significantly outperformed ChatGPT.

Copied to clipboard

Xiaowei Yuan, Ziyang Huang, Zhao Yang, Yequan Wang, Jun Zhao, Kang Liu

Does Multi-Encoder Help? A Case Study on Context-Aware Neural Machine Translation (2020.acl-main)

Challenge:	Retrieval-Augmented Generation (RAG) has become a standard paradigm for grounding Large Language Models (LLMs) however, performance degrades substantially when faced with noisy, outdated, or conflicting retrieved information.
Approach:	They propose a framework that explicitly elicits the model’s parametric knowledge as prior information to guide reasoning on retrieved documents.
Outcome:	The proposed framework achieves robust performance across varying degrees of external inconsistency and noise.

Copied to clipboard

Bei Li, Hui Liu, Ziyang Wang, Yufan Jiang, Tong Xiao, Jingbo Zhu, Tongran Liu, Changliang Li

GRASPrune: Global Gating for Budgeted Structured Pruning of Large Language Models (2026.acl-long)

Challenge:	In encoder-decoder neural models, multiple encoders are used to represent contextual information in addition to the individual sentence.
Approach:	They propose to use multiple context encoders to encode the individual sentences in document-level neural machine translation (NMT) They propose a noisy dropout setup and a single-encoder approach to encode context sentences.
Outcome:	The proposed approach encodes the context and the current sentence without contexts.

Copied to clipboard

Ziyang Wang, Jiangfeng Xiao, Chuan Xiao, Ruoxiang LI, Rui Mao, Jianbin Qin

Same Claim, Different Judgment: Benchmarking Scenario-Induced Bias in Multilingual Financial Misinformation Detection (2026.findings-acl)

Challenge:	Large language models are expensive to serve because dense FFN blocks, multi-head attention, and KV caches dominate memory.
Approach:	They propose a global budgeted structured pruning framework that prunes FFN channels and attention KV head groups under a single global parameter budget.
Outcome:	The proposed model removes 50% of parameters and achieves 12.18 perplexity on WikiText-2 while maintaining competitive average zero-shot accuracy on five downstream benchmarks.

Copied to clipboard

Zhiwei Liu, Yupeng Cao, Yuechen Jiang, Mohsinul Kabir, Polydoros Giannouris, Chen Xu, Ziyang Xu, Tianlei Zhu, Md. Tariquzzaman, Triantafillos Papadopoulos, Yan Wang, Lingfei Qian, Xueqing Peng, Zhuohan Xie, Ye Yuan, Saeed Almheiri, Abdulrazzaq Alnajjar, Ming-Bin Chen, Harry Stuart, Paul Thompson, Prayag Tiwari, Alejandro Lopez-Lira, Xue Liu, Jimin Huang, Sophia Ananiadou

Social Welfare Function Leaderboard: On the Emergence of LLM Agents as the Welfare Dictator (2026.findings-acl)

Challenge:	Existing research on LLM biases has focused on direct questioning or general-purpose settings . pronounced behavioral biase despite their growing deployment in financial analysis, forecasting, and decision support.
Approach:	They propose a benchmark to evaluate behavioral biases of large language models in MFMD . they use a multilingual financial misinformation dataset to integrate these with misinformation claims .
Outcome:	The proposed benchmark evaluates behavioral biases of large language models across economic scenarios.

Copied to clipboard

Zhengliang Shi, Ruotian Ma, Jen-tse Huang, Xinbei Ma, Xingyu Chen, Mengru Wang, Qu Yang, Yue Wang, Fanghua Ye, Ziyang Chen, Shanyi Wang, Cixing LI, Wenxuan Wang, Zhaopeng Tu, Xiaolong Li, Zhaochun Ren, Liefeng Bo

RAM-SD: Retrieval-Augmented Multi-agent framework for Sarcasm Detection (2026.acl-long)

Challenge:	Large language models (LLMs) are increasingly entrusted with high-stakes decisions that affect human welfare.
Approach:	They evaluate 20 state-of-the-art Large language models (LLMs) and 20 LLM dictators to create a social welfare function benchmark.
Outcome:	The proposed model creates dilemma between maximizing collective efficiency and ensuring distributive fairness.

Copied to clipboard

Ziyang Zhou, Ziqi Liu, Yan Wang, Yiming Lin, Yangbin Chen

A Simple LLM Framework for Long-Range Video Question-Answering (2024.emnlp-main)

Challenge:	Existing approaches to sarcastic detection use a uniform reasoning strategy . existing approaches lack a framework to deal with the diverse analytical demands of sarcasm .
Approach:	They propose a Retrieval-Augmented Multi-Agent framework for Sarcasm Detection . the framework provides transparent and interpretable reasoning traces .
Outcome:	The proposed framework outperforms existing methods on four benchmarks and outperformed the strong GPT-4o+CoC baseline.

Copied to clipboard

Ce Zhang, Taixi Lu, Md Mohaiminul Islam, Ziyang Wang, Shoubin Yu, Mohit Bansal, Gedas Bertasius

Text Generation

Challenge:	a recent study has shown that short video understanding is not trivial due to the need for long-range temporal reasoning capabilities.
Approach:	They propose a language-based short- and long-range question-answering framework LLoVi . they propose 'multi-round summarization prompt' that asks the LLM to summarize the captions .
Outcome:	The proposed framework outperforms the state-of-the-art on the EgoSchema dataset and to grounded VideoQA.

GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinement (2025.acl-long)

Copied to clipboard

Yifan Yang, Zheshu Song, Jianheng Zhuo, Mingyu Cui, Jinpeng Li, Bo Yang, Yexing Du, Ziyang Ma, Xunying Liu, Ziyuan Wang, Ke Li, Shuai Fan, Kai Yu, Wei-Qiang Zhang, Guoguo Chen, Xie Chen

Exploiting Contextual Knowledge in LLMs through 𝒱-usable Information based Layer Enhancement (2025.acl-long)

Challenge:	GigaSpeech 2 is a large-scale, multi-domain, multilingual speech recognition corpus for low-resource languages.
Approach:	They propose a large-scale, multi-domain, multilingual speech recognition corpus for low-resource languages and an automated pipeline for data crawling, transcription, and label refinement.
Outcome:	The proposed corpus reduces the word error rate for Thai, Indonesian, and Vietnamese on a realistic YouTube test set by 25% to 40% compared to Whisper large-v3.

Copied to clipboard

Xiaowei Yuan, Zhao Yang, Ziyang Huang, Yequan Wang, Siqi Fan, Yiming Ju, Jun Zhao, Kang Liu

Challenge:	Existing approaches to enhance the context-faithfulness of Large Language Models (LLMs) ignore the fundamental mechanism of how contextual information is processed within LLMs’ internal states.
Approach:	They propose a method that enhances the utilization of contextual knowledge within LLMs’ internal representations by employing V-usable information analysis.
Outcome:	The proposed method improves context-faithfulness generation in Question-Answering tasks, particularly in scenarios involving unknown or conflicting contextual knowledge.

Focus-Driven Contrastive Learning for Medical Question Summarization (2022.coling-1)

Copied to clipboard

Ming Zhang, Shuai Dou, Ziyang Wang, Yunfang Wu

Calibrating Inference Time Alignment with Sequence-level Risk Accumulation (2026.acl-long)

Challenge:	Existing methods to summarize health questions are not able to capture well question focus and lack the ability to understand sentence-level semantics.
Approach:	They propose a question focus-driven contrastive learning framework to capture question focus and exploit contrastive training at both encoder and decoder to obtain better sentence representations.
Outcome:	The proposed model achieves 5.33, 12.85 and 3.81 points over the baseline model on three medical benchmark datasets.

Copied to clipboard

Shanwen Tan, Ziyang Dong, Wei Ju, Yiwei Fu, Hao Wu, Kun Wang, Yifan Wang, Ziyue Qiao

TeRDy: Temporal Relation Dynamics through Frequency Decomposition for Temporal Knowledge Graph Completion (2025.acl-long)

Challenge:	Existing approaches to decode large language models (LLMs) often over-reject benign information, limiting their generalizability in real-world scenarios where harmful and benign information coexist.
Approach:	They propose a framework to regulate decoding alignments for Large Language Models (LLMs) they employ a reward-guided branch decoding paradigm to incorporate safety awareness during generation.
Outcome:	The proposed framework achieves superior performance on four attack benchmarks and two neutral datasets.

Copied to clipboard

Ziyang Liu, Chaokun Wang

ChatMusician: Understanding and Generating Music Intrinsically with LLM (2024.findings-acl)

Challenge:	Existing methods for temporal knowledge graph completion struggle to capture long-term changes and short-term variability of relations.
Approach:	They propose a method that captures temporal relational dynamics by time-invariant embeddings and time-outvariant time-variant embeddedding.
Outcome:	The proposed method outperforms state-of-the-art methods on benchmark datasets.

Copied to clipboard

Ruibin Yuan, Hanfeng Lin, Yi Wang, Zeyue Tian, Shangda Wu, Tianhao Shen, Ge Zhang, Yuhang Wu, Cong Liu, Ziya Zhou, Liumeng Xue, Ziyang Ma, Qin Liu, Tianyu Zheng, Yizhi Li, Yinghao Ma, Yiming Liang, Xiaowei Chi, Ruibo Liu, Zili Wang, Chenghua Lin, Qifeng Liu, Tao Jiang, Wenhao Huang, Wenhu Chen, Jie Fu, Emmanouil Benetos, Gus Xia, Roger Dannenberg, Wei Xue, Shiyin Kang, Yike Guo

MEXA: Towards General Multimodal Reasoning with Dynamic Multi-Expert Aggregation (2025.findings-emnlp)

Challenge:	Despite LLMs' impressive capabilities in musical knowledge, music reasoning remains an unsolved task.
Approach:	They propose an open-source large language model (LLM) that integrates intrinsic musical abilities into LLaMA2 and GPT-3.5.
Outcome:	The proposed model can understand and generate music with a pure text tokenizer without external multi-modal neural structures or tokenizers.

Copied to clipboard

Shoubin Yu, Yue Zhang, Ziyang Wang, Jaehong Yoon, Mohit Bansal

FPT: Feature Prompt Tuning for Few-shot Readability Assessment (2024.naacl-long)

Challenge:	MEXA is a training-free framework that performs modality- and task-aware aggregation of multiple expert models to enable effective multimodal reasoning across diverse domains.
Approach:	MEXA is a training-free framework that performs modality- and task-aware aggregation of multiple expert models.
Outcome:	MEXA performs modality- and task-aware aggregation of multiple expert models . it generates interpretable textual reasoning outputs and reasons over them using a Large Reasoning Model (LRM) MEX A consistently delivers performance improvements over strong multimodal benchmarks .

Copied to clipboard

Ziyang Wang, Sanwoo Lee, Hsiu-Yuan Huang, Yunfang Wu

VocalNet: Speech LLMs with Multi-Token Prediction for Faster and High-Quality Generation (2025.emnlp-main)

Challenge:	Prompt-based methods lack crucial linguistic knowledge for readability assessment tasks such as word length, sentence length, and usage of different difficulty-level words.
Approach:	They propose a new prompt-based tuning framework that incorporates linguistic knowledge and a loss function to calibrate the similarity ranking order between categories.
Outcome:	The proposed framework outperforms the large language model gpt-3.5-turbo-16k in most cases.

Copied to clipboard

Yuhao Wang, Heyang Liu, Ziyang Cheng, Ronghua Wu, Qunshan Gu, Yanfeng Wang, Yu Wang

Easy Dataset: A Unified and Extensible Framework for Synthesizing LLM Fine-Tuning Data from Unstructured Documents (2025.emnlp-demos)

Challenge:	Experimental results show VocalNet outperforms existing open-source speech LLMs despite limited training data.
Approach:	They propose a scalable and model-agnostic training framework and a novel multi-token prediction paradigm for speech generation.
Outcome:	The proposed model outperforms open-source speech LLMs while outperforming existing open-sourced models.

Copied to clipboard

Ziyang Miao, Qiyu Sun, Jingyuan Wang, Yuchen Gong, Yaowei Zheng, Shiqi Li, Richong Zhang

Evaluating the Expressive Appropriateness of Speech in Rich Contexts (2026.acl-long)

Challenge:	Existing data synthesis tools struggle to extract reliable fine-tuning data from heterogeneous documents.
Approach:	They propose a framework for synthesizing fine-tuning data from unstructured documents via an intuitive graphical user interface.
Outcome:	The proposed framework can extract reliable data from unstructured documents via an intuitive graphical user interface (GUI) it leverages persona-driven prompting approach to generate diverse question-answer pairs using public-available LLMs.

Copied to clipboard

Tianrui Wang, Ziyang Ma, Yizhou Peng, Haoyu Wang, Zhikang Niu, Zikang Huang, Yihao Wu, Yi-Wen Chao, Yu Jiang, Yuheng Lu, Guanrou Yang, Xuanchen Li, Hexin Liu, Chunyu Qiang, Cheng Gong, Yifan Yang, Tianchi Liu, Junyu Wang, Nana Hou, Meng Ge, Fuming You, Yang Wei, Zhongqian Sun, Hu Haifeng, Xiaobao Wang, Eng Siong Chng, Xie Chen, Longbiao Wang, Jianwu Dang

Speech & Audio in NLP

Challenge:	Existing methods for evaluating expressive speech focus on word accuracy, naturalness, signal quality, or emotional intensity at the utterance level.
Approach:	They propose a framework for Evaluating Expressive Appropriateness in speech that assesses whether a speech sample aligns with the underlying communicative intent implied by its discourse-level narrative context.
Outcome:	The proposed framework outperforms existing speech evaluation and analysis systems on a human-annotated test set.

Shallow-to-Deep Training for Neural Machine Translation (2020.emnlp-main)

Copied to clipboard

Bei Li, Ziyang Wang, Hui Liu, Yufan Jiang, Quan Du, Tong Xiao, Huizhen Wang, Jingbo Zhu

Multilinguality

Challenge:	Experimental results show that deep training is 1:4 faster than training from scratch.
Approach:	They propose a shallow-to-deep training method that learns deep models by stacking shallow models.
Outcome:	The proposed method is 1:4 faster than training from scratch and achieves BLEU scores of 30:33 and 43:29 on two translation tasks.

SemPA: Improving Sentence Embeddings of Large Language Models through Semantic Preference Alignment (2026.findings-acl)

Copied to clipboard

Ziyang Chen, Zhenxuan Huang, Yile Wang, Weiqin Wang, Lu Yin, Hui Huang

Doc-V*: Coarse-to-Fine Interactive Visual Reasoning for Multi-Page Document VQA (2026.acl-long)

Challenge:	Existing sentence embedding methods rely on fixed prompt templates or involve modifications to the model architecture, compromising its generative capabilities.
Approach:	They propose a sentence-level direct preference optimization approach that boosts the sentence representations while preserving the generative ability of LLMs.
Outcome:	The proposed method improves representations of semantically meaningful vectors without sacrificing generation capability.

Copied to clipboard

Yuanlei Zheng, Pei Fu, Hang Li, Ziyang Wang, Yuyi Zhang, Wenyu Ruan, Xiaojin Zhang, Zhongyu Wei, Zhenbo Luo, Jian Luan, Wei Chen, Xiang Bai

UNO Arena for Evaluating Sequential Decision-Making Capability of Large Language Models (2024.emnlp-main)

Challenge:	Existing OCR-free approaches to document visual question answering are brittle and passive.
Approach:	They propose an OCR-free agentic framework that casts multi-page DocVQA as sequential evidence aggregation.
Outcome:	The proposed framework outperforms open-source and proprietary models in five benchmarks and improves out-of-domain performance by 47.9% over baseline.

Copied to clipboard

Zhanyue Qin, Haochuan Wang, Deyuan Liu, Ziyang Song, Cunhang Fan, Zhao Lv, Jinlin Wu, Zhen Lei, Zhiying Tu, Dianhui Chu, Xiaoyan Yu, Dianbo Sui

LMR-BENCH: Evaluating LLM Agent’s Ability on Reproducing Language Modeling Research (2025.emnlp-main)

Challenge:	Existing LLMs demonstrate powerful capabilities between tasks, but can they make sequential decisions?
Approach:	They propose to evaluate sequential decision-making capability of large language models (LLMs) using novel metrics based Monte Carlo methods.
Outcome:	The proposed benchmark improves sequential decision-making performance compared to the vanilla LLM player.

Copied to clipboard

Shuo Yan, Ruochen Li, Ziming Luo, Zimu Wang, Daoyang Li, Liqiang Jing, Kaiyu He, Peilin Wu, Juntong Ni, George Michalopoulos, Yue Zhang, Ziyang Zhang, Mian Zhang, Zhiyu Chen, Xinya Du

DiffPO: Diffusion-styled Preference Optimization for Inference Time Alignment of Large Language Models (2025.acl-long)

Challenge:	Large language model (LLM) agents have demonstrated remarkable potential in advancing scientific discovery, but their capability in reproducing code from research papers remains underexplored.
Approach:	They propose to evaluate LLM agents' ability to reproduce scientific research papers by analyzing code reproduction tasks from 23 research papers published in top-tier NLP venues.
Outcome:	The proposed benchmark systematically evaluates the capability of large language model (LLM) agents on code reproduction from Language Modeling Research.

Copied to clipboard

Ruizhe Chen, Wenhao Chai, Zhifei Yang, Xiaotian Zhang, Ziyang Wang, Tony Quek, Joey Tianyi Zhou, Soujanya Poria, Zuozhu Liu

MoPrune: Scene-Guided Motion-Aware Token Pruning for Efficient Video Large Language Models (2026.findings-acl)

Challenge:	Inference-time alignment approaches still face limitations due to policy-specific value functions and latency during the inference phase.
Approach:	They propose an efficient and policy-agnostic preference optimization method that avoids time latency associated with token generation.
Outcome:	The proposed method achieves a favorable trade-off between alignment quality and inference-time latency.

Copied to clipboard

Wenhao Hong, Ziyang Wang, Yixin Zhang, Zilei Wang

REACT: Representation Extraction And Controllable Tuning to Overcome Overfitting in LLM Knowledge Editing (2025.emnlp-main)

Challenge:	Prior approaches to token pruning ignore video dynamics and the fact that different scenes exhibit different redundancy patterns.
Approach:	They propose a token pruning framework that is train-free and scene-guided to accelerate VideoLLMs by removing redundant visual information from video frames.
Outcome:	MoPrune is a training-free, scene-guided and motion-centric token pruning framework for accelerating VideoLLMs.

Copied to clipboard

Haitian Zhong, Yuhuan Liu, Ziyang Xu, Guofan Liu, Qiang Liu, Shu Wu, Zhe Zhao, Liang Wang, Tieniu Tan

Unified Embeddings for Multimodal Retrieval via Frozen LLMs (2024.findings-eacl)

Challenge:	Large language model editing methods suffer from overfitting, where factual updates can propagate beyond their intended scope, overemphasizing the edited target even when it’s contextually inappropriate.
Approach:	They propose a framework for precise and controllable knowledge editing that utilizes two-phase representations and a linear transformation to compute a directional "belief shift" vector.
Outcome:	The proposed framework significantly reduces overfitting across nearly all evaluation metrics and on COUNTERFACT and MQuAKE.

Copied to clipboard

Ziyang Wang, Heba Elfardy, Markus Dreyer, Kevin Small, Mohit Bansal

Large Language Models Have Intrinsic Meta-Cognition, but Need a Good Lens (2025.emnlp-main)

Challenge:	Unified Embeddings for Multimodal Retrieval (UniMuR) is a simple but effective approach that embeds multimodal inputs and retrieves visual and textual outputs via frozen Large Language Models (LLMs).
Approach:	They propose a method that embeds multimodal inputs and retrieves visual and textual outputs via frozen Large Language Models (LLMs).
Outcome:	The proposed method significantly reduces LLM’s modality bias towards generating text-only outputs and achieves strong image/text retrieval ability.

Copied to clipboard

Ziyang Ma, Qingyue Yuan, Zhenglin Wang, Deyu Zhou

A Unified Neural Network Model for Readability Assessment with Feature Projection and Length-Balanced Loss (2022.emnlp-main)

Challenge:	Existing studies have focused on the cognitive error detection capabilities of Large Language Models (LLMs), but few studies have examined the meta-cognitive abilities of LLMs.
Approach:	They propose an automated meta-cognition evaluation framework for evaluation of LLMs and a Markovian Intrinsic Reward Adjustment strategy to boost current lenses.
Outcome:	The proposed framework can be used to evaluate the meta-cognition abilities of LLMs and improve them.

Copied to clipboard

Wenbiao Li, Wang Ziyang, Yunfang Wu

Easy and Efficient Transformer: Scalable Inference Solution For Large NLP Model (2022.naacl-industry)

Challenge:	Traditional readability assessment models employ hundreds of linguistic features, but it is less explored for readability assessments.
Approach:	They propose a BERT-based model with feature projection and length-balanced loss to determine the difficulty level of a given text.
Outcome:	The proposed model achieves significant improvements over baseline models on three English benchmark datasets and one Chinese dataset.

Copied to clipboard

Gongzheng Li, Yadong Xi, Jingzhen Ding, Duan Wang, Ziyang Luo, Rongsheng Zhang, Bai Liu, Changjie Fan, Xiaoxi Mao, Zeng Zhao

LAGCL4Rec: When LLMs Activate Interactions Potential in Graph Contrastive Learning for Recommendation (2025.findings-emnlp)

Challenge:	Recent studies show that transformer-based models are effective over many tasks, but they are expensive to deploy in the industrial application.
Approach:	They propose a transformer-based inference solution that optimizes kernels for long inputs and large hidden sizes and a flexible CUDA memory manager to reduce the memory footprint when deploying a large model.
Outcome:	The proposed solution achieves an average speedup of 1.40-4.20x on the transformer decoder layer with an A100 GPU.

Copied to clipboard

Leqi Zheng, Chaokun Wang, Canzhi Chen, Jiajun Zhang, Cheng Wu, Zixin Song, Shannan Yan, Ziyang Liu, Hongwei Li

Large Language Models Meet Harry Potter: A Dataset for Aligning Dialogue Agents with Characters (2023.findings-emnlp)

Challenge:	Traditional contrastive learning methods treat negative feedback as equally hard or easy, ignoring informative semantic difficulty during training.
Approach:	They propose a framework leveraging Large Language Models to Activate interactions in Graph Contrastive Learning for Recommendation.
Outcome:	The proposed framework outperforms state-of-the-art benchmarks on multiple benchmarks.

Copied to clipboard

Nuo Chen, Yan Wang, Haiyun Jiang, Deng Cai, Yuhan Li, Ziyang Chen, Longyue Wang, Jia Li

Dialogue Systems & Conversational Agents

Challenge:	Existing models that can create open-domain dialogue agents lack character representation and annotations.
Approach:	They propose a dataset to study character alignment and character representation . it includes all dialogue sessions from the Harry Potter series and includes annotations .
Outcome:	The proposed dataset can be used as a universal benchmark for character-driven LLMs.

Aria-UI: Visual Grounding for GUI Instructions (2025.findings-acl)

Copied to clipboard

Yuhao Yang, Yue Wang, Dongxu Li, Ziyang Luo, Bei Chen, Chao Huang, Junnan Li