Papers by Lei Gao

Modeling Document-level Causal Structures for Event Causal Relation Identification (N19-1)

Challenge:	Language models (LMs) generate toxic, biased content and reveal private training records.
Approach:	They propose an efficient approach that rectifies LMs to mitigate toxicity and bias . Ethos distinguishes general beneficial and undesired knowledge when reconstructing task vectors .
Outcome:	The proposed approach mitigates toxicity and bias in outputs and avoids privacy leakage.

Copied to clipboard

Lei Gao, Prafulla Kumar Choubey, Ruihong Huang

Challenge:	a study aims to identify all the event causal relations in a document, both within a sentence and across sentences . main challenges for achieving comprehensive causal relation identification are sparse among all possible event pairs . few causal relations are explicitly stated, especially for identifying cross-sentence causal relations .
Approach:	They propose to identify all event causal relations in a document, both within a sentence and across sentences.
Outcome:	The proposed model improves the performance of causal relation identification . it shows that the model can be used to identify cross-sentence causal relations .

R³A: Reinforced Reasoning for Relevance Assessment for RAG in User-Generated Content Platforms (2026.acl-industry)

Copied to clipboard

Xiaowei Yuan, Lei Jin, Haoxin Zhang, Ziyang Huang, Yan Gao, null Yiwu, Yao Hu, Jun Zhao, Kang Liu

Reasoning

Challenge:	Existing approaches to query–document relevance assessment are limited . ambiguous user intent and asymmetric relevance are challenges for RAG platforms .
Approach:	They propose a decomposed reasoning model for relevance assessment that decomposes query intent into intent inference and evidence grounding.
Outcome:	The proposed model outperforms strong baselines on offline benchmarks and achieves significant gains in large-scale online A/B testing.

MINED: Probing and Updating with Multimodal Time-Sensitive Knowledge for Large Multimodal Models (2026.findings-acl)

Copied to clipboard

Kailin Jiang, Ning Jiang, Yuntao Du, Yuchen Ren, Yuchen Li, Yifan Gao, Jinhe Bi, Yunpu Ma, Bin Li, Lei Liu, Qing Li

Exploring the Universal Vulnerability of Prompt-based Learning Paradigm (2022.findings-naacl)

Challenge:	Existing benchmarks for Large Multimodal Models (LMMs) are constrained by static representations, inadequately evaluating their ability to understand time-sensitive knowledge.
Approach:	They propose a benchmark containing 2,104 time-sensitive knowledge samples spanning six knowledge types to evaluate temporal awareness along 6 key dimensions and 11 challenging tasks.
Outcome:	The proposed benchmark measures temporal awareness along 6 key dimensions and 11 tasks, while most open-source LMMs still lack time understanding ability.

Copied to clipboard

Lei Xu, Yangyi Chen, Ganqu Cui, Hongcheng Gao, Zhiyuan Liu

Responsible & Trustworthy NLP

Challenge:	Prompt-based learning inherits the vulnerability from pre-training, where model predictions can be misled by inserting triggers into the text.
Approach:	They propose a potential solution to mitigate this vulnerability by injecting triggers into pre-trained language models using only plain text.
Outcome:	The proposed learning paradigm inherits the vulnerability from the pre-training stage . it can totally control or severely decrease the performance of prompt-based models .

GODBench: A Benchmark for Multimodal Large Language Models in Video Comment Art (2025.acl-long)

Copied to clipboard

Yiming Lei, Chenkai Zhang, Zeming Liu, Haitao Leng, ShaoGuo Liu, Tingting Gao, Qingjie Liu, Yunhong Wang

RACQC: Advanced Retrieval-Augmented Generation for Chinese Query Correction (2025.findings-emnlp)

Challenge:	Existing benchmarks for video comment art are constrained by their limited modalities and insufficient categories, hindering creativity in video-based comment art creation.
Approach:	They propose a benchmark that integrates video and text modalities to evaluate MLLMs’ abilities to compose video Comment art.
Outcome:	The proposed framework integrates video and text modalities to evaluate MLLMs’ abilities to compose video comment art.

Copied to clipboard

Jinbo Su, Lingzhe Gao, Wei Li, Shihao Liu, Haojie Lei, Xinyi Wang, Yuanzhao Guo, Ke Wang, Daiting Shi, Dawei Yin

Information Retrieval

Challenge:	Large language models (LLMs) exhibit remarkable capabilities across many tasks, but face critical challenges in the CSC scenario: (1) poor generalization to rare entities in open-domain searches; and (2) failure to adapt to temporal entity variations due to static parameters, resulting in serious over-correction issues.
Approach:	They propose a Chinese Spelling Check system with RAG and multi-task learning that integrates dynamic knowledge retrieval and entity-centric RAG to address rare entities.
Outcome:	The proposed system outperforms existing baselines in the CSC task and achieves a maximum improvement of +9.92% on the search scenario benchmark and +3.2% on the general-domain dataset.

BU-NEmo: an Affective Dataset of Gun Violence News (2022.lrec-1)

Copied to clipboard

Carley Reardon, Sejin Paik, Ge Gao, Meet Parekh, Yanling Zhao, Lei Guo, Margrit Betke, Derry Tanti Wijaya

Sentiment Analysis

Challenge:	Using a dataset that contains headline and image pairings from 840 news articles, we explore the relationship between image and text influence on human emotional response.
Approach:	They propose to use a U.S. gun violence news dataset that contains headline and image pairings from 840 news articles with 15K high-quality crowdsourced annotations on emotional responses.
Outcome:	The proposed dataset includes annotations on the dominant emotion experienced with the content, the intensity of the selected emotion and an open-ended, written component.

A Neural Network Architecture for Program Understanding Inspired by Human Behaviors (2022.acl-long)

Copied to clipboard

Renyu Zhu, Lei Yuan, Xiang Li, Ming Gao, Wenyuan Cai

Representation Learning

Challenge:	Existing studies for understanding programs do not take human behaviors as reference.
Approach:	They propose a graph neural network model that takes human behaviors as reference in understanding programs.
Outcome:	The proposed model performs better on code summarization and code clone detection tasks.

CONE: An Efficient COarse-to-fiNE Alignment Framework for Long Video Temporal Grounding (2023.acl-long)

Copied to clipboard

Zhijian Hou, Wanjun Zhong, Lei Ji, Difei Gao, Kun Yan, W.k. Chan, Chong-Wah Ngo, Mike Zheng Shou, Nan Duan

Compensate Quantization Errors: Make Weights Hierarchical to Compensate Each Other (2024.findings-naacl)

Challenge:	Existing work on video temporal grounding for long videos is limited by existing datasets.
Approach:	They propose a query-guided window selection strategy and a coarse-to-fine mechanism to speed up inference for long videos.
Outcome:	The proposed framework accelerates inference time by 2x on Ego4D-NLQ and 15x on MAD while keeping SOTA results.

Copied to clipboard

Yifei Gao, Jie Ou, Lei Wang, Yuting Xiao, Xiangzhiyuan Xiangzhiyuan, Ruiting Dai, Jun Cheng

Think-Search-Patch: A Retrieval-Augmented Reasoning Framework for Repository-Level Code Repair (2025.emnlp-industry)

Challenge:	Emergent Large Language Models (LLMs) use extraordinary performance and powerful deduction capacity to discern from traditional language models.
Approach:	They propose a method that uses weights to compensate quantization error and learnable singular value incremental (LSI) LSI is a technique that helps weights compensate each other conditioned on activation.
Outcome:	The proposed method achieves state-of-the-art performance in diverse quantization settings, no matter in weight-only, weight-activation or extremely low bit scenarios.

Copied to clipboard

Bojian Xiong, Yikun Lei, Xikai Liu, Shaowei Zhang, Pengyun Zhu, Yan Liu, Yongqi Leng, Ling Shi, Meizhi Zhong, Yurong Zhang, Yan Gao, null Yiwu, Yao Hu, Deyi Xiong

Information Retrieval

Challenge:	Large language models suffer from multiple-file coding scenarios with strong inter-file dependencies . experimental results show that large language models exhibit inadequate performance in multi-file scenarios .
Approach:	They propose a retrieval-augmented reasoning framework for repository-level code repair . they use a dataset to generate standardized patches based on the key snippets .
Outcome:	The proposed framework improves retrieval accuracy and repair success on SWE-bench Lite . it surpasses models with larger size in managing extensive code contexts and fixing bugs spanning across multiple files.

BloomEval: A Bloom’s Cognitive Taxonomy-Based Benchmark for Evaluating LRMs via Cognitive Hierarchy Trace (2026.findings-acl)

Copied to clipboard

Zhiyi Duan, Lei Gao, Jiangshan Guan, Qi Wang, Rui Liu

Reasoning

Challenge:	Existing benchmarks for Large Reasoning Models rely on answer correctness, but fail to assess the structural coherence and cognitive soundness of the reasoning process itself.
Approach:	They propose a framework that maps a model's reasoning trajectory onto hierarchical cognitive levels and an annotation pipeline to ensure a scalable yet reliable annotation pipeline.
Outcome:	The proposed framework detects hierarchy jumps, breaks, and overthinking errors and enables scalable yet reliable annotation.

DiffCL: Difference-Aware Contrastive Learning for Automatic Answer Grading with Multi-Level Semantic Modeling (2026.findings-acl)

Copied to clipboard

Lei Chen, BoYu Gao, Zitao Liu, Tingjie Wan, Weiqi Luo

ARTIST: A Transformer-based Chinese Text-to-Image Synthesizer Digesting Linguistic and World Knowledge (2022.findings-emnlp)

Challenge:	Existing approaches to automate answer grading lack semantic understanding and scoring consistency.
Approach:	They propose a difference-aware AAG framework that integrates heuristic difference labeling with dual-contrastive learning.
Outcome:	The proposed method outperforms cross-entropy-based baselines on SciEntsBank and Beetle datasets.

Copied to clipboard

Tingting Liu, Chengyu Wang, Xiangru Zhu, Lei Li, Minghui Qiu, Jun Huang, Ming Gao, Yanghua Xiao

DecEx-RAG: Boosting Agentic Retrieval-Augmented Generation with Decision and Execution Optimization via Process Supervision (2025.emnlp-industry)

Challenge:	Text-to-Image Synthesis (TIS) is a popular task to convert natural language texts into realistic images.
Approach:	They propose a transformer-based Chinese text-to-image synthesizer for high-resolution image generation that incorporates linguistic and relational knowledge facts into the model to ensure better performance without the usage of ultra-large models.
Outcome:	The proposed model outperforms existing models in Chinese with linguistic and relational knowledge facts.

Copied to clipboard

Yongqi Leng, Yikun Lei, Xikai Liu, Meizhi Zhong, Bojian Xiong, Yurong Zhang, Yan Gao, null Yiwu, Yao Hu, Deyi Xiong

Green & Sustainable NLP

Challenge:	Recent advances in outcome-supervised reinforcement learning (RL) have shown strong performance, but this approach still suffers from inefficient exploration, sparse reward signals, and ambiguous global reward feedback.
Approach:	They propose a model that models RAG as a Markov Decision Process (MDP) and introduces an efficient pruning strategy to optimize data expansion.
Outcome:	The proposed model outperforms existing methods and achieves an average performance improvement of 6.2% across six datasets.

GeoRA: Geometry-Aware Low-Rank Adaptation for RLVR (2026.acl-long)

Copied to clipboard

Jiaying Zhang, Lei Shi, Jiguo Li, Jun Xu, Jiuchong Gao, Jinghua Hao, Renqing He

Live-Aid: A Large-Scale Dialogue Dataset and Benchmark for Interleaved Multi-party Interactions in Live Streaming (2026.findings-acl)

Challenge:	Existing parameter-efficient methods for RLVR face limitations . low-rank adaptation methods do not account for the distinct optimization dynamics .
Approach:	They propose a low-rank adaptation method tailored for RLVR that exploits the anisotropic structure of RL update subspace and extracts its principal directions via Singular Value Decomposition (SVD).
Outcome:	Experiments on large reasoning models show that GeoRA outperforms strong low-rank baselines across RLVR settings while showing stronger generalization and less forgetting on out-of-domain tasks.

Copied to clipboard

Yiming Lei, Yize Fan, Zeming Liu, Jiaji Dong, Hui Qiu, Haitao Leng, Qingjie Liu, Kehai Chen, Tingting Gao, Yunhong Wang

Fine-Mem: Fine-Grained Feedback Alignment for Long-Horizon Memory Management (2026.acl-long)

Challenge:	Existing Multimodal Large Language Models struggle with dynamic interactions due to the scarcity of high-quality interleaved data.
Approach:	They propose a large-scale interleaved live interaction Chinese dataset with human-annotated video responses.
Outcome:	The proposed model can be used to evaluate live interactions in Chinese over 1,100 hours and 80,037 dialogue turns.

Copied to clipboard

Weitao Ma, Xiaocheng Feng, Lei Huang, Xiachong Feng, Zhanyu Ma, Jun Xu, Jiuchong Gao, Jinghua Hao, Renqing He, Bing Qin

GLTW: Joint Improved Graph Transformer and LLM via Three-Word Language for Knowledge Graph Completion (2025.findings-acl)

Challenge:	Existing approaches to memory management rely on final task performance as the primary reward, resulting in severe reward sparsity and ineffective credit assignment.
Approach:	They propose a framework for fine-grained feedback alignment using a Chunk-level step reward and Evidence-Anchored Reward Attribution to redistribute global rewards based on memory items utilized as evidence in reasoning.
Outcome:	The proposed framework outperforms baselines and supports generalization across different model configurations and backbones.

Copied to clipboard

Kangyang Luo, Yuzhuo Bai, Cheng Gao, Shuzheng Si, Zhu Liu, Yingli Shen, Zhitong Wang, Cunliang Kong, Wenhao Li, Yufei Huang, Ye Tian, Xuantang Xiong, Lei Han, Maosong Sun

Dialogue Medical Information Extraction with Medical-Item Graph and Dialogue-Status Enriched Representation (2023.findings-emnlp)

Challenge:	Existing knowledge graphs lack the ability to integrate structural information into LLMs and output predictions deterministically.
Approach:	They propose a method which encodes structural information of KGs and merges it with LLMs to enhance KGC performance.
Outcome:	The proposed method improves the performance of KG Completion datasets on KGs by integrating structural information with LLMs.

Copied to clipboard

Lei Gao, Xinnan Zhang, Xian Wu, Shen Ge, Yefeng Zheng

Structured Data in NLP

Challenge:	Existing approaches ignore relationships between medical items and statuses in the multi-turn doctor-patient dialogue.
Approach:	They propose a task to extract structured medical information from free text dialogues . they propose 'Dialogue Medical Information Extraction' to model relationships between items .
Outcome:	The proposed model outperforms previous models and achieves state-of-the-art performance on the public benchmark data set.

KVPR: Efficient LLM Inference with I/O-Aware KV Cache Partial Recomputation (2025.findings-acl)

Copied to clipboard

Chaoyi Jiang, Lei Gao, Hossein Entezari Zarch, Murali Annavaram

Green & Sustainable NLP

Challenge:	Existing methods to inference large language models are limited by CPU capabilities and memory constraints.
Approach:	They propose an efficient I/O-aware LLM inference method that overlaps GPU computation with KV cache transfer to minimize idle GPU time.
Outcome:	The proposed method reduces the cost of auto-regressive decoding by 35.8% . it also achieves 46.2% higher throughput during decoding compared to state-of-the-art methods.

Understanding the RoPE Extensions of Long-Context LLMs: An Attention Perspective (2025.coling-main)

Copied to clipboard

Meizhi Zhong, Chen Zhang, Yikun Lei, Xikai Liu, Yan Gao, Yao Hu, Kehai Chen, Min Zhang

Open-Set Living Need Prediction with Large Language Models (2025.findings-acl)

Challenge:	Enabling LLMs to handle lengthy context is currently a research hotspot . a notable challenge limiting further customization is the inability of LLM to utilize context beyond pretrained length due to the inherent flaw of rotary position embedding (RoPE).
Approach:	They propose to extend the RoPE from an attention perspective and on two benchmarking tasks.
Outcome:	The proposed extension of the RoPE improves extrapolation and retrieval errors.

Copied to clipboard

Xiaochong Lan, Jie Feng, Yizhou Sun, Chen Gao, Jiahuan Lei, Xinleishi Xinleishi, Hengliang Luo, Yong Li

ProReason: Multi-Modal Proactive Reasoning with Decoupled Eyesight and Wisdom (2025.emnlp-main)

Challenge:	Existing approaches to living need prediction treat it as a closed-set classification problem, severely limiting their ability to capture diversity and complexity of living needs.
Approach:	They propose a system leveraging large language models for unrestricted need prediction that leverages Maslow's hierarchy of needs to align predictions with human living needs.
Outcome:	The proposed system outperforms closed-set approaches on need-based life service recall by an average of 19.37% on real-world datasets.

Copied to clipboard

Jingqi Zhou, Sheng Wang, Jingwei Dong, Kai Liu, Lei Li, Jiahui Gao, Jiyue Jiang, Lingpeng Kong, Chuan Wu

Large Language Models Are Poor Clinical Decision-Makers: A Comprehensive Benchmark (2024.emnlp-main)

Challenge:	Large vision-language models often prioritize language knowledge over image information on visual reasoning tasks, incurring performance degradation.
Approach:	They propose a visual reasoning framework that decouples vision-reasoning capabilities and multi-run proactive perception.
Outcome:	The proposed framework outperforms existing models on benchmarks for open-source and closed-source models with 13.2% performance gain.

Copied to clipboard

Fenglin Liu, Zheng Li, Hongjian Zhou, Qingyu Yin, Jingfeng Yang, Xianfeng Tang, Chen Luo, Ming Zeng, Haoming Jiang, Yifan Gao, Priyanka Nigam, Sreyashi Nag, Bing Yin, Yining Hua, Xuan Zhou, Omid Rohanian, Anshul Thakur, Lei Clifton, David Clifton

MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation (2025.emnlp-main)

Challenge:	Existing studies focus on evaluating large language models in close-ended QA tasks, but many clinical decisions involve answering open-ended questions without pre-set options.
Approach:	They construct a benchmark to better understand large language models in the clinic . they use existing datasets to evaluate LLMs in clinical situations .
Outcome:	The proposed model outperforms human experts in multiple medical tasks.

Copied to clipboard

Weihao Xuan, Rui Yang, Heli Qi, Qingcheng Zeng, Yunze Xiao, Aosong Feng, Dairui Liu, Yun Xing, Junjue Wang, Fan Gao, Jinghui Lu, Yuang Jiang, Huitao Li, Xin Li, Kunyu Yu, Ruihai Dong, Shangding Gu, Yuekang Li, Xiaofei Xie, Felix Juefei-Xu, Foutse Khomh, Osamu Yoshie, Qingyu Chen, Douglas Teodoro, Nan Liu, Randy Goebel, Lei Ma, Edison Marrese-Taylor, Shijian Lu, Yusuke Iwasawa, Yutaka Matsuo, Irene Li

Multilinguality

Challenge:	Existing large language model evaluation benchmarks focus on English, while current multilingual tasks lack parallel questions that specifically assess cross-lingual reasoning abilities.
Approach:	They propose a comprehensive benchmark covering 29 languages, built on an English benchmark.
Outcome:	The MMLU-ProX is a comprehensive benchmark covering 29 languages, built on an English benchmark.

Weighted Contrastive Learning With False Negative Control to Help Long-tailed Product Classification (2023.acl-industry)

Copied to clipboard

Tianqi Wang, Lei Chen, Xiaodan Zhu, Younghun Lee, Jing Gao

OTExtSum: Extractive Text Summarisation with Optimal Transport (2022.findings-naacl)

Challenge:	Item categorization (IC) aims to classify a product into leaf nodes in a categorical taxonomy due to scarce supervision.
Approach:	They propose to use K-positive contrastive loss (KCL) to address IC task’s long-tail issue by re-weighting positive pairs in the KCL loss with a regularization that the sum of weights should be constrained to K+1 as close as possible.
Outcome:	The proposed method improves on the long-tail issue in the image classification task and when using text-based contrastive learning, it can be applied on the IC task.

Copied to clipboard

Peggy Tang, Kun Hu, Rui Yan, Lei Zhang, Junbin Gao, Zhiyong Wang

Information Extraction & Text Mining

Challenge:	Extractive text summarisation aims to select salient sentences from a document to form a short yet informative summary.
Approach:	They propose to formulate extractive text summarisation as an Optimal Transport (OT) problem and use it to obtain an optimal summary that minimises the transportation cost to a given document.
Outcome:	The proposed method outperforms state-of-the-art methods and learning-based methods on multiNews, PubMed, BillSum, and CNN/DM datasets.

AssistSR: Task-oriented Video Segment Retrieval for Personal AI Assistant (2022.findings-emnlp)

Copied to clipboard

Weixian Lei, Difei Gao, Yuxuan Wang, Dongxing Mao, Zihan Liang, Lingmin Ran, Mike Zheng Shou

FashionKLIP: Enhancing E-Commerce Image-Text Retrieval with Fashion Multi-Modal Conceptual Knowledge Graph (2023.acl-industry)

Challenge:	Currently, personal AI assistants on the phone and AR glasses can assist our daily life in addressing our questions like "how to adjust the date for this watch?"
Approach:	They propose a task that asks a question about affordance of items in our daily life . they construct a dataset that contains 3.2k multimodal questions on 1.6k video segments .
Outcome:	The proposed task outperforms baseline methods while still having room for improvement in the future.

Copied to clipboard

Xiaodan Wang, Chengyu Wang, Lei Li, Zhixu Li, Ben Chen, Linbo Jin, Jun Huang, Yanghua Xiao, Ming Gao

TIGEr: Text-to-Image Grounding for Image Caption Evaluation (D19-1)

Challenge:	Recent advances in visual-language pre-trained (VLP) models have greatly improved cross-modal retrieval performance . however, the fine-grained interactions between objects from different modalities are far from well-established . e-commerce domain lacks sufficient training data and fine-granular cross-modulal knowledge .
Approach:	They propose a visual-language pre-trained (VLP) image-text retrieval model that integrates cross-modal knowledge into the model to improve performance.
Outcome:	The proposed model improves performance on e-commerce image-text retrieval task by a large margin.

Copied to clipboard

Ming Jiang, Qiuyuan Huang, Lei Zhang, Xin Wang, Pengchuan Zhang, Zhe Gan, Jana Diesner, Jianfeng Gao

Prediction of People’s Emotional Response towards Multi-modal News (2022.aacl-main)

Challenge:	Existing metrics based on text-level comparisons fail to assess the quality of captions produced by machines.
Approach:	They propose to use a machine-learned text-image grounding model to measure the accuracy of machine-generated captions and their correlation with human judgments.
Outcome:	The proposed metric has higher consistency with human judgments and is more accurate than existing metrics.

Copied to clipboard

Ge Gao, Sejin Paik, Carley Reardon, Yanling Zhao, Lei Guo, Prakash Ishwar, Margrit Betke, Derry Tanti Wijaya

ZigZagKV: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty (2025.coling-main)

Challenge:	BU-NEmo dataset extends from 320 to 1,297 news headline and lead image pairings and collects 38,910 annotations in a crowdsourcing experiment.
Approach:	They extend the U.S. gun violence news-to-emotions dataset from 320 to 1,297 news headline and lead image pairings and collect annotations in a crowdsourcing experiment.
Outcome:	The proposed models outperform baseline models on the NEmo+ dataset by large margins across several metrics.

Copied to clipboard

Meizhi Zhong, Xikai Liu, Chen Zhang, Yikun Lei, Yan Gao, Yao Hu, Kehai Chen, Min Zhang

MobiZO: Enabling Efficient LLM Fine-Tuning at the Edge via Inference Engines (2025.emnlp-main)

Challenge:	Existing methods to accelerate inference of Large Language models (LLMs) are limited in their ability to retain key tokens as input length increases.
Approach:	They propose a method that leverages layer uncertainty to allocate budget size for each layer to reduce memory usage.
Outcome:	The proposed method reduces memory usage of the KV caches to only 20% when compared to full KV inference while achieving nearly lossless performance.

Copied to clipboard

Lei Gao, Amir Ziashahabi, Yue Niu, Salman Avestimehr, Murali Annavaram

REO-Relevance, Extraness, Omission: A Fine-grained Evaluation for Image Captioning (D19-1)

Challenge:	Large Language Models (LLMs) are currently pre-trained and fine-tuned on large cloud servers . fine-timing on resource-constrained edge devices presents significant memory and computational demands .
Approach:	They propose a resource-efficient fine-tuning framework for LLMs specifically designed for edge devices.
Outcome:	Experiments show that MobiZO achieves substantial runtime speedups and memory savings while improving fine-tuning accuracy.

Copied to clipboard

Ming Jiang, Junjie Hu, Qiuyuan Huang, Lei Zhang, Jana Diesner, Jianfeng Gao

DELTA: Dynamic Layer-Aware Token Attention for Efficient Long-Context Reasoning (2026.findings-acl)

Challenge:	Existing metrics for image captioning evaluation provide an overall quality score, which is difficult to infer specific description errors.
Approach:	They propose a fine-grained evaluation method REO for automatically measuring the performance of image captioning systems.
Outcome:	The proposed method achieves higher consistency with human judgments and provides more intuitive evaluation results than other metrics.

Copied to clipboard

Hossein Entezari Zarch, Lei Gao, Chaoyi Jiang, Murali Annavaram

Responsible & Trustworthy NLP

Challenge:	Large reasoning models generate long chains of intermediate steps, but their inference cost is dominated by decoding, where each new token must attend to the entire growing sequence.
Approach:	They propose a training-free sparse attention mechanism that reduces inference cost by evicting entries from the key-value cache.
Outcome:	The proposed model matches or surpasses full attention on reasoning benchmarks . it reduces the number of attended tokens by up to 4.25 and delivers 1.54 speedup .

VLMInferSlow: Evaluating the Efficiency Robustness of Large Vision-Language Models as a Service (2025.acl-long)

Copied to clipboard

Xiasi Wang, Tianliang Yao, Simin Chen, Runqi Wang, Lei Ye, Kuofeng Gao, Yi Huang, Yuan Yao

Responsible & Trustworthy NLP

Challenge:	Existing studies evaluate efficiency robustness of vision-language models under unrealistic assumptions, requiring access to model architecture and parameters.
Approach:	They propose a novel approach to evaluate VLM efficiency robustness in a realistic black-box setting.
Outcome:	The proposed approach generates adversarial images with imperceptible perturbations, increasing the computational cost by up to 128.47%.

Breaking through Deterministic Barriers: Randomized Pruning Mask Generation and Selection (2023.findings-emnlp)

Copied to clipboard

Jianwei Li, Weizhi Gao, Qi Lei, Dongkuan Xu