IMAGE CLASSIFICATION

Generating Natural Language Adversarial Examples through Probability Weighted Word Saliency (P19-1)

Challenge:	AutoTrain is an open-source, no code tool/library which can be used to train models on custom datasets.
Approach:	They propose an open-source, no-code tool/library to train models on custom datasets.
Outcome:	The open-source, no-code tool/library can be used to train models on custom datasets.

Copied to clipboard

Shuhuai Ren, Yihe Deng, Kun He, Wanxiang Che

A Combinatorial Approach to Neural Emergent Communication (2025.coling-main)

Challenge:	Existing approaches to attack text classification are limited due to the complexity of the problem.
Approach:	They propose a greedy algorithm to generate adversarial examples that maintain lexical correctness, grammatical correctiness and semantic similarity.
Outcome:	The proposed algorithm maintains lexical correctness, grammatical correctity and semantic similarity well and is hard for humans to perceive.

Copied to clipboard

Zheyuan Zhang

Faithful and Plausible Natural Language Explanations for Image Classification: A Pipeline Approach (2024.findings-emnlp)

Challenge:	Existing research on emergent communication uses the Lewis signaling game . however, the training data is limited and the messages are often ineffective .
Approach:	They propose a combinatorial algorithm to solve the symbolic complexity for classification, which is the minimum number of symbols in the message for successful communication.
Outcome:	The proposed algorithm increases the number of effective symbols in the emergent language.

Copied to clipboard

Adam Wojciechowski, Mateusz Lango, Ondrej Dusek

Explainability & Interpretability in NLP

Challenge:	Existing explanation methods for image classification struggle to provide faithful and plausible explanations for predictions.
Approach:	They propose a natural language explanation method that can be applied to any CNN-based classifier without altering its training process or affecting predictive performance.
Outcome:	The proposed method can be applied to any CNN-based classifier without altering its training process or affecting predictive performance.

Are Sample-Efficient NLP Models More Robust? (2023.acl-short)

Copied to clipboard

Nelson F. Liu, Ananya Kumar, Percy Liang, Robin Jia

Multilingual Image Corpus – Towards a Multimodal and Multilingual Dataset (2022.lrec-1)

Challenge:	Recent work in image classification and extractive question answering have observed that pre-trained models trained on less in-distribution data have better out-of-distortion performance.
Approach:	They conduct a large empirical study to investigate the relationship between sample efficiency and robustness.
Outcome:	The results show that pre-trained models with lower sample efficiency perform better on some tasks but not others.

Copied to clipboard

Svetla Koeva, Ivelina Stoyanova, Jordan Kralev

Visual Data in NLP

Challenge:	The goal of the project Multilingual Image Corpus is to provide a large image dataset with annotated objects and object descriptions in 24 languages.
Approach:	They propose to provide a large image dataset with annotated objects and object descriptions in 24 languages.
Outcome:	The project provides a large image dataset with annotated objects and object descriptions in 24 languages.

Continual and Multi-Task Architecture Search (P19-1)

Copied to clipboard

Ramakanth Pasunuru, Mohit Bansal

Learning with Latent Language (N18-1)

Challenge:	Recent studies have shown that architecture search can improve performance on language modeling and image classification tasks with reasonable training speed.
Approach:	They propose a continual architecture search approach that continually evolves the model parameters during sequential training of several tasks without losing performance on previously learned tasks.
Outcome:	The proposed approach improves language modeling and image classification with reasonable training speed and a weight-sharing strategy.

Copied to clipboard

Jacob Andreas, Dan Klein, Sergey Levine

Information Extraction & Text Mining

Challenge:	Using the space of natural language strings as a parameter space is an effective way to capture natural task structure.
Approach:	They propose to use natural language as a parameter space for few-shot learning problems including classification, transduction and policy search.
Outcome:	The proposed model outperforms models with a linguistic parameterization on image classification, text editing, and reinforcement learning.

Annealing Knowledge Distillation (2021.eacl-main)

Copied to clipboard

Aref Jafari, Mehdi Rezagholizadeh, Pranav Sharma, Ali Ghodsi

Generalized but not Robust? Comparing the Effects of Data Modification Methods on Out-of-Domain Generalization and Adversarial Robustness (2022.findings-acl)

Challenge:	Knowledge distillation (KD) is a powerful model compression technique for deep neural networks.
Approach:	They propose a method to feed the rich information provided by teacher’s soft-targets incrementally and more efficiently by annealing the teacher output incrementally.
Outcome:	The proposed method can be used on image classification and NLP language inference tasks with BERT-based models on the GLUE benchmark.

Copied to clipboard

Tejas Gokhale, Swaroop Mishra, Man Luo, Bhavdeep Sachdeva, Chitta Baral

CPL: Counterfactual Prompt Learning for Vision and Language Models (2022.emnlp-main)

Challenge:	Data modification has been proposed as an effective solution for generalizing to out-of-domain (OOD) inputs.
Approach:	They propose to use data modification to generalize to out-of-domain inputs . they also analyze their adversarial robustness using a synthetic dataset .
Outcome:	The proposed data modification strategies improve OOD accuracy and AR, but data filtering hurts OOD on other tasks.

Copied to clipboard

Xuehai He, Diji Yang, Weixi Feng, Tsu-Jui Fu, Arjun Akula, Varun Jampani, Pradyumna Narayana, Sugato Basu, William Yang Wang, Xin Wang

Semantic Text Processing

Challenge:	Existing prompt tuning methods tend to learn spurious or entangled representations, leading to poor generalization to unseen concepts.
Approach:	They propose a prompt tuning technique that tunes the learnable prompt for pre-trained vision and language models.
Outcome:	The proposed method improves few-shot performance on vision and language tasks over existing prompt tuning methods.

FENAS: Flexible and Expressive Neural Architecture Search (2020.findings-emnlp)

Copied to clipboard

Ramakanth Pasunuru, Mohit Bansal

Mixup-Transformer: Dynamic Data Augmentation for NLP Tasks (2020.coling-main)

Challenge:	Recent approaches to architecture search have shown good improvements in terms of performance with reasonable training speed.
Approach:	They propose an algorithm with more activation functions, input edges, and atomic operations to search for architectures that are optimal for given task.
Outcome:	The proposed algorithm reproduces well-known LSTM and GRU architectures and initializes with them for finding architectures more efficiently.

Copied to clipboard

Lichao Sun, Congying Xia, Wenpeng Yin, Tingting Liang, Philip Yu, Lifang He

Rethinking Skip Connection with Layer Normalization (2020.coling-main)

Challenge:	Recent work on data augmentation techniques that interpolate inputs and labels shows strong effectiveness in image classification.
Approach:	They propose to integrate mixup to transformer-based pre-trained architecture for NLP tasks while keeping the whole end-to-end training system.
Outcome:	The proposed framework improves on GLUEbenchmark and transformer-based learning models while keeping the whole end-to-end training system.

Copied to clipboard

Fenglin Liu, Xuancheng Ren, Zhiyuan Zhang, Xu Sun, Yuexian Zou

Challenge:	Existing methods to solve the optimization problem of deep neural networks are not linear, but can be used as a modulating mechanism between the input and output.
Approach:	They propose to use skip connection to adjust the scale of the input and output to improve the performance.
Outcome:	The proposed approach improves performance and convergence of deep neural networks and can be applied to machine translation and image classification datasets.

Tiny Budgets, Big Gains: Parameter Placement Strategy in Parameter Super-Efficient Fine-Tuning (2025.emnlp-main)

Copied to clipboard

Jinman Zhao, Xueyan Zhang, Jiaru Li, Jingcheng Niu, Yulan Hu, Erxue Min, Gerald Penn

Green & Sustainable NLP

Challenge:	Existing methods such as LoRA and VeRA use memory-efficient methods to fine-tune large language models.
Approach:	They propose a method that uses only 1–5% of the standard LoRA parameters and achieves state-of-the-art performance across a wide range of tasks.
Outcome:	The proposed method achieves state-of-the-art performance across a wide range of tasks using only 1–5% of the standard LoRA parameters.

An Effective Label Noise Model for DNN Text Classification (N19-1)

Copied to clipboard

Ishan Jindal, Daniel Pressel, Brian Lester, Matthew Nokleby

Information Extraction & Text Mining

Challenge:	Existing methods to train deep neural networks with label noise are limited to image classification models . label noise is important because of the large number of errors and errors in training datasets .
Approach:	They propose a non-linear processing layer that models label noise into a convolutional neural network (CNN) they add a noise model layer on top of their target model to account for label noise .
Outcome:	The proposed approach is robust to label noise and can learn better sentences . it is based on extensive experiments on text classification datasets .

ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension (2022.acl-long)

Copied to clipboard

Sanjay Subramanian, William Merrill, Trevor Darrell, Matt Gardner, Sameer Singh, Anna Rohrbach

XtremeCLIP: Extremely Parameter-efficient Tuning for Low-resource Vision Language Understanding (2023.findings-acl)

Challenge:	Visual referring expression comprehension (ReC) models can be trained for a domain, but it remains unclear if they can be applied in a zero-shot manner to more complex tasks like ReC.
Approach:	They propose a method that repurposes CLIP, a state-of-the-art large-scale model, for training a referring expression comprehension model for a new visual domain.
Outcome:	The proposed model reduces the gap between zero-shot baselines from prior work and supervised models by as much as 29% on RefCOCOg, and on ReFGTA (video game imagery), and its relative improvement over supervised ReC models is 8%.

Copied to clipboard

Moming Tang, Chengyu Wang, Jianing Wang, Chuanqi Tan, Songfang Huang, Cen Chen, Weining Qian

Depth Aware Hierarchical Replay Continual Learning for Knowledge Based Question Answering (2024.lrec-main)

Challenge:	Existing approaches to fine-tune visual-language understanding (VLU) require tasks-specific designs and sufficient training data.
Approach:	They propose a simple yet efficient paradigm for low-resource Visual Language Understanding (VLU) they reformulate a series of VLU tasks as an open-book affinity-matching problem.
Outcome:	The proposed framework outperforms baselines in low-resource settings.

Copied to clipboard

Zhixiong Cao, Hai-Tao Zheng, Yangning Li, Jin Xu, Rongsheng Li, Hong-Gee Kim

Pro-KD: Progressive Distillation by Following the Footsteps of the Teacher (2022.coling-1)

Challenge:	Continual learning models adapt well to the latest data but lose ability to remember past data due to changes in the data source.
Approach:	They propose a hierarchical replay framework that allows models to keep a small memory of previous learned data that uses replay.
Outcome:	The proposed model outperforms previous continual learning methods in mitigating catastrophic forgetting.

Copied to clipboard

Mehdi Rezagholizadeh, Aref Jafari, Puneeth S.M. Saladi, Pranav Sharma, Ali Saheb Pasand, Ali Ghodsi

Is it Time to Swish? Comparing Deep Learning Activation Functions Across NLP tasks (D18-1)

Challenge:	Knowledge distillation (KD) is a powerful tool for deep learning applications.
Approach:	They propose a method which defines a smoother training path for the student by following the training footprints of the teacher rather than solely relying on distilling from a single mature fully-trained teacher.
Outcome:	The proposed technique is quite effective in mitigating the capacity-gap problem and the checkpoint search problem.

Copied to clipboard

Steffen Eger, Paul Youssef, Iryna Gurevych

Challenge:	Activation functions are nonlinearities which have been attributed to the success story of deep learning.
Approach:	They propose to use a penalized tanh function to replace the sigmoid and tansh gates in LSTM cells and to improve the performance of the activation function.
Outcome:	The proposed activation function performs best on all tasks and can replace the sigmoid and tanh gates in LSTM cells.

LM-Searcher: Cross-domain Neural Architecture Search with LLMs via Unified Numerical Encoding (2025.emnlp-main)

Copied to clipboard

Yuxuan Hu, Jihao Liu, Ke Wang, Jinliang Zheng, Weikang Shi, Manyuan Zhang, Qi Dou, Rui Liu, Aojun Zhou, Hongsheng Li

Semantic Text Processing

Challenge:	Recent advances in Large Language Models have opened new avenues for solving complex optimization problems, including Neural Architecture Search (NAS).
Approach:	They propose a framework that leverages LLMs for cross-domain neural architecture optimization without extensive domain-specific tuning.
Outcome:	The proposed framework achieves competitive performance in both in-domain and out-of-domain tasks.

Visual Prompt Tuning for Few-Shot Text Classification (2022.coling-1)

Copied to clipboard

Jingyuan Wen, Yutian Luo, Nanyi Fei, Guoxing Yang, Zhiwu Lu, Hao Jiang, Jie Jiang, Zhao Cao

AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities (2023.findings-acl)

Challenge:	Existing work on pretraining models for text classification uses image encoders instead of visual prompts.
Approach:	They propose a method to deploy large-scale pre-trained models in the prompt-tuning paradigm in few-shot learning.
Outcome:	The proposed method outperforms the most recent prompt-tuning methods on five public text classification datasets.

Copied to clipboard

Zhongzhi Chen, Guang Liu, Bo-Wen Zhang, Qinghong Yang, Ledell Wu

Enhancing Interpretable Image Classification Through LLM Agents and Conditional Concept Bottleneck Models (2025.acl-long)

Challenge:	Existing methods to build a strong multilingual multimodal representation model are lacking in good-quality text-image pairs.
Approach:	They propose a method to build a strong multilingual multimodal representation model using English text-image pairs instead of a model from scratch.
Outcome:	The proposed model outperforms the original CLIP model on multilingual multimodal benchmarks.

Copied to clipboard

Yiwen Jiang, Deval Mehta, Wei Feng, Zongyuan Ge

Delving into the Openness of CLIP (2023.findings-acl)

Challenge:	Concept Bottleneck Models (CBMs) map visual representations to a set of humanunderstandable textual concepts, which are then interpreted by a linear combination of these concept scores.
Approach:	They propose a dynamic, agent-based approach that adjusts the concept bank in response to environmental feedback, optimizing the number of concepts for sufficiency yet concise coverage.
Outcome:	The proposed model improves classification accuracy by 6% and interpretability assessments by 30%.

Copied to clipboard

Shuhuai Ren, Lei Li, Xuancheng Ren, Guangxiang Zhao, Xu Sun

Visual Data in NLP

Challenge:	Contrastive Language-Image Pre-training (CLIP) allows for open-vocabulary visual recognition, where the model can recognize images from an open class set in a zero-shot manner.
Approach:	They propose to use image classification as an image-to-text matching task instead of discrete category IDs to achieve open-vocabulary visual recognition.
Outcome:	The proposed model can recognize images from an open vocabulary in a zero-shot manner, but its performance deteriorates as the vocabulary expands.

How Do Hyenas Deal with Human Speech? Speech Recognition and Translation with ConfHyena (2024.lrec-main)

Copied to clipboard

Marco Gaido, Sara Papi, Matteo Negri, Luisa Bentivogli

Text Generation

Challenge:	Currently, attention-based models face computational hurdles in processing long sequences due to its quadratic complexity.
Approach:	They propose a conformer whose encoder self-attentions are replaced with Hyena for speech processing . they propose 'confhyena' model that reduces training time by 27% at minimal cost .
Outcome:	The proposed model reduces training time by 27% at the cost of minimal quality degradation.

WISE: Weak-Supervision-Guided Step-by-Step Explanations for Multimodal LLMs in Image Classification (2025.emnlp-main)

Copied to clipboard

Yiwen Jiang, Deval Mehta, Siyuan Yan, Yaling Shen, Zimu Wang, Zongyuan Ge

SkillAggregation: Reference-free LLM-Dependent Aggregation (2025.acl-long)

Challenge:	Existing MCoT methods focus on inter-object reasoning, overlooking intra-object understanding crucial for image classification.
Approach:	They propose a Weak-supervision-guided Step-by-step Explanation method that reformulates MCoTs under weak supervision into concise, interpretable reasoning chains.
Outcome:	The proposed method improves interpretability by 37% and improves classification accuracy.

Copied to clipboard

Guangzhi Sun, Anmol Kagrecha, Potsawee Manakul, Phil Woodland, Mark Gales

Challenge:	Existing methods in NLP assign equal weight to all LLM judgments or are designed for specific tasks such as hallucination detection.
Approach:	They propose a method that learns to combine LLM judgments without additional data or ground truth to exploit the judge estimates during inference.
Outcome:	The proposed method outperforms Crowdlayer on all tasks and yields the best performance over all approaches on the majority of tasks.

SeqVAT: Virtual Adversarial Training for Semi-Supervised Sequence Labeling (2020.acl-main)

Copied to clipboard

Luoxin Chen, Weitong Ruan, Xinyue Liu, Jianhua Lu

PAD-Net: An Efficient Framework for Dynamic Networks (2023.acl-long)

Challenge:	Empirical studies show that virtual adversarial training (VAT) significantly improves the sequence labeling performance over baselines under supervised and semi-supervised settings.
Approach:	They propose a method which naturally applies VAT to sequence labeling models with conditional random field (CRF) Empirical studies show that SeqVAT significantly improves the sequence labelling performance over baselines under supervised settings, and outperforms state-of-the-art approaches under semi-supervised settings.
Outcome:	Empirical results show that the proposed method outperforms state-of-the-art approaches under semi-supervised settings.

Copied to clipboard

Shwai He, Liang Ding, Daize Dong, Boan Liu, Fuqiang Yu, Dacheng Tao

Green & Sustainable NLP

Challenge:	Dynamic networks can significantly improve the model’s representation power with acceptable computational cost.
Approach:	They propose a partially dynamic network to transform redundant dynamic parameters into static ones and iterative mode partition to partition dynamic and static parameters efficiently.
Outcome:	The proposed network surpasses fully dynamic networks by +0.7% top-1 acc with only 30% dynamic parameters for DY-Conv and +1.9% average score in language understanding with only 50% dynamic parameters.

Generalisation First, Memorisation Second? Memorisation Localisation for Natural Language Classification Tasks (2024.findings-acl)

Copied to clipboard

Verna Dankers, Ivan Titov

Text Classification

Challenge:	Memorisation in neural models is concerned due to overfitting and privacy concerns . a dominant hypothesis based on image classification is that lower layers learn generalisable features and deeper layers specialise and memorise.
Approach:	They apply 4 techniques to localise and edit models' memories.
Outcome:	The proposed method shows that memorisation is a gradual process rather than a localised one.

RanLoRA: Residual-aware Nonlinear Low-Rank Adaptation (2026.findings-acl)

Copied to clipboard

Xu Luo, Yongbin Liu, Chunping Ouyang, Ying Yu

MaCP: Minimal yet Mighty Adaptation via Hierarchical Cosine Projection (2025.acl-long)

Challenge:	Low-Rank Adaptation (LoRA) relying on linear low-rank projections restricts adaptation to linear subspaces, limiting flexibility on complex downstream tasks.
Approach:	They propose a nonlinear low-rank Adaptation approach that leverages pretrained weights to decompose them into principal components that are kept frozen and residual components that can be used for task-specific adaptation.
Outcome:	The proposed approach outperforms vanilla LoRA and representative variants on commonsense reasoning, image classification, and mathematical reasoning tasks.

Copied to clipboard

Yixian Shen, Qi Bi, Jia-hong Huang, Hongyi Zhu, Andy D. Pimentel, Anuj Pathania

Challenge:	MaCP is a new adaptation method for large foundation models that requires minimal parameters and memory for fine-tuning.
Approach:	They propose a method that exploits the superior energy compaction and decorrelation properties of cosine projection to improve model efficiency and accuracy.
Outcome:	The proposed method improves model efficiency and accuracy across a wide range of single-modality tasks including natural language understanding, natural language generation, text summarization, and multi-modalities such as image classification and video understanding.

RingFormer: Rethinking Recurrent Transformer with Adaptive Level Signals (2025.findings-emnlp)

Copied to clipboard

Jaemu Heo, Eldor Fozilov, Hyunmin Song, Taehwan Kim

CLIPErase: Efficient Unlearning of Visual-Textual Associations in CLIP (2025.acl-long)

Challenge:	Transformers have shown strong performance in processing sequential data, but their parameters are larger . a novel approach to reduce the model parameters while maintaining high performance is proposed .
Approach:	They propose a transformer-based model that processes input repeatedly in a circular, ring-like manner.
Outcome:	The proposed approach reduces model parameters while maintaining high performance . the proposed approach is validated in the experiments.

Copied to clipboard

Tianyu Yang, Lisen Dai, Xiangqi Wang, Minhao Cheng, Yapeng Tian, Xiangliang Zhang

Multimodality

Challenge:	MU has gained significant attention as a means to remove the influence of specific data from a trained model without requiring full retraining.
Approach:	They propose a novel approach that disentangles and selectively forgets both visual and textual associations, ensuring that unlearning does not compromise model performance.
Outcome:	Experiments on CIFAR-100, Flickr30K, and Conceptual 12M show that CLIPErase effectively removes designated associations from multimodal samples in downstream tasks while preserving model performance on retain set.

HTMuon: Improving Muon via Heavy-Tailed Spectral Correction (2026.findings-acl)

Copied to clipboard

Tianyu Pang, Yujie Fang, Zihang Liu, Shenyang Deng, Lei Hsiung, Shuhua Yu, Yaoqing Yang