论文检索

Applications · Health / Medicine

Olga Ovcharenko, Florian Barkmann, Philip Toma, Imant Daunhawer, Julia Vogt, Sebastian Schelter, Valentina Boeva

Self-supervised learning (SSL) has proven to be a powerful approach for extracting biologically meaningful representations from single-cell data. To advance our understanding of SSL methods applied to single-cell data, we present scSSL-Bench, a comprehensive benchmark that evaluates nineteen SSL methods. Our evaluation spans nine datasets and focuses on three common downstream tasks: batch correction, cell type annotation, and missing modality prediction. Furthermore, we systematically assess various data augmentation strategies. Our analysis reveals task-specific trade-offs: the specialized single-cell frameworks, scVI, CLAIRE, and the finetuned scGPT excel at uni-modal batch correction, while generic SSL methods, such as VICReg and SimCLR, demonstrate superior performance in cell typing and multi-modal data integration. Random masking emerges as the most effective augmentation technique across all tasks, surpassing domain-specific augmentations. Notably, our results indicate the need for a specialized single-cell multi-modal data integration framework. scSSL-Bench provides a standardized evaluation platform and concrete recommendations for applying SSL to single-cell analysis, advancing the convergence of deep learning and single-cell genomics.

Applications

Patara Trirat, Wonyong Jeong, Sung Ju Hwang

Automated machine learning (AutoML) accelerates AI development by automating tasks in the development pipeline, such as optimal model search and hyperparameter tuning. Existing AutoML systems often require technical expertise to set up complex tools, which is in general time-consuming and requires a large amount of human effort. Therefore, recent works have started exploiting large language models (LLM) to lessen such burden and increase the usability of AutoML frameworks via a natural language interface, allowing non-expert users to build their data-driven solutions. These methods, however, are usually designed only for a particular process in the AI development pipeline and do not efficiently use the inherent capacity of the LLMs. This paper proposes *AutoML-Agent*, a novel multi-agent framework tailored for full-pipeline AutoML, i.e., from data retrieval to model deployment. *AutoML-Agent* takes user's task descriptions, facilitates collaboration between specialized LLM agents, and delivers deployment-ready models. Unlike existing work, instead of devising a single plan, we introduce a retrieval-augmented planning strategy to enhance exploration to search for more optimal plans. We also decompose each plan into sub-tasks (e.g., data preprocessing and neural network design) each of which is solved by a specialized agent we build via prompting executing in parallel, making the search process more efficient. Moreover, we propose a multi-stage verification to verify executed results and guide the code generation LLM in implementing successful solutions. Extensive experiments on seven downstream tasks using fourteen datasets show that *AutoML-Agent* achieves a higher success rate in automating the full AutoML process, yielding systems with good performance throughout the diverse domains.

Reinforcement Learning · Deep RL

Bryan L. M. de Oliveira, Luana G. B. Martins, Bruno Brandão, Murilo L. da Luz, Telma Woerle de Lima Soares, Luckeciano C. Melo

Effective visual representation learning is crucial for reinforcement learning (RL) agents to extract task-relevant information from raw sensory inputs and generalize across diverse environments. However, existing RL benchmarks lack the ability to systematically evaluate representation learning capabilities in isolation from other learning challenges. To address this gap, we introduce the Sliding Puzzles Gym (SPGym), a novel benchmark that transforms the classic 8-tile puzzle into a visual RL task with images drawn from arbitrarily large datasets. SPGym's key innovation lies in its ability to precisely control representation learning complexity through adjustable grid sizes and image pools, while maintaining fixed environment dynamics, observation, and action spaces. This design enables researchers to isolate and scale the visual representation challenge independently of other learning components. Through extensive experiments with model-free and model-based RL algorithms, we uncover fundamental limitations in current methods' ability to handle visual diversity. As we increase the pool of possible images, all algorithms exhibit in- and out-of-distribution performance degradation, with sophisticated representation learning techniques often underperforming simpler approaches like data augmentation. These findings highlight critical gaps in visual representation learning for RL and establish SPGym as a valuable tool for driving progress in robust, generalizable decision-making systems.

Deep Learning · Generative Models and Autoencoders

Zhengyu Fang, Zhimeng Jiang, Huiyuan Chen, Xiao Li, Jing Li

Tabular data generation has attracted significant research interest in recent years, with the tabular diffusion models greatly improving the quality of synthetic data. However, while memorization—where models inadvertently replicate exact or near-identical training data—has been thoroughly investigated in image and text generation, its effects on tabular data remain largely unexplored. In this paper, we conduct the first comprehensive investigation of memorization phenomena in diffusion models for tabular data. Our empirical analysis reveals that memorization appears in tabular diffusion models and increases with larger training epochs. We further examine the influence of factors such as dataset sizes, feature dimensions, and different diffusion models on memorization. Additionally, we provide a theoretical explanation for why memorization occurs in tabular diffusion models. To address this issue, we propose TabCutMix, a simple yet effective data augmentation technique that exchanges randomly selected feature segments between random same-class training sample pairs. Building upon this, we introduce TabCutMixPlus, an enhanced method that clusters features based on feature correlations and ensures that features within the same cluster are exchanged together during augmentation. This clustering mechanism mitigates out-of-distribution (OOD) generation issues by maintaining feature coherence. Experimental results across various datasets and diffusion models demonstrate that TabCutMix effectively mitigates memorization while maintaining high-quality data generation. Our code is available at https://github.com/fangzy96/TabCutMix.

Deep Learning · Large Language Models

Jiawei Zhang, Xuan Yang, Taiqi Wang, Yu Yao, Aleksandr Petiushko, Bo Li

Traditional autonomous driving systems often struggle to connect high-level reasoning with low-level control, leading to suboptimal and sometimes unsafe behaviors. Recent advances in multimodal large language models (MLLMs), which process both visual and textual data, offer an opportunity to unify perception and reasoning. However, effectively embedding precise safety knowledge into MLLMs for autonomous driving remains a significant challenge.To address this, we propose SafeAuto, a framework that enhances MLLM-based autonomous driving by incorporating both unstructured and structured knowledge. First, we introduce a Position-Dependent Cross-Entropy (PDCE) loss to improve low-level control signal predictions when values are represented as text. Second, to explicitly integrate safety knowledge, we develop a reasoning component that translates traffic rules into first-order logic (e.g., "red light => stop") and embeds them into a probabilistic graphical model (e.g., Markov Logic Network) to verify predicted actions using recognized environmental attributes.Additionally, our Multimodal Retrieval-Augmented Generation (RAG) model leverages video, control signals, and environmental attributes to learn from past driving experiences. Integrating PDCE, MLN, and Multimodal RAG, SafeAuto outperforms existing baselines across multiple datasets, enabling more accurate, reliable, and safer autonomous driving. The code is available at https://github.com/AI-secure/SafeAuto.

Applications · Health / Medicine

Ihab Bendidi, Yassir El Mesbahi, Alisandra Denton, Karush Suri, Kian Kenyon-Dean, Auguste Genovesio, Emmanuel Noutahi

Understanding cellular responses to stimuli is crucial for biological discovery and drug development. Transcriptomics provides interpretable, gene-level insights, while microscopy imaging offers rich predictive features but is harder to interpret. Weakly paired datasets, where samples share biological states, enable multimodal learning but are scarce, limiting their utility for training and multimodal inference. We propose a framework to enhance transcriptomics by distilling knowledge from microscopy images. Using weakly paired data, our method aligns and binds modalities, enriching gene expression representations with morphological information. To address data scarcity, we introduce (1) *Semi-Clipped*, an adaptation of CLIP for cross-modal distillation using pretrained foundation models, achieving state-of-the-art results, and (2) *PEA* (**P**erturbation **E**mbedding **A**ugmentation), a novel augmentation technique that enhances transcriptomics data while preserving inherent biological information. These strategies improve the predictive power and retain the interpretability of transcriptomics, enabling rich unimodal representations for complex biological tasks.

General Machine Learning · Supervised Learning

Chengyuan Li, Liangxiao Jiang, Wenjun Zhang, Liangjun Yu, Huan Zhang

Due to its simplicity, effectiveness and robustness, naive Bayes (NB) has continued to be one of the top 10 data mining algorithms. To improve its performance, a large number of improved algorithms have been proposed in the last few decades. However, in addition to Gaussian naive Bayes (GNB), there is little work on numerical attributes. At the same time, none of them takes into account the correlations among instances. To fill this gap, we propose a novel algorithm called instance correlation graph-based naive Bayes (ICGNB). Specifically, it first uses original attributes to construct an instance correlation graph (ICG) to represent the correlations among instances. Then, it employs a variational graph auto-encoder (VGAE) to generate new attributes from the constructed ICG and uses them to augment original attributes.Finally, it weights each augmented attribute to alleviate the attribute redundancy and builds GNB on the weighted attributes. The experimental results on tens of datasets show that ICGNB significantly outperforms its deserved competitors.Our codes and datasets are available at https://github.com/jiangliangxiao/ICGNB.

Deep Learning · Large Language Models

Seongheon Park, Xuefeng Du, Min-Hsuan Yeh, Haobo Wang, Sharon Li

Hallucinations in LLMs pose a significant concern to their safe deployment in real-world applications. Recent approaches have leveraged the latent space of LLMs for hallucination detection, but their embeddings, optimized for linguistic coherence rather than factual accuracy, often fail to clearly separate truthful and hallucinated content.To this end, we propose the **T**ruthfulness **S**eparator **V**ector (**TSV**), a lightweight and flexible steering vector that reshapes the LLM’s representation space during inference to enhance the separation between truthful and hallucinated outputs, without altering model parameters.Our two-stage framework first trains TSV on a small set of labeled exemplars to form compact and well-separated clusters.It then augments the exemplar set with unlabeled LLM generations, employing an optimal transport-based algorithm for pseudo-labeling combined with a confidence-based filtering process.Extensive experiments demonstrate that TSV achieves state-of-the-art performance with minimal labeled data, exhibiting strong generalization across datasets and providing a practical solution for real-world LLM applications.

Deep Learning · Large Language Models

Lutfi Erdogan, Hiroki Furuta, Sehoon Kim, Nicholas Lee, Suhong Moon, Gopala Anumanchipalli, Kurt Keutzer, Amir Gholaminejad

Large language models (LLMs) have shown remarkable advancements in enabling language agents to tackle simple tasks. However, applying them for complex, multi-step, long-horizon tasks remains a challenge. Recent work have found success by separating high-level planning from low-level execution, which enables the model to effectively balance high-level planning objectives and low-level execution details. However, generating accurate plans remains difficult since LLMs are not inherently trained for this task. To address this, we propose Plan-and-Act, a novel framework that incorporates explicit planning into LLM-based agents and introduces a scalable method to enhance plan generation through a novel synthetic data generation method. Plan-and-Act consists of a Planner model which generates structured, high-level plans to achieve user goals, and an Executor model that translates these plans into environment-specific actions. To train the Planner effectively, we introduce a synthetic data generation method that annotates ground-truth trajectories with feasible plans, augmented with diverse and extensive examples to enhance generalization. We evaluate Plan-and-Act using web navigation as a representative long-horizon planning environment, demonstrating a state-of-the-art 57.58% success rate on the WebArena-Lite benchmark as well as a text-only state-of-the-art 81.36% success rate on WebVoyager.

Applications · Computer Vision

Yuanhuiyi Lyu, Xu Zheng, Lutao Jiang, Yibo Yan, Xin Zou, Huiyu Zhou, Linfeng Zhang, Xuming Hu

Recent text-to-image generative models, e.g., Stable Diffusion V3 and Flux, have achieved notable progress. However, these models are strongly restricted to their limited knowledge, a.k.a., their own fixed parameters, that are trained with closed datasets. This leads to significant hallucinations or distortions when facing fine-grained and unseen novel real-world objects, e.g., the appearance of the Tesla Cybertruck. To this end, we present **the first** real-object-based retrieval-augmented generation framework (**RealRAG**), which augments fine-grained and unseen novel object generation by learning and retrieving real-world images to overcome the knowledge gaps of generative models. Specifically, to integrate missing memory for unseen novel object generation, we train a reflective retriever by **self-reflective contrastive learning**, which injects the generator's knowledge into the sef-reflective negatives, ensuring that the retrieved augmented images compensate for the model's missing knowledge. Furthermore, the real-object-based framework integrates fine-grained visual knowledge for the generative models, tackling the distortion problem and improving the realism for fine-grained object generation. Our Real-RAG is superior in its modular application to **all types** of state-of-the-art text-to-image generative models and also delivers **remarkable** performance boosts with all of them, such as a **gain of *16.18\%* FID score** with the auto-regressive model on the Stanford Car benchmark.

Applications · Computer Vision

Yu Zhou, Bingxuan Li, Mohan Tang, Xiaomeng Jin, Te-Lin Wu, Kuan-Hao Huang, Heng Ji, Kai-Wei Chang, Nanyun Peng

Large multimodal models (LMMs) often struggle to recognize novel concepts, as they rely on pre-trained knowledge and have limited ability to capture subtle visual details. Domain-specific knowledge gaps in training also make them prone to confusing visually similar, commonly misrepresented, or low-resource concepts. To help LMMs better align nuanced visual features with language, improving their ability to recognize and reason about novel or rare concepts, we propose a Contrastive visual Data Augmentation (CoDA) strategy. CoDA extracts key contrastive textual and visual features of target concepts against the known concepts they are misrecognized as, and then uses multimodal generative models to produce targeted synthetic data. Automatic filtering of extracted features and augmented images is implemented to guarantee their quality, as verified by human annotators. We show the effectiveness and efficiency of CoDA on low-resource concept and diverse scene recognition datasets including INaturalist and SUN. We additionally collect NovelSpecies, a benchmark dataset consisting of newly discovered animal species that are guaranteed to be unseen by LMMs. LLaVA-1.6 1-shot updating results on these three datasets show CoDA significantly improves SOTA visual data augmentation strategies by 12.3% (NovelSpecies), 5.1% (SUN), and 6.0% (iNat) absolute gains in accuracy.

Qianlan Yang, Yu-Xiong Wang

In offline reinforcement learning (RL), managing the distribution shift between the learned policy and the static offline dataset is a persistent challenge that can result in overestimated values and suboptimal policies. Traditional offline RL methods address this by introducing conservative biases that limit exploration to well-understood regions, but they often overly restrict the agent's generalization capabilities. Recent work has sought to generate trajectories using generative models to augment the offline dataset, yet these methods still struggle with overestimating synthesized data, especially when out-of-distribution samples are produced. To overcome this issue, we propose RTDiff, a novel diffusion-based data augmentation technique that synthesizes trajectories *in reverse*, moving from unknown to known states. Such reverse generation naturally mitigates the risk of overestimation by ensuring that the agent avoids planning through unknown states. Additionally, reverse trajectory synthesis allows us to generate longer, more informative trajectories that take full advantage of diffusion models' generative strengths while ensuring reliability. We further enhance RTDiff by introducing flexible trajectory length control and improving the efficiency of the generation process through noise management. Our empirical results show that RTDiff significantly improves the performance of several state-of-the-art offline RL algorithms across diverse environments, achieving consistent and superior results by effectively overcoming distribution shift.

Reinforcement Learning · Planning

Jan Robine, Marc Höftmann, Stefan Harmeling

What are the essential components of world models? How far do we get with world models that are not employing RNNs, transformers, discrete representations, and image reconstructions? This paper introduces SGF, a Simple, Good, and Fast world model that uses self-supervised representation learning, captures short-time dependencies through frame and action stacking, and enhances robustness against model errors through data augmentation. We extensively discuss SGF’s connections to established world models, evaluate the building blocks in ablation studies, and demonstrate good performance through quantitative comparisons on the Atari 100k benchmark. The code is available at https://github.com/jrobine/sgf.

Applications · Computer Vision

Itsumi Saito, Haruto Yoshida, Keisuke Sakaguchi

We address the challenge of automatically generating high-quality vector diagrams from hand-drawn sketches. Vector diagrams are essential for communicating complex ideas across various fields, offering flexibility and scalability. While recent research has progressed in generating diagrams from text descriptions, converting hand-drawn sketches into vector diagrams remains largely unexplored due to the lack of suitable datasets. To address this gap, we introduce SketikZ, a dataset comprising 3,231 pairs of hand-drawn sketches and thier corresponding TikZ codes as well as reference diagrams.Our evaluations reveal the limitations of state-of-the-art vision and language models (VLMs), positioning SketikZ as a key benchmark for future research in sketch-to-diagram conversion.Along with SketikZ, we present ImgTikZ, an image-to-TikZ model that integrates a 6.7B parameter code-specialized open-source large language model (LLM) with a pre-trained vision encoder. Despite its relatively compact size, ImgTikZ performs comparably to GPT-4o.This success is driven by using our two data augmentation techniques and a multi-candidate inference strategy.Our findings open promising directions for future research in sketch-to-diagram conversion and broader image-to-code generation tasks. SketikZ is publicly available.

Applications · Computer Vision

Jingcheng Ke, Jun-Cheng Chen, I-Hong Jhuo, Chia-Wen Lin, Yen-Yu Lin

Referring expression generation (REG) and comprehension (REC) are vital and complementary in joint visual and textual reasoning. Existing REC datasets typically contain insufficient image-expression pairs for training, hindering the generalization of REC models to unseen referring expressions. Moreover, REG methods frequently struggle to bridge the visual and textual domains due to the limited capacity, leading to low-quality and restricted diversity in expression generation. To address these issues, we propose a novel VIsion-guided Expression Diffusion Model (VIE-DM) for the REG task, where diverse synonymous expressions adhering to both image and text contexts of the target object are generated to augment REC datasets. VIE-DM consists of a vision-text condition (VTC) module and a transformer decoder. Our VTC and token selection design effectively addresses the feature discrepancy problem prevalent in existing REG methods. This enables us to generate high-quality, diverse synonymous expressions that can serve as augmented data for REC model learning. Extensive experiments on five datasets demonstrate the high quality and large diversity of our generated expressions. Furthermore, the augmented image-expression pairs consistently enhance the performance of existing REC models, achieving state-of-the-art results.

Applications · Robotics

Royina Karegoudra Jayanth, Yinshuang Xu, Ziyun Wang, Evangelos Chatzipantazis, Kostas Daniilidis, Daniel Gehrig

Neural network-based odometry using accelerometer and gyroscope readings from a single IMU can achieve robust, and low-drift localization capabilities, through the use of _neural displacement priors (NDPs)_. These priors learn to produce denoised displacement measurements but need to ignore data variations due to specific IMU mount orientation and motion directions, hindering generalization.This work introduces EqNIO, which addresses this challenge with _canonical displacement priors_, i.e., priors that are invariant to the orientation of the gravity-aligned frame in which the IMU data is expressed. We train such priors on IMU measurements, that are mapped into a learnable canonical frame, which is uniquely defined via three axes: the first is gravity, making the frame gravity aligned, while the second and third are predicted from IMU data. The outputs (displacement and covariance) are mapped back to the original gravity-aligned frame. To maximize generalization, we find that these learnable frames must transform equivariantly with global gravity-preserving roto-reflections from the subgroup $O_g(3)\subset O(3)$, acting on the trajectory, rendering the NDP $O(3)$-_subequivariant_. We tailor specific linear, convolutional, and non-linear layers that commute with the actions of the group. Moreover, we introduce a bijective decomposition of angular rates into vectors that transform similarly to accelerations, allowing us to leverage both measurement types. Natively, angular rates would need to be inverted upon reflection, unlike acceleration, which hinders their joint processing. We highlight EqNIO's flexibility and generalization capabilities by applying it to both filter-based (TLIO), and end-to-end (RONIN) architectures, and outperforming existing methods that use _soft equivariance from auxiliary losses or data augmentation on various datasets. We believe this work paves the way for low-drift and generalizable neural inertial odometry on edge devices. The project details and code can be found at [https://github.com/RoyinaJayanth/EqNIO](https://github.com/RoyinaJayanth/EqNIO).

Deep Learning · Large Language Models

Zitong Yang, Neil Band, Shuangping Li, Emmanuel Candes, Tatsunori Hashimoto

Pretraining on large-scale, unstructured internet text enables language models to acquire a significant amount of world knowledge.However, this knowledge acquisition is data-inefficient---to learn a fact, models must be trained on hundreds to thousands of diverse representations of it.This poses a challenge when adapting a pretrained model to a small corpus of domain-specific documents, where each fact may appear rarely or only once.We propose to bridge this gap with synthetic continued pretraining: using the small domain-specific corpus to synthesize a large corpus more amenable to learning, and then performing continued pretraining on the synthesized corpus.We instantiate this proposal with EntiGraph, a synthetic data augmentation algorithm that extracts salient entities from the source corpus and then generates diverse text by drawing connections between those entities.Synthetic continued pretraining with EntiGraph enables a language model to answer questions and follow generic instructions related to the source documents without access to them.If the source documents are instead available at inference time, we show that the knowledge acquired through our approach compounds with retrieval-augmented generation.To better understand these results, we build a simple mathematical model of EntiGraph, and show how synthetic data augmentation can "rearrange" knowledge to enable more data-efficient learning.

Deep Learning · Large Language Models

Zitong Yang, Neil Band, Shuangping Li, Emmanuel Candes, Tatsunori Hashimoto

Pretraining on large-scale, unstructured internet text enables language models to acquire a significant amount of world knowledge.However, this knowledge acquisition is data-inefficient---to learn a fact, models must be trained on hundreds to thousands of diverse representations of it.This poses a challenge when adapting a pretrained model to a small corpus of domain-specific documents, where each fact may appear rarely or only once.We propose to bridge this gap with synthetic continued pretraining: using the small domain-specific corpus to synthesize a large corpus more amenable to learning, and then performing continued pretraining on the synthesized corpus.We instantiate this proposal with EntiGraph, a synthetic data augmentation algorithm that extracts salient entities from the source corpus and then generates diverse text by drawing connections between those entities.Synthetic continued pretraining with EntiGraph enables a language model to answer questions and follow generic instructions related to the source documents without access to them.If the source documents are instead available at inference time, we show that the knowledge acquired through our approach compounds with retrieval-augmented generation.To better understand these results, we build a simple mathematical model of EntiGraph, and show how synthetic data augmentation can "rearrange" knowledge to enable more data-efficient learning.

Applications · Computer Vision

Ziqi Pang, Xin Xu, Yu-Xiong Wang

With success in image generation, generative diffusion models are increasingly adopted for discriminative scenarios because generating pixels is a unified and natural perception interface. Although directly re-purposing their generative denoising process has established promising progress in specialist (e.g., depth estimation) and generalist models, the inherent gaps between a generative process and discriminative objectives are rarely investigated. For instance, generative models can tolerate deviations at intermediate sampling steps as long as the final distribution is reasonable, while discriminative tasks with rigorous ground truth for evaluation are sensitive to such errors. Without mitigating such gaps, diffusion for perception still struggles on tasks represented by multi-modal understanding (e.g., referring image segmentation). Motivated by these challenges, we analyze and improve the alignment between the generative diffusion process and perception objectives centering around the key observation: how perception quality evolves with the denoising process. (1) Notably, earlier denoising steps contribute more than later steps, necessitating a tailored learning objective for training: loss functions should reflect varied contributions of timesteps for each perception task. (2) Perception quality drops unexpectedly at later denoising steps, revealing the sensitiveness of perception to training-denoising distribution shift. We introduce diffusion-tailored data augmentation to simulate such drift in the training data. (3) We suggest a novel perspective to the long-standing question: why should a generative process be useful for discriminative tasks - interactivity. The denoising process can be leveraged as a controllable user interface adapting to users' correctional prompts and conducting multi-round interaction in an agentic workflow. Collectively, our insights enhance multiple generative diffusion-based perception models without architectural changes: state-of-the-art diffusion-based depth estimator, previously underplayed referring image segmentation models, and perception generalists. Our code is available at https://github.com/ziqipang/ADDP.

Deep Learning · Generative Models and Autoencoders

Zihan Ye, Shreyank Gowda, Shiming Chen, Xiaowei Huang, Haotian Xu, Fahad Khan, Yaochu Jin, Kaizhu Huang, Xiaobo Jin

Zero-shot Learning (ZSL) aims to enable classifiers to identify unseen classes. This is typically achieved by generating visual features for unseen classes based on learned visual-semantic correlations from seen classes. However, most current generative approaches heavily rely on having a sufficient number of samples from seen classes. Our study reveals that a scarcity of seen class samples results in a marked decrease in performance across many generative ZSL techniques. We argue, quantify, and empirically demonstrate that this decline is largely attributable to spurious visual-semantic correlations. To address this issue, we introduce ZeroDiff, an innovative generative framework for ZSL that incorporates diffusion mechanisms and contrastive representations to enhance visual-semantic correlations. ZeroDiff comprises three key components: (1) Diffusion augmentation, which naturally transforms limited data into an expanded set of noised data to mitigate generative model overfitting; (2) Supervised-contrastive (SC)-based representations that dynamically characterize each limited sample to support visual feature generation; and (3) Multiple feature discriminators employing a Wasserstein-distance-based mutual learning approach, evaluating generated features from various perspectives, including pre-defined semantics, SC-based representations, and the diffusion process. Extensive experiments on three popular ZSL benchmarks demonstrate that ZeroDiff not only achieves significant improvements over existing ZSL methods but also maintains robust performance even with scarce training data. Our codes are available at https://github.com/FouriYe/ZeroDiff_ICLR25.