论文检索

Computer Vision · Vision Models & Multimodal

Hanlei Zhang, zhuohang li, Hua Xu, Yeshuang Zhu, Peiwu Wang, Haige Zhu, Jie Zhou, Jinchao Zhang

Multimodal language analysis is a rapidly evolving field that leverages multiple modalities to enhance the understanding of high-level semantics underlying human conversational utterances. Despite its significance, little research has investigated the capability of multimodal large language models (MLLMs) to comprehend cognitive-level semantics. In this paper, we introduce MMLA, a comprehensive benchmark specifically designed to address this gap. MMLA comprises over 61K multimodal utterances drawn from both staged and real-world scenarios, covering six core dimensions of multimodal semantics: intent, emotion, dialogue act, sentiment, speaking style, and communication behavior. We evaluate eight mainstream branches of LLMs and MLLMs using three methods: zero-shot inference, supervised fine-tuning, and instruction tuning. Extensive experiments reveal that even fine-tuned models achieve only about 60~70% accuracy, underscoring the limitations of current MLLMs in understanding complex human language. We believe that MMLA will serve as a solid foundation for exploring the potential of large language models in multimodal language analysis and provide valuable resources to advance this field. The datasets and code are open-sourced at https://github.com/thuiar/MMLA.

Deep Learning · Theory

Benjamin Walker, Lingyi Yang, Nicola Muca Cirone, Cristopher Salvi, Terry Lyons

This work introduces Structured Linear Controlled Differential Equations (SLiCEs), a unifying framework for sequence models with structured, input-dependent state-transition matrices that retain the maximal expressivity of dense matrices whilst being cheaper to compute. The framework encompasses existing architectures, such as input-dependent block-diagonal linear recurrent neural networks and DeltaNet's diagonal-plus-low-rank structure, as well as two novel variants based on sparsity and the Walsh-Hadamard transform. We prove that, unlike the diagonal state-transition matrices of S4D and Mamba, SLiCEs employing block-diagonal, sparse, or Walsh-Hadamard matrices match the maximal expressivity of dense matrices. Empirically, SLiCEs solve the $A_5$ state-tracking benchmark with a single layer, achieve best-in-class length generalisation on regular language tasks among parallel-in-time models, and match the performance of log neural controlled differential equations on six multivariate time-series classification datasets while cutting the average time per training step by a factor of twenty.

Deep Learning · Generative Models and Autoencoders

Sian-Yao Huang, Li-Hsien Chang, Che-Yu Lin, Cheng-Lin Yang

Large language models (LLMs) are often prompted with multi-level directives, such as system instructions and user queries, that imply a hierarchy of authority. Yet models frequently fail to enforce this structure, especially in multi-step reasoning where errors propagate across intermediate steps. Existing methods rely on oracle completions but lack verifiable reward signals or intermediate traces, limiting their applicability. We introduce a unified supervision framework that embeds programmatically verifiable checkers into synthesized instruction-conflict instances. Each instance pairs a compliance directive with a conflicting one, along with an executable verifier that deterministically checks output adherence. This enables alignment without oracle labels or reasoning traces, supporting both instruction-tuned and reasoning models. The framework is instantiated via a synthesis pipeline that includes unit-test–based validation, LLM-assisted repair, and a probabilistic analysis of cleaning reliability. Fine-tuning on the resulting data improves instruction hierarchy adherence and boosts safety robustness, generalizing to adversarial safety benchmarks without task-specific supervision. This highlights verifiable supervision as a scalable foundation for robust alignment. All code, dataset, and verifier pipeline are publicly available at: https://github.com/cycraft-corp/BeyondOracle.

Data-centric AI · Data-centric AI methods and tools

Jiongli Zhu, Parjanya Prashant, Alex Cloninger, Babak Salimi

Data valuation techniques quantify each training example's contribution to model performance, providing a principled basis for data cleaning, acquisition, and selection. Existing valuation methods remain inadequate: \emph{model-based} techniques depend on a single fitted model and inherit its biases, while \emph{algorithm-based} approaches like Data Shapley scale poorly due to their need to train multiple models. Recent work has proposed model-agnostic alternatives based on Wasserstein distance between the training set and a clean reference set, but exact computation is expensive and approximations often misrank examples. We introduce KAIROS, a model-agnostic framework that values examples by their contribution to the Maximum Mean Discrepancy (MMD) between the training set and a clean reference distribution. Unlike Wasserstein methods, MMD admits a closed-form solution that requires no approximations and is scalable to large datasets. Additionally, KAIROS enables efficient online valuation: adding a new batch of $m$ examples requires only $O(mN)$ computation to update all scores, compared to $O(N^2)$ in prior work where $N$ is the training set size. Empirical evaluations on noise, mislabeling, and poisoning benchmarks show that KAIROS consistently outperforms state-of-the-art baselines in both accuracy and runtime. On ImageNet, KAIROS achieves up to 15 $\times$ speedup over the fastest baseline while maintaining superior data valuation quality. Our results demonstrate that model-agnostic methods can match or exceed model-based approaches in performance while scaling to large datasets.

Computer Vision · Classification and Understanding

Yunqing Liu, Nan Zhang, Fangjun Wang, Kengo Murata, Takuma Yamamoto, Osafumi Nakayama, Genta Suzuki, Zhiming Tan

Mamba, a lightweight sequence modeling framework offering near-linear complexity, presents a promising alternative to Transformers. In this work, we introduce MOGO (Mamba Only Glances Once), an end-to-end framework for efficient video action detection built entirely on the Mamba architecture. In MOGO, our newly designed Mamba-based decoder can even use just one Mamba layer to effectively perform action detection. It uses neither Transformer structures nor RCNN-like methods for proposal detection. Our framework introduces two key innovations. First, we propose a pure Mamba-based encoder-decoder architecture. The encoder processes cross-frame video information, while the decoder incorporates two novel Mamba-based structures that leverage Mamba’s intrinsic capabilities to detect actions. Theoretical analysis and ablation experiments confirm their synergy and the necessity of each structure. Second, we design a video token construction mechanism to improve the model's performance. The token importance block can ensure that the retained token information is highly relevant to the predicted targets. These two innovations make MOGO both efficient and accurate, as demonstrated on the JHMDB and UCF101-24 benchmark datasets. Compared to SOTA action detection methods, MOGO achieves superior performance in terms of GFLOPs, model parameters, and inference speed (latency) with comparable detection precision. Additionally, it requires significantly less GPU memory than some SOTA token reconstruction methods. Code is available at https://github.com/YunqingLiu-ML/MOGO.

General Machine Learning · Transfer, Multitask and Meta-learning

Benjamin Ramtoula, Pierre-Yves Lajoie, Paul Newman, Daniele De Martini

Foundation models (FMs) trained with different objectives and data learn diverse representations, making some more effective than others for specific downstream tasks. Existing adaptation strategies, such as parameter-efficient fine-tuning, focus on individual models and do not exploit the complementary strengths across models. Probing methods offer a promising alternative by extracting information from frozen models, but current techniques do not scale well with large feature sets and often rely on dataset-specific hyperparameter tuning. We propose Combined backBones (ComBo), a simple and scalable probing-based adapter that effectively integrates features from multiple models and layers. ComBo compresses activations from layers of one or more FMs into compact token-wise representations and processes them with a lightweight transformer for task-specific prediction. Crucially, ComBo does not require dataset-specific tuning or backpropagation through the backbone models. However, not all models are equally relevant for all tasks. To address this, we introduce a mechanism that leverages ComBo’s joint multi-backbone probing to efficiently evaluate each backbone’s task-relevance, enabling both practical model comparison and improved performance through selective adaptation. On the 19 tasks of the VTAB-1k benchmark, ComBo outperforms previous probing methods, matches or surpasses more expensive alternatives, such as distillation-based model merging, and enables efficient probing of tuned models. Our results demonstrate that ComBo offers a practical and general-purpose framework for combining diverse representations from multiple FMs.

Applications · Everything Else

Hwiwon Lee, Ziqi Zhang, Hanxiao Lu, LINGMING ZHANG

Rigorous security-focused evaluation of large language model (LLM) agents is imperative for establishing trust in their safe deployment throughout the software development lifecycle. However, existing benchmarks largely rely on synthetic challenges or simplified vulnerability datasets that fail to capture the complexity and ambiguity encountered by security engineers in practice. We introduce SEC-bench, the first fully automated benchmarking framework for evaluating LLM agents on authentic security engineering tasks. SEC-bench employs a novel multi-agent scaffold that automatically constructs code repositories with harnesses, reproduces vulnerabilities in isolated environments, and generates gold patches for reliable evaluation. Our framework automatically creates high-quality software vulnerability datasets with reproducible artifacts at a cost of only $0.87 per instance. Using SEC-bench, we implement two critical software security tasks to rigorously evaluate LLM agents' capabilities: proof-of-concept (PoC) generation and vulnerability patching. A comprehensive evaluation of state-of-the-art LLM code agents reveals significant performance gaps, achieving at most 18.0% success in PoC generation and 34.0% in vulnerability patching on our complete dataset. These results highlight the crucial steps needed toward developing LLM agents that are more practical, intelligent, and autonomous for security engineering.

Deep Learning · Algorithms

Zhenwei Zhang, Fanhua Shang, Hongying Liu, Liang Wan, Wei Feng, Yanming Hui

While model quantization has become pivotal for deploying super-resolution (SR) networks on mobile devices, existing works focus on quantization methods only for image super-resolution. Different from image super-resolution, the temporal error propagation, shared temporal parameterization, and temporal metric mismatch significantly degrade the performance of a video SR model. To address these issues, we propose the first quantization method, QBasicVSR, for video super-resolution. A novel temporal awareness adaptation post-training quantization (PTQ) framework for video super-resolution with the flow-gradient video bit adaptation and temporal shared layer bit adaptation is presented. Moreover, we put forward a novel fine-tuning method for VSR with the supervision of the full-precision model. Our method achieves extraordinary performance with state-of-the-art efficient VSR approaches, delivering up to $\times$200 faster processing speed while utilizing only 1/8 of the GPU resources. Additionally, extensive experiments demonstrate that the proposed method significantly outperforms existing PTQ algorithms on various datasets. For instance, it attains a 2.53 dB increase on the UDM10 benchmark when quantizing BasicVSR to 4-bit with 100 unlabeled video clips. The code and models will be released on GitHub.

Computer Vision · Everything Else

Qiyuan Guan, Xiang Chen, Guiyue Jin, Jiyu Jin, Shumin Fan, Tianyu Song, Jinshan Pan

Compared to daytime image deraining, nighttime image deraining poses significant challenges due to inherent complexities of nighttime scenarios and the lack of high-quality datasets that accurately represent the coupling effect between rain and illumination. In this paper, we rethink the task of nighttime image deraining and contribute a new high-quality benchmark, HQ-NightRain, which offers higher harmony and realism compared to existing datasets. In addition, we develop an effective Color Space Transformation Network (CST-Net) for better removing complex rain from nighttime scenes. Specifically, we propose a learnable color space converter (CSC) to better facilitate rain removal in the Y channel, as nighttime rain is more pronounced in the Y channel compared to the RGB color space. To capture illumination information for guiding nighttime deraining, implicit illumination guidance is introduced enabling the learned features to improve the model's robustness in complex scenarios. Extensive experiments show the value of our dataset and the effectiveness of our method. The source code and datasets are available at https://github.com/guanqiyuan/CST-Net.

Applications · Language, Speech and Dialog

Yang Xiao, Jiashuo WANG, Ruifeng Yuan, Chunpu Xu, Kaishuai Xu, Wenjie Li, Pengfei Liu

Large language models (LLMs) have demonstrated remarkable reasoning capabilities through test-time scaling approaches, particularly when fine-tuned with chain-of-thought (CoT) data distilled from more powerful large reasoning models (LRMs). However, these reasoning chains often contain verbose elements that mirror human problem-solving, categorized as progressive reasoning (the essential solution development path) and functional elements (verification processes, alternative solution approaches, and error corrections). While progressive reasoning is crucial, the functional elements significantly increase computational demands during test-time inference. We introduce PIR (Perplexity-based Importance Refinement), a principled framework that quantitatively evaluates the importance of each reasoning step based on its impact on answer prediction confidence. PIR systematically identifies and selectively prunes only low-importance functional steps while preserving all progressive reasoning components, creating optimized training data that maintains the integrity of the core solution path while reducing verbosity. Models fine-tuned on PIR-optimized data exhibit superior test-time scaling properties, generating more concise reasoning chains while achieving improved accuracy (+0.9\% to +6.6\%) with significantly reduced token usage (-3\% to -41\%) across challenging reasoning benchmarks (AIME, AMC, and GPQA Diamond). Our approach demonstrates strong generalizability across different model sizes, data sources, and token budgets, offering a practical solution for deploying reasoning-capable LLMs in scenarios where efficient test-time scaling, response time, and computational efficiency are valuable constraints. Code and dataset are available at the [LIMOPro GitHub repository.](https://github.com/GAIR-NLP/LIMOPro)

Computer Vision · Vision Models & Multimodal

Andrea Amaduzzi, Pierluigi Zama Ramirez, Giuseppe Lisanti, Samuele Salti, Luigi Di Stefano

Neural Radiance Fields (NeRFs) are neural networks -- typically multilayer perceptrons (MLPs) -- that represent the geometry and appearance of objects, with applications in vision, graphics, and robotics. Recent works propose understanding NeRFs with natural language using Multimodal Large Language Models (MLLMs) that directly process the weights of a NeRF's MLP. However, these approaches rely on a global representation of the input object, making them unsuitable for spatial reasoning and fine-grained understanding. In contrast, we propose **weights2space**, a self-supervised framework featuring a novel meta-encoder that can compute a sequence of spatial tokens directly from the weights of a NeRF. Leveraging this representation, we build **Spatial LLaNA**, a novel MLLM for NeRFs, capable of understanding details and spatial relationships in objects represented as NeRFs. We evaluate Spatial LLaNA on NeRF captioning and NeRF Q&A tasks, using both existing benchmarks and our novel **Spatial ObjaNeRF** dataset consisting of $100$ manually-curated language annotations for NeRFs. This dataset features 3D models and descriptions that challenge the spatial reasoning capability of MLLMs. Spatial LLaNA outperforms existing approaches across all tasks.

Reinforcement Learning · Batch Offline

Juan Formanek, Omayma Mahjoub, Louay Nessir, Sasha Abramowitz, Ruan John de Kock, Wiem Khlifi, Daniel Rajaonarivonivelomanantsoa, Simon Du Toit, Arnol Fokam, Siddarth Singh 等

A key challenge in offline multi-agent reinforcement learning (MARL) is achieving effective many-agent multi-step coordination in complex environments. In this work, we propose Oryx, a novel algorithm for offline cooperative MARL to directly address this challenge. Oryx adapts the recently proposed retention-based architecture Sable and combines it with a sequential form of implicit constraint Q-learning (ICQ), to develop a novel offline autoregressive policy update scheme. This allows Oryx to solve complex coordination challenges while maintaining temporal coherence over long trajectories. We evaluate Oryx across a diverse set of benchmarks from prior works—SMAC, RWARE, and Multi-Agent MuJoCo—covering tasks of both discrete and continuous control, varying in scale and difficulty. Oryx achieves state-of-the-art performance on more than 80% of the 65 tested datasets, outperforming prior offline MARL methods and demonstrating robust generalisation across domains with many agents and long horizons. Finally, we introduce new datasets to push the limits of many-agent coordination in offline MARL, and demonstrate Oryx's superior ability to scale effectively in such settings.

General Machine Learning · Everything Else

Zhengyao Huang, Daniel Huang, Tiannan Xiao, Dina Ma, Zhenyu Ming, Hao Shi, Yuanhui Wen

Symbolic regression aims to discover concise, interpretable mathematical expressions that satisfy desired objectives, such as fitting data, posing a highly combinatorial optimization problem. While genetic programming has been the dominant approach, recent efforts have explored reinforcement learning methods for improving search efficiency. Monte Carlo Tree Search (MCTS), with its ability to balance exploration and exploitation through guided search, has emerged as a promising technique for symbolic expression discovery. However, its traditional bandit strategies and sequential symbol construction often limit performance. In this work, we propose an improved MCTS framework for symbolic regression that addresses these limitations through two key innovations: (1) an extreme bandit allocation strategy tailored for identifying globally optimal expressions, with finite-time performance guarantees under polynomial reward decay assumptions; and (2) evolution-inspired state-jumping actions such as mutation and crossover, which enable non-local transitions to promising regions of the search space. These state-jumping actions also reshape the reward landscape during the search process, improving both robustness and efficiency. We conduct a thorough numerical study to the impact of these improvements and benchmark our approach against existing symbolic regression methods on a variety of datasets, including both ground-truth and black-box datasets. Our approach achieves competitive performance with state-of-the-art libraries in terms of recovery rate, attains favorable positions on the Pareto frontier of accuracy versus model complexity.

Applications · Climate

Anass El Aouni, Quentin Gaudel, J. Emmanuel Johnson, REGNIER Charly, Julien Le Sommer, Simon van Gennip, ronan fablet, Marie Drevillon, Yann DRILLET, Pierre Le Traon

Data-driven approaches, particularly those based on deep learning, are rapidly advancing Earth system modeling. However, their application to ocean forecasting remains limited despite the ocean's pivotal role in climate regulation and marine ecosystems. To address this gap, we present OceanBench, a benchmark designed to evaluate and accelerate global short-range (1–10 days) data-driven ocean forecasting.OceanBench is constructed from a curated dataset comprising first-guess trajectories, nowcasts, and atmospheric forcings from operational physical ocean models, typically unavailable in public datasets due to assimilation cycles. Matched observational data are also included, enabling realistic evaluation in an operational-like forecasting framework.The benchmark defines three complementary evaluation tracks: (i) Model-to-Reanalysis, where models are compared against the reanalysis dataset commonly used for training; (ii) Model-to-Analysis, assessing generalization to a higher-resolution physical analysis; and (iii) Model-to-Observations, Intercomparison and Validation (IV-TT) CLASS-4 evaluation against independent observational data. The first two tracks are further supported by process-oriented diagnostics to assess the dynamical consistency and physical plausibility of forecasts.OceanBench includes key ocean variables: sea surface height, temperature, salinity, and currents, along with standardized metrics grounded in physical oceanography. Baseline comparisons with operational systems and state-of-the-art deep learning models are provided. All data, code, and evaluation protocols are openly available at https://github.com/mercator-ocean/oceanbench, establishing OceanBench as a foundation for reproducible and rigorous research in data-driven ocean forecasting.

Computer Vision · Everything Else

Zixuan Liu, Siavash H. Khajavi, Guangkai Jiang

Recent advances in multi-modal models have demonstrated strong performance in tasks such as image generation and reasoning. However, applying these models to the fire domain remains challenging due to the lack of publicly available datasets with high-quality fire domain annotations. To address this gap, we introduce $\textbf{DetectiumFire}$, a large-scale, multi-modal dataset comprising of 22.5k high-resolution fire-related images and 2.5k real-world fire-related videos covering a wide range of fire types, environments, and risk levels. The data are annotated with both traditional computer vision labels (e.g., bounding boxes) and detailed textual prompts describing the scene, enabling applications such as synthetic data generation and fire risk reasoning. DetectiumFire offers clear advantages over existing benchmarks in scale, diversity, and data quality, significantly reducing redundancy and enhancing coverage of real-world scenarios. We validate the utility of DetectiumFire across multiple tasks, including object detection, diffusion-based image generation, and vision-language reasoning. Our results highlight the potential of this dataset to advance fire-related research and support the development of intelligent safety systems. We release DetectiumFire to promote broader exploration of fire understanding in the AI community.

Data-centric AI · Everything Else

hanzhuo tan, Xiaolong Tian, Hanrui Qi, Jiaming Liu, Siyi Wang, GAO Zuchen, Qi Luo, Jing Li, Yuqun Zhang

Recent advances in LLM-based decompilers have been shown effective to convert low-level binaries into human-readable source code. However, there still lacks a comprehensive benchmark that provides large-scale binary-source function pairs, which is critical for advancing the LLM decompilation technology. Creating accurate binary-source mappings incurs severe issues caused by complex compilation settings and widespread function inlining that obscure the correspondence between binaries and their original source code. Previous efforts have either relied on used contest‐style benchmarks, synthetic binary–source mappings that diverge significantly from the mappings in real world, or partially matched binaries with only code lines or variable names, compromising the effectiveness of analyzing the binary functionality. To alleviate these issues, we introduce Decompile-Bench, the first open-source dataset comprising two million binary-source function pairs condensed from 100 million collected function pairs, i.e., 450GB of binaries compiled from permissively licensed GitHub projects. For the evaluation purposes, we also developed a benchmark Decompile-Bench-Eval including manually crafted binaries from the well-established HumanEval and MBPP, alongside the compiled GitHub repositories released after 2025 to mitigate data leakage issues. We further explore commonly-used evaluation metrics to provide a thorough assessment of the studied LLM decompilers and find that fine-tuning with Decompile-Bench causes a 20% improvement over previous benchmarks in terms of the re-executability rate. Our code and data has been released in HuggingFace and Github. https://github.com/anonepo/LLM4Decompile

Data-centric AI · Data-centric AI methods and tools

Bettina Messmer, Vinko Sabolčec, Martin Jaggi

Dataset curation has become a basis for strong large language model (LLM) performance.While various rule-based filtering heuristics exist for English and multilingual datasets, model-based filtering techniques have primarily focused on English.To address the disparity stemming from limited research on non-English languages, we develop a model-based filtering framework for multilingual datasets that aims to identify a diverse set of structured and knowledge-rich samples.Our approach emphasizes transparency, simplicity, and efficiency, leveraging Transformer- and FastText-based classifiers to ensure the broad accessibility of our technique and data.We conduct comprehensive ablation studies on the FineWeb-2 web crawl dataset across diverse language families, scripts, and resource availability to demonstrate the effectiveness of our method.Training a 1B-parameter Llama model for 70B and 119B tokens, our approach can match the baseline MMLU score with as little as 15\% of the training tokens, while also improving across other benchmarks and mitigating the curse of multilinguality.These findings provide strong evidence for the generalizability of our approach to other languages. As a result, we extend our framework to 20 languages for which we release the refined pretraining datasets.

Applications · Chemistry and Drug Discovery

Ming Hsiu Wu, Ziqian Xie, Shuiwang Ji, Degui Zhi

Advancements in AI for science unlocks capabilities for critical drug discovery tasks such as protein-ligand binding affinity prediction. However, current models overfit to existing oversimplified datasets that does not represent naturally occurring and biologically relevant proteins with modifications. In this work, we curate a complete and modification-aware version of the widely used DAVIS dataset by incorporating 4,032 kinase–ligand pairs involving substitutions, insertions, deletions, and phosphorylation events. This enriched dataset enables benchmarking of predictive models under biologically realistic conditions. Based on this new dataset, we propose three benchmark settings—Augmented Dataset Prediction, Wild-Type to Modification Generalization, and Few-Shot Modification Generalization—designed to assess model robustness in the presence of protein modifications. Through extensive evaluation of both docking-free and docking-based methods, we find that docking-based model generalize better in zero-shot settings. In contrast, docking-free models tend to overfit to wild-type proteins and struggle with unseen modifications but show notable improvement when fine-tuned on a small set of modified examples. We anticipate that the curated dataset and benchmarks offer a valuable foundation for developing models that better generalize to protein modifications, ultimately advancing precision medicine in drug discovery. The benchmark is available at: https://github.com/ZhiGroup/DAVIS-complete

Data-centric AI · Data-centric AI methods and tools

Zhining Liu, Zihao Li, Ze Yang, Tianxin Wei, Jian Kang, Yada Zhu, Hendrik Hamann, Jingrui He, Hanghang Tong

Class-imbalanced learning (CIL) on tabular data is important in many real-world applications where the minority class holds the critical but rare outcomes. In this paper, we present CLIMB, a comprehensive benchmark for class-imbalanced learning on tabular data. CLIMB includes 73 real-world datasets across diverse domains and imbalance levels, along with unified implementations of 29 representative CIL algorithms. Built on a high-quality open-source Python package with unified API designs, detailed documentation, and rigorous code quality controls, CLIMB supports easy implementation and comparison between different CIL algorithms. Through extensive experiments, we provide practical insights on method accuracy and efficiency, highlighting the limitations of naive rebalancing, the effectiveness of ensembles, and the importance of data quality. Our code, documentation, and examples are available at https://github.com/ZhiningLiu1998/imbalanced-ensemble.

Applications · Robotics

Xiangyu Wang, Donglin Yang, Yue Liao, Wenhao Zheng, wenjun wu, Bin Dai, Hongsheng Li, Si Liu

Unmanned Aerial Vehicles (UAVs) are evolving into language-interactive platforms, enabling more intuitive forms of human-drone interaction. While prior works have primarily focused on high-level planning and long-horizon navigation, we shift attention to language-guided fine-grained trajectory control, where UAVs execute short-range, reactive flight behaviors in response to language instructions. We formalize this problem as the Flying-on-a-Word (Flow) task and introduce UAV imitation learning as an effective approach. In this framework, UAVs learn fine-grained control policies by mimicking expert pilot trajectories paired with atomic language instructions. To support this paradigm, we present UAV-Flow, the first real-world benchmark for language-conditioned, fine-grained UAV control. It includes a task formulation, a large-scale dataset collected in diverse environments, a deployable control framework, and a simulation suite for systematic evaluation. Our design enables UAVs to closely imitate the precise, expert-level flight trajectories of human pilots and supports direct deployment without sim-to-real gap. We conduct extensive experiments on UAV-Flow, benchmarking VLN and VLA paradigms. Results show that VLA models are superior to VLN baselines and highlight the critical role of spatial grounding in the fine-grained Flow setting.