Abstract:In this report we describe the development of Command A, a powerful large language model purpose-built to excel at real-world enterprise use cases. Command A is an agent-optimised and multilingual-capable model, with support for 23 languages of global business, and a novel hybrid architecture balancing efficiency with top of the range performance. It offers best-in-class Retrieval Augmented Generation (RAG) capabilities with grounding and tool use to automate sophisticated business processes. These abilities are achieved through a decentralised training approach, including self-refinement algorithms and model merging techniques. We also include results for Command R7B which shares capability and architectural similarities to Command A. Weights for both models have been released for research purposes. This technical report details our original training pipeline and presents an extensive evaluation of our models across a suite of enterprise-relevant tasks and public benchmarks, demonstrating excellent performance and efficiency.
Abstract:Large Reasoning Models (LRMs) significantly improve the reasoning ability of Large Language Models (LLMs) by learning to reason, exhibiting promising performance in complex task-solving. However, their deliberative reasoning process leads to inefficiencies in token usage, memory consumption, and inference time. Thus, this survey provides a review of efficient inference methods designed specifically for LRMs, focusing on mitigating token inefficiency while preserving the reasoning quality. First, we introduce a taxonomy to group the recent methods into two main categories: (a) explicit compact Chain-of-Thought (CoT), which reduces tokens while keeping the explicit reasoning structure, and (b) implicit latent CoT, which encodes reasoning steps within hidden representations instead of explicit tokens. Meanwhile, we discuss their strengths and weaknesses. Then, we conduct empirical analyses on existing methods from performance and efficiency aspects. Besides, we present open challenges in this field, including human-centric controllable reasoning, trade-off between interpretability and efficiency of reasoning, ensuring safety of efficient reasoning, and broader applications of efficient reasoning. In addition, we highlight key insights for enhancing LRMs' inference efficiency via techniques such as model merging, new architectures, and agent routers. We hope this work serves as a valuable guide, helping researchers overcome challenges in this vibrant field\footnote{https://github.com/yueliu1999/Awesome-Efficient-Inference-for-LRMs}.
Abstract:The hallucination of large multimodal models (LMMs), providing responses that appear correct but are actually incorrect, limits their reliability and applicability. This paper aims to study the hallucination problem of LMMs in video modality, which is dynamic and more challenging compared to static modalities like images and text. From this motivation, we first present a comprehensive benchmark termed HAVEN for evaluating hallucinations of LMMs in video understanding tasks. It is built upon three dimensions, i.e., hallucination causes, hallucination aspects, and question formats, resulting in 6K questions. Then, we quantitatively study 7 influential factors on hallucinations, e.g., duration time of videos, model sizes, and model reasoning, via experiments of 16 LMMs on the presented benchmark. In addition, inspired by recent thinking models like OpenAI o1, we propose a video-thinking model to mitigate the hallucinations of LMMs via supervised reasoning fine-tuning (SRFT) and direct preference optimization (TDPO)-- where SRFT enhances reasoning capabilities while TDPO reduces hallucinations in the thinking process. Extensive experiments and analyses demonstrate the effectiveness. Remarkably, it improves the baseline by 7.65% in accuracy on hallucination evaluation and reduces the bias score by 4.5%. The code and data are public at https://github.com/Hongcheng-Gao/HAVEN.
Abstract:Large Language Models (LLMs) are increasingly employed as automated evaluators to assess the safety of generated content, yet their reliability in this role remains uncertain. This study evaluates a diverse set of 11 LLM judge models across critical safety domains, examining three key aspects: self-consistency in repeated judging tasks, alignment with human judgments, and susceptibility to input artifacts such as apologetic or verbose phrasing. Our findings reveal that biases in LLM judges can significantly distort the final verdict on which content source is safer, undermining the validity of comparative evaluations. Notably, apologetic language artifacts alone can skew evaluator preferences by up to 98\%. Contrary to expectations, larger models do not consistently exhibit greater robustness, while smaller models sometimes show higher resistance to specific artifacts. To mitigate LLM evaluator robustness issues, we investigate jury-based evaluations aggregating decisions from multiple models. Although this approach both improves robustness and enhances alignment to human judgements, artifact sensitivity persists even with the best jury configurations. These results highlight the urgent need for diversified, artifact-resistant methodologies to ensure reliable safety assessments.
Abstract:Recently, large language models (LLMs) and visionlanguage models (VLMs) have achieved significant success, demonstrating remarkable capabilities in understanding various images and videos, particularly in classification and detection tasks. However, due to the substantial differences between remote sensing images and conventional optical images, these models face considerable challenges in comprehension, especially in detection tasks. Directly prompting VLMs with detection instructions often fails to yield satisfactory results. To address this issue, this letter explores the application of VLMs for object detection in remote sensing images. Specifically, we utilize publicly available remote sensing object detection datasets, including SSDD, HRSID, and NWPU-VHR-10, to convert traditional annotation information into natural language, thereby constructing an instruction-tuning (SFT) dataset for VLM training. We then evaluate the detection performance of different fine-tuning strategies for VLMs and obtain optimized model weights for object detection in remote sensing images. Finally, we assess the model's prior knowledge capabilities through natural language queries.Experimental results demonstrate that, without modifying the model architecture, remote sensing object detection can be effectively achieved using natural language alone. Additionally, the model exhibits the ability to perform certain vision question answering (VQA) tasks. Our dataset and relevant code will be released soon.
Abstract:Equivalence checking, i.e., determining whether two programs produce identical outputs for all possible inputs, underpins a broad range of applications, including software refactoring, testing, and optimization. We present the task of equivalence checking as a new way to evaluate the code reasoning abilities of large language models (LLMs). We introduce EquiBench, a dataset of 2400 program pairs spanning four programming languages and six equivalence categories. These pairs are systematically generated through program analysis, compiler scheduling, and superoptimization, covering nontrivial structural transformations that demand deep semantic reasoning beyond simple syntactic variations. Our evaluation of 17 state-of-the-art LLMs shows that OpenAI o3-mini achieves the highest overall accuracy of 78.0%. In the most challenging categories, the best accuracies are 62.3% and 68.8%, only modestly above the 50% random baseline for binary classification, indicating significant room for improvement in current models' code reasoning capabilities.
Abstract:Breast cancer is one of the most common causes of death among women worldwide. Early detection helps in reducing the number of deaths. Automated 3D Breast Ultrasound (ABUS) is a newer approach for breast screening, which has many advantages over handheld mammography such as safety, speed, and higher detection rate of breast cancer. Tumor detection, segmentation, and classification are key components in the analysis of medical images, especially challenging in the context of 3D ABUS due to the significant variability in tumor size and shape, unclear tumor boundaries, and a low signal-to-noise ratio. The lack of publicly accessible, well-labeled ABUS datasets further hinders the advancement of systems for breast tumor analysis. Addressing this gap, we have organized the inaugural Tumor Detection, Segmentation, and Classification Challenge on Automated 3D Breast Ultrasound 2023 (TDSC-ABUS2023). This initiative aims to spearhead research in this field and create a definitive benchmark for tasks associated with 3D ABUS image analysis. In this paper, we summarize the top-performing algorithms from the challenge and provide critical analysis for ABUS image examination. We offer the TDSC-ABUS challenge as an open-access platform at https://tdsc-abus2023.grand-challenge.org/ to benchmark and inspire future developments in algorithmic research.
Abstract:In E-commerce platforms, a full advertising image is composed of a background image and marketing taglines. Automatic ad image design reduces human costs and plays a crucial role. For the convenience of users, a novel automatic framework named Product-Centric Advertising Image Design (PAID) is proposed in this work. PAID takes the product foreground image, required taglines, and target size as input and creates an ad image automatically. PAID consists of four sequential stages: prompt generation, layout generation, background image generation, and graphics rendering. Different expert models are trained to conduct these sub-tasks. A visual language model (VLM) based prompt generation model is leveraged to produce a product-matching background prompt. The layout generation model jointly predicts text and image layout according to the background prompt, product, and taglines to achieve the best harmony. An SDXL-based layout-controlled inpainting model is trained to generate an aesthetic background image. Previous ad image design methods take a background image as input and then predict the layout of taglines, which limits the spatial layout due to fixed image content. Innovatively, our PAID adjusts the stages to produce an unrestricted layout. To complete the PAID framework, we created two high-quality datasets, PITA and PIL. Extensive experimental results show that PAID creates more visually pleasing advertising images than previous methods.
Abstract:This paper introduces the Maritime Ship Navigation Behavior Dataset (MID), designed to address challenges in ship detection within complex maritime environments using Oriented Bounding Boxes (OBB). MID contains 5,673 images with 135,884 finely annotated target instances, supporting both supervised and semi-supervised learning. It features diverse maritime scenarios such as ship encounters under varying weather, docking maneuvers, small target clustering, and partial occlusions, filling critical gaps in datasets like HRSID, SSDD, and NWPU-10. MID's images are sourced from high-definition video clips of real-world navigation across 43 water areas, with varied weather and lighting conditions (e.g., rain, fog). Manually curated annotations enhance the dataset's variety, ensuring its applicability to real-world demands in busy ports and dense maritime regions. This diversity equips models trained on MID to better handle complex, dynamic environments, supporting advancements in maritime situational awareness. To validate MID's utility, we evaluated 10 detection algorithms, providing an in-depth analysis of the dataset, detection results from various models, and a comparative study of baseline algorithms, with a focus on handling occlusions and dense target clusters. The results highlight MID's potential to drive innovation in intelligent maritime traffic monitoring and autonomous navigation systems. The dataset will be made publicly available at https://github.com/VirtualNew/MID_DataSet.
Abstract:In this work, we introduce a new framework for active experimentation, the Prediction-Guided Active Experiment (PGAE), which leverages predictions from an existing machine learning model to guide sampling and experimentation. Specifically, at each time step, an experimental unit is sampled according to a designated sampling distribution, and the actual outcome is observed based on an experimental probability. Otherwise, only a prediction for the outcome is available. We begin by analyzing the non-adaptive case, where full information on the joint distribution of the predictor and the actual outcome is assumed. For this scenario, we derive an optimal experimentation strategy by minimizing the semi-parametric efficiency bound for the class of regular estimators. We then introduce an estimator that meets this efficiency bound, achieving asymptotic optimality. Next, we move to the adaptive case, where the predictor is continuously updated with newly sampled data. We show that the adaptive version of the estimator remains efficient and attains the same semi-parametric bound under certain regularity assumptions. Finally, we validate PGAE's performance through simulations and a semi-synthetic experiment using data from the US Census Bureau. The results underscore the PGAE framework's effectiveness and superiority compared to other existing methods.