VLM Evaluation

Rapid advances in vision-language models (VLMs) have generated growing interest in their application to autonomous driving. A prevailing assumption is that successive VLM generations will continually improve driving performance and eventually outperform state-of-the-art methods. To systematically examine this assumption, we introduce LightEMMA, a longitudinal framework for evaluating the autonomous driving performance of VLMs. LightEMMA uses a lightweight, unified evaluation protocol that assesses each model's intrinsic driving capability without model-specific fine-tuning, architectural changes, or prompt engineering. Using this protocol, we evaluate 15 models from five major families on the challenging nuScenes prediction benchmark. Empirical findings show that, despite increased model scale and enhanced general reasoning capabilities, successive VLM generations do not consistently achieve better driving performance. Further analysis of driving scenarios reveals recurring failure modes, including overreliance on historical actions and difficulty reconciling conflicting visual cues. These findings highlight the need for domain-specific adaptation to improve the safety of VLM-based autonomous driving systems. The source code is available at https://github.com/michigan-traffic-lab/LightEMMA.

Unimodal vision models are known to rely on spurious correlations, but it remains unclear to what extent Multimodal Large Language Models (MLLMs) exhibit similar biases despite language supervision. In this paper, we investigate spurious bias in MLLMs and introduce SpurLens, a pipeline that leverages GPT-4 and open-set object detectors to automatically identify spurious visual cues without human supervision. Our findings reveal that spurious correlations cause two major failure modes in MLLMs: (1) over-reliance on spurious cues for object recognition, where removing these cues reduces accuracy, and (2) object hallucination, where spurious cues amplify the hallucination by over 10x. We validate our findings in various MLLMs and datasets. Beyond diagnosing these failures, we explore potential mitigation strategies, such as prompt ensembling and reasoning-based prompting, and conduct ablation studies to examine the root causes of spurious bias in MLLMs. By exposing the persistence of spurious correlations, our study calls for more rigorous evaluation methods and mitigation strategies to enhance the reliability of MLLMs.

Humans develop perception through a bottom-up hierarchy: from basic primitives and Gestalt principles to high-level semantics. Current Multimodal Large Language Models (MLLMs) are trained directly on complex downstream tasks. Does it guarantee their performance on these foundational visual capabilities? To systematically investigate this gap, we introduce VisFacor, a benchmark that digitizes 20 vision-centric subtests from FRCT, a well-established cognitive psychology assessment spanning four domains of human visual cognition. Furthermore, we design algorithms to automatically construct and validate unlimited test cases with controllable difficulty. Using VisFacor, we evaluate 39 frontier MLLMs, including both proprietary (e.g., GPT, Gemini) and open-source (e.g., LLaMA, Qwen) models. The best model achieves a score of only 55.9%. Analysis reveals good internal consistency (Cronbach's alpha = 0.94) and construct validity (compared to existing vision benchmarks). Models consistently fail on tasks such as mental rotation, spatial relation inference, and figure-ground discrimination, regardless of model size or prompting strategy. These findings suggest that performance improvements on existing general benchmarks might represent castles in the air instead of a genuine mastery of human-like visual cognition.

In recent years, a substantial body of work in visually grounded natural language processing has focused on real-life multimodal scenarios such as describing content depicted in images or videos. However, comparatively less attention has been devoted to studying the nature and degree of interaction between the different modalities in these scenarios. In this paper, we argue that any task dealing with natural language generation from sequences of images or frames is an instance of the broader, more general problem of modeling the intricate relationships between visual events unfolding over time and the features of the language used to interpret, describe, or narrate them. Therefore, solving these tasks requires models to be capable of identifying and managing such intricacies. We consider five seemingly different tasks, which we argue are compelling instances of this broader multimodal problem. Subsequently, we survey representative modeling and evaluation approaches adopted for these tasks in recent years and examine the common set of challenges these tasks pose. Building on this perspective, we identify key open questions and propose several research directions for future investigation.

Multiple works have emerged to push the boundaries of multi-modal large language models (MLLMs) towards pixel-level understanding. The current trend is to train MLLMs with pixel-level grounding supervision in terms of masks on large-scale labelled data and specialized decoders for the segmentation task. However, we show that such MLLMs when evaluated on recent challenging vision-centric benchmarks, exhibit a weak ability in visual question answering (VQA). Surprisingly, some of these methods even downgrade the grounding ability of MLLMs that were never trained with such pixel-level supervision. In this work, we propose two novel challenging benchmarks with paired evaluation for both VQA and grounding. We demonstrate that simple baselines that are not unified achieve performance that matches or surpasses some of the pixel-level MLLMs. Our paired benchmarks and evaluation enable additional analysis on whether the failure stems from VQA and/or grounding abilities. Furthermore, we propose a paired prompt sensitivity analysis on both the language and visual prompts tailored for the grounding task. Our benchmarking pushes pixel-level MLLMs to improve in both accuracy and robustness, without sacrificing language abilities. More importantly, we study the research question of ``When does grounding emerge in MLLMs with respect to the output tokens?'' We propose a post-hoc interpretability tool that can be plugged into any MLLM to study the aforementioned question. We show that grounding does not necessarily coincide with the exact referring expression in the output, but can coincide with the object parts, its location, appearance, context or state. Code and datasets are publicly available at https://msiam.github.io/PixFoundationSeries/.

Large-scale Vision-Language Models (VLMs) have achieved notable progress in aligning visual inputs with text. However, their ability to deeply understand the unique physical properties of non-RGB vision sensor images remains limited. In this paper, we revisit and analyze these limitations and introduce a novel, cost-efficient paradigm that significantly advances sensor image understanding-without requiring extensive training data or any modifications to the existing VLM architectures. Specifically, we propose Sensor-Aware Attributes Fine-Tuning (SAFT) with the Diverse Negative Attributes (DNA) optimization, which leverages minimal sensor-specific data to enable robust learning of non-RGB characteristics and overcome RGB-centric biases inherent in current VLMs. In addition, we present VS-TDX-the first comprehensive, public benchmark designed to rigorously evaluate VLMs' sensor-specific understanding across diverse and realistic scenarios. Through extensive experiments on VLMs and various sensor modalities, we validate that our method consistently delivers superior performance and generalization under resource-constrained and architecture-invariant settings. Our approach provides a practical advance towards scalable deployment of VLMs in increasingly sensor-diverse real-world environments.

Pre-trained foundation models have recently made significant progress in table-related tasks such as table understanding and reasoning. However, recognizing the structure and content of unstructured tables using Vision Large Language Models (VLLMs) remains under-explored. To bridge this gap, we propose a benchmark based on a hierarchical design philosophy to evaluate the recognition capabilities of VLLMs in training-free scenarios. Through in-depth evaluations, we find that low-quality image input is a significant bottleneck in the recognition process. Drawing inspiration from this, we propose the Neighbor-Guided Toolchain Reasoner (NGTR) framework, which is characterized by integrating diverse lightweight tools for visual operations aimed at mitigating issues with low-quality images. Specifically, we transfer a tool selection experience from a similar neighbor to the input and design a reflection module to supervise the tool invocation process. Extensive experiments on public datasets demonstrate that our approach significantly enhances the recognition capabilities of the vanilla VLLMs. We believe that the benchmark and framework could provide an alternative solution to table recognition.

We present VLMEvalKit: an open-source toolkit for evaluating large multi-modality models based on PyTorch. The toolkit aims to provide a user-friendly and comprehensive framework for researchers and developers to evaluate existing multi-modality models and publish reproducible evaluation results. In VLMEvalKit, we implement over 450+ large multi-modality model configurations, including both proprietary APIs and open-source models, and support 330+ benchmarks across diverse multi-modal benchmarks. By implementing a single interface, new models can be easily added to the toolkit, while the toolkit automatically handles the remaining workloads, including data preparation, distributed inference, prediction post-processing, and metric calculation. VLMEvalKit has also evolved to a broader evaluation suite spanning video/audio, document understanding, GUI grounding, spatial reasoning, safety, scientific reasoning, and multi-turn dialogue. Based on the evaluation results obtained with the toolkit, we host the OpenVLM Leaderboard, a comprehensive leaderboard to track the progress of multi-modality learning research. The toolkit is released on https://github.com/open-compass/VLMEvalKit and is actively maintained.

As Visual Language Models (VLMs) become increasingly embedded in everyday applications, ensuring they can recognise and appropriately handle privacy-sensitive content is thus essential to protect users. To this end, we conduct a comprehensive evaluation of twelve state-of-the-art VLMs and identify limitations in their understanding of visual privacy. However, existing privacy-related datasets often suffer from label inconsistencies, limiting their reliability. To address this, we introduce two compact, high-quality benchmarks, PrivBench and PrivBench-H, that focus on commonly recognised visual privacy categories aligned with the General Data Protection Regulation (GDPR). Additionally, we present PrivTune, an instruction-tuning dataset specifically curated to improve privacy sensitivity. We obtain multiple Privacy VLMs by fine-tuning off-the-shelf VLMs on only a few hundred samples from PrivTune, which leads to substantial gains on all benchmarks, surpassing even GPT-4, while maintaining strong performance on other tasks. Our findings show that privacy-awareness in VLMs can be substantially improved with minimal data and careful dataset design, setting the stage for safer, more privacy-aligned AI systems.