Yusuf Meric Karadag | Searcharxiv

arXiv2026

CBX-Bench: A Human-Aligned MLLM Council for Benchmarking Concept Bottleneck Model Explanations

Concept Bottleneck Models (CBMs) are designed to make visual classification interpretable by expressing predictions through human-understandable concepts. Although interpretability is the central motivation for CBMs, they are still largely evaluated as predictive models by downstream classification accuracy, supplemented by isolated qualitative examples. This highlights a pressing need for quantitative measures, a challenge complicated by the infeasibility of ground-truth concept annotation at scale and the open nature of concept lists due to a lack of consensus. To fill this gap, we develop a multimodal large language model (MLLM) council that, given an image and its CBM explanation, produces an explanation quality score. To ground and validate the council, we first conduct a human study to establish a ground-truth reference for CBM explanation quality: for an image, annotators compare explanations from two of LF-CBM, VLG-CBM, and CBM-Suite and choose the more useful one, or mark them as equally good or equally bad, yielding 2700 judgments over 900 image-comparison items on CUB-200, ImageNet-100, and Places365. Against this human reference, our five-model council, consisting of open-weight MLLMs, recovers over 70% of strict human preference rankings, rising to 83% on items where human annotators unanimously agree. Building on this validated council, we introduce CBX-Bench, a public benchmark and leaderboard: authors of new CBMs can submit their model's explanations, and CBX-Bench scores them with the council and maintains dataset-level rankings of explanation quality. CBX-Bench thus provides a human-aligned, scalable evaluation of CBM explanations beyond accuracy and isolated qualitative examples. The benchmark is available at https://github.com/meric-karadag/cbx-bench.

cs.CV↗

arXiv2026

ms-Mamba: Multi-scale Mamba for Time-Series Forecasting

The problem of Time-series Forecasting is generally addressed by recurrent, Transformer-based and the recently proposed Mamba-based architectures. However, existing architectures generally process their input at a single temporal scale, which may be sub-optimal for many tasks where information changes over multiple time scales. In this paper, we introduce a novel architecture called Multi-scale Mamba (ms-Mamba) to address this gap. ms-Mamba incorporates multiple temporal scales by using multiple Mamba blocks with different sampling rates ($Δ$s). Our experiments on many benchmarks demonstrate that ms-Mamba outperforms state-of-the-art approaches, including the recently proposed Transformer-based and Mamba-based models. For example, on the Solar-Energy dataset, ms-Mamba outperforms its closest competitor S-Mamba (0.229 vs. 0.240 in terms of mean-squared error) while using fewer parameters (3.53M vs. 4.77M), less memory (13.46MB vs. 18.18MB), and less operations (14.93G vs. 20.53G MACs), averaged across four forecast lengths. Codes and models will be made available.

cs.LG↗