Sketch recognition is the process of identifying and categorizing hand-drawn sketches using deep learning techniques.
Mathematical reasoning is a hallmark of human intelligence, and whether large language models (LLMs) can meaningfully perform it remains a central question in artificial intelligence and cognitive science. As LLMs are increasingly integrated into scientific workflows, rigorous evaluation of their mathematical capabilities becomes a practical necessity. Existing benchmarks are limited by synthetic settings and data contamination. We present LiveMathematicianBench, a dynamic multiple-choice benchmark for research-level mathematical reasoning built from recent arXiv papers published after model training cutoffs. By grounding evaluation in newly published theorems, it provides a realistic testbed beyond memorized patterns. The benchmark introduces a thirteen-category logical taxonomy of theorem types (e.g., implication, equivalence, existence, uniqueness), enabling fine-grained evaluation across reasoning forms. It employs a proof-sketch-guided distractor pipeline that uses high-level proof strategies to construct plausible but invalid answer choices reflecting misleading proof directions, increasing sensitivity to genuine understanding over surface-level matching. We also introduce a substitution-resistant mechanism to distinguish answer recognition from substantive reasoning. Evaluation shows the benchmark is far from saturated: Gemini-3.1-pro-preview, the best model, achieves only 43.5%. Under substitution-resistant evaluation, accuracy drops sharply: GPT-5.4 scores highest at 30.6%, while Gemini-3.1-pro-preview falls to 17.6%, below the 20% random baseline. A dual-mode protocol reveals that proof-sketch access yields consistent accuracy gains, suggesting models can leverage high-level proof strategies for reasoning. Overall, LiveMathematicianBench offers a scalable, contamination-resistant testbed for studying research-level mathematical reasoning in LLMs.
A sketch is a distilled form of visual abstraction that conveys core concepts through simplified yet purposeful strokes while omitting extraneous detail. Despite its expressive power, quantifying the efficiency of semantic abstraction in sketches remains challenging. Existing evaluation methods that rely on reference images, low-level visual features, or recognition accuracy do not capture abstraction, the defining property of sketches. To address these limitations, we introduce SEA (Sketch Evaluation metric for Abstraction efficiency), a reference-free metric that assesses how economically a sketch represents class-defining visual elements while preserving semantic recognizability. These elements are derived per class from commonsense knowledge about features typically depicted in sketches. SEA leverages a visual question answering model to determine the presence of each element and returns a quantitative score that reflects semantic retention under visual economy. To support this metric, we present CommonSketch, the first semantically annotated sketch dataset, comprising 23,100 human-drawn sketches across 300 classes, each paired with a caption and element-level annotations. Experiments show that SEA aligns closely with human judgments and reliably discriminates levels of abstraction efficiency, while CommonSketch serves as a benchmark providing systematic evaluation of element-level sketch understanding across various vision-language models.
Collinearity is a visual perception phenomenon in the human brain that amplifies spatially aligned edges arranged along a straight line. However, it is vague for which purpose humans might have this principle in the real-world, and its utilization in computer vision and engineering applications even is a largely unexplored field. In this work, our goal is to transfer the collinearity principle to computer vision, and we explore the potential usages of this novel principle for computer vision applications. We developed a prototype model to exemplify the principle, then tested it systematically, and benchmarked it in the context of four use cases. Our cases are selected to spawn a broad range of potential applications and scenarios: sketching the combination of collinearity with deep learning (case I and II), using collinearity with saliency models (case II), and as a feature detector (case I). In the first use case, we found that collinearity is able to improve the fault detection of wafers and obtain a performance increase by a factor 1.24 via collinearity (decrease of the error rate from 6.5% to 5.26%). In the second use case, we test the defect recognition in nanotechnology materials and achieve a performance increase by 3.2x via collinearity (deep learning, error from 21.65% to 6.64%), and also explore saliency models. As third experiment, we cover occlusions; while as fourth experiment, we test ImageNet and observe that it might not be very beneficial for ImageNet. Therefore, we can assemble a list of scenarios for which collinearity is beneficial (wafers, nanotechnology, occlusions), and for what is not beneficial (ImageNet). Hence, we infer collinearity might be suitable for industry applications as it helps if the image structures of interest are man-made because they often consist of lines. Our work provides another tool for CV, hope to capture the power of human processing.
We introduce the first unified framework for *Fine-Grained Domain-Generalized Generalized Category Discovery* (FG-DG-GCD), bringing open-world recognition closer to real-world deployment under domain shift. Unlike conventional GCD, which assumes labeled and unlabeled data come from the same distribution, DG-GCD learns only from labeled source data and must both recognize known classes and discover novel ones in unseen, unlabeled target domains. This problem is especially challenging in fine-grained settings, where subtle inter-class differences and large intra-class variation make domain generalization significantly harder. To support systematic evaluation, we establish the first *FG-DG-GCD benchmarks* by creating identity-preserving *painting* and *sketch* domains for CUB-200-2011, Stanford Cars, and FGVC-Aircraft using controlled diffusion-adapter stylization. On top of this ,we propose FoCUS, a single-stage framework that combines *Domain-Consistent Parts Discovery* (DCPD) for geometry-stable part reasoning with *Uncertainty-Aware Feature Augmentation* (UFA) for confidence-calibrated feature regularization through uncertainty-guided perturbations. Extensive experiments show that FoCUS outperforms strong GCD, FG-GCD, and DG-GCD baselines by **3.28%**, **9.68%**, and **2.07%**, respectively, in clustering accuracy on the proposed benchmarks. It also remains competitive on coarse-grained DG-GCD tasks while achieving nearly **3x** higher computational efficiency than the current state of the art. ^[Code and datasets will be released upon acceptance.]
AIs are increasingly being deployed with greater autonomy and capabilities, which increases the risk that a misaligned AI may be able to cause catastrophic harm. Untrusted monitoring -- using one untrusted model to oversee another -- is one approach to reducing risk. Justifying the safety of an untrusted monitoring deployment is challenging because developers cannot safely deploy a misaligned model to test their protocol directly. In this paper, we develop upon existing methods for rigorously demonstrating safety based on pre-deployment testing. We relax assumptions that previous AI control research made about the collusion strategies a misaligned AI might use to subvert untrusted monitoring. We develop a taxonomy covering passive self-recognition, causal collusion (hiding pre-shared signals), acausal collusion (hiding signals via Schelling points), and combined strategies. We create a safety case sketch to clearly present our argument, explicitly state our assumptions, and highlight unsolved challenges. We identify conditions under which passive self-recognition could be a more effective collusion strategy than those studied previously. Our work builds towards more robust evaluations of untrusted monitoring.
Modern AI systems achieve remarkable capabilities at the cost of substantial energy consumption. To connect intelligence to physical efficiency, we propose two complementary bits-per-joule metrics under explicit accounting conventions: (1) Thermodynamic Epiplexity per Joule -- bits of structural information about a theoretical environment-instance variable newly encoded in an agent's internal state per unit measured energy within a stated boundary -- and (2) Empowerment per Joule -- the embodied sensorimotor channel capacity (control information) per expected energetic cost over a fixed horizon. These provide two axes of physical intelligence: recognition (model-building) vs.control (action influence). Drawing on stochastic thermodynamics, we show how a Landauer-scale closed-cycle benchmark for epiplexity acquisition follows as a corollary of a standard thermodynamic-learning inequality under explicit subsystem assumptions, and we clarify how Landauer-scaled costs act as closed-cycle benchmarks under explicit reset/reuse and boundary-closure assumptions; conversely, we give a simple decoupling construction showing that without such assumptions -- and without charging for externally prepared low-entropy resources (e.g.fresh memory) crossing the boundary -- information gain and in-boundary dissipation need not be tightly linked. For empirical settings where the latent structure variable is unavailable, we align the operational notion of epiplexity with compute-bounded MDL epiplexity and recommend reporting MDL-epiplexity / compression-gain surrogates as companions. Finally, we propose a unified efficiency framework that reports both metrics together with a minimal checklist of boundary/energy accounting, coarse-graining/noise, horizon/reset, and cost conventions to reduce ambiguity and support consistent bits-per-joule comparisons, and we sketch connections to energy-adjusted scaling analyses.
Person identification in forensic investigations becomes very challenging when common identification means for DNA (i.e., hair strands, soft tissue) are not available. Current methods utilize deep learning methods for face recognition. However, these methods lack effective mechanisms to model cross-domain structural correspondence between two different forensic modalities. In this paper, we introduce a SPOT-Face, a superpixel graph-based framework designed for cross-domain forensic face identification of victims using their skeleton and sketch images. Our unified framework involves constructing a superpixel-based graph from an image and then using different graph neural networks(GNNs) backbones to extract the embeddings of these graphs, while cross-domain correspondence is established through attention-guided optimal transport mechanism. We have evaluated our proposed framework on two publicly available dataset: IIT\_Mandi\_S2F (S2F) and CUFS. Extensive experiments were conducted to evaluate our proposed framework. The experimental results show significant improvement in identification metrics ( i.e., Recall, mAP) over existing graph-based baselines. Furthermore, our framework demonstrates to be highly effective for matching skulls and sketches to faces in forensic investigations.




Pretrained models like CLIP have demonstrated impressive zero-shot classification capabilities across diverse visual domains, spanning natural images, artistic renderings, and abstract representations. However, real-world applications often demand the removal (or "unlearning") of specific object classes without requiring additional data or retraining, or affecting the model's performance on unrelated tasks. In this paper, we propose a novel training- and data-free unlearning framework that enables three distinct forgetting paradigms: (1) global unlearning of selected objects across all domains, (2) domain-specific knowledge removal (e.g., eliminating sketch representations while preserving photo recognition), and (3) complete unlearning in selective domains. By leveraging a multimodal nullspace through synergistic integration of text prompts and synthesized visual prototypes derived from CLIP's joint embedding space, our method efficiently removes undesired class information while preserving the remaining knowledge. This approach overcomes the limitations of existing retraining-based methods and offers a flexible and computationally efficient solution for controlled model forgetting.
The Drawing Projection Test (DPT) is an essential tool in art therapy, allowing psychologists to assess participants' mental states through their sketches. Specifically, through sketches with the theme of "a person picking an apple from a tree (PPAT)", it can be revealed whether the participants are in mental states such as depression. Compared with scales, the DPT can enrich psychologists' understanding of an individual's mental state. However, the interpretation of the PPAT is laborious and depends on the experience of the psychologists. To address this issue, we propose an effective identification method to support psychologists in conducting a large-scale automatic DPT. Unlike traditional sketch recognition, DPT more focus on the overall evaluation of the sketches, such as color usage and space utilization. Moreover, PPAT imposes a time limit and prohibits verbal reminders, resulting in low drawing accuracy and a lack of detailed depiction. To address these challenges, we propose the following efforts: (1) Providing an experimental environment for automated analysis of PPAT sketches for depression assessment; (2) Offering a Visual-Semantic depression assessment based on LLM (VS-LLM) method; (3) Experimental results demonstrate that our method improves by 17.6% compared to the psychologist assessment method. We anticipate that this work will contribute to the research in mental state assessment based on PPAT sketches' elements recognition. Our datasets and codes are available at https://github.com/wmeiqi/VS-LLM.
As lovely as bunnies are, your sketched version would probably not do them justice (Fig.~\ref{fig:intro}). This paper recognises this very problem and studies sketch quality assessment for the first time -- letting you find these badly drawn ones. Our key discovery lies in exploiting the magnitude ($L_2$ norm) of a sketch feature as a quantitative quality metric. We propose Geometry-Aware Classification Layer (GACL), a generic method that makes feature-magnitude-as-quality-metric possible and importantly does it without the need for specific quality annotations from humans. GACL sees feature magnitude and recognisability learning as a dual task, which can be simultaneously optimised under a neat cross-entropy classification loss with theoretic guarantee. This gives GACL a nice geometric interpretation (the better the quality, the easier the recognition), and makes it agnostic to both network architecture changes and the underlying sketch representation. Through a large scale human study of 160,000 \doublecheck{trials}, we confirm the agreement between our GACL-induced metric and human quality perception. We further demonstrate how such a quality assessment capability can for the first time enable three practical sketch applications. Interestingly, we show GACL not only works on abstract visual representations such as sketch but also extends well to natural images on the problem of image quality assessment (IQA). Last but not least, we spell out the general properties of GACL as general-purpose data re-weighting strategy and demonstrate its applications in vertical problems such as noisy label cleansing. Code will be made publicly available at github.com/yanglan0225/SketchX-Quantifying-Sketch-Quality.