Grounding natural language queries in graphical user interfaces (GUIs) presents a challenging task that requires models to comprehend diverse UI elements across various applications and systems, while also accurately predicting the spatial coordinates for the intended operation. To tackle this problem, we propose GMS: Generalist Scanner Meets Specialist Locator, a synergistic coarse-to-fine framework that effectively improves GUI grounding performance. GMS leverages the complementary strengths of general vision-language models (VLMs) and small, task-specific GUI grounding models by assigning them distinct roles within the framework. Specifically, the general VLM acts as a 'Scanner' to identify potential regions of interest, while the fine-tuned grounding model serves as a 'Locator' that outputs precise coordinates within these regions. This design is inspired by how humans perform GUI grounding, where the eyes scan the interface and the brain focuses on interpretation and localization. Our whole framework consists of five stages and incorporates hierarchical search with cross-modal communication to achieve promising prediction results. Experimental results on the ScreenSpot-Pro dataset show that while the 'Scanner' and 'Locator' models achieve only $2.0\%$ and $3.7\%$ accuracy respectively when used independently, their integration within GMS framework yields an overall accuracy of $35.7\%$, representing a $10 \times$ improvement. Additionally, GMS significantly outperforms other strong baselines under various settings, demonstrating its robustness and potential for general-purpose GUI grounding.

Recent research has explored the constrained generation capabilities of Large Language Models (LLMs) when explicitly prompted by few task-specific requirements. In contrast, we introduce Large-Scale Constraint Generation (LSCG), a new problem that evaluates whether LLMs can parse a large, fine-grained, generic list of constraints. To examine the LLMs' ability to handle an increasing number constraints, we create a practical instance of LSCG, called Words Checker. In Words Checker, we evaluate the impact of model characteristics (e.g., size, family) and steering techniques (e.g., Simple Prompt, Chain of Thought, Best of N) on performance. We also propose FoCusNet, a small and dedicated model that parses the original list of constraints into a smaller subset, helping the LLM focus on relevant constraints. Experiments reveal that existing solutions suffer a significant performance drop as the number of constraints increases, with FoCusNet showing an 8-13% accuracy boost.

Context-grounded hallucinations are cases where model outputs contain information not verifiable against the source text. We study the applicability of LLMs for localizing such hallucinations, as a more practical alternative to existing complex evaluation pipelines. In the absence of established benchmarks for meta-evaluation of hallucinations localization, we construct one tailored to LLMs, involving a challenging human annotation of over 1,000 examples. We complement the benchmark with an LLM-based evaluation protocol, verifying its quality in a human evaluation. Since existing representations of hallucinations limit the types of errors that can be expressed, we propose a new representation based on free-form textual descriptions, capturing the full range of possible errors. We conduct a comprehensive study, evaluating four large-scale LLMs, which highlights the benchmark's difficulty, as the best model achieves an F1 score of only 0.67. Through careful analysis, we offer insights into optimal prompting strategies for the task and identify the main factors that make it challenging for LLMs: (1) a tendency to incorrectly flag missing details as inconsistent, despite being instructed to check only facts in the output; and (2) difficulty with outputs containing factually correct information absent from the source - and thus not verifiable - due to alignment with the model's parametric knowledge.

The Minimum Description Length (MDL) principle offers a formal framework for applying Occam's razor in machine learning. However, its application to neural networks such as Transformers is challenging due to the lack of a principled, universal measure for model complexity. This paper introduces the theoretical notion of asymptotically optimal description length objectives, grounded in the theory of Kolmogorov complexity. We establish that a minimizer of such an objective achieves optimal compression, for any dataset, up to an additive constant, in the limit as model resource bounds increase. We prove that asymptotically optimal objectives exist for Transformers, building on a new demonstration of their computational universality. We further show that such objectives can be tractable and differentiable by constructing and analyzing a variational objective based on an adaptive Gaussian mixture prior. Our empirical analysis shows that this variational objective selects for a low-complexity solution with strong generalization on an algorithmic task, but standard optimizers fail to find such solutions from a random initialization, highlighting key optimization challenges. More broadly, by providing a theoretical framework for identifying description length objectives with strong asymptotic guarantees, we outline a potential path towards training neural networks that achieve greater compression and generalization.

Simulation-based testing is a cornerstone of Autonomous Driving System (ADS) development, offering safe and scalable evaluation across diverse driving scenarios. However, discrepancies between simulated and real-world behavior, known as the reality gap, challenge the transferability of test results to deployed systems. In this paper, we present a comprehensive empirical study comparing four representative testing modalities: Software-in-the-Loop (SiL), Vehicle-in-the-Loop (ViL), Mixed-Reality (MR), and full real-world testing. Using a small-scale physical vehicle equipped with real sensors (camera and LiDAR) and its digital twin, we implement each setup and evaluate two ADS architectures (modular and end-to-end) across diverse indoor driving scenarios involving real obstacles, road topologies, and indoor environments. We systematically assess the impact of each testing modality along three dimensions of the reality gap: actuation, perception, and behavioral fidelity. Our results show that while SiL and ViL setups simplify critical aspects of real-world dynamics and sensing, MR testing improves perceptual realism without compromising safety or control. Importantly, we identify the conditions under which failures do not transfer across testing modalities and isolate the underlying dimensions of the gap responsible for these discrepancies. Our findings offer actionable insights into the respective strengths and limitations of each modality and outline a path toward more robust and transferable validation of autonomous driving systems.

We investigate why deep neural networks suffer from loss of plasticity in deep continual learning, failing to learn new tasks without reinitializing parameters. We show that this failure is preceded by Hessian spectral collapse at new-task initialization, where meaningful curvature directions vanish and gradient descent becomes ineffective. To characterize the necessary condition for successful training, we introduce the notion of $τ$-trainability and show that current plasticity preserving algorithms can be unified under this framework. Targeting spectral collapse directly, we then discuss the Kronecker factored approximation of the Hessian, which motivates two regularization enhancements: maintaining high effective feature rank and applying L2 penalties. Experiments on continual supervised and reinforcement learning tasks confirm that combining these two regularizers effectively preserves plasticity.

Chain-of-Thought (CoT) prompting helps Large Language Models (LLMs) tackle complex reasoning by eliciting explicit step-by-step rationales. However, CoT's verbosity increases latency and memory usage and may propagate early errors across long chains. We propose the Reasoning Capsule (R-Capsule), a framework that aims to combine the efficiency of latent reasoning with the transparency of explicit CoT. The core idea is to compress the high-level plan into a small set of learned latent tokens (a Reasoning Capsule) while keeping execution steps lightweight or explicit. This hybrid approach is inspired by the Information Bottleneck (IB) principle, where we encourage the capsule to be approximately minimal yet sufficient for the task. Minimality is encouraged via a low-capacity bottleneck, which helps improve efficiency. Sufficiency is encouraged via a dual objective: a primary task loss for answer accuracy and an auxiliary plan-reconstruction loss that encourages the capsule to faithfully represent the original textual plan. The reconstruction objective helps ground the latent space, thereby improving interpretability and reducing the use of uninformative shortcuts. Our framework strikes a balance between efficiency, accuracy, and interpretability, thereby reducing the visible token footprint of reasoning while maintaining or improving accuracy on complex benchmarks. Our codes are available at: https://anonymous.4open.science/r/Reasoning-Capsule-7BE0

Deep learning has achieved remarkable success in jet classification tasks, yet a key challenge remains: understanding what these models learn and how their features relate to known QCD observables. Improving interpretability is essential for building robust and trustworthy machine learning tools in collider physics. To address this challenge, we investigate graph neural networks for quark-gluon discrimination, systematically incorporating physics-motivated inductive biases. In particular, we design message-passing architectures that enforce infrared and collinear (IRC) safety, as well as E(2) and O(2) equivariance in the rapidity-azimuth plane. Using simulated jet datasets, we compare these networks against unconstrained baselines in terms of classification performance, robustness to soft emissions, and latent representation structures. Our analysis shows that physics-aware networks are more stable across training instances and distribute their latent variance across multiple interpretable directions. By regressing Energy Flow Polynomials onto the leading principal components, we establish a direct correspondence between learned representations and established IRC-safe jet observables. These results demonstrate that embedding symmetry and safety constraints not only improves robustness but also grounds network representations in known QCD structures, providing a principled approach toward interpretable deep learning in collider physics.

Plantar pressure mapping is essential in clinical diagnostics and sports science, yet large heterogeneous datasets often contain outliers from technical errors or procedural inconsistencies. Statistical Parametric Mapping (SPM) provides interpretable analyses but is sensitive to alignment and its capacity for robust outlier detection remains unclear. This study compares an SPM approach with an explainable machine learning (ML) approach to establish transparent quality-control pipelines for plantar pressure datasets. Data from multiple centers were annotated by expert consensus and enriched with synthetic anomalies resulting in 798 valid samples and 2000 outliers. We evaluated (i) a non-parametric, registration-dependent SPM approach and (ii) a convolutional neural network (CNN), explained using SHapley Additive exPlanations (SHAP). Performance was assessed via nested cross-validation; explanation quality via a semantic differential survey with domain experts. The ML model reached high accuracy and outperformed SPM, which misclassified clinically meaningful variations and missed true outliers. Experts perceived both SPM and SHAP explanations as clear, useful, and trustworthy, though SPM was assessed less complex. These findings highlight the complementary potential of SPM and explainable ML as approaches for automated outlier detection in plantar pressure data, and underscore the importance of explainability in translating complex model outputs into interpretable insights that can effectively inform decision-making.

Chain-of-Thought (CoT) prompting often improves classification accuracy, but it introduces a significant throughput penalty with rationale generation (Wei et al., 2022; Cheng and Van Durme, 2024). To resolve this trade-off, we introduce Dual-Head Reasoning Distillation (DHRD), a simple training method for decoder-only language models (LMs) that adds (i) a pooled classification head used during training and inference and (ii) a reasoning head supervised by teacher rationales used only in training. We train with a loss function that is a weighted sum of label cross-entropy and token-level LM loss over input-plus-rationale sequences. On seven SuperGLUE tasks, DHRD yields relative gains of 0.65-5.47% over pooled baselines, with notably larger gains on entailment/causal tasks. Since we disable the reasoning head at test time, inference throughput matches pooled classifiers and exceeds CoT decoding on the same backbones by 96-142 times in QPS.