Large-scale numerical simulations underpin modern scientific discovery but remain constrained by prohibitive computational costs. AI surrogates offer acceleration, yet adoption in mission-critical settings is limited by concerns over physical plausibility, trustworthiness, and the fusion of heterogeneous data. We introduce PHASE, a modular deep-learning framework for physics-integrated, heterogeneity-aware surrogates in scientific simulations. PHASE combines data-type-aware encoders for heterogeneous inputs with multi-level physics-based constraints that promote consistency from local dynamics to global system behavior. Using only the first 20 simulation years, PHASE infers a near-equilibrium state that otherwise requires more than 1,200 years of integration, yielding an effective reduction in required integration length by at least 60 . The framework is enabled by a pipeline for fusing heterogeneous scientific data and demonstrates strong generalization to higher spatial resolutions with minimal fine-tuning. These results indicate that PHASE captures governing physical regularities rather than surface correlations, enabling practical, physically consistent acceleration of land-surface modeling and other complex scientific workflows. Numerical simulations, mainly grounded in domain knowledge and partial differential equations (PDEs), are fundamental pillars of modern scientific discovery, driving advances in fields from climate modeling to materials design (Hao et al., 2024; Koehler et al., 2024; Danabasoglu et al., 2020; Pathak et al., 2020; Reichstein et al., 2019).

Frame of Reference (FoR) is a fundamental concept in spatial reasoning that humans utilize to comprehend and describe space. With the rapid progress in Multimodal Language models, the moment has come to integrate this long-overlooked dimension into these models. In particular, in text-to-image (T2I) generation, even state-of-the-art models exhibit a significant performance gap when spatial descriptions are provided from perspectives other than the camera. To address this limitation, we propose Frame of Reference-guided Spatial Adjustment in LLM-based Diffusion Editing (FoR-SALE), an extension of the Self-correcting LLM-controlled Diffusion (SLD) framework for T2I. For-Sale evaluates the alignment between a given text and an initially generated image, and refines the image based on the Frame of Reference specified in the spatial expressions. It employs vision modules to extract the spatial configuration of the image, while simultaneously mapping the spatial expression to a corresponding camera perspective. This unified perspective enables direct evaluation of alignment between language and vision. When misalignment is detected, the required editing operations are generated and applied. FoR-SALE applies novel latent-space operations to adjust the facing direction and depth of the generated images. We evaluate FoR-SALE on two benchmarks specifically designed to assess spatial understanding with FoR. Our framework improves the performance of state-of-the-art T2I models by up to 5.3% using only a single round of correction.

Binary code similarity detection is a core task in reverse engineering. It supports malware analysis and vulnerability discovery by identifying semantically similar code in different contexts. Modern methods have progressed from manually engineered features to vector representations. Hand-crafted statistics (e.g., operation ratios) are interpretable, but shallow and fail to generalize. Embedding-based methods overcome this by learning robust cross-setting representations, but these representations are opaque vectors that prevent rapid verification. They also face a scalability-accuracy trade-off, since high-dimensional nearest-neighbor search requires approximations that reduce precision. Current approaches thus force a compromise between interpretability, generalizability, and scalability. We bridge these gaps using a language model-based agent to conduct structured reasoning analysis of assembly code and generate features such as input/output types, side effects, notable constants, and algorithmic intent. Unlike hand-crafted features, they are richer and adaptive. Unlike embeddings, they are human-readable, maintainable, and directly searchable with inverted or relational indexes. Without any matching training, our method respectively achieves 42% and 62% for recall@1 in cross-architecture and cross-optimization tasks, comparable to embedding methods with training (39% and 34%). Combined with embeddings, it significantly outperforms the state-of-the-art, demonstrating that accuracy, scalability, and interpretability can coexist.

The imperative of user privacy protection and regulatory compliance necessitates sensitive data removal in model training, yet this process often induces distributional shifts that undermine model performance-particularly in out-of-distribution (OOD) scenarios. We propose a novel data removal approach that enhances deep predictive models through factor decorrelation and loss perturbation. Our approach introduces: (1) a discriminative-preserving factor decorrelation module employing dynamic adaptive weight adjustment and iterative representation updating to reduce feature redundancy and minimize inter-feature correlations. (2) a smoothed data removal mechanism with loss perturbation that creates information-theoretic safeguards against data leakage during removal operations. Extensive experiments on five benchmark datasets show that our approach outperforms other baselines and consistently achieves high predictive accuracy and robustness even under significant distribution shifts. The results highlight its superior efficiency and adaptability in both in-distribution and out-of-distribution scenarios.

Abstract-- Convolutional Neural Networks (CNNs) have become a cornerstone of medical image analysis due to their proficiency in learning hierarchical spatial features. However, this focus on a single domain is inefficient at capturing global, holistic patterns and fails to explicitly model an image's frequency-domain characteristics. To address these challenges, we propose the Spatial-Spectral Summa-rizer Fusion Network (S F-Net), a dual-branch framework that learns from both spatial and spectral representations simultaneously. The S F-Net performs a fusion of a deep spatial CNN with our proposed shallow spectral encoder, SpectraNet. SpectraNet features the proposed SpectralFilter layer, which leverages the Convolution Theorem by applying a bank of learnable filters directly to an image's full Fourier spectrum via a computation-efficient element-wise multiplication. This allows the SpectralFilter layer to attain a global receptive field instantaneously, with its output being distilled by a lightweight summarizer network. We evaluate S F-Net across four diverse medical imaging datasets spanning different scales and modalities: HAM10000 (dermoscopy), BUSI (ultrasound), BRISC2025 (MRI), and Chest X-Ray Pneumonia (radiography), to validate its efficacy and generalizability, and reveal the task-dependent nature of the optimal fusion strategy. Our framework consistently and significantly outperforms its strong spatial-only baseline in all cases, with accuracy improvements of up to 5.13%. With a powerful Bilinear Fusion, S F-Net achieves a state-of-the-art competitive accuracy of 98.76% on the BRISC2025 dataset. A simpler Concatenation Fusion performs better on the texture-dominant Chest X-Ray Pneumonia dataset, achieving 93.11% accuracy, surpassing many top-performing, much deeper models. Our explainability analysis also reveals that the S F-Net learns to dynamically adjust its reliance on each branch based on the input pathology. These results verify that our dual-domain approach is a powerful and generalizable paradigm for medical image analysis.

The creation of high-quality multimodal datasets remains fundamental for advancing role-playing capabilities in large language models (LLMs). While existing works predominantly focus on text-based persona simulation, Audio Role-Playing (ARP) presents unique challenges due to the need for synchronized alignment of semantic content and vocal characteristics. To address this gap, we propose AudioRole, a meticulously curated dataset from 13 TV series spanning 1K+ hours with 1M+ character-grounded dialogues, providing synchronized audio-text pairs annotated with speaker identities and contextual metadata. In addition, to demonstrate the effectiveness of the dataset, we introduced ARP-Eval, a dual-aspect evaluation framework that assesses both response quality and role fidelity. Empirical validation showing GLM-4-Voice trained on AudioRole (which we called ARP-Model) achieve an average Acoustic Personalization score of 0.31, significantly outperforming the original GLM-4-voice and the more powerful model MiniCPM-O-2.6, which specifically supports role-playing in one-shot scenarios. The ARP-Model also achieves a Content Personalization score of 0.36, surpassing the untrained original model by about 38% and maintaining the same level as MiniCPM-O-2.6. AudioRole features dialogues from over 115 main characters, 6 trained ARP-Models that role-play different characters, and evaluation protocols. Together, they provide an essential resource for advancing audio-grounded role-playing research.

Communication challenges between autistic and neurotypical individuals stem from a mutual lack of understanding of each other's distinct, and often contrasting, communication styles. Yet, autistic individuals are expected to adapt to neurotypical norms, making interactions inauthentic and mentally exhausting for them. To help redress this imbalance, we build NeuroBridge, an online platform that utilizes large language models (LLMs) to simulate: (a) an AI character that is direct and literal, a style common among many autistic individuals, and (b) four cross-neurotype communication scenarios in a feedback-driven conversation between this character and a neurotypical user. Through NeuroBridge, neurotypical individuals gain a firsthand look at autistic communication, and reflect on their role in shaping cross-neurotype interactions. In a user study with 12 neurotypical participants, we find that NeuroBridge improved their understanding of how autistic people may interpret language differently, with all describing autism as a social difference that "needs understanding by others" after completing the simulation. Participants valued its personalized, interactive format and described AI-generated feedback as "constructive", "logical" and "non-judgmental". Most perceived the portrayal of autism in the simulation as accurate, suggesting that users may readily accept AI-generated (mis)representations of disabilities. To conclude, we discuss design implications for disability representation in AI, the need for making NeuroBridge more personalized, and LLMs' limitations in modeling complex social scenarios.

Federated Learning (FL) enables participant devices to collaboratively train deep learning models without sharing their data with the server or other devices, effectively addressing data privacy and computational concerns. However, FL faces a major bottleneck due to high communication overhead from frequent model updates between devices and the server, limiting deployment in resource-constrained wireless networks. In this paper, we propose a three-fold strategy. Firstly, an Adaptive Feature-Elimination Strategy to drop less important features while retaining high-value ones; secondly, Adaptive Gradient Innovation and Error Sensitivity-Based Quantization, which dynamically adjusts the quantization level for innovative gradient compression; and thirdly, Communication Frequency Optimization to enhance communication efficiency. We evaluated our proposed model's performance through extensive experiments, assessing accuracy, loss, and convergence compared to baseline techniques. The results show that our model achieves high communication efficiency in the framework while maintaining accuracy.

Language models (LMs) encode substantial factual knowledge, but often produce answers judged as incorrect. We hypothesize that many of these answers are actually correct, but are expressed in alternative surface forms that are dismissed due to an overly strict evaluation, leading to an underestimation of models' parametric knowledge. We propose Retrieval-Constrained Decoding (RCD), a decoding strategy that restricts model outputs to unique surface forms. We introduce YAGO-QA, a dataset of 19,137 general knowledge questions. Evaluating open-source LMs from 135M to 70B parameters, we show that standard decoding undervalues their knowledge. For instance, Llama-3.1-70B scores only 32.3% F1 with vanilla decoding but 46.0% with RCD. Similarly, Llama-3.1-8B reaches 33.0% with RCD, outperforming the larger model under vanilla decoding. We publicly share the code and dataset at https://github.com/Rajjaa/disambiguated-LLM.

Despite the impressive performance of LLM-powered agents, their adoption for Electronic Health Record (EHR) data access remains limited by the absence of benchmarks that adequately capture real-world clinical data access flows. In practice, two core challenges hinder deployment: query ambiguity from vague user questions and value mismatch between user terminology and database entries. To address this, we introduce EHR-ChatQA an interactive database question answering benchmark that evaluates the end-to-end workflow of database agents: clarifying user questions, using tools to resolve value mismatches, and generating correct SQL to deliver accurate answers. To cover diverse patterns of query ambiguity and value mismatch, EHR-ChatQA assesses agents in a simulated environment with an LLM-based user across two interaction flows: Incremental Query Refinement (IncreQA), where users add constraints to existing queries, and Adaptive Query Refinement (AdaptQA), where users adjust their search goals mid-conversation. Experiments with state-of-the-art LLMs (e.g., o4-mini and Gemini-2.5-Flash) over five i.i.d. trials show that while agents achieve high Pass@5 of 90-95% (at least one of five trials) on IncreQA and 60-80% on AdaptQA, their Pass^5 (consistent success across all five trials) is substantially lower by 35-60%. These results underscore the need to build agents that are not only performant but also robust for the safety-critical EHR domain. Finally, we provide diagnostic insights into common failure modes to guide future agent development.