arXiv:2508.09449v2 Announce Type: replace
Abstract: Reference-based Super Resolution (RefSR) improves upon Single Image Super Resolution (SISR) by leveraging high-quality reference images to enhance texture fidelity and visual realism. However, a critical limitation of existing RefSR approaches is their reliance on manually curated target-reference image pairs, which severely constrains their practicality in real-world scenarios. To overcome this, we introduce Retrieval-Augmented Super Resolution (RASR), a new and practical RefSR paradigm that automatically retrieves semantically relevant high-resolution images from a reference database given only a low-quality input. This enables scalable and flexible RefSR in realistic use cases, such as enhancing mobile photos taken in environments like zoos or museums, where category-specific reference data (e.g., animals, artworks) can be readily collected or pre-curated. To facilitate research in this direction, we construct RASR-Flickr30, the first benchmark dataset designed for RASR. Unlike prior datasets with fixed target-reference pairs, RASR-Flickr30 provides per-category reference databases to support open-world retrieval. We further propose RASRNet, a strong baseline that combines a semantic reference retriever with a diffusion-based RefSR generator. It retrieves relevant references based on semantic similarity and employs a diffusion-based generator enhanced with semantic conditioning. Experiments on RASR-Flickr30 demonstrate that RASRNet consistently improves over SISR baselines, achieving +0.38 dB PSNR and -0.0131 LPIPS, while generating more realistic textures. These findings highlight retrieval augmentation as a promising direction to bridge the gap between academic RefSR research and real-world applicability.
Science Journals
arXiv:2509.13177v2 Announce Type: replace
Abstract: Continuum robots are advancing bronchoscopy procedures by accessing complex lung airways and enabling targeted interventions. However, their development is limited by the lack of realistic training and test environments: Real data is difficult to collect due to ethical constraints and patient safety concerns, and developing autonomy algorithms requires realistic imaging and physical feedback. We present ROOM (Realistic Optical Observation in Medicine), a comprehensive simulation framework designed for generating photorealistic bronchoscopy training data. By leveraging patient CT scans, our pipeline renders multi-modal sensor data including RGB images with realistic noise and light specularities, metric depth maps, surface normals, optical flow and point clouds at medically relevant scales. We validate the data generated by ROOM in two canonical tasks for medical robotics: multi-view pose estimation and monocular depth estimation, demonstrating diverse challenges that state-of-the-art methods must overcome to transfer to these medical settings. Furthermore, we show that the data produced by ROOM can be used to fine-tune existing depth estimation models to overcome these challenges, also enabling other downstream applications such as navigation. We expect that ROOM will enable large-scale data generation across diverse patient anatomies and procedural scenarios that are challenging to capture in clinical settings. Code and data: https://github.com/iamsalvatore/room.
arXiv:2509.14075v2 Announce Type: replace
Abstract: Robotic-assisted minimally invasive surgery (RAMIS) requires accurate enforcement of the remote center of motion (RCM) constraint to ensure safe tool motion through a trocar. Existing virtual RCM controllers are commonly formulated either at the kinematic level or as task-space objectives, which makes torque-level enforcement under trocar motion and physical interaction difficult to formulate consistently. This paper models the RCM as a rheonomic holonomic constraint and incorporates it into a projection-based inverse-dynamics controller with explicit constrained/free-motion torque decomposition. The resulting formulation unifies kinematic RCM enforcement and task-space tracking at the torque level, while preserving a constraint-consistent structure for residual regulation and null-space compliance. The proposed controller is validated in simulation and on a RAMIS training platform against representative projection-based and constrained-dynamics baselines. Across spiral tracking, varying insertion depth, moving trocar conditions, and human interaction, the method achieves lower RCM residuals and smoother torque profiles while maintaining accurate tool-tip tracking. These results support the use of constraint-consistent torque control for reliable virtual RCM enforcement in surgical robotics. The project page is available at https://rcmpc-cube.github.io
arXiv:2605.28397v1 Announce Type: new
Abstract: Predicting conversion from Mild Cognitive Impairment (MCI) to Alzheimer's Disease (AD) is critical for early intervention. Current deep learning paradigms predominantly rely on cross-sectional structural MRI, neglecting prognostic value in patient-specific anatomical trajectories. We introduce the Temporal Adaptive Fusion Network (TAF-Net), a hybrid CNN-Transformer architecture that models paired longitudinal 3D MRI scans. Central to TAF-Net is a Temporal Fusion Module governed by an Adaptive Temporal Gate, which learns patient-specific weightings to synthesize three spatiotemporal representations: explicit structural change, region-to-region temporal cross-attention, and bilateral feature concatenation. Evaluated on the Alzheimer's Disease Neuroimaging Initiative cohort for three-year MCI-to-AD conversion prediction, TAF-Net achieved the highest discriminative performance among all evaluated methods using only structural MRI, significantly outperforming the strongest baseline and approaching multimodal methods requiring PET, CSF, or genetic data. The architecture exhibited exceptional data efficiency, matching baseline performance with a fraction of training data. Ablation studies demonstrate that longitudinal fusion improves discrimination while reducing predictive variance by 48% compared to single-timepoint evaluation. Interpretability analyses reveal spatial attention aligned with established AD pathology in the medial temporal lobe and ventricles, while the gating mechanism prioritizes explicit volumetric change with strong positive correlation to conversion risk.
arXiv:2605.28476v1 Announce Type: new
Abstract: Digital forensic relies on validated tools and established procedures, yet the underlying operating systems, applications, and analysis tools evolve rapidly. This evolution can cause artifact behavior and tool outputs to drift, silently degrading repeatability and confidence in long-lived forensic interpretations. We present test-driven forensics, a practical approach that treats forensic expectations as executable specifications: expected artifacts and expected tool outputs are encoded as tests that can be rerun across versions to detect regressions. Crucially, our approach also enables State Transition Testing, validating the system's expected state after each user action rather than only performing post-mortem checks on a final disk image; this supports causal attribution and makes transient behavior testable. We implement the methodology in ADARE, an open-source framework that runs controlled experiments in virtual machines and simulates realistic user activity via computer-vision-guided GUI automation. ADARE includes a companion web platform for sharing experiments, environments, and results to facilitate independent reruns and peer verification. We evaluate ADARE in five case studies spanning artifact research and tool validation. In particular, a 25-version regression study of Autopsy reveals substantial, largely undocumented changes in exported report outputs, demonstrating how executable tests make drift measurable and reproducible at scale.
arXiv:2605.28483v1 Announce Type: new
Abstract: Linking learning resources to a structured competency framework is key to enabling competency-based search and curriculum analytics in Learning Management Systems (LMS). However, manual tagging is labor-intensive, and fully automatic methods often lack transparency. In this paper, we present an end-to-end alignment pipeline that uses a large language model (LLM) as a constrained, evidence-producing tagger. LMS resources -both instructional content and assessments -are first segmented into meaningful pedagogical fragments. For each fragment, a small set of candidate competencies is retrieved from structured competency profiles enriched with graph-based context. The LLM then selects the most relevant competencies from this set and provides supporting evidence spans from the fragment text. These predictions are refined using the structure of the competency graph and aggregated at the resource level. We evaluate our approach on a dataset built from the Computer Science department's competency referential at the Universit\'e de Technologie de Compi\`egne (UTC), covering 22 competencies across multiple course materials. Our LLM+BM25+Graph (LBG) pipeline achieves strong results, with a micro-F1 of 0.57 and macro-F1 of 0.50 at the fragment level, 0.51 macro-F1 at the resource level, and an MRR of 0.82outperforming zero-shot and few-shot LLM variants, retrieval/similarity baselines, and supervised classifiers -while also producing more mechanically traceable evidence spans to support human auditing and educational analysis.
arXiv:2510.05291v2 Announce Type: replace
Abstract: As Large Language Models (LLMs) develop stronger multilingual capabilities, their sensitivity to culturally diverse entities becomes increasingly important. Prior work by Naous et al. (2024) has shown that LLMs often favor Western-associated entities in Arabic. Due to the lack of entity-centric multilingual benchmarks, it remains unclear if such biases also manifest in various non-Western languages. In this paper, we introduce Camellia, a benchmark for evaluating entity-centric cultural biases in nine Asian languages, spanning six Asian cultures. Camellia includes 19,530 manually annotated entities associated with the covered Asian or Western cultures, as well as 2,173 masked contexts for these entities derived from social media posts. Using Camellia, we evaluate cultural biases in four recent multilingual LLMs across three tasks: cultural context adaptation, sentiment association, and entity extractive QA. Our analyses show that LLMs struggle with cultural adaptation across these languages, with performance differing across models developed in different regions. We further observe that different LLM families can hold distinct biases, reflected in the ways they link cultures to particular sentiments. Lastly, we find that LLMs can struggle with context understanding in some Asian languages, creating performance gaps between cultures in entity extraction.
arXiv:2510.17046v2 Announce Type: replace
Abstract: The stable atmospheric boundary layer (SABL) is broadly classified into two subtypes: the nocturnal SABL, driven primarily by surface cooling, and the long-lived SABL, in which ambient stratification coexists with surface cooling and persists well beyond a single diurnal cycle. Despite its prevalence in polar regions and over open oceans, the long-lived SABL has received comparatively little attention, and a systematic direct numerical simulation (DNS) study distinguishing it from the nocturnal SABL has not previously been reported. Here we present DNS of long-lived SABLs at $Re_D=900$, contrasting weak and strong ambient stratification cases against a nocturnal SABL. A striking feature of the long-lived SABLs is the emergence of a multi-layered thermal structure -- including an intermediate layer of reduced static stability capped by a buoyancy inversion -- driven not by enhanced turbulent mixing, but by a stratification-induced reorganisation of the buoyancy field. Budget analyses identify a turbulent potential energy-centred transport mechanism absent in nocturnal SABLs, lending support to total-energy-based closure approaches. Assessment of an extended Monin--Obukhov similarity theory incorporating a composite length scale $L_*$ shows strong collapse of dimensionless gradients of velocity $\phi_m$ and potential temperature $\phi_h$, and a new similarity function for $\phi_h$ is proposed. Combining DNS with linear stability analysis, we construct a regime map delineating linearly stable, weakly stable, and very stable regimes within a two-parameter dimensionless space, demonstrating the inherently multi-parameter nature of long-lived SABLs and the limitations of single-parameter subgrid-scale parameterisations.
arXiv:2511.02398v2 Announce Type: replace
Abstract: We present a novel decentralized algorithm for coverage control in unknown spatial environments modeled by Gaussian Processes (GPs). To trade-off between exploration and exploitation, each agent autonomously determines its trajectory by minimizing a local cost function. Inspired by the GP-UCB (Upper Confidence Bound for GPs) acquisition function, the proposed cost combines the expected locational cost with a variance-based exploration term, guiding agents toward regions that are both high in predicted density and model uncertainty. Compared to previous work, our algorithm operates in a fully decentralized fashion, relying only on local observations and communication with neighboring agents. In particular, agents periodically update their inducing points using a greedy selection strategy, enabling scalable online GP updates. We demonstrate the effectiveness of our algorithm in simulation.
arXiv:2510.24941v4 Announce Type: replace
Abstract: Large language models can generate long chain-of-thought (CoT) reasoning, yet prior work suggests that CoT can be post-hoc rationalization rather than a faithful reflection of the computation through explicitly designed settings. In this work, we go further and propose a True Thinking Score (TTS) to quantify the causal contribution of each step in CoT to the model's final prediction in realistic reasoning problems. Across eleven models ranging from 1.5B to 1.1T parameters on common reasoning benchmarks, we find that CoTs often interleave true-thinking steps, which causally affect the final answer, with decorative-thinking steps, which appear useful but have little causal influence; Such decorative steps remain prevalent even for frontier models: Over 30% of steps in Kimi-K2.6 are decorative on MATH with TTS <= 0.005. Furthermore, TTS enables effective CoT pruning: removing 50% of CoT steps with the lowest TTS can largely maintain the performance. Self-training on these pruned CoTs reduces reasoning length by 66% while preserving performance on Nemotron3-Nano-30B. Finally, we provide a mechanistic analysis showing that LLMs can be steered in the latent space to engage or disengage with reasoning steps. Overall, our results reveal that frontier LLMs often verbalize reasoning steps that are not causally used, challenging both the efficiency and the trustworthiness of CoT.
arXiv:2511.00254v3 Announce Type: replace
Abstract: A multiflow in a planar graph is uncrossed if its support paths do not cross. Recently such flows have played a role in approximation algorithms for maximum disjoint paths in "fully-planar" instances, where the combined supply-demand graph is planar, as well as low-congestion unsplittable flows for fully-planar and single-source instances.
We investigate the utility of uncrossed flow more generally and ask three key questions. First, are there other interesting planar multiflow instances that admit uncrossed flows? We answer affirmatively, demonstrating a new family of "pairwise-planar" instances whose flows can be uncrossed. This family subsumes fully-planar but includes substantially more, such as fully-compliant series-parallel instances and some instances that have large clique demand graphs. Second, can we always round a fractional uncrossed flow to a "good" integral flow? We again answer positively. For maximization problems, we obtain integral flows with a constant fraction of the original value. For congestion problems (where we fully route all given demands), we obtain integral flows with edge congestion 2. Consequently, we obtain constant-factor approximation algorithms for maximum disjoint paths and minimum congestion integer multiflow for pairwise-planar instances, and show such instances have a constant integral flow-multicut gap. Finally, given a planar multiflow instance, can we determine if there exists a congestion-1 uncrossed fractional flow (congestion) or find the maximum value uncrossed fractional flow (maximization)? For congestion, we show this problem is NP-hard, but finding uncrossed edge-disjoint paths is polytime solvable if the demands span a bounded number of faces. For maximization, we present a strong inapproximability result.
arXiv:2605.28691v1 Announce Type: new
Abstract: Diffusion Transformers achieve strong video generation quality, but the quadratic cost of full attention limits efficiency. We introduce OSP-Next, an efficient text-to-video generation model that integrates sparse attention, parallelism, quantization, and reinforcement learning. OSP-Next uses a hybrid full-sparse attention architecture, where the sparse component is implemented with Skiparse-2D Attention. This fixed-pattern mechanism applies token-wise and group-wise sparse attention along spatial dimensions, leveraging locality while maintaining native compatibility with FlashAttention kernels. Based on the local equivalence of rearrangement in Skiparse-2D Attention, we further propose Sparse Sequence Parallelism (SSP), which partitions subsequences across ranks and switches sparse patterns through a single All-to-All communication. Compared with Ulysses Sequence Parallelism (SP), SSP provides a native parallel strategy for sparse attention and reduces communication volume by 75%. OSP-Next also incorporates HiF8 quantization to enable stable joint training with 8-bit quantization and sparse fine-tuning, and applies Mix-GRPO post-training to improve the performance of the sparse model. Experiments show that OSP-Next achieves a VBench total score of 83.73%, surpassing the Wan2.1 baseline. Under the 5-second 720P and 5-second 768P settings, OSP-Next achieves up to 1.64$\times$ single-GPU speedup and over 1.52$\times$ eight-GPU speedup on NVIDIA H200 GPUs. In addition, with only a 0.4% drop in VBench total score, OSP-Next-HiF8 achieves 1.69$\times$ and 2.27$\times$ speedups under the two settings on a single Ascend 950PR, demonstrating the efficiency and performance of OSP-Next across hardware platforms.
arXiv:2605.28778v1 Announce Type: new
Abstract: LLMs' linguistically expressed confidence should faithfully reflect their intrinsic uncertainty. While recent work shows LLMs struggle to use epistemic markers (e.g., "it is likely...") in a human-aligned fashion, it remains unclear whether models can apply their own linguistic confidence framework to associate markers with specific confidence levels in a stable and generalizable way, and how contextual features impact this ability. We conduct the first systematic study of this question, formalizing _marker internal confidence_ (MIC) as the estimated intrinsic confidence a model associates with a specific epistemic marker in a given task domain. We present 7 metrics to evaluate the stability of MICs within and across distributions. Applying our analysis framework to diverse models and tasks, we find that LLMs remain faithfully miscalibrated even under model-centric interpretation of marker meanings, struggling to differentiate markers by internal confidence across distributions despite preserving a somewhat consistent ranking order across tasks. This supplies critical, complementary evidence to existing work toward a holistic understanding of faithful calibration in LLMs, emphasizing the need for more aligned and stable marker use to improve trustworthiness and reliability.
arXiv:2602.12586v2 Announce Type: replace
Abstract: While plan-and-infill decoding in Masked Diffusion Models (MDMs) shows promise for mathematical and code reasoning, performance remains highly sensitive to slot infilling order, often yielding substantial output variance. We introduce McDiffuSE, a framework that formulates slot selection as decision making and optimises infilling orders through Monte Carlo Tree Search (MCTS). McDiffuSE uses look-ahead simulations to evaluate partial completions before commitment, systematically exploring the combinatorial space of generation orders. Experiments show an average improvement of 3.2% over autoregressive baselines and 8.0% over baseline plan-and-infill, with notable gains of 19.5% on MBPP and 4.9% on MATH500. Our analysis reveals that while McDiffuSE predominantly follows sequential ordering, incorporating non-sequential generation is essential for maximising performance. We observe that larger exploration constants, rather than increased simulations, are necessary to overcome model confidence biases and discover effective orderings. These findings establish MCTS-based planning as an effective approach for enhancing generation quality in MDMs.
arXiv:2602.15198v2 Announce Type: replace
Abstract: Multi-agent systems, where LLM agents communicate through free-form language, enable sophisticated coordination for solving complex cooperative tasks. This surfaces a unique safety problem when a group of agents forms a coalition and colludes to pursue secondary goals and degrade the joint objective. In this paper, we present Colosseum, a framework for auditing LLM agents' collusive behavior in multi-agent settings. We ground how agents cooperate through a formal multi-agent decision-making framework and measure action-based collusive behavior in actions via regret relative to the cooperative optimum and compare it with communication-based collusive behavior. Colosseum enables audits of LLM agents for collusion under benign settings, different coalition objectives, persuasion tactics, and network topologies. We then introduce a new behavioral probe by creating secret communication channels between agents, showing that most out-of-the-box models exhibit a propensity to collude under this probe, which we term emergent collusion. Furthermore, we discover ``collusion on paper'' when agents plan to collude in text but often pick non-collusive actions. Colosseum provides a new way to audit collusion in cooperative multi-agent systems while presenting observations about how collusion emerges, what affects collusion efficacy, and which strategies may mitigate it.
arXiv:2603.26630v2 Announce Type: replace
Abstract: Ultraweak photon emission, also referred to as biological autoluminescence or biophoton emission, is the spontaneous emission of extremely low levels of light from a broad range of biological systems. Recent studies have reported that UPE measured extracranially can serve as a potential non-invasive biomarker of brain activity. Here, we show that this interpretation suffers from serious problems. We show that, when observed under properly dark conditions, the UPE from the head is much weaker than what is reported in certain papers on 'brain UPE' from human heads. We also show that the large signals reported in these studies can be explained by background light contamination. Furthermore, photons with wavelengths < 600 nm are strongly attenuated by scalp and skull tissues, and longer wavelengths fall largely outside the effective spectral sensitivity of the photomultiplier tubes (PMTs) used. As a consequence, even if UPE from the head is detected under properly background-free conditions, it is likely to be dominated by emission from the scalp rather than from the brain, certainly as long as PMTs are used. Our results emphasize the importance of careful experimental design to make genuine progress on this important question.
arXiv:2512.16483v2 Announce Type: replace
Abstract: Visual Autoregressive (VAR) modeling departs from the next-token prediction paradigm of traditional Autoregressive (AR) models through next-scale prediction, enabling high-quality image generation. However, the VAR paradigm suffers from sharply increased computational complexity and running time at large-scale steps. Although existing acceleration methods reduce runtime for large-scale steps, but rely on manual step selection and overlook the varying importance of different stages in the generation process. To address this challenge, we present FasterVAR, a systematic study and plug-and-play acceleration framework for VAR models. Our analysis shows that early steps are critical for preserving semantic and structural consistency and should remain intact,while later steps mainly refine details and can be pruned or approximated for acceleration. Building on these insights, FasterVAR introduces a plug-and-play acceleration strategy that exploits semantic irrelevance and low-rank properties in late-stage computations, without requiring additional training. Our proposed FasterVAR achieves up to 3.4x speedup with almost no performance loss. consistently outperforming existing acceleration baselines.These results highlight stage-aware design as a powerful principle for efficient visual autoregressive image generation.
arXiv:2512.22777v2 Announce Type: replace
Abstract: Generalization across domains requires stable structure that links the source and target distributions. Building on causal transportability theory, we study a sequential prediction setting in which the target predictor can be represented as a circuit composed of causal mechanisms that are learnable from source data. We introduce two classes of transportability. Module transportability captures the atomic case, where the target predictor is given by a mechanism learnable from a single source domain. Circuit transportability generalizes this idea to target predictors obtained by composing several modules learned from source data, enabling zero-shot prediction even when no source mechanism directly predicts the target label. We study these classes of circuits under increasingly relaxed assumptions. First, we provide conditions under which the relevant circuits can be learned from source data alone, given causal knowledge about the source and target domains. We then relax these structural assumptions by allowing limited data from the target domain. In particular, we develop a supervised domain adaptation scheme that learns circuits without requiring explicit causal structure. The resulting few-shot guarantees tie the achievable error to the size of the smallest target circuit composable from modules learned from source data. Finally, we propose a gradient-based relaxation of the symbolic circuit search and evaluate it empirically, showing that it qualitatively tracks the predicted regimes of fast adaptation -- with and without process supervision over intermediate positions -- and slow adaptation when no source mechanism matches.
arXiv:2605.25378v2 Announce Type: replace
Abstract: Customized image editing aims to equip pre-trained diffusion models with specific visual effects using limited paired data, typically via Low-Rank Adaptation (LoRA). As the number of desired effects grows, storing and dynamically loading numerous these effect LoRAs significantly increases deployment overhead. Furthermore, current pipelines typically cascade these effect LoRAs with acceleration modules for fast generation, which triggers severe parameter interference and results in concept bleeding and style degradation. We propose CollectionLoRA, a multi-teacher on-policy distillation framework capable of distilling the concepts of up to 50 different effect LoRAs along with few-step generation capabilities into a single LoRA. This fundamentally resolves the feature interference issue and significantly reduces deployment costs. Specifically, the method introduces (i) a Probabilistic Dual-Stream Routing mechanism that enables the model to randomly switch between data sources during training, effectively enhancing its generalization in unseen scenarios; (ii) an Asymmetric Orthogonal Prompting strategy to achieve concept isolation within the prompt space; (iii) a Coarse-to-Fine Distillation Objective to mitigate the distribution gap between the teacher and student models. Extensive evaluations show that CollectionLoRA distills all customized effects and few-step generation into a single LoRA, reducing deployment overhead while achieving concept fidelity comparable to or better than independently trained teacher models. Code: https://github.com/Qwen-Applications/CollectionLoRA
arXiv:2504.09637v3 Announce Type: replace
Abstract: We establish optimal convergence rates for the continuous piecewise affine finite element approximation of the Sobolev constant in arbitrary dimensions N\geq 2 and for Lebesgue exponents 1<p<N. Our analysis relies on a refined study of the Sobolev deficit in suitable quasi-norms, which have been introduced and utilized in the context of finite element approximations of the p-Laplacian. The proof further involves sharp estimates for the finite element approximation of Sobolev minimizers.
arXiv:2605.25670v2 Announce Type: replace
Abstract: Test beam studies of ITk pixel sensors and full modules are an essential tool for assessing their performance and operational behavior. In the 2025 test beam campaigns, quad and triplet modules equipped with both pre-production and production readout chips were evaluated. For the first time, triplet modules were tested in beam conditions, both before and after irradiation. Measurements were performed at multiple incident angles to study charge-collection efficiency under conditions representative of actual detector operation. The 2025 test beam dataset contains several important new elements, enabling further progress toward the full qualification of ITk pixel modules. This work presents an overview of the ITk pixel test beam program including recent triplet module results from the 2025 campaigns.
arXiv:2605.28064v1 Announce Type: cross
Abstract: Automatic deepfake detection has received considerable research attention, yet the socio-technical environment in which humans actually encounter synthetic speech remains poorly understood. We investigate voice deepfake detection as a perceptual and contextual process, presenting a localization task in which 47 participants marked suspected synthetic segments across authentic, fully synthetic, and partially synthetic utterances under three manipulated trust cues: instructional framing, affective priming, and provenance labeling. Participants provided quality ratings on mechanicalness, expressiveness, intelligibility, clarity, calmness, and confidence of evaluation. Utterance class was the primary determinant of detection accuracy and perceptual quality; trust cues produced no main effects but motivated detection behavior. Fully synthetic speech was detected at below-chance levels. Quality ratings tracked utterance type, indicating implicit discrimination where overt detection failed.
arXiv:2605.28395v1 Announce Type: cross
Abstract: We present a systematic benchmark of MACE potentials for iron-nickel alloys, focusing on structural, elastic, magnetic, and finite-temperature properties relevant to phase stability. The reference dataset comprises spin-polarized PBE density functional theory (DFT) calculations for chemically disordered special quasirandom structures (SQS), spanning compositions, bcc and fcc crystal structures, and volumetric and shear deformations. A system-specific MACE-sqs model trained on this dataset achieves validation errors of 2.0 meV/atom for energies and 24.3 meV/Angstrom for forces. Compared with several MACE foundation models, including models trained with Hubbard U corrections, MACE-sqs gives the most consistent agreement with DFT and experiment for equations of state, equilibrium volumes, elastic constants, and thermal expansion trends in bcc and fcc Fe-Ni alloys. For the bcc-to-hcp transition, MACE-sqs predicts a pure-Fe transition pressure closer to experiment than the tested foundation models, but all models predict an incorrect increase of transition pressure with Ni content. This failure indicates that high-pressure magnetic collapse and composition-dependent magnetoelastic effects are not yet fully captured. Overall, targeted SQS-based training substantially improves the accuracy of MACE potentials for Fe-Ni alloys, while phase stability under magnetic collapse remains a key limitation for future model development.
arXiv:2405.09689v2 Announce Type: replace
Abstract: Hyperdimensional Computing (HDC) is a computationally and data-efficient paradigm that acts as a bridge between connectionist and symbolic approaches to artificial intelligence (AI). However, HDC's simplicity poses challenges for encoding complex compositional structures, especially in its binding operation. To address this, we propose Generalized Holographic Reduced Representations (GHRR), an extension of Fourier Holographic Reduced Representations (FHRR), a specific HDC implementation. GHRR introduces a flexible, non-commutative binding operation, enabling improved encoding of complex data structures while preserving HDC's desirable properties of robustness and transparency. In this work, we introduce the GHRR framework, prove its theoretical properties and its adherence to HDC properties, explore its kernel and binding characteristics, and perform empirical experiments showcasing its flexible non-commutativity, enhanced decoding accuracy for compositional structures. We also demonstrate that binding in GHRR is more expressive than that in other HDC variants; in particular, we show that binding in GHRR can implement a kind of attention mechanism. We verify this by replacing the attention mechanism in a transformer with its GHRR-equivalent and testing it on a language modeling task, showing improved performance compared to a vanilla transformer.
arXiv:2512.23959v3 Announce Type: replace
Abstract: Multi-step retrieval-augmented generation (RAG) has become a widely adopted strategy for enhancing large language models (LLMs) on tasks that demand global comprehension and intensive reasoning. Although many RAG systems incorporate a working memory to consolidate information, existing designs primarily function as a passive storage for isolated facts. This static nature overlooks crucial high-order correlations among primitive facts, thereby limiting models' capacity for multi-step reasoning and resulting in fragmented reasoning and weak global sense-making within extended contexts. We introduce HGMem, a hypergraph-based working memory system, extending the concept of memory beyond simple storage into a dynamic, expressive structure for complex reasoning and global understanding. In our approach, memory is represented as a hypergraph where hyperedges correspond to distinct memory units, enabling the progressive formation of high-order interactions within memory. This mechanism connects facts and thoughts around the focal problem, evolving the memory into an integrated and situated knowledge structure that provides strong propositions for deeper reasoning. We evaluate HGMem on several challenging global sense-making benchmarks. Extensive experiments and in-depth analyses demonstrate that our method consistently improves multi-step RAG and substantially outperforms strong baseline systems across diverse datasets.