Cryptography and Security
Papers
Fresh from arXiv, typeset properly. Highlighted words trade on the market.
Friday 14 August
Graph encryption schemes (GES) enable secure outsourcing of graph data while supporting efficient queries. This report provides a comprehensive analysis of structural leakage in GES for single-pair shortest path (SPSP) queries, integrating findings from two recent works. First, we analyze PathGES, a scheme designed to resist query recovery attacks through heavy-light decomposition (HLD) and canonical fragment encoding. Our analysis reveals that PathGES suffers from significant imbalances in HLD decomposition, with over 99% of token-path mappings being one-to-one on real-world datasets, enabling both the Falzon-Paterson attack and side-channel inference of path lengths. Second, we present Fragment Tree attack that exploits these structural weaknesses to recover query contents, achieving up to 10.24% exact recovery on sparse graphs. Third, we introduce BlindGES, an enhanced scheme incorporating a Merge-and-Divide mechanism and two-level multimap index that reduces one-to-one mappings to below 20%, cuts setup time by 50%, reduces storage overhead by 32%, and limits path length leakage to under 1%. This report systematically presents attack methodologies, defense mechanisms, security proofs, and experimental evaluations on seven real-world datasets.
Computer Vision
FIRM: Fine-Grained Intra-Token Representation of Masks for Remote Sensing Reasoning Segmentation
Reasoning segmentation requires multimodal large language models (MLLMs) to translate implicit instructions into precise pixel-level masks. MLLMs encode an image as visual tokens, each of which merges a group of image patches. In remote sensing images, small targets, thin structures, and adjacent instances can occupy different parts of the same visual token. Assigning a single binary mask label to such a token loses its internal spatial structure, causing nearby targets to merge and object boundaries to become coarse. To bridge this representational gap, we introduce FIRM, a Fine-grained Intra-token Representation of Masks. For each visual token, FIRM predicts a mask code that specifies an $r\times r$ binary sub-cell pattern rather than a single foreground/background label. Given a target identified by the MLLM, the complete grid of mask codes is predicted in one mask pass. Fixed lookup converts the predicted codes into a discrete sub-cell mask, while marginalizing the code distribution yields a soft structural field. To further recover fine-grained boundaries within each sub-cell, we introduce a lightweight continuous renderer that refines this field using pre-merge visual features and image details. Across five reasoning and referring segmentation benchmarks on satellite and UAV images, FIRM achieves leading results, including $70.5/80.5$ gIoU/cIoU on LaSeRS and a $3.0$-point average gain on EarthReason. These results demonstrate the value of explicitly representing intra-token mask patterns for fine-grained MLLM segmentation.
Read the full abstract
Computer Vision
ProFocus: Interpreting Affective Experience in Artistic Images with Progressive Visual Focusing
Interpreting the emotional responses triggered by images is central to achieving emotional intelligence. Compared with natural images, visual art is intentionally created to elicit emotional responses from its viewers through abstract concepts and visual metaphors, making affective interpretation particularly challenging. However, most existing methods rely on general-purpose visual embeddings (e.g., CLIP), failing to capture the nuanced cues underlying artistic emotion. To address this gap, we propose ProFocus, a novel framework that models affective experience in artistic images via progressive visual focusing. The key idea is to model visual representation learning inspired by a hierarchical cognitive theory of human aesthetic appreciation. Technically, ProFocus contains two core components: a Hierarchical Art Critic (HAC) and a Progressive Hint Fusion (PHF) module. HAC leverages multimodal large language models to generate structured linguistic priors at three cognitive levels–atmospheric style, narrative subjects, and concrete details–thereby translating artistic perception into coherent semantic guidance. Building upon these priors, PHF departs from conventional cross-modal fusion by sequentially injecting the hierarchical hints into visual features, enabling a progressive focusing process that mirrors human perception. This design allows the model to capture subtle affective cues and produce more faithful explanations. Extensive experiments on the ArtEmis v1.0 and v2.0 datasets demonstrate that ProFocus consistently outperforms state-of-the-art methods in both emotion recognition and affective explanation. Project page: https://github.com/Zhang-Zhiyan/ProFocus.
Read the full abstract
Computer Vision
Rethinking Auxiliary Modalities in Multimodal Zero-shot Anomaly Detection: From Semantic Fusion to Conditional Modulation
Recent foundation model-based methods have endowed RGB images with strong zero-shot anomaly detection (ZSAD) through vision-language pretraining. However, RGB observations alone remain limited in perceiving anomalies dominated by geometric deformation, depth variation, or subtle surface changes. Auxiliary modalities can provide complementary structural information, but existing multimodal methods typically fuse them directly into a shared semantic space, which may disturb the text-aligned anomaly semantics established by RGB foundation models and often requires modality-specific architectures. To address this issue, we propose a plug-and-play auxiliary-conditioned enhancement framework for zero-shot anomaly detection. Instead of reconstructing a joint multimodal anomaly semantic space, our framework preserves the original RGB image-text anomaly matching pathway and uses auxiliary observations as conditional signals for RGB feature refinement, allowing auxiliary modalities to seamlessly enhance existing RGB-based zero-shot anomaly detectors. Specifically, a lightweight meta-learning module takes global RGB and auxiliary representations as input and generates sample-adaptive low-rank residual updates to determine how RGB features should be refined. We further construct uncertainty-aware spatial modulation from the initial RGB anomaly response and auxiliary reliability, which determines where local residual updates are strengthened or suppressed. This global-to-local conditional modulation enables selective multimodal enhancement while preserving the original RGB anomaly semantics. Extensive experiments on MVTec 3D-AD and Eyecandies demonstrate that our framework consistently improves multiple popular RGB-based zero-shot anomaly detectors, achieving state-of-the-art performance for multimodal zero-shot anomaly detection.
Read the full abstract
Data Structures and Algorithms
Horospherically convex optimization for fractional subspace packing and its applications
In this paper, we address a semi-infinite LP relaxation of the vector-subspace packing problem. This is a higher-dimensional generalization of the fractional linear matroid parity problem and is closely related to Brascamp-Lieb polytopes. We show that the dual of this LP can be formulated as “linear programming on a Euclidean building," namely, the problem of minimizing a Busemann function over an intersection of horoballs. This provides a natural example of horospherically convex optimization, recently introduced by Goodwin et al. (2026) and Criscitiello and Kim (2025). By applying the incremental Busemann subgradient method, we obtain an additive FPTAS for the problem. As applications, we obtain a new and simpler polynomial-time algorithm for fractional linear matroid parity, and new algorithms for the membership problem of Brascamp-Lieb polytopes.
Read the full abstract
Data Structures and Algorithms
CavityRank: Zero-Extra-Byte Residual Routing for Cuckoo Filters
Near capacity, a cuckoo filter may reject an insertion even though a legal placement still exists: the table remains structurally feasible, but a bounded policy fails to find an augmenting path. Random kick-out keeps each step cheap but leaves no persistent direction; breadth-first search recovers direction by expanding a frontier and maintaining table-scaled state. CavityRank exploits a resource already present in four-slot packed buckets. Lookup observes only the fingerprint multiset, so query-equivalent lane orders can encode two comparison bits without widening the 64-bit bucket or changing the two-bucket query. The bits form a four-level ordinal residual rank. Insertion follows a minimum-rank edge and re-encodes each modified bucket from its outgoing edges after relocation, propagating the rank actually realized by the packed word. An exact capacity-four orientation oracle separates structural infeasibility from bounded-search loss. In a paired 4,096-bucket XOR16 ladder, CR2 closes 86.47% of Random CF's oracle gap and CavityRank leaves 1.39% of that original gap. A canonical-tie CR2-versus-CavityRank ablation isolates the second implicit bit, which closes 89.95% and 90.69% of CR2's residual gap; the corresponding closures at 65,536 buckets are 83.95% and 84.27%. A separate packed implementation study at 64 MiB and 97.75% load records 42.53 logical reads per insertion, versus 62.67 for explicit labels and 355.74 for depth-10 BFS, with zero extra bytes per bucket and no table-scaled workspace. CavityRank therefore occupies a practical design point between unguided eviction and frontier search.
Read the full abstract
Computer Vision
PPOM: Marginalizing Patch-Grid Phase for CLIP-Based Generalizable Vision-Language Prompt Tuning
Prompt tuning adapts CLIP-based vision-language models with few trainable parameters, yet its predictions remain sensitive to the spatial sampling imposed by a frozen vision transformer. In particular, non-overlapping patch tokenization makes predictions depend on the alignment (phase) between image and the patch lattice. To reduce prediction sensitivity to patch-grid alignment, we introduce Patch-Phase Orbit Marginalization (PPOM), a training-free inference operator that treats phase shift as a nuisance variable. Given a patch stride, PPOM evaluates the identity view and reflection-padded translations, pairs opposite shifts into horizontal, vertical, and diagonal antithetic families, and assigns equal mass to these families and the identity prediction to avoid view-count bias during phase integration. In summary, PPOM provides a deterministic interface between prompt adaptation and patch-grid sensitivity. Across multiple prompt-learning hosts, PPOM improves host performance without re-training.
Read the full abstract
Numerical Analysis
Nonparametric Schrödinger Bridge Time Series Generator: Algorithm, Convergence Analysis and Applications
We conduct a convergence analysis for the Schrödinger Bridge Time Series (SBTS) data generator. Starting from a regularized formulation in which the data ensemble is mixed with a standard multivariate Gaussian distribution with a prescribed probability, we prove that the Euler-Maruyama discretization converges to the mixed target distribution with half-order convergence rate, provided that the ensemble size and kernel bandwidth are chosen appropriately. We further show that the regularized distribution converges to the original target distribution as the mixing probability tends to zero. The analysis simultaneously accounts for the ensemble approximation error, kernel approximation error, and time-discretization error, and therefore provides a full distributional convergence result for the SBTS generator. Empirically, we further examine the flexibility of the method by replacing the Wiener reference measure with the path measure induced by a more general SDE. The numerical experiments show that the schemes based on both the original Wiener reference measure and the SDE-induced reference measure achieve comparable performance, demonstrating the robustness and stability of the SBTS framework.
Read the full abstract
Computer Vision
SAFE: Scene-Aware Feature Modulation for Color Constancy with Learned Color Space in Pure-Color Scenes
Color constancy on pure-color scenes is challenging: when most pixels share a narrow band of hues, every chromaticity-based cue collapses to a single point and standard estimators become ambiguous. We propose a compact framework that couples two innovations: (i) SAFE, a Scene-Aware FeaturE modulation network that organizes illumination cues into a structured four-token representation, which is then selectively reweighted based on scene complexity features; (ii) the Learned Color Space (LCS), a scene-dependent chromaticity normalization that directly addresses the chromaticity collapse problem for pure-color scenes. Experiment results show that SAFE consistently improves performance in pure-color scenes. Compared to the best-performing baseline in each metric, it reduces the mean angular error by 10%, the best-25% error by 20%, and the worst-25% error by 5.8%.
Read the full abstract
Machine Learning
QUASAR: Lowering the Loss Floor of Quantization-Aware Training with Loss-Aware Reconstruction
As large language model inference shifts toward lower precision, post-training quantization (PTQ) becomes increasingly brittle, making quantization-aware training (QAT) essential for preserving model quality. However, QAT has a structural mismatch: gradient updates are applied to latent full-precision weights, while the loss and gradients are computed on lossy reconstructions of those weights. This mismatch can lead to suboptimal training trajectories and a higher loss floor. Second-order PTQ methods address a similar problem by minimizing loss-aware reconstruction error, but applying such expensive reconstruction repeatedly during QAT as the weights evolve is impractical. We introduce QUASAR, a QAT method that brings lightweight, loss-aware reconstruction into the training loop. At each training step, QUASAR reconstructs the latent weights by searching over a small set of clipping ranges and fitting dequantization parameters through saliency-weighted least squares. We use an exponential moving average of squared gradients as the per-parameter saliency signal. Our theoretical analysis shows that optimizing QUASAR's reconstruction objective tightens both the convergence and final-loss bounds of QAT. We evaluate QUASAR across four model families and across INT4, INT3, INT2, and NVFP4 quantization formats. QUASAR consistently achieves lower training and evaluation loss than competitive QAT methods and outperforms QAT and PTQ baselines on downstream benchmarks. At INT2, QUASAR improves average accuracy over the best QAT baseline by 13.3 points with quantization-aware distillation and by 10.9 points with QAT on mathematical reasoning data. Notably, after distillation on only about 600M tokens, QUASAR's INT4 Gemma-4 E4B checkpoint outperforms the corresponding QAT checkpoint released by Google, with 66% lower KL divergence and 1.8 points higher average accuracy.
Read the full abstract
Discrete Mathematics · Cross-listed from math.CO
A counterexample to the Albertson-Berman conjecture about induced forests in planar graphs
For a graph $G$, denote by $a(G)$ the number of vertices in the largest induced forest in $G$. The Albertson-Berman conjecture, which had been open since 1979, states that $a(G) \geq \frac{n}{2}$ for every simple planar graph $G$ on $n$ vertices. Although the Albertson-Berman conjecture was recently resolved in the negative by constructing a counterexample with the help of AI, we independently found a counterexample to the Albertson-Berman conjecture without AI and present it in this article. Our counterexample is on $39$ vertices with $a(G)=19$. Finally, we indicate, without a full proof, a variant of this construction with a larger number of vertices, but with a slightly smaller ratio $\frac{a(G)}{n}=\frac{37}{76}$.
Read the full abstract
Hardware Architecture
MoE Expert Execution in Disaggregated LLM Serving with a High-Bandwidth ReRAM Near-Memory Architecture
Attention-FFN disaggregation maps LLM modules to specialized pools, creating an opening to keep Mixture-of-Experts (MoE) weights resident in a high-bandwidth FFN pool. Decode SLOs, however, cap the run-batch while sparse routing expands the activated-expert union, so weight traffic amortizes poorly and routing skew idles cold-expert resources. The FFN pool must therefore deliver weight-read bandwidth density under sparse unions and recover occupancy under skew without a global sharing fabric. We present a ReRAM near-memory architecture that keeps expert weights resident behind high-bandwidth local reads. The design factors actual MFU into ideal MFU and occupancy, recovers occupancy with bounded core-local multicast pooling, coactivation-aware placement, and load-aware fetch, and sizes each communication level from induced demand. A measured + modeled study on Qwen3.5-35B-A3B, Qwen3.5-397B-A17B, and GLM-5.2 shows that side-4 pooling raises occupancy from 0.328 to 0.519 and, at iso-peak compute, lowers per-token FFN-pool latency by 9.5x versus H20 with 20x lower weight-movement energy; an H20-attention + ReRAM-FFN system reduces decode TPOT by 1.25-4.0x, 2.4-10.3x, and 2.5-10.4x versus a homogeneous H20 pool.
Read the full abstract
Machine Learning
Polar Code Based Federated Learning: Convergence Analysis and Resource Allocation
Federated learning (FL) enables collaborative model training across distributed devices without sharing raw data; however, it faces significant communication bottlenecks and channel impairments in practice. Conventional network layer treatments either idealize the channel as error free or apply equal error protection (EEP) to transmitted model updates, failing to account for the inherently unequal importance of quantization bits within a single local model. To address this limitation, we propose a cross layer polar code based FL scheme that leverages the unequal error protection (UEP) property of polar codes under finite block lengths. Specifically, the proposed design selectively protects more significant quantization bits, thereby mitigating the detrimental effects of channel noise. We further provide a rigorous convergence analysis of the proposed scheme, deriving an upper bound on the convergence gap, which we then jointly optimize over the number of quantization bits and the polar code block length across all training iterations. Experimental results demonstrate that both constant and variable block length configurations of our polar code based scheme consistently achieve substantial performance gains over uncoded and LDPC-based EEP benchmarks, with the advantage becoming increasingly pronounced as the channel quality deteriorating. These findings confirm the efficacy of our cross-layer design in enhancing FL robustness and efficiency under realistic channel conditions.
Read the full abstract
Social and Information Networks
Spectral Efficiency Centrality: An Efficient Spectral Approach for Influential Node Identification in Temporal Networks
Centrality measures play a vital role in identifying influential nodes in evolving networks. While existing temporal centrality measures primarily rely on local structural properties or temporal paths, spectral node-removal approaches have been largely limited to static networks. To bridge this gap, we propose Spectral Efficiency Centrality (SEC), a temporal spectral centrality framework that quantifies node importance by evaluating the change in spectral radius caused by node removal across temporal snapshots. By capturing the global structural influence of nodes throughout network evolution, SEC identifies nodes that are critical for preserving the structural connectivity and efficiency of temporal networks. To improve computational scalability, we further develop an efficient approximation, ASEC, based on Perron-Frobenius theory and first-order eigenvalue perturbation. ASEC requires only the leading eigenpair and avoids repeated eigendecomposition, making it suitable for large temporal networks. Extensive experiments on multiple real-world temporal datasets demonstrate that SEC and ASEC outperform existing baseline centrality measures in identifying influential nodes under SI, SIS, and IC diffusion models. Statistical significance and robustness analyses further confirm their effectiveness, while ASEC offers a computationally efficient solution for large-scale temporal networks.
Read the full abstract
Computation and Language
Repair, Not Improvement: Decomposing Constrained Decoding in Tool-Call Abstention
A tool-calling router has to pick the right tool when one applies and decline when none does. Restricting the decoder to a grammar over the tool names is the standard remedy for the first, and on small models it buys a large accuracy gain. Recent work separates the loss caused by asking for a format from the loss caused by enforcing it at decode time. The second is small, which made enforcement look nearly free. The same work declines to extend that to function calling, where a constraint decides which answers exist rather than how one is written. Declining to call anything is the answer it most easily removes, and the one a router can least afford to lose. A grammar decides which tokens may be emitted and where generation stops, and a two-condition design charges both to the restriction. We therefore run three conditions over one prompt: free generation, generation stopped at the first line, and both applied together. We evaluate open-weight models from 0.6B to 4B on the same items in English and Korean, comparing the languages item by item. The two-condition contrast is negative on abstention accuracy in four of six cells with intervals excluding zero, and positive in none, costing -29.5 points at worst. On the smallest model in Korean the stop costs -20.0 points, the restriction returns +19.5, and together they leave -0.5. What the restriction gives back is readable output, not judgment. Of the 698 abstentions it repairs, 545 had no readable answer at all and 0 were correct decisions the scoring rule rejected. On items that do need a tool the contrast is positive throughout, and abstention is reported first because it is the registered measure. Both preregistered claims about language fail: Korean does not lose more of the abstentions it holds without the constraint, and the removed mass does not explain what does.
Read the full abstract
Artificial Intelligence
Implementing Computational Law in Wolfram Language for the Governance of Artificial Intelligence
How do we govern AI systems whose reasoning we cannot fully inspect? Governance does not require understanding a system's reasoning. It requires stating what the system is obliged, permitted, and forbidden to do, and checking whether it complied. I present an implementation of Reified Input/Output Logic, the formalism behind the DAPRECO knowledge base, in Wolfram Language: the core I/O axioms, obligations, permissions, constitutive norms, reified eventualities, and temporal operators. I then test whether GPT-4 can translate English legal statements into the formalism, and report the failures: hallucinated functions, omitted temporal scope, deviation from the formalism, and (in the worst cases) code that runs, reads plausibly, but silently encodes the wrong norm. A case study, an AI guard dog operating under a computational contract, shows how formalized rules can extend from a contract directly into the operational code of an embodied agent, producing symbolic, auditable justifications for its behaviour. I argue that computational law can be used as a governance tool and that a desirable goal would be to formalize the law that can and ought to be programmatically executable.
Read the full abstract
Sound
H2H Music Improv: A Communication Model and Audio-Visual Dataset for Music Improvisation
Current real-time AI improvisation systems lack the communication awareness human musicians rely on: rather than treating communication as a foundational algorithm design concern, most systems layer interaction strategies post-hoc onto generative algorithms through explicit controls and predefined modes. This gap persists in part because no formalized, machine-readable communication model with musicians exists. To address this, we study how expert musicians communicate in free (non-idiomatic) improvisation, unconstrained by prior discussion or agreement. Through a collaborative co-design process with expert improvisers, we derive a communication model that (1) captures how free improvisers negotiate musical ideas and enter stable musical spaces, and (2) is formalized as a machine-readable annotation scheme. We further present the H2H (Human-to-Human) Music Improvisation dataset: six hours of audio-visual expert duo improvisations with clean per-player stems and per-player annotations of both their own intentions and their perception of their partner's intentions. To our knowledge, this is the first such dataset for free improvisation. Together, the communication model and the dataset offer a new lens and resource for studying musician communication and may in future inform the design of AI musical partners that communicate by design.
Read the full abstract
Information Retrieval
How retriever redundancy and diversity impact RAG effectiveness
In RAG, while the retriever typically ranks documents by their individual relevance to the query, the generator instead produces an answer based on the retrieved documents as a whole. This paper investigates how redundancy and diversity from the retrieved document set impact the generator in terms of answer correctness. Previous work has provided a mix of findings: some showing that redundancy improves generation by reinforcing relevant information, others that LLM-based paraphrasing of the same content may be beneficial. Many of these studies did not control for confounding factors like whether the documents contained the exact answer or not, and if parametric knowledge plays a role. We conduct a carefully controlled experiment investigating three key scenarios of retrieved document sets: 1) Duplicate (exact copies of the same document), 2) Paraphrased (LLM rephrased versions of one document) and 3) Diverse (documents from different genres each containing relevant information in different forms). We control for which documents contain the answer in exact match or rephrased form. Evaluation is done with FictionalQA, a synthetic, fictional question-answer dataset that ensures the LLM generator prior knowledge cannot answer the question; the answer must come from retrieved documents. We show that duplicate redundancy and LLM paraphrasing does not significantly improve answer correctness. However, providing diverse documents is highly beneficial, improving answer correctness by 17%-47%. We further show this improvement is driven by diverse forms of document genre (news, blogs, etc.) alone and not a consequence of more relevant answer being available to generator. Our findings help to direct more attention to how new retrieval methods might improve RAG by catering to the generator preference for diversity in retrieval results.
Read the full abstract
Neural and Evolutionary Computing
Reducing ANN-SNN Conversion Error via Residual Membrane Potential Alignment
Spiking Neural Networks (SNNs) serve as core architectures for neuromorphic computing thanks to event-driven operation and ultra-low power consumption. Direct SNN training is hindered by non-differentiable spikes that induce vanishing gradients and unstable optimization. ANN-SNN conversion circumvents such issues by reusing well-trained ANN weights for low-latency, energy-efficient inference. Nevertheless, existing conversion schemes suffer from severe accuracy drops at small timesteps, large inference delays and cumulative quantization errors, even with marginal performance loss at large $T$. To address these limitations, we first analyze flaws of conventional conversion pipelines from residual membrane potential statistics and propose a novel conversion strategy combining dynamic initial potential tuning and feature enhancement. We then introduce a regularization loss $\mathcal{L}_{\mathrm{RMPD}}$ to adapt initial potential of IF neurons and mitigate systematic truncation bias from boundary aggregation. A dedicated SCR-Conv2d competitive refinement layer with grouped convolution is further built to sharpen feature discrimination, eliminate redundant spikes and stabilize encoding under tiny time windows. Integrated with the state-of-the-art QCFS baseline, our approach delivers consistent low-latency performance gains and generalizes to ReLU CNNs, ANN Transformers, and multi-threshold SNN variants. Evaluations on CIFAR-10, CIFAR-100 and ImageNet verify prominent accuracy improvements at $T=2,4,8$, with negligible extra computation overhead. This work offers an effective conversion paradigm to facilitate real-world SNN deployment on neuromorphic chips.
Read the full abstract
Artificial Intelligence
HELIX: Model-Harness Co-evolution for Recursive Self-Improvement
Scaling agent capability has largely focused on improving the model, yet an interactive agent acts through a runtime harness that mediates context, tools, control flow, and stopping. The harness shapes both what a model can accomplish and the trajectories from which it learns. This coupling motivates model-harness co-evolution for recursive self-improvement: build harnesses for a fixed model, update the model from verified sibling trajectories, and rebuild the harnesses as model capabilities change. Realizing this loop requires a controlled way to evolve harnesses while preserving intervention identity and effect. We present HELIX, a source-traceable substrate for harness evolution. HELIX decomposes agent systems into typed ports, reusable atoms, recipes, product shells, and runtime policies. It makes interventions explicit and auditable while retaining trajectories, test outcomes, and provenance. Harness evolution thus serves two linked roles: improving fixed-model execution and producing matched successes, regressions, near misses, and alternative solutions as data for subsequent model improvement. We evaluate HELIX in one evolution round on code repair. A 65-candidate portfolio discovers a fixed harness that improves task coverage by 4.0% over Pi, while the full portfolio exposes up to 58.0% more verified coverage through complementary sibling behavior. Selected candidates are assessed with repeated runs and the SWE-bench evaluator. A 200-slot sibling slice yields 438 verified SFT, critic, filter, and preference records. These results show how harness, model, and data form a feedback system: harness evolution expands current capability and creates learning signal for the next model; model updates motivate the next round of harness evolution. HELIX provides an auditable interface for studying this recursive process. Code is available at https://github.com/HKUDS/HELIX.
Read the full abstract
Computer Vision
Fast Implicit Neural Light Field Representation via Geometric Decomposition and Multi-Resolution Low-Rank Features
Implicit neural representations provide a compact and continuous way to reconstruct dense light fields from sampled ray coordinates. However, fast light field reconstruction remains challenging because a light field is a high-dimensional signal with strong spatial-angular redundancy and structured disparity variations. Directly fitting 4D ray coordinates with a neural network often requires considerable optimization time to recover both view appearance and cross-view consistency. To address this issue, this paper proposes a fast implicit light field representation based on geometric decomposition and multi-resolution low-rank features. The proposed method decomposes a 4D light field into a horizontal disparity plane, a spatial texture plane, and a vertical disparity plane. Each plane is represented by a low-rank structure that combines a low-resolution 2D grid with the element-wise product of two high-resolution 1D line features at multiple resolution levels. The fused features are decoded by a lightweight multilayer perceptron to predict RGB values. Experiments on public light field datasets show that the proposed method achieves competitive reconstruction quality while providing a better trade-off among model parameters, training time, and inference efficiency.
Read the full abstract
Cryptography and Security
Exposing SIMD Parallelism in SQIsign: An AVX-512 Implementation
Modern isogeny-based cryptosystems spend much of their running time in finite-field, elliptic-curve, and higher-dimensional isogeny arithmetic. Exploiting SIMD parallelism is nontrivial: routines such as Montgomery ladders contain loop-carried dependencies, while point, pairing, and theta-coordinate formulas expose only irregular fine-grained parallelism. We show that substantial SIMD parallelism can be recovered by reorganizing the arithmetic dependency graphs of higher-level primitives rather than vectorizing field multiplication in isolation. We develop an end-to-end AVX-512IFMA implementation of SQIsign in which data remain in a radix-$2^{51}$ vector representation across most of the curve-side computation. Our redesign includes projective xDBLADD schedules, batched point doubling in several coordinate systems, a vectorized biscalar ladder, fused cubical-arithmetic pairing steps, and batched one- and two-dimensional isogeny evaluation. Relative to the reference C implementation, we achieve end-to-end speedups of $1.76\times$, $1.71\times$, and $3.18\times$ for key generation, signing, and verification at NIST level~I; combined with Qlapoti, key-generation and signing speedups rise to $2.90\times$ and $2.69\times$. We further apply the same backend and methodology to CORAL, a recent isogeny group action for post-quantum non-interactive key exchange based on two-dimensional $2$-isogenies. Across five parameter sets, this yields $1.28$–$1.40\times$ speedups for key generation and $1.92$–$2.46\times$ for shared-key computation. These results provide cross-scheme evidence that algorithm-level SIMD scheduling is a reusable optimization dimension for higher-dimensional isogeny cryptography.
Read the full abstract
Computation and Language
Scaling Creative Writing Beyond Story-Centric Data with Attribute-Guided Genre Expansion
High-quality creative writing data for large language models (LLMs) remains dominated by story-centric data, limiting models' ability to follow the structural and functional conventions of diverse creative formats. We propose an attribute-guided genre expansion framework for scaling creative writing data beyond story generation. By separating thematic breadth from genre-form control, our framework leverages human-authored story prompts as diverse creative seeds, while utilizing manually curated genre attributes to enforce distinct structural, stylistic, and formatting conventions. We combine these to prompt strong LLMs for genre-faithful query-response pairs, which are then quality-filtered. Applying this framework, we construct the Multi-Genre Collection, a 50K-example corpus spanning 13 creative genres, including story, rap, lyrics, scripts, game design, character design, and other creative formats. Experiments across out-of-distribution writing benchmarks and held-out genre diagnostics demonstrate that models fine-tuned on our data consistently surpass not only base models and writing-specialized baselines, but also models trained on existing writing corpora. Genre-count ablations further indicate that controlled genre expansion, rather than story-centric scaling alone, is a key driver of robust creative writing capability.
Read the full abstract
Numerical Analysis · Cross-listed from stat.ME
Semi-supervised Concordance Learning for Optimal Individual Treatment Regimes
Finding the optimal individualized treatment rule that maps individual characteristics or contextual information to treatment assignments has been extensively investigated in existing literature, with widespread practical applications. This paper considers the estimation of optimal treatment regimes within a semi-supervised data framework (exemplified by electronic medical record data). In such settings, only a tiny proportion of observations have observed outcome labels, owing to high labeling costs, time limitations, data privacy concerns, and other constraints, while covariates and treatment assignments are available for all study subjects. We develop a semi-parametric inference method for optimal treatment regimes, which leverages outcome- unlabeled samples with complete covariate and treatment information to enhance estimation efficiency. The proposed estimation framework consists of two key steps: first, flexible nonparametric imputation via single-index kernel smoothing; second, subsequent estimation of the optimal treatment regime based on concordance-assisted learning. We establish the consistency and asymptotic normality of our proposed estimators. Numerical simulation studies demonstrate that our method achieves higher efficiency and stronger robustness relative to fully supervised estimators under finite-sample settings. We further validate the practical value of our proposed framework using the MIMIC-III and ACTG175 datasets.
Read the full abstract
Human-Computer Interaction
Musical Mirrors: The LLM as Sounding Board in Songwriting
This paper examines a use of AI in creative practice as an interpretive sounding board for human-generated material, rather than the more familiar pattern of AI generation followed by human curation. Through the lens of resonance as theorized by Hartmut Rosa, I present a first-person case study of songwriting from July 2025 to March 2026, drawing on 16 original pieces in English, French, and other languages along with piano solos. I describe a configuration in which resonance is not located between user and model, but in the author's deepening contact with their own material, mediated through the model. This kind of resonance was supported rather than inhibited by AI when sounding-board behavior was cultivated through sustained calibration by the user. Two failure modes appeared when calibration was absent: sycophantic drift and magical overinterpretation. This account suggests both the potential and the risks of AI as an interpretive partner in creative practice.
Read the full abstract
Artificial Intelligence
AI Research Preference Models
AI research agents (AIRA) can now carry machine learning experiments from proposal through implementation and evaluation. Yet progress on frontier tasks is throttled by the cost of evaluations that can consume days of GPU time. When an agent can propose far more candidates than it can afford to run, progress depends on its research preference: how it allocates a fixed execution budget across many candidates. We introduce AI Research Preference Models (RPMs) that predict which candidate solution is most promising, without paying the cost of running them all. We build RPMs from frozen pretrained language models in two variants: an inference-only model that reasons over candidate plans, code, and previously executed solutions, and an agentic model that additionally runs small-scale pilot experiments. Integrated into the AIRA-dojo research agent and evaluated on the machine learning research benchmark AIRS-Bench, the two variants increase the average normalized score from 0.684 to 0.711 and 0.729, respectively. Both reach the unguided agent's 24-hour performance in roughly 15 hours, using less than two-thirds of its execution budget, and together yield new state-of-the-art results on two AIRS-Bench tasks.
Read the full abstract
Computer Vision
CMCNet: Aligning Ultrasound Image Embeddings with Textual TI-RADS Representations for Fine-Grained Thyroid Classification
Ultrasound is the primary imaging modality for assessing thyroid nodules, and the ACR TI-RADS framework standardizes diagnosis through five ultrasound feature categories that are aggregated into five risk levels (TR1-TR5). Although widely adopted in clinical practice, most deep learning approaches focus on binary malignancy classification, while multi-class prediction and explicit utilization of feature-level supervision remain underexplored, largely due to limited annotated data. In this study, we introduce the STN dataset of 600 thyroid nodules with paired transverse and longitudinal ultrasound images, bounding box annotations, and complete labels for all five TI-RADS feature categories. Following the clinical decision process, we investigate how structured feature information can guide representation learning during training while requiring only images at inference. We demonstrate that text embeddings derived from standardized feature descriptions form a stable surrogate representation for TI-RADS risk levels. Based on this observation, we propose CMCNet, which aligns image embeddings to fixed textual embeddings via a Center-Margin Contrastive Loss that simultaneously promotes intra-class compactness and inter-class separation. Experimental results show that this embedding alignment strategy is more data-efficient and robust than direct multitask learning, and consistently outperforms InfoNCE, center loss, a strong multitask baseline, and a VQA-style multimodal model, particularly in imbalanced settings. The dataset is freely available at doi: 10.5281/zenodo.19125693 and the source code is available at: https://www.healthinformaticslab.org/supp/.
Read the full abstract
Computer Vision
CoANeRV: Coordinate-Aware Token-Space Neural Video Representation
Neural representations for videos (NeRV) have shown strong reconstruction fidelity by storing video-specific information in network weights. However, existing formulations typically require either costly per-video optimization or video-specific weight generation, making it difficult to scale to efficient amortized video representation. We propose CoANeRV, a coordinate-aware token-space framework that adapts the broader token-conditioned neural-field paradigm to amortized video representation. CoANeRV forms compact video tokens in one feed-forward pass and uses a shared coordinate-conditioned decoder to reconstruct continuous spatio-temporal queries, avoiding per-video decoder optimization or generation while retaining coordinate-level reconstruction flexibility. To make token-space reconstruction effective, CoANeRV introduces a coordinate-aware decoding architecture that aligns spatio-temporal queries with video tokens through axis-adaptive positional encoding and temperature-modulated cross-attention. Block-wise coordinate querying further reduces peak attention memory, making high-resolution reconstruction practical. Experiments on diverse video datasets show that CoANeRV consistently improves reconstruction quality over prior feed-forward NeRV and INR baselines, reduces peak memory compared with attention-based coordinate decoders, and provides efficient amortized encoding without per-video optimization. These results support the proposed video-specific combination of feed-forward token formation, spatio-temporal coordinate retrieval, and memory-bounded dense querying. The code is available at https://github.com/jialong2023/CoANeRV.
Read the full abstract
Machine Learning · Cross-listed from stat.ML
Deep Vision in Smart Manufacturing: MODERN Framework for Intelligent Quality Monitoring and Diagnosis
Smart manufacturing processes are often installed with a large number of sensors, imaging devices and computers, which not only enable instant communication across various modules of a production system but also aid in intelligent manufacturing management. In this paper, we introduce MODERN, a deep learning framework for quality monitoring and fault isolation, which integrates these enhanced capabilities into the practice of industrial quality control. Using the architecture of an inception residual neural network, we develop a control chart that monitors the likelihood of a product containing defects. We also propose a faulty region estimator that identifies the defective area using transfer learning. To extend our framework to cases where there are not sufficient training data, we suggest a transfer monitoring technique that requires only a small sample size and a hypothesis testing approach for quantitatively assessing the applicability of our method. Theoretically, we establish the minimax optimal convergence rate for both our defect likelihood estimation and fault diagnosis. Our results lead to a seemingly counter-intuitive managerial implication - it may not always be in a manufacturer's best interests to keep upgrading its monitoring equipment regardless of the cost. Empirically, we demonstrate the superior performance of our method in comparison with a state-of-the-art approach using both simulated experiments and real data.
Read the full abstract
Machine Learning
Probabilistic indirect models for undrained shear strength: addressing significant data missing and variability with advanced imputation and machine learning techniques
Accurate prediction of undrained shear strength (su) is crucial for geotechnical design, but is often hampered by substantial uncertainty in traditional empirical methods. This study uses the CLAY/10/7490 global database to develop probabilistic indirect models to predict su based on Atterberg limits and piezocone cone penetration (CPTU) measurements. Firstly, the dataset has a high missing data rate and variability. We test three imputation methods - multivariate normal (MN), multiple imputation by chained equations (MICE), and miss forest (MF) - to fill the missing values. To validate their effectiveness, a Probabilistic Extreme Gradient Boosting (PXGB) model is developed, and the imputation methods are evaluated by comparing the PXGB's performance when trained on the imputed datasets against that on the original incomplete data. Secondly, the indirect model is built by integrating a multi-head attention (MHA) mechanism into an artificial neural network (ANN) to enhance information extraction from limited data, which leads to the MHA-based probabilistic neural networks (MHA-PNN) model. The models' performance, alongside a conventional MN-based prediction model, was evaluated using root mean square error (RMSE), coefficient of determination (R2), mean absolute percentage error (MAPE), conditional interval width (wCI), and coverage rate (CR). Results demonstrate that the proposed MN-enhanced MHA-PNN model substantially outperforms other models in both prediction accuracy and uncertainty quantification. These findings highlight the potential of this integrated strategy for building robust probabilistic indirect models in geotechnical applications, particularly when confronted with sparse and incomplete datasets.