Computation and Language
A generative-informed neuro-symbolic framework for syntactic ambiguity resolution: Evidence from Arabic DPs
Mohammed Damom, Mohammed Q. Shormani, Muneef Y. Alshawsh et al. (+5 more)
Syntactic ambiguity poses a persistent challenge for Arabic NLP, particularly in morphologically rich nominal constructions where multiple structu6ral interpretations may be compatible with the same surface sequence. This study proposes a generatively informed neuro-symbolic framework for resolving structural ambiguity in Modern Standard Arabic (MSA) DPs. The framework integrates generative syntactic notions with AraBERT by representing ambiguity as a candidate-based decision task in which linguistically motivated alternatives are explicitly constructed and evaluated through candidate-conditioned input representations. Findings indicate that the model achieved 96.88% accuracy, 95.92% macro-F1, 96.83% weighted F1, and 93.94% binary F1 on the unseen evaluation set. Class-level analysis revealed asymmetric performance, with recall of 99.71% for High/VP Attachment (N1) and 89.26% for Low/NP/Embedded Attachment (N2), indicating greater difficulty in recovering the embedded interpretation. The study concludes that formal syntactic representations can be operationalized within
Transformer-based NLP as an explicit interface between linguistic structure and contextual neural modeling, providing a controlled and interpretable approach to Arabic syntactic ambiguity resolution and beyond.
Read the full abstract ▾
All authors Mohammed Damom, Mohammed Q. Shormani, Muneef Y. Alshawsh, Ashraf A. Naji, Mustafa Ali Alhamzi, Fawwaz An-Nashef, Jameel Ahmed Elayah, Noman AL-Sayadi
Machine Learning
Autoregressive Differentiable Method for Integer Programming
Ouns El Harzli and Yudong Cao
We introduce an autoregressive differentiable method to solve 0-1 integer programs. We fix an arbitrary order of the binary variables and we train a
transformer to predict the next bit while remaining in the feasible set. Our method is first trained on feasible incumbents provided by any solver, thus allowing us to initialize the
transformer in the feasible set. Our procedure then implements a Lagrangian penalty to penalize infeasible solutions, and the
transformer is further trained to explore the feasible set using Gumbel-softmax activations on the relaxed objective. We have tested our method on non-convex instances of quadratic knapsack problem and demonstrated consistent improvement upon state-of-the-art open-source solvers for dense problems up to 10,000 binary variables. In particular, we empirically demonstrate a phenomenon akin to a tunneling effect where the effective change of variables from binary variable to the continuous weights of the
transformer that the method implements enables crossing barriers in the relaxed objective landscape.
Read the full abstract ▾
Robotics
CriticHack: Evaluating Visual Rewards Under Robot Policy Optimization
Jiaxuan Luo, Xingguo Xu, Shanshan Wang et al. (+2 more)
Learned visual reward models are increasingly used to optimize
robot policies, yet a reward model can score an execution that acts on the wrong object as highly as one that completes the task. We show that optimizing such a reward can amplify these wrong-object failures while reward and task success both rise, so the signals a practitioner would normally monitor look healthy. We fine-tune every denoiser parameter of a
diffusion policy against Robometer on a drawer task. Starting from a supervised policy with no prior reward exposure, five training runs raise task success by 10.2 percentage points and wrong-object failures by 10.9 points on 512 evaluation seeds, whereas five runs trained on the simulator's task-completion signal raise success without amplifying wrong-object failures (difference 9.2 points, 95% CI 5.6 to 13.0). The amplification recurs from a policy previously optimized against learned rewards, under the policy's native
diffusion sampler, at matched distance from the initial policy, and across constrained-policy experiments with two critics and two optimizers. A tilt model explains when it occurs: under KL-regularized optimization, an outcome becomes more frequent whenever its expected reward under the initial policy exceeds the population average. Robometer separates successes from failures well overall (AUROC .81) but scores wrong-object failures slightly above successes (AUROC .37), so optimization raises both. The same model predicts the outcome shifts across 26 constrained settings (Spearman .89), including those in which task success falls, and Robometer's own published success-termination recipe inherits the error. A frozen outcome verifier redirects the same optimization toward the requested task.
Read the full abstract ▾
All authors Jiaxuan Luo, Xingguo Xu, Shanshan Wang, Yuhan Zhou, Zhen Zhang
Combinatorics
123-Avoiding permutations with an adjacency constraint
Nathaniel Nadler
We study permutations $\pi \in S_n$ that avoid $123$ while satisfying the adjacency constraint $\lvert \pi_{i+1}-\pi_i\rvert \le m$ for some $m\in\mathbb{Z}^{+}$. We first show that every admissible permutation is localized within vertical distance $m$ of the reverse diagonal, revealing a strong global restriction imposed by the interaction between pattern avoidance and bounded adjacency. For every fixed $m$, we then construct an exact finite-state description of the family, with precisely $2^{m+1}-m-1$ realizable states. This yields an explicit transfer-
matrix enumeration and, in particular, a rational generating function for every fixed $m$; consequently, the enumeration sequence satisfies an eventual constant-coefficient linear recurrence. We further identify the exponential growth rate with the spectral radius $\rho_m$ of the corresponding transfer
matrix and show that $\rho_m<4$, is nondecreasing in $m$, and converges to the Catalan growth constant $4$ as $m\to\infty$. Finally, we show that the bounded-adjacency constraint breaks the ordinary length-three Wilf equivalence, and we develop algorithmic and graph-theoretic interpretations of the family, including a correspondence with constrained
Hamiltonian paths in powers of the path graph.
Read the full abstract ▾
Artificial Intelligence
Learning What to Investigate Next: Meta-Reasoning for Long-Horizon Research Agents
Ankur Samanta, Yonathan Efroni, Paul Sajda et al. (+2 more)
Long-horizon research
agents must decide both how to investigate and what to investigate next as evidence accumulates. This is hard to learn because such decisions are sparse in long execution traces, and their consequences may emerge several investigations later. We introduce Meta-
reasoning for Iterative Research
Agents (MIRA), a hierarchical architecture separating research allocation from execution. An outer-loop meta-reasoner curates context from a persistent research record, then writes a work order for the next investigation or ends the episode. A fresh inner-loop executor carries out each work order, making execution part of the transition between meta-
reasoning actions. Without policy training, MIRA improves long-horizon inference and allocates additional compute more effectively in
theorem proving and open-ended neural-architecture research. Its decision boundaries also provide natural units for credit assignment. At each boundary, we train a generative critic to forecast expected remaining return from partial states, outperforming
token-level alternatives. Cross-environment pretraining improves
forecasting and adaptation, yielding a transferable prior for valuing partial progress. We use this prior to initialize MIRA-AC, a generative actor-critic jointly trained to forecast remaining return and choose the next investigation, without a separate critic model. MIRA-AC concentrates policy optimization on meta-
reasoning decisions, enabling efficient long-horizon reinforcement learning without directly optimizing the longer execution traces they initiate. Training MIRA-AC on the model's own proxy hill-climbing signals improves gold performance across four autoresearch environments; the actor transfers with cross-environment value initialization. Together, these results show that meta-
reasoning can be learned as an explicit policy for directing long-horizon autonomous research.
Read the full abstract ▾
All authors Ankur Samanta, Yonathan Efroni, Paul Sajda, Kaveh Hassani, Anirudh Goyal
Machine Learning
BaCP: Backbone Contrastive Pruning for Preserving Representations in Extremely Sparse Neural Networks
Mohammad Haroon Khawaja, Muhammad Haseeb, Mohammad Fatim Shoaib et al. (+1 more)
Unstructured
pruning at extreme sparsity often suffers from representational collapse, causing sharp drops in accuracy. To address this, we study Backbone Contrastive
Pruning (BaCP), which regularizes the sparse network's
embedding space by aligning it with pretrained, fine-tuned, and historical snapshot models. Building on the contrastive decomposition of the CAP framework (Xu et al., 2022), we provide a rigorous matched-budget characterization of this approach across multiple
pruning criteria. Evaluated across 90 settings, BaCP improves accuracy substantially in extreme sparsity regimes where standard
pruning fails, and is close to baseline where representations remain intact.
Read the full abstract ▾
All authors Mohammad Haroon Khawaja, Muhammad Haseeb, Mohammad Fatim Shoaib, Muhammad Tahir
Artificial Intelligence
Hypothesis-guided discovery of cognitive algorithms via program refinement
Huiwen Alex Yang, Mark K. Ho and Bill D. Thompson
Developing cognitive models of algorithmic
reasoning from behavioral data is a central problem in cognitive science that challenges current methods. Traditional approaches to cognitive modeling are interpretable and benefit from human expertise, but lack flexibility and scalability. Emerging techniques using large
language models (LLMs) for de novo generation of cognitive models are scalable and flexible, but lack a role for human expertise and have mostly been applied to simpler tasks than
algorithm recovery. We propose a hybrid system that treats discovery of cognitive
algorithms as a program refinement problem. Human-created cognitive models are expressed as probabilistic programs and provided to a system of LLM
agents with a mandate to: identify mismatches between model and behavior; propose code-level modifications within researcher-specified constraints; and verify structural fidelity. Revisions propagate to a probabilistic inference module that performs inference for latent variables and data likelihood computations. We evaluate the pipeline on human behavior in a problem-solving paradigm that exposes a variety of cognitive
algorithms. Revised models consistently improve model fit relative to ancestral models and reveal a small set of recurring innovations that capture meaningful behavioral variability in this task.
Read the full abstract ▾
Distributed Computing
Beaver: Elastic GPU Sharing between ML and Latency-Critical vRAN Workloads
Yuncheng Yao, Zhenzhou Qi, Junyao Zheng et al. (+3 more)
Within the shared industry
vision of AI-RAN, AI-and-RAN seeks to co-locate virtualized
radio access network (vRAN) workloads and AI services on shared GPUs. This sharing is inherently asymmetric: vRAN workload is latency-critical, whereas the machine learning (ML) workload is a throughput-oriented, best-effort co-tenant. We present Beaver, a GPU sharing system that jointly manages compute and
memory resources while protecting the vRAN's strict processing deadline. Beaver sizes the vRAN's streaming multiprocessor (SM) allocation from each slot's scheduled workload, repartitions SM allocations at slot granularity, and rewrites compiled ML kernels to yield HBM bandwidth during the vRAN's
memory-critical phases. We implement Beaver and evaluate it using NVIDIA Aerial with heterogeneous multi-
cell workloads, real-world cellular traces, production inference kernels, and full-stack LLM serving. On an H200 GPU, Beaver keeps the vRAN's p99.9 latency within its 1.5ms uplink deadline while retaining 74% of Llama-3.3-70B serving throughput. It also incurs no observed deadline misses under replayed cellular traces, protects a 375us downlink deadline, and generalizes to other GPUs including A100, GB10 and GH200.
Read the full abstract ▾
All authors Yuncheng Yao, Zhenzhou Qi, Junyao Zheng, Chung-Hsuan Tung, Danyang Zhuo, Tingjun Chen
Computer Vision
Spatial Memory Intelligence: Endowing World Models with Understanding-Driven Long-Term Memory
Ying Yang, Guiyu Zhang, Lianghua Huang et al. (+5 more)
Long-
video generation and world models have shown strong potential for interactive entertainment and
embodied simulation by predicting future observations conditioned on user actions and historical
memory. However, as
memory sequences grow longer and their structures become increasingly complex, managing long-range spatial context becomes increasingly challenging, calling for a more intelligent and systematic
memory-management strategy. Building on the advancing spatial
reasoning capabilities of
multimodal large
language models (MLLMs) and the broader
vision of unified models, we propose Spatial
Memory Intelligence (SMI), the first framework to systematically employ an understanding model for spatial-
memory management in long-
video world models. SMI introduces four coordinated atomic operations: spatial clustering, within-cluster sparsification, action-aware
retrieval, and reliability-aware filtering. Extensive experiments across multiple baselines,
benchmarks, and world-model backbones demonstrate the effectiveness and generalizability of SMI, achieving comprehensive improvements in
memory sparsity, generation stability, and spatial consistency.
Read the full abstract ▾
All authors Ying Yang, Guiyu Zhang, Lianghua Huang, Chang Nie, Chenyang Si, Haofan Wang, Shaoshuai Shi, Li Jiang
Machine Learning
Instance-Dependent Regret for CMDPs with Step-Wise Constraints
Qian Zuo, Francesco Emanuele Stradi, Leyang Xue et al. (+1 more)
We study online learning in episodic tabular constrained Markov decision processes with step-wise safety constraints. In such a setting, the constraints induce a safe subgraph that shapes the variance of cumulative rewards under feasible policies and, consequently, the difficulty of learning. Exploiting this structure, however, requires learning which actions are safe while controlling constraint violations. We propose Safe Variance-Adaptive Exploration (SVAE), an efficient
algorithm that learns candidate safe subgraphs and performs variance-adaptive optimistic planning within them. With high probability, SVAE achieves cumulative regret of order $\widetilde{\mathcal{O}}(\sqrt{SAH\min\{\mathbb{V}_\Sigma,K\mathrm{Var}^{\star}\}}+S\sqrt{AH^3\min\{K,\mathcal{C}\}}+S^2AH^2)$ over $K$ episodes, where $H$ is the horizon of a single episode, while $S$ and $A$ are the numbers of states and actions, respectively. Here, $\mathrm{Var}^{\star}$ is the maximum return variance among safe policies, $\mathbb{V}_\Sigma$ is the variance accumulated before the first unsafe action is encountered, and $\mathcal{C}$ captures the statistical complexity of eliminating actions incorrectly considered potentially safe. SVAE additionally attains $\widetilde{\mathcal{O}}(H\sqrt{SAK}+S^2AH^2)$ step-wise constraint violation and a gap-dependent violation bound that is polylogarithmic in $K$. Finally, we establish a lower bound showing that dependence on these instance-specific quantities is unavoidable.
Read the full abstract ▾
All authors Qian Zuo, Francesco Emanuele Stradi, Leyang Xue, Sattar Vakili
Differential Geometry
Almost Hermitian geometry and generalized Ricci flow
Anna Fino and Julieth Saavedra
We study almost Hermitian
manifolds whose lowered Nijenhuis tensor is totally skew-symmetric and whose characteristic (Bismut) torsion is closed, the almost-SKT condition. This extends the SKT (pluriclosed) condition beyond the integrable setting. For a fixed almost complex structure, these constraints are linear in the metric. We introduce an overdetermined ellipticity condition which, on compact
manifolds, makes the admissible infinitesimal deformation space finite-dimensional and yields short-time existence for a constrained Bismut–
Ricci flow. In real dimension six, almost-SKT structures satisfy a dichotomy: either the almost complex structure is integrable, or the skew Nijenhuis tensor is nowhere vanishing with constant norm and the Bismut
Ricci form vanishes. Hence, on compact non-integrable almost-SKT six-
manifolds, the constrained Bismut–
Ricci flow is stationary. In dimension eight, ellipticity always fails, while in higher dimensions Nijenhuis
rigidity holds on an open dense locus. In arbitrary dimension, we characterize when total skew-
symmetry of the lowered Nijenhuis tensor determines the compatible metric pointwise up to scale. On compact
manifolds, with closed torsion, this implies uniqueness of the almost-SKT metric up to scaling; the constrained Bismut–
Ricci flow is then an explicit homothetic solution. We also relate this flow to generalized
Ricci flow and characterize the infinitesimal obstruction to lifting the
evolution when the almost complex structure varies. Finally, we construct non-integrable almost-SKT structures with nowhere vanishing Nijenhuis tensor and non-flat characteristic connection on compact six-
manifolds, including $S^1\times S^2\times S^3$ and $S^3\times S^3$. In these families, the metric is fixed and the compatible almost complex structures form an $S^2$-family. These structures have vanishing Bismut
Ricci form and are therefore almost-CYT.
Read the full abstract ▾
Optics
Digital twin for full field-of-view Fraunhofer holographic patterning
Antoni J. Wojcik, Dilawer Singh, Hannah J. Joyce et al. (+1 more)
Computer-generated holography allows for nearly complete dynamic control of optical fields, but discrepancies between idealised propagation models and physical hardware limit its performance, particularly across large fields of view. We present a compact differentiable model of a Fraunhofer
holographic projector which describes the complete propagation chain, from a phase-only spatial light modulator (SLM) to the camera recording the focal plane of a
Fourier lens. It uses physically interpretable parameters for the SLM, illumination, pupil, coherent stray light, and camera. The model is identified in situ from noise-probed hologram-image pairs without additional hardware, system modification, or camera-in-the-loop refinement. The recovered digital twin is used to generate holograms for patterns spanning the entire first diffraction order of the SLM at its spatial-bandwidth limit. This full-field capability is enabled by measuring field-dependent pupil aberrations and compensating severe inter-pixel crosstalk by operating at the $4\pi$ phase modulation range. The stray light responsible for residual zeroth-order artefacts is recovered in amplitude and phase, allowing its physical origin to be investigated, and its contribution suppressed during hologram synthesis. The work establishes a framework for calibration-aware field synthesis in
holographic systems operating in the Fraunhofer regime for applications such as maskless lithography and optical tweezer arrays.
Read the full abstract ▾
All authors Antoni J. Wojcik, Dilawer Singh, Hannah J. Joyce, Timothy D. Wilkinson
Machine Learning
Learning the Latent Structure: A Feature-Centric Approach to Graph Data Augmentation
Yu Song, Zhigang Hua, Yan Xie et al. (+5 more)
Graph-structured data plays a pivotal role in modeling complex relationships. However, real-world graphs are often incomplete due to data collection and observational constraints, severely limiting the effectiveness of modern graph learning pipelines. While existing Graph Data Augmentation (GDA) methods attempt to refine graph structures for improved downstream performance, they are typically label-dependent, computationally expensive, and inherently transductive, limiting their applicability in practical scenarios. In this work, we present a novel feature-centric graph data augmentation framework that bypasses explicit structure modeling by operating directly in the
embedding space. Through a self-supervised inverse masking process, our method captures latent ties between observed and complete graphs, enabling recovery of unobserved structural signals through refined node representations. To enhance robustness under noisy and sparse supervision, we introduce a message regularizer and a bootstrap strategy for effective training and generalization. Evaluated on ten graph
datasets spanning multiple domains, our approach, SelfAug, consistently outperforms state-of-the-art methods in both accuracy and efficiency across inductive and cold-start settings, highlighting its potential as a scalable and generalizable solution for real-world graph learning scenarios.
Read the full abstract ▾
All authors Yu Song, Zhigang Hua, Yan Xie, Bingheng Li, Jingzhe Liu, Bo Long, Jiliang Tang, Hui Liu
Machine Learning
Student-Guided Teacher Distillation for Efficient LLM Task Routing: Positioning Against Jev-Style System-1 Classifiers
Haifeng Wu, Srinivasan Manoharan, Jian Wan et al. (+3 more)
Zero-shot classifiers are useful for routing user requests to specialized LLM tasks, but scoring every request against a large candidate set is expensive: a zero-shot NLI classifier must evaluate one premise-hypothesis pair per label, so cost scales linearly with taxonomy size. We study a student-guided teacher
distillation pipeline for a fixed taxonomy of 60 LLM task categories: a compact ModernBERT classifier predicts the full category distribution in one forward pass and retrieves a small top-k candidate set, and a larger DeBERTa-v3 zero-shot NLI classifier reranks only those candidates rather than all 60 labels; the resulting teacher labels iteratively improve the student, which produces sharper candidates for the next round. Unlike generic
embedding retrieval or clustering-derived shortlists used in extreme multi-label classification, our candidate generator is trained end-to-end on the target taxonomy and is the same model serving production traffic, distinguishing it from LLM-routing work that routes between candidate models, and from concurrent System-1 encoder-classifier proposals (e.g. TypeSafe AI's Jev and the open-source Laya project) whose training methodology is undocumented or RL-based. Our best student checkpoint reaches 77.5% teacher agreement on a 200-example evaluation set, and preliminary coverage measurements show Coverage@16 of 91-100%, suggesting top-k sets retain most of the teacher's decision-relevant information. We further show truncated top-k teacher scores should not be treated as full 60-class soft targets for KL
distillation: zeroing untruncated classes destroys the dark knowledge soft-label
distillation depends on, introducing systematic bias rather than a harmless sparse approximation. A complete evaluation, including coverage at multiple k on a held-out set, an
embedding-
retrieval baseline, and a larger human-reviewed test set, remains in progress.
Read the full abstract ▾
All authors Haifeng Wu, Srinivasan Manoharan, Jian Wan, Fangbo Tu, Junhua Zhao, Xin Chen
Plasma Physics
IGNITE Tokamak World Model Architecture
Peter Steiner, Azarakhsh Jalalvand, Nathaniel Chen et al. (+4 more)
We introduce IGNITE, a generative world foundation model for fusion
plasma behavior simulation trained in a self-supervised manner from over a decade of unlabeled experimental data at the DIII-D National Fusion Facility. The core of IGNITE is a dynamics model that can simulate DIII-D discharges from a given set of actuator trajectories. These trajectories can be supplied or generated on-the-fly from a textual
prompt or from desired experimental outcomes. The model architecture consists of several spatio-temporal tokenizers that embed the different input modalities, including time-series like spatio-temporal measurement data, image sequences, and high-resolution spectrograms, each of which collected at vastly different time scales. The backbone is composed of an auto-regressive dynamics model that has the capacity to predict entire DIII-D discharges given initial latent
plasma states and actuator trajectories over a theoretical infinite horizon. IGNITE paves the way towards efficient AI-driven experimental planning and world modeling for
nuclear fusion.
Read the full abstract ▾
All authors Peter Steiner, Azarakhsh Jalalvand, Nathaniel Chen, Kouroche Bouchiat, Ricardo Shousha, SangKyeun Kim, Egemen Kolemen
Mesoscale and Nanoscale Physics
Quantum materials QED with van der Waals crystals
Suheng Xu, Brian Vermilyea, Ran Jing et al. (+19 more)
A central goal of the emerging field of materials QED is to harness subwavelength electromagnetic confinement in engineered cavities to tailor light-matter interactions. Here, we demonstrate that van der Waals multilayer cavities composed of stacked
graphene and hexagonal boron nitride (hBN) provide unprecedented control over hybridization between their electromagnetic resonances. By magnetically tuning
graphene inter-Landau-level transitions (ILTs) into resonance with hBN
phonons, we witness broadband, mode-selective strong coupling in the mid-infrared. Our
quantum-material QED framework shows that cavity geometry and layer placement jointly control both coupling strength and modal selectivity. For experimentally realistic cavity parameters, the predicted mode splitting exceeds the width of the hBN Reststrahlen band, providing a direct route to the ultrastrong coupling regime. Together, these results establish van der Waals multilayer cavities as a scalable platform for tunable multimode QED and broaden the design space for reconfigurable
quantum materials.
Read the full abstract ▾
All authors Suheng Xu, Brian Vermilyea, Ran Jing, Lukas Wehmeier, Jihoon Park, Rafael A. Mayer, Xinzhong Chen, Samuel L. Moore, Fuyang Tay, Boyi Zhou, Wenjun Zheng, Dihao Sun, Birui Yang, Cory R. Dean, Daniel Cazorla, Xu Du, Milan Delor, Andrew J. Millis, Angel Rubio, Michael M. Fogler, Mengkun Liu, D. N. Basov
Computer Vision
From Fragments to Global Maps: Learning Vectorized Map Aggregation with Large Language Models
Ziwei Li, Yi-Tang Chen, Xiaoqi Wang et al. (+3 more)
Large-scale vectorized HD maps provide structured road information that is essential for perception, localization, and planning in autonomous driving. Constructing such maps requires aggregating noisy, fragmented, and overlapping local predictions collected along a vehicle trajectory into a coherent global map. Existing aggregation methods typically rely on hand-crafted rules for fragment association and refinement. However, a fixed set of thresholds cannot effectively handle variations in road structures and prediction errors, often requiring detector-specific tuning or manual adjustment. To address this limitation, we propose MapMergeLLM, a data-driven framework that formulates vectorized map aggregation as conditional sequence generation with a large
language model. Given serialized local vectorized maps, our model directly predicts the aggregated global map polylines. To reduce dependence on any particular upstream detector, we train the model on synthetic local maps generated from clean vector maps using corruptions that simulate representative prediction errors. We further introduce a coordinate tokenizer with geometry-aware pretraining to precisely represent map coordinates. In addition, we propose a line-level association loss that explicitly supervises correspondences between local observations of the same map element. Experiments on Argoverse2 and nuScenes using multiple recent upstream detectors demonstrate that MapMergeLLM substantially outperforms heuristic and optimization-based aggregation baselines without detector-specific retraining.
Read the full abstract ▾
All authors Ziwei Li, Yi-Tang Chen, Xiaoqi Wang, Wenbin He, Han-Wei Shen, Liu Ren
Information Theory
Product Expansion of Random Codes via Analytic Techniques
Eshan Chattopadhyay, Noam Ringach and Nicholas Spooner
Beginning with the work of Dinur, Lin, and Vidick (FOCS, 2024), tensor codes with constant product expansion have been foundational to recent advances in
quantum locally testable codes (qLTCs) based on cubical complexes. Informally, product expansion says that any low-weight parity check of the tensor code can be written as the sum of few parity checks of each component code in each dimension. Recent work of Kalachev and Panteleev (FOCS, 2025) showed that tensors of random linear codes have constant product expansion. In this work we initiate the study of random linear codes with prescribed
automorphism groups. For every sufficiently large
prime $k$, we construct pairs of rate $1/2$ MDS codes of length $2k$, over finite fields whose size depends on $k$, that have constant two-sided product expansion and are invariant under the simultaneous cyclic shift of two cycles of length $k$. This shift is the local action in the cube complexes of Rungtanapirom, Stix, and Vdovina (Internat. J.
Algebra Comput., 2019). Along the way we give a proof of the existence of two-sided product expanding codes which, unlike the earlier result of [KP25], does not rely on explicit constructions of asymptotically optimal locally testable codes. Our proof relies on several new techniques that we view as interesting in their own right. Instead of working directly over finite fields, we work over the reals and use random Rademacher
matrices for the generator
matrices of the component codes. From here, we show how to relate product expansion to the operator norm of sparse restrictions of carefully chosen Gram
matrices, which we bound using tools from random
matrix theory. More generally, we propose a method for studying properties of random linear codes by lifting to random codes over $\mathbb{R}$ and $\mathbb{C}$, which we anticipate will be applicable more broadly to existential problems in coding theory.
Read the full abstract ▾
Machine Learning
Post-Training Quantization of Autoregressive Weather Models
Ananyo Bhattacharya, Swastik Bhattacharya and Christiane Jablonowski
Advancements in high-resolution numerical weather prediction (NWP) and data assimilation (DA) have shaped the developments in deep learning (DL) architectures emulating atmospheric dynamics. Emulators for weather
forecasting exhibit forecast quality comparable to physics based models at forecast horizon scaling from few days to subseasonal time scales. The emulators are driven by hardware-accelerated
matrix multiplication in autoregressive inferences, significantly reducing the computation time and resources required for NWP. Optimization of the
matrix multiplication processes in GPU architectures provides opportunities to scale towards high-resolution domain, and offers implementation of out of the box solutions. Post-training quantization (PTQ) has been demonstrated across multiple DL architectures to accelerate and increase the number of computations in unit time while consuming less power, enabling applications on edge hardware. In this study, we investigate the effect of PTQ on pre-trained AI emulators for global-scale weather
forecasting. We implement PTQ
algorithms in Deep Learning Weather Prediction (DLWP) and FourCastNet (FCN) models as a proof of concept for geophysical fluid dynamics applications. We systematically investigate the effect of PTQ on emulator inferences over short-range forecast horizons. Evaluation of PTQ configurations using simulated quantization hints at qualitatively meaningful forecasts over short-time horizons. These results provide a first
benchmark of PTQ for autoregressive weather emulators and a basis for quantization-based optimization of DL models for dynamical systems.
Read the full abstract ▾
Artificial Intelligence
On-Premises Multi-Course RAG Tutoring for Business Education: Hardware-Software Trade-offs in a Campus AI Tutor
Sidney Shapiro and Joshua Lindemann
Campus AI tutors based on
retrieval-augmented generation (RAG) must ground answers in assigned course materials while keeping textbooks and student dialogue on institutional infrastructure. We present CourseChat, an on-premises, multi-course RAG tutor for undergraduate business education, deployed behind a campus web gateway and intended for use embedded in Moodle. Six isolated course offerings, each keyed by its own course reference number (CRN), share twin-edge AI hosts running a FastAPI service, a local vector database, and a local large
language model (LLM) served by Ollama. We report two generation-model bake-off rounds, a separate fixed-evidence source-fidelity comparison, and conversation and quiz audits. Several larger models failed the classroom speed gate, but a 12B model and a 7B alternative passed. A separate mixture-of-experts candidate improved some corrections while introducing new factual and continuity errors. We therefore retain the 8B production model pending a demonstrated overall improvement, rather than claiming that 8B is universally optimal. Software changes improved follow-up topic resolution while preserving course scope; 435 prebuilt questions across 65 modules decouple practice from live generation. The results support treating model choice, evidence selection, serving compatibility, and product design as a joint engineering decision. They do not establish learning gains: faculty ratings, peak-load capacity, and complete public-gateway acceptance remain separate evaluation needs.
Read the full abstract ▾
Analysis of PDEs
Finite-time blowup of the Euler equation without forcing
Fan Zheng
These notes present the construction in \cite{euler} of finite-time blowup for the three-dimensional incompressible, unforced Euler equations on $\mathbb R^3$: \begin{equation} \partial_tu+(u\cdot\nabla)u+\nabla p=0,\qquad \nabla\cdot u=0. \end{equation} The construction successively adds oscillatory layers to smooth parent solutions. Each layer is constructed by a finite expansion and an exact correction, so that the resulting child solves Euler.
Read the full abstract ▾
Artificial Intelligence
World Action Modeling with Progressive Visual Planning
Fei Zhang, Zhaochong An, Duncan Frost et al. (+5 more)
World action models (WAMs) have emerged as a promising paradigm for robotic control by jointly predicting future visual dynamics and actions from an initial observation and instruction. However, existing WAMs struggle with long-horizon prediction, as generating dense
video rollouts is highly inefficient. Some recent WAMs address this by predicting a single future frame without generating the full
video, but this approach neglects how to progress toward the goal. We present ProWAM, a progressive world action model that jointly predicts actions and an ordered sequence of sparse visual sub-goals, providing explicit visual guidance to anchor action generation throughout task execution. This design scales naturally, as sub-goal prediction can be learned from large-scale action-free
videos, allowing the
video backbone to offload complex visual planning from the action policy. For efficient action generation, ProWAM executes a single
video-backbone forward pass to cache sparse sub-goal features, eliminating iterative full-
video generation and requiring only lightweight action denoising during replanning. Across extensive evaluations, ProWAM achieves superior out-of-distribution robustness. On simulation
benchmarks, it sets new state-of-the-art results on LIBERO-Plus (85.8%) and randomized RoboTwin (75.7%), outperforming the strongest baseline with relative gains of up to +35.9%. On RoboCasa365, ProWAM achieves a 48.1% success rate and 18.2% on the challenging Composite-Unseen split, ranking 4th overall. Crucially, in zero-shot real-world experiments, ProWAM achieves 70.0% success, outperforming the strongest baseline by +15.0 (from 55.0% to 70.0%, a +27.3% relative gain) in novel scenes. These results demonstrate the value of progress-indexed visual foresight for closed-loop control. Our program is in https://sii-ferenas.github.io/ProWAM-page.
Read the full abstract ▾
All authors Fei Zhang, Zhaochong An, Duncan Frost, Yikai Wang, Pengfei Liu, Ya Zhang, Michal Drozdzal, Amir Bar
Computer Vision
MeshQuery: Agentic Seam Planning for UV Parametrization
Marco Schouten, Arthur Roullier, Elie Michel et al. (+3 more)
We present MeshQuery, a training-free agentic approach to automatic UV unwrapping of production-grade quad meshes. A
Vision-
Language Model (VLM) plans artist-aligned seams using a set of edge-selection tools, conditioned on domain-specific UV-unwrapping knowledge expressed in natural
language and refined with a feedback loop. We design a queryable mesh representation together with a domain-specific
language (DSL) that enables the
agent to retrieve mesh information on demand, express a seam plan as a compact program of edge-selection operators over topological,
geometric, and semantic mesh attributes, and iteratively refine it from UV quality feedback. On Adobe Substance 3D and Toys4K meshes, MeshQuery produces 2.9x/4.29x fewer charts and 1.63x/1.7x shorter seams than the strongest baseline, and professional artists prefer its results in 80.9% of comparisons. Ultimately, decoupling high-level intent planning from low-level edge selection and compact mesh representation lets MeshQuery run on different backend VLMs and scale to meshes an order of magnitude larger than autoregressive seam prediction
Read the full abstract ▾
All authors Marco Schouten, Arthur Roullier, Elie Michel, Ruben Wiersma, Axel Paris, Tamy Boubekeur
Combinatorics
Burning Signed Graphs
Shaun Fallat, Himanshu Gupta, Kamyar Khodamoradi et al. (+1 more)
We introduce and analyze a new model of graph burning, in which two competing fires (coloured yellow and green) ignite vertices of a given signed graph and propagate along its edges. The boolean sign of an edge determines whether a fire spreading along the edge changes colour or not. In each step, a player ignites a new vertex in a colour of their choice, while previously activated fires continue to spread. Given a signed graph $\Gamma$, the objective is to burn the maximum possible number of vertices in a single colour; the optimal achievable value is called the plurality number of $\Gamma$. We express the plurality number through Hamming distances to a binary code associated with $\Gamma$. In particular, the minimum plurality number over the switching class of $\Gamma$ equals the number of vertices minus the covering radius of this code. Under certain conditions on the signature, we determine exact values of the plurality number of signed paths. By contrast, we prove hardness results for multiple variants of the problem of determining or approximating the plurality number.
Read the full abstract ▾
All authors Shaun Fallat, Himanshu Gupta, Kamyar Khodamoradi, Sandra Zilles
Machine Learning
Multi-Fidelity Policy Gradients Stabilize Data-Scarce Reinforcement Learning
Xinjie Liu, Ruihan Zhao, Anirban Chaudhuri et al. (+3 more)
Policy gradient methods for on-policy reinforcement learning (RL) can become unstable when expensive, scarce target-domain data yield noisy gradient estimates. We address this challenge by complementing limited high-fidelity (HF) target-domain data with abundant, cheap, but biased low-fidelity (LF) data, e.g., from a simplified simulator. Most existing methods directly optimize biased objectives based on LF data. In contrast, the recently introduced multi-fidelity policy gradient (MFPG) framework uses LF data solely to construct a control variate that reduces variance and improves HF data efficiency without biasing the policy gradient
estimator. However, published work on MFPG is limited to REINFORCE on small-scale simulation tasks. We develop MFPG for modern actor-critic learning in GPU-parallel simulation and on a physical
robot. Our analysis and experiments show that naive extensions to proximal policy optimization (PPO) can lose cross-fidelity correlation or inflate variance. Our MFPG-PPO addresses these failures by redesigning the sampling, advantage estimation, and control variate construction to preserve cross-fidelity correlation, and by monitoring
estimator uncertainty to prevent variance inflation. We also introduce a budget-aware MFPG-PPO to divide a fixed sampling budget among high- and low-fidelity data sources. Across simulated
robot locomotion tasks of varying LF-to-HF transfer difficulty and HF data budgets, MFPG-PPO improves upon PPO trained on HF data alone in nearly all settings, and consistently matches the performance of PPO trained with 16x more HF data on the hardest task at the smallest HF budgets. In contrast, most baselines that use LF data perform well only where direct LF-to-HF transfer succeeds. MFPG-PPO enables stable learning on a physical Franka arm using only 4 real-
robot episodes per update and no human demonstrations.
Read the full abstract ▾
All authors Xinjie Liu, Ruihan Zhao, Anirban Chaudhuri, Cyrus Neary, Ufuk Topcu, David Fridovich-Keil
Artificial Intelligence
HXAI: Hierarchical Privacy-Preserving Explainable AI in Distributed Energy Systems
Poushali Sengupta, Sabita Maharjan, Frank Eliassen et al. (+1 more)
Balancing electricity demand and supply is increasingly difficult due to the inherent intermittency of renewable power generation and the
stochastic power consumption. Grid operators require fine-grained, decision-relevant insights into household energy consumption to manage peak loads and design responsive tariffs, but increased transparency at this level raises significant
privacy concerns. Traditional methods for explainable AI (XAI) can reveal sensitive information, while standard
privacy techniques often reduce the usefulness of explanations. To address this issue, we introduce HXAI, a hierarchical framework that preserves
privacy while enabling reasonable explainable analysis for grid-level demand management. HXAI consists of two main components: (1) a local model that generates fine-grained explanations within a secure, private environment, and (2) a zonal model that aggregates these explanations to support grid-level analysis while enforcing
privacy through flexible
privacy-budget management. We explicitly limit cumulative
privacy exposure under repeated operator queries and show that the proposed framework preserves decision-relevant information without compromising household
privacy. Experiments on both simulated and real-world energy
datasets demonstrate that HXAI provides useful insights for zonal load management while ensuring that appliance-level consumption remains local and is never transmitted to grid operators. Our results show that preserving the semantic structure of explanations, rather than minimizing numerical error, is the key to XAI under differential
privacy. This framework provides a way to achieve both
privacy and explainability in energy management.
Read the full abstract ▾
All authors Poushali Sengupta, Sabita Maharjan, Frank Eliassen, Yan Zhang
Software Engineering
Compound AI System Reliability: A Failure Taxonomy and Resilience Pattern Catalog from 150 Production Incidents
Rudrendu Kumar Paul and Sourav Nandy
Deploying compound AI systems reliably and safely requires understanding failure modes that emerge at component boundaries, not within individual models. Cascading errors propagate across component boundaries, silent quality degradation evades standard monitoring, and coordination failures yield incorrect collective behavior from individually correct parts. We analyze 150 production incident reports from open-source compound AI projects and anonymized enterprise deployments to construct a taxonomy of 23 failure modes organized into five categories:
retrieval failures, generation failures, tool failures, orchestration failures, and integration failures. For each category, we propose resilience patterns with measured effectiveness from controlled fault injection experiments.
Circuit breakers reduce cascade propagation by 89%, output quality gates catch 73% of silent degradation before user impact, and component isolation reduces blast radius by 64%. Systems implementing three or more resilience patterns from our catalog reduce mean-time-to-recovery (MTTR) by 71% compared to unstructured monitoring baselines. We release the incident taxonomy and pattern catalog as a practitioner resource.
Read the full abstract ▾
Hardware Architecture
RAPID: Row-Parallel Arithmetic Processing in DRAM
William C. Tegge, João Paulo Cardoso de Lima, Shouzhi Fang et al. (+2 more)
Processing-using-
memory (PUM) architectures perform computation directly within DRAM to reduce costly data movement between
memory and processors. Because charge-sharing operations are confined to individual bitlines, existing DRAM-PUM architectures reorganize data into column-oriented, bit-serial representations. This organization is fundamentally incompatible with the row-oriented, word-parallel layouts used by conventional processors and accelerators, requiring expensive data-layout transformations whenever computation transitions between PUM and conventional execution. In this paper, we present RAPID, a Row-parallel Arithmetic Processing-In-DRAM architecture. RAPID augments the DRAM subarray with two lightweight extensions: migration
cells that enable localized horizontal data movement between neighboring bitlines and inversion
cells that provide efficient in-array logical inversion. These primitives enable RAPID to operate directly on row-parallel, bit-parallel data, preserving CPU-compatible layouts while exploiting the massive parallelism of the DRAM subarray. In particular, RAPID demonstrates that localized horizontal communication is sufficient to realize shallow arithmetic networks and efficient parallel reduction for multiplication, reducing arithmetic latency while preserving throughput and eliminating costly data-layout transformations, all while maintaining the conventional DRAM array organization. We demonstrate the feasibility and overhead of augmenting DRAM subarrays with migration and inversion
cells through detailed transistor-level layout and SPICE-validated
circuit simulations. Using the RAPID compiler it is possible to evaluate the performance and data reorganization tradeoffs to ensure the best execution across combined CPU and PUM. Evaluating RAPID on 19 MLPerf
benchmarks, there is a 5.9x higher end-to-end performance compared to SIMDRAM for DDR4 PUM execution.
Read the full abstract ▾
All authors William C. Tegge, João Paulo Cardoso de Lima, Shouzhi Fang, Jeronimo Castrillon, Alex K. Jones
Disordered Systems and Neural Networks
Quantum transmission in 1D disordered stealthy hyperuniform Kronig–Penney-like models
Shaobing Yuan, Carlo Vanoni and Salvatore Torquato
Disordered stealthy hyperuniform (SHU) systems are emerging as platforms for controlling classical and
quantum transport due to vanishing single-scattering contributions in the stealthy regime. Here, to our knowledge, we present the first perturbation theory of one-dimensional
quantum transport through a continuum of identical point scatterers with SHU positional disorder. Our perturbation theory indicates the exact cancellation of all the lower-order terms due to the
Fourier-space stealthy condition $S(q)=0$, and the further suppression of the lowest non-vanishing fourth order in the Lyapunov exponent $\lambda(k)$ due to the real-space hyperuniform constraint $\lim\limits_{D\to\infty}\sigma_D^2=c<\infty$. Our findings presents universal implications of the general wave-propagation phenomena in disordered SHU systems.
Read the full abstract ▾
Logic in Computer Science
Proving at Scale for Universal Algebra
João Araújo, Jan Hůla, Mikoláš Janota et al. (+2 more)
We introduce SemiBase, a project that computes and formally certifies finite identity bases for small
semigroups. Deciding finite basability is undecidable for finite
algebras and remains open for finite
semigroups. The task requires a proof that a candidate basis is complete, or a proof that none exists, rather than a single first-order validity query. LLM-guided
agents search for these proofs; a referee
agent rebuilds them from source, and the Lean kernel checks the resulting corpus in a final audit. Humans choose targets and approve final outcomes. We certify every
semigroup of order at most 6: all 1309
semigroups of order at most 5 and all 15973 of order 6, including proofs that the four known nonfinitely based
semigroups have no finite basis. The bases for order 6 define 505 distinct varieties, whose inclusion order Vampire determines except for four pairs. The resulting catalogue is a machine-checked account of results scattered across the literature and a tested foundation for order 7.
Read the full abstract ▾
All authors João Araújo, Jan Hůla, Mikoláš Janota, Edmond W. H. Lee, Bartosz Naskręcki