Numerical Analysis
Residual neural networks overcome the curse of dimensionality for semilinear heat equations
Ilkhom Mukhammadiev and Diyora Salimova
Rigorous results show that feedforward neural networks can overcome the curse of dimensionality in the numerical approximation of high-dimensional partial differential equations (PDEs), but comparatively little is known about residual neural networks (ResNets) in the nonlinear PDE setting. We prove that ResNets overcome the curse of dimensionality in the numerical approximation of solutions of semilinear heat equations with globally Lipschitz continuous, gradient-independent nonlinearities: under
polynomial growth and network approximability hypotheses on the PDE data, there exist $\eta\in(0,\infty)$ and ResNets $\Psi_{d,\varepsilon}$, $d\in\mathbb{N}$, $\varepsilon\in(0,1]$, with at most $\eta d^{\eta}\varepsilon^{-\eta}$ parameters whose realizations approximate the solution in dimension $d$ with an $L^2$-error of at most $\varepsilon$. The proof represents one deterministic realization of a multilevel Picard
estimator by a ResNet whose shortcut connections transmit the spatial variable and a scalar accumulator, while the residual branches successively add the summands of the
estimator. For ridge-sum initial conditions, admissible sigmoidal activations, and globally Lipschitz truncations of the nonlinearity, we obtain, for every $\xi>0$, the explicit bound $C_\xi d^{4+\xi}\varepsilon^{-(3+\xi)}$ on the number of parameters.
Read the full abstract ▾
Robotics
QLAUN: A Research-Oriented, Robust, Agile, Modular, and Affordable Torque-Controlled Quadruped Robot
Mohamad S. Moudallal and Noel J. Maalouf
QLAUN Bot (Quad-Legged Adaptive Unmanned Navigator
Robot) is a torque-controlled quadruped
robot that is research-oriented, cost-effective, and aimed at achieving simultaneous robustness and agility while being completely 3D-printed. It is a quadruped
robot that is aimed at empowering robotics research at universities and research institutes in Lebanon and the MENA region. Using a novel electronics-free leg design strategy, we present a modular
robot with interchangeable and easily replaceable legs. The 15 kg
robot possesses 12 DoF (Degrees-of-Freedom) with three per leg, each paired with a completely 3D-printed Quasi-Direct Drive (QDD) actuator that consists of a brushless DC motor and a low-ratio gearbox transmission that is connected to a belt transmission system for significantly increasing the torque outputs at the joints. We present legs that have decoupled hip and knee actuators to improve the overall modularity of the
robot. QLAUN is almost completely 3D-printed using polylactic acid (PLA) and assembled using off-the-shelf parts to create a robust, agile, and affordable
robot for legged
robot locomotion research. The legs possess joints with wide ranges of motion, including a continuous hip flexion-extension joint. A compliant foot, printed using TPU-95A is also implemented for alleviating hard impacts and handling terrain uncertainties. This extended abstract aims to introduce QLAUN, a novel platform for robotics research, emphasizing the design concepts and principles that underpin its development to the academic and research communities in the field of robotics.
Read the full abstract ▾
Sound
Test-time adaptation for speech enhancement with an autoregressive speech prior
Sofiene Kammoun, Simon Leglaive, Xavier Alameda-Pineda et al. (+1 more)
Test-time adaptation (TTA) offers a promising direction for improving
speech enhancement models under mismatched acoustic conditions, without requiring access to labeled target data. In this work, we propose a single-utterance TTA method that regularizes a pretrained
speech enhancement model using an autoregressive prior trained on clean
speech latent representations extracted from a neural audio codec. Adaptation is performed by minimizing the Kullback-Leibler divergence between the enhanced
speech distribution and the clean
speech prior. Experiments across multiple noisy
speech datasets show consistent improvements in
speech quality, particularly under training-testing noise mismatch conditions. Code and audio examples are available online.
Read the full abstract ▾
All authors Sofiene Kammoun, Simon Leglaive, Xavier Alameda-Pineda, Timo Gerkmann
Artificial Intelligence
A computable representation of the physical laboratory enables verifiable workflows
Xiaobo Li, Luyao Ge, Xiaohui Li et al. (+8 more)
Making science computable requires representations of both scientific knowledge and the physical world in which scientific claims are tested. A computable representation of the physical laboratory is established through typed research objects, capability-bound operations and a compositional workflow
algebra. It provides the physical-world counterpart to machine-readable knowledge, expressing workflows as programs over evolving laboratory states with explicit dependencies, decisions, iteration and concurrency. The representation was implemented in a modular agentic robotic laboratory by binding formal operations to executable Function Skills. For diverse scientific intents, capability-relative workflows were generated, while stateful simulation propagated object transformations and verified operation preconditions and laboratory constraints before dispatch. The proposed representation and its engineering framework jointly establish a general computational interface between
agent reasoning and capability-bound physical transformations, providing a foundation for end-to-end autonomous scientific discovery.
Read the full abstract ▾
All authors Xiaobo Li, Luyao Ge, Xiaohui Li, Lulu Guo, Ming Mao, Jiwang Zheng, Wenting Guan, Xin Yang, Yi Luo, Jun Jiang, Linjiang Chen
Artificial Intelligence · Cross-listed from eess.AS
ToolDF: Tool-Integrated Reasoning for Mixed-Authenticity Audio Deepfake Detection
Taewoo Kim, Young Han Lee, Nam In Park et al. (+1 more)
Audio deepfake detection is commonly formulated as clip-level binary classification of single-domain audio. However, real-world manipulated audio can exhibit mixed authenticity, where genuine and manipulated cues coexist across temporal transitions, overlapping sources, or both. This setting requires not only detecting manipulated audio but also localizing the components that provide evidence for the decision. We propose ToolDF, a tool-integrated
reasoning framework for mixed-authenticity audio deepfake detection. ToolDF employs an audio large
language model as an orchestrator trained with supervised tool-use trajectories. It adaptively analyzes the audio scene, selectively performs source separation, routes components to domain-specific experts, and aggregates their evidence into an interpretable verdict. We further introduce a mixed-authenticity ADD
benchmark covering temporal transitions, acoustic overlaps, and hybrid mixtures. Experimental results show that ToolDF achieves the best overall performance on composite-type detection, achieving macro-F1 gains of 3.72 and 14.39 points over the strongest monolithic baseline and a fixed pipeline, respectively, while providing interpretable evidence localized to temporal regions and acoustic sources. Our source code and
dataset are publicly available online.
Read the full abstract ▾
All authors Taewoo Kim, Young Han Lee, Nam In Park, Chanwoo Kim
Computation and Language
Remember and Reweight: Enhancing Multi-Agent Debate with Experience Memory and Confidence Estimation
Xuanfa Jin, Zhijian Ma, Yongcheng Zeng et al. (+3 more)
Multi-
agent debate (MAD) improves the
reasoning capabilities of large
language models by having multiple
agents iteratively refine their responses through discussion. However, MAD suffers from a critical vulnerability known as shared misconception: when a majority of
agents initially converge on an incorrect answer, the debate process tends to amplify rather than correct the error. Existing methods primarily address peer skew but leave the
agents' inherently biased concept priors unaddressed. To mitigate this systematic weakness, we propose R$^2$-MAD (Remember and Reweight for Multi-
Agent Debate), a framework that equips
agents with an experience
memory accumulated from past debates. R$^2$-MAD intervenes on both failure modes through two complementary mechanisms: A debate-state-aware
retrieval policy dynamically calibrates the concept prior by retrieving relevant historical evidence based on the current consensus level. Then these retrieved experiences provide a basis for estimating per-
agent reliability, yielding confidence weights to modulate peer influence. Experiments on various
benchmarks show that R$^2$-MAD achieves consistent improvements over existing single-
agent and MAD baselines.
Read the full abstract ▾
All authors Xuanfa Jin, Zhijian Ma, Yongcheng Zeng, Xinyu Cui, Haifeng Zhang, Jun Wang
Computer Vision
Auditing Patient Privacy in Medical Generative Models: Scalable Memorization Detection with DeepSSIM++
Antonio Scardace, Francesco Guarnera, Sebastiano Battiato et al. (+1 more)
While deep generative models offer new opportunities for medical image synthesis and data sharing, their ability to memorize and reproduce training samples raises serious concerns about patient confidentiality. Detecting such memorization at scale remains challenging: traditional pixel-based metrics are sensitive to generation artifacts, whereas generic
embedding-based metrics often lack the anatomical sensitivity required for medical data. To address this challenge, we introduce DeepSSIM++, a self-supervised similarity metric for scalable memorization
auditing in medical generative models. By leveraging multi-scale feature aggregation and anatomy-preserving augmentations, DeepSSIM++ learns an
embedding space where cosine similarity approximates the Structural Similarity Index (SSIM), eliminating the need for exact pixel-level registration. Compared with state-of-the-art baselines, DeepSSIM++ achieves an average Macro F1 improvement of 33 percentage points under ideal
alignment and 46 percentage points under realistic spatial and intensity perturbations. Furthermore, it accelerates large-scale similarity computation by several orders of magnitude compared with analytical SSIM. By combining anatomical sensitivity and computational efficiency, DeepSSIM++ provides an open-source tool for scalable memorization
auditing in medical generative AI. Code and data are publicly available at: https://github.com/
brAIn-science/DeepSSIM.
Read the full abstract ▾
All authors Antonio Scardace, Francesco Guarnera, Sebastiano Battiato, Daniele Ravì
Graphics
TileGS: Tile-Local Depth Binning for Gaussian Splatting Rasterization
Wei Tan, Matias Turkulainen, Lauri Ilola et al. (+2 more)
Real-time 3D Gaussian Splatting (3DGS) achieves high rendering quality, but standard rasterization still traverses a globally sorted tile stream that creates long per-tile ranges and heavy geometry-attribute traffic. We present TileGS, a tile-local reorganization of Gaussian splatting. TileGS turns each long tile range into a sequence of shorter depth-local ranges, rasterizes those ranges in front-to-back order, and applies selective repair where coarse ordering is insufficient to match baseline compositing. Across a 9-scene
benchmark on desktop and laptop Ada GPUs, our default No-GW (No Geometry-Write) variant delivers a mean 1.44x raster-kernel speedup on RTX 4090 and mean end-to-end frame speedups of 1.069x on RTX 4090 and 1.094x on RTX 1000 Ada over gsplat–a widely used optimized open-source 3DGS implementation–while matching the gsplat output up to numerical noise (|Delta PSNR| < 0.001 dB, |Delta SSIM| < 0.001, |Delta LPIPS| < 0.001). Full-suite RTX 4090 Nsight Compute profiling reveals TileGS is faster despite lower SM throughput, lower active-warp occupancy, and higher DRAM traffic, while total SASS thread instructions fall by 1.26x. Source-attributed profiling confirms that geometry attributes dominate the remaining
memory pressure (85.8% of total raster traffic and 88.6% of excess sectors). Together, these counters support the interpretation that TileGS improves raster performance by reducing effective raster traversal work, rather than by reducing byte volume, improving coalescing, increasing occupancy, or directly reducing measured warp divergence.
Read the full abstract ▾
All authors Wei Tan, Matias Turkulainen, Lauri Ilola, Hamed Rezazadegan Tavakoli, Juho Kannala
Robotics
FailBench: How Reliable are VLMs at Judging Robot Task Success?
Zaruhi Navasardyan, Tatul Danielyan and Hrant Davtyan
Vision-
Language Models (VLMs) are increasingly used to evaluate
robot manipulation outcomes, but existing
benchmarks offer limited evidence of cross-domain generalization. We introduce FailBench, a
benchmark for
robot failure detection comprising 2,197 manipulation attempts across 14 public sources (12 real-world, 2 simulated). In FailBench, 75% of failures occur naturally, and six real-world sources come from non-failure-detection
datasets. Evaluating 13 VLM-based detectors, we find the best model achieves only 0.77 mean balanced accuracy. Notably, models fine-tuned for failure detection consistently underperform general-purpose VLMs and their own pretrained baselines. Performance depends heavily on required visual evidence: models approach saturation when outcomes depend on observable object motion, but degrade to near-chance (<0.60 balanced accuracy) on contact-intensive assembly tasks. Error analysis reveals a systematic bias toward predicting success under ambiguous evidence, which persists even with increased
reasoning effort. Finally, we show that input-level intervention–spatially localizing and cropping outcome-relevant regions–improves the top detector by 2.4 percentage points without extra training.
Read the full abstract ▾
Machine Learning
On the Interaction Between Model Compression and Test-Time Adaptation
Francesco Corti, Dong Wang, Young D. Kwon et al. (+2 more)
Deep neural networks deployed in the wild must be both efficient and adaptable, requiring model compression and test-time adaptation (TTA). While both are well studied in isolation, their interaction remains poorly understood. We systematically analyze how structured compression affects a model's ability to adapt under distribution shift. Using ResNet-18 and ViT-Base on CIFAR-10-C and ImageNet-C, we evaluate multiple compression methods combined with standard TTA techniques. We introduce a diagnostic framework that examines representational expressivity and adaptation subspace compatibility. Our results reveal a consistent gap: although compressed models retain high accuracy under supervised adaptation, their TTA performance degrades significantly with increasing compression. We show that this stems from reduced representational diversity and structural constraints that limit recoverability. These effects strongly depend on the compression method, highlighting the need to design compression strategies that preserve adaptability.
Read the full abstract ▾
All authors Francesco Corti, Dong Wang, Young D. Kwon, Cecilia Mascolo, Olga Saukh
Machine Learning
Neural-Network Maxent: a general extension with learned nonlinearity, applied to time-series for Desert Locust distribution modelling
Alessandro Grassi, Edoardo Kimani Bellotto, Wassim El Azami et al. (+2 more)
Species Distribution Modelling (SDM) is essential for understanding how environmental conditions shape biodiversity, particularly for destructive pests such as the Desert Locust (Schistocerca gregaria), whose breeding dynamics are tightly coupled to rapidly evolving environmental conditions. Maxent has become the dominant method for presence-only data, but its reliance on a linear combination of hand chosen feature transforms limits its ability to capture the nonlinear, temporal relationships common in ecological monitoring, where
covariates such as precipitation, soil moisture, and vegetation indices evolve meaningfully over time. Standard implementations flatten time-series
covariates into independent features, discarding sequential structure that carries critical signal. We introduce RNN Maxent, an extension of the Maxent framework that replaces the fixed feature dictionary with a neural network, specifically a Gated Recurrent Unit (GRU), trained end to end via backpropagation. The approach preserves Maxent's presence only statistical foundations, background normalization, and probability calibration, differing only in that the nonlinearity is learned from data rather than fixed in advance. We apply RNN Maxent to map suitable habitat for the Desert Locust using 50 day environmental time series derived from ERA5 Land, MODIS, and Sentinel 3, maintaining a 7 day gap between
covariates and presence records to yield
forecasting behavior. Compared against standard Maxent, RNN Maxent improves performance across metrics (ROC AUC 0.862 std 0.036 vs. 0.792; F1 0.671 std 0.056 vs. 0.590).
Read the full abstract ▾
All authors Alessandro Grassi, Edoardo Kimani Bellotto, Wassim El Azami, Sabrina Outmani, Maximilien Houel
Computer Vision
SV-WAM: An Efficient Surround-View World-Action Model for End-to-End Autonomous Driving
Jinyang Wang, Shiwei Li, Junjian Wang et al. (+12 more)
World models (WMs) have demonstrated strong potential for end-to-end autonomous driving by learning predictive representations of future scene dynamics. However, generating future
videos during inference introduces substantial computational overhead, leading many recent driving WMs to adopt a single front camera as input for efficient deployment. This design restricts spatial coverage in safety-critical maneuvers such as lane changes, merges, and turns. To address this limitation, we propose SV-WAM, a surround-view world-action model (WAM) that preserves full six-camera observations while maintaining efficient inference. SV-WAM leverages future-
video prediction as dense training supervision for action learning within a shared generative model, rather than as an inference-time output. At the core of this design is an action-centered causal mask that prevents action
tokens from attending to future-
video tokens during joint action-
video denoising. Consequently, the
video branch can be discarded at deployment, enabling efficient action-only planning. Furthermore, we introduce a differentiable drivable-area compliance regularizer that penalizes vehicle-footprint corners approaching or crossing drivable boundaries, improving planning safety and boundary awareness. Extensive experiments on the closed-loop NAVSIMv2
benchmark and the open-loop nuScenes
benchmark demonstrate that SV-WAM achieves state-of-the-art planning performance with low inference latency and competitive zero-shot transfer capability.
Read the full abstract ▾
All authors Jinyang Wang, Shiwei Li, Junjian Wang, Zhiqiang Deng, Jianbin Gao, Yihang Zhao, Liu Liu, Yongjia Zhao, Jinlong Chen, Huirui Xu, Yifeng Pan, Kangwei Liu, Fan Ren, Ji Tao, Minghao Yang
Networking
Employing the Structural Power to Achieve Supply-Demand Balanced Payment Channel Networks
Shuyao Xiao, Shengling Wang, Hongwei Shi et al. (+2 more)
Blockchain technology faces scalability challenges because transactions must be validated and recorded across the network. Payment channel networks (PCNs) improve efficiency by moving transactions off-chain and recording only critical interactions on the mainnet. However, PCNs require pre-deposited channel balances (supply) to match transaction demands (demand), and insufficient balances cause supply shortages. Existing approaches, including transaction path optimization and channel balance allocation, address this problem but incur high costs due to dynamic adaptation to fluctuating demands. We reveal a correlation between balance deficits in PCNs and network
topology by uncovering the structural organization of liquidity allocation. This enables supply-demand conflicts to be mitigated from a static topological perspective through channel reconfiguration, without additional balance replenishment. We further introduce payment topological
entropy (PTE), an information-theoretic metric that quantifies each node's deviation from the global average connection pattern and captures structural properties of balance supply. Based on PTE, we design MaxPTE, a
topology optimization
algorithm that reorganizes balance allocation across channels through structural reconfiguration, aligning static balance distribution with dynamic transaction demand. Extensive experiments show that MaxPTE reduces balance deficits by 27.25%, increases average maximum flow by 12.23%, and decreases transaction failure probability by 25.96%, outperforming existing
benchmarks. The method also remains robust across diverse balance-demand distributions, improving supply-demand balance without prior demand prediction.
Read the full abstract ▾
All authors Shuyao Xiao, Shengling Wang, Hongwei Shi, Weicheng Wang, Anlin Chen
Performance
RASER: Resilient Agent Scheduling and Execution Runtime for HPC Clusters
Sima Attar-Khorasani, Matthias Lieber and Siavash Ghiasvand
The emergence of modern
agents powered by large
language models has created a demand for executing long-horizon, autonomous workflows in various domains that require significant computational resources. While High Performance Computing clusters provide the ideal infrastructure for these computation-intensive workloads, traditional HPC job schedulers such as Slurm are not designed for dynamic, agentic workflows characterized by unpredictable task durations, external API calls, and fault tolerance requirements of modern
agents. This work presents RASER, a user-space framework that enables seamless execution of agentic workflows on production HPC clusters by extending Slurm's internal primitives. RASER introduces agentic job arrays with work stealing via shared filesystem queues, user-space checkpointing through application-level state serialization combined with Slurm requeue, and Apptainer container-based isolation without requiring any image modifications. Evaluations demonstrate that RASER reduces makespan by nearly 39% compared to static partitioning while achieving near-full CPU utilization. RASER provides resilience against preemption and failures while maintaining minimal checkpoint/restore overhead. It requires no kernel privileges or external database infrastructure, making it an accessible solution for deploying agentic workflows on existing HPC infrastructure.
Read the full abstract ▾
Computation and Language
KhatianDoc: A Human-Verified Benchmark Diagnosing Multimodal LLM Failure on Bengali Legal Land Records
Tasmiad Hasan, Arafat Zaman Ratul, Sarker Sadman Saalim et al. (+3 more)
Land ownership in Bangladesh is recorded in Ana-Ganda-Kora-Kranti-Til, a base-16 positional fraction system with dedicated Unicode glyphs, no mainstream font, and no coverage in any OCR pipeline or tokenizer. The handwritten records that carry these fractions, RS Khatians, are the authoritative title record for millions of parcels and a frequent subject of civil litigation, yet no
benchmark has asked whether a machine can read one. We introduce KhatianDoc, a four-task
benchmark built from 107 real RS Khatian records from the Vumi (land) Office of Munshiganj, Bangladesh: symbol recognition, base-16-to-decimal conversion, structured field extraction, and legal document question answering over 1,634 QA pairs. Ground truth was transcribed by hand, verified by a land-law practitioner to full agreement, and anonymized through positional
tokens that keep the referential distinctions multi-hop questions depend on. We evaluate six
multimodal LLMs (8B to 72B+, open and closed) under a fixed zero-shot protocol. Five QA categories, 39.3% of our stratified set, return zero correct answers from every model; on the arithmetic task, every model that emits a number does worse than a constant-mean baseline, with exact- and near-match scores coinciding: decorrelation, not approximation.
Auditing our own metrics surfaced two artifacts in opposite directions: we correct a refusal-scoring bug and report the fixed scores beside the originals, and flag an inflated metadata metric as an upper bound. KhatianDoc documents not a performance gap but the absence of a capability, with verified ground truth for future systems. Code and data, with a redacted image release, are publicly available.
Read the full abstract ▾
All authors Tasmiad Hasan, Arafat Zaman Ratul, Sarker Sadman Saalim, S.M. Shah Nawaz Hossain, Khan Raiyan Ibne Reza, Sumaiya Tabassum Nimi
Graphics
ReRoom: Blending Virtual and Physical Contexts for In Situ Room Planning in Mixed Reality
Hongliang Yang, Yanjing Xu, Anhang Zhang et al. (+2 more)
Planning a real domestic space is an in situ authoring process: users evaluate candidate layouts at true scale, refine their intent, and carry accepted decisions into later iterations. Existing approaches either separate layout editing from the physical room or provide limited support for evaluating and refining whole-room proposals in situ. We present ReRoom, a mixed-reality system for in situ room-layout authoring. ReRoom presents a shared layout state through a virtual room proxy spatially registered to the target room, allowing interaction and layout generation to remain grounded in the physical context. Users refine the current proposal through direct manipulation or
language and preserve accepted placements, allowing each generated update to continue the same evolving design. To balance layout quality with generation efficiency, ReRoom uses a skill-guided layout
agent whose room-layout design skill operationalizes three principles that we formulate by synthesizing established interior-design guidance for real-room layout generation. The skill grounds these principles in a normalized representation of the scanned room and reusable
geometric checks. Evaluations show that ReRoom produces high-quality layouts for non-rectangular rooms, while its in situ workflow improves the room-planning experience over an otherwise equivalent off-site VR workflow. Code will be released upon acceptance of the paper.
Read the full abstract ▾
All authors Hongliang Yang, Yanjing Xu, Anhang Zhang, Hui Ye, Pengfei Xu
Computation and Language
How Far Can Synthetic Data Take Thai OCR?
Kunat Pipatanakul
We investigate what makes synthetic OCR supervision transfer to real Thai documents and use the resulting insights to build Wayu-Paxa-OCR-Zero, a Thai OCR model adapted without OCR labels from real Thai document pages. Synthetic data provide exact labels at scale, but "realism" conflates source domain, page context, typography, spatial structure, and glyph variation. We disentangle these factors with a controlled document-reconstruction pipeline and evaluate each variant under page- and crop-level training on printed and handwritten Thai documents. Non-text context has little consistent effect, whereas typeface diversity, two-dimensional structure, and real handwriting glyphs improve transfer; moreover, source-domain matching depends on training granularity, with in-domain reconstruction approaching real printed supervision under page-level training (1.82% versus 1.31% median character error rate) but underperforming out-of-domain reconstruction under crop-level training (15.59% versus 5.52%). Guided by these findings, we adapt the 0.9B-parameter PaddleOCR-VL-1.6 into Wayu-Paxa-OCR-Zero using 45,723 synthetic pages: relative to its base checkpoint, it reduces median character error rate from 6.64% to 1.24% on printed pages and from 74.87% to 20.55% on handwriting and outperforms Typhoon OCR v1 7B on all five evaluation sets, showing that synthetic-only training can be competitive.
Read the full abstract ▾
Hardware Architecture
LevelSyn: Physical-Aware Logic Synthesis via Level-Asynchronous Graph Neural Networks
Jingyi Zhou, Zhengyuan Shi, Ziyang Zheng et al. (+1 more)
As integrated
circuit technology scales into the nanometer regime, the traditional disconnect between logic synthesis and physical design has led to significant PPA (Power, Performance, and Area) degradation and prolonged design closure cycles. Traditional logic synthesis relies on non-physical Wire Load Models (WLMs), while recent spectral-based placement predictors often neglect the inherent hierarchical logic depth and signal flow of netlists, which leads to low-fidelity spatial estimations. To bridge this gap, we propose LevelSyn, a novel physical-aware logic synthesis framework that integrates hierarchical representation learning with a wirelength-driven optimization engine. At its core, LevelSyn leverages a level-asynchronous Graph Neural Network (GNN) to predict high-fidelity gate coordinates by capturing the structural and directional semantics of And-Inverter Graphs (AIGs). To handle industrial-scale designs, a level-aligned subgraph partitioning strategy is introduced to eliminate
memory bottlenecks while preserving local logical dependencies. These spatial insights are seamlessly integrated into a newly developed physical-informed synthesis engine within the Berkeley ABC framework. Experimental results on the EPFL
benchmark suite demonstrate that LevelSyn significantly outperforms state-of-the-art (SOTA) methods, achieving an average power reduction of 6.89% and a timing delay improvement of 27.48%. Furthermore, post-place-and-route validation shows a 99.59% reduction in design rule check (DRC) violations, highlighting its effectiveness in accelerating design convergence.
Read the full abstract ▾
All authors Jingyi Zhou, Zhengyuan Shi, Ziyang Zheng, Qiang Xu
Software Engineering
Code Transformation Rule Synthesis using LLMs: Potential and Limits
Axel Allain, Aymeric Blot, Djamel Eddine Khelladi et al. (+1 more)
Due to their black-box nature, LLMs suffer from limited explain- ability and a lack of determinism. Their usage cost can also rise, particularly with repetitive tasks on large codebases. To mitigate this, we conduct a novel empirical study targeting three domain- specific
languages for transformation rules, namely Comby, GritQL, and Ast-Grep. We evaluate three LLMs (GPT-5.4, GPT-oss-120B, and Llama3.1-8B) on six diverse
datasets covering four software-
evolution tasks: API misuse correction, program repair, API migra- tion, and
language version migration. Our results provide evidence that transformation rule synthesis moves beyond proof-of-concept with strong frontier models. GPT-5.4 achieves consistently high rule applicability rates and produces transformations closest to the ground truth across most
benchmarks. Smaller and open-weight GPT-oss-120B and Llama3.1-8B models remain effective for simpler, localized changes but struggle with complex migration scenarios. We also observe non-negligible generalizability through the usage of meta-variables and through a high reuse score in the first quartile of many
datasets. Finally, when compared to the anti-unification
algorithm, LLMs outperform it in correctness, but underperform in rule applicability. Overall, our results show great potential for LLMs to generate sound, correct, generalizable, and reusable rules.
Read the full abstract ▾
All authors Axel Allain, Aymeric Blot, Djamel Eddine Khelladi, Mathieu Acher
Robotics
Scaling Bimanual Household Manipulation from 1,500 hours of Demonstrations to On-Policy Corrections
Jiafeng Xu, Qi Li, Yan Shen et al. (+7 more)
Learning generalist policies for robust bimanual manipulation is bottlenecked by the scarcity of high quality large scale human demonstration data. In this work, we release 1,500 hours of diverse bimanual manipulation demonstrations covering everyday household tasks, and use this comprehensive corpus to train XR-2, a powerful
vision-
language-action (VLA) model. Enabled by a purpose built high throughput data pipeline and a carefully designed multi stage training paradigm, XR-2 attains strong manipulation performance in our systematic experiments while retaining favorable training efficiency and high data utilization. We further study two critical scaling axes: varying the amount of expert demonstration data, and post training on DAgger correction data from real time human interventions. In both settings, task success rate improves steadily over the data ranges we probe, exhibiting a clear consistent scaling trend at our current data scale. These results validate both the learning capacity of XR-2 and the promising scaling properties of the released
dataset, which we open source to support reproducible research on bimanual
robot manipulation learning.
Read the full abstract ▾
All authors Jiafeng Xu, Qi Li, Yan Shen, Yiyu Ren, Travis Davies, Shaowen He, Ze Wang, Yifan Yang, Ran Cheng, Hao Dong
Networking
From Prior-Guided Heuristics to Deployable Agents: Accelerating Demonstration-Driven Reinforcement Learning for Deadline-Constrained Network Control
Vincenzo Norman Vitale, Mohammad Solki, Antonia Maria Tulino et al. (+2 more)
Timely delivery of delay-sensitive information over dynamic, heterogeneous networks is essential for NextG interactive applications, yet providing strict End-to-End (E2E) peak latency guarantees remains an open challenge. Two obstacles limit the adoption of learning-based network control in this setting: traditional volume-based routing metrics, while highly effective for general traffic management, are not designed to capture traffic urgency; and Deep Reinforcement Learning (DRL) controllers trained from scratch suffer from sample inefficiency, long training times, and early-stage exploration
volatility. This paper introduces a deployment-focused network control framework that addresses both obstacles. First, we present Effective Congestion (EC), a deadline-aware metric family that quantifies interface congestion by packet urgency and proactively filters non-viable traffic, coupled with a Uniform Path Grouping (UPG) distribution heuristic promoting robust load-balancing; the resulting policies are embedded into Multi-
Agent Deep Reinforcement Learning Effective Congestion ($p^*$) (MADRL EC ($p^*$)), a hybrid architecture combining a distributed scheduler with a centralized RL-based router. Second, we introduce a unified training objective that generalizes existing policy-learning paradigms—behavioral cloning, offline Reinforcement Learning (RL), online RL, and offline-to-online schemes—as special cases, combining a live-reward term, a pre-collected-reward term, and a policy-imitation term. From this objective, we derive the Model-Guided Annealed Reinforcement Learning (MGA-RL) protocol, instantiated on a Deep Deterministic Policy Gradient (DDPG) backbone: a deployment-oriented, demonstration-driven training approach that generalizes conventional Offline-to-Online (O2O) schemes, in which trajectories from a lightweight [...]
Read the full abstract ▾
All authors Vincenzo Norman Vitale, Mohammad Solki, Antonia Maria Tulino, Andreas F. Molisch, Jaime Llorca
Machine Learning · Cross-listed from math.PR
Correlated initialization of deep residual networks
Felix Benning, Ivan Nourdin and Giovanni Peccati
We study the large-depth behavior of residual networks whose weights are correlated across layers at initialization. Our results confirm and extend a
conjecture of Marion et al. [2025], according to which correlated initializations should interpolate continuously between the Brownian
stochastic differential equation arising from independent initialization and the ordinary differential equation arising from perfectly correlated initialization. When the initialization is obtained from the application of a feature function to a stationary Gaussian sequence with regularly varying correlation, we prove that there exists a unique critical scaling such that the infinite-depth limit is the solution of a Young differential equation driven by a Hermite process. Hermite processes reduce to the fractional Brownian motion if the feature function generating the initialization has Hermite rank one, which is the case for the identity function, for example. We show that the critical scaling and asymptotic limit are uniquely determined by the decay of correlations together with the Hermite rank of the feature function. Consequently, the correlation structure and Hermite rank of the initialization represent meaningful hyperparameters in the asymptotic regime. By contrast, under finite-variance iid initialization, the asymptotic driver is universally Brownian up to normalization regardless of the choice of distribution. Our proofs rely on a collection of novel results establishing a robust stability theory for Young differential equations in
Banach spaces.
Read the full abstract ▾
Artificial Intelligence
KC-Bench: A Dynamic Interactive Benchmark for Evaluating Knowledge Conflicts in LLM Agents
Yaxing Lyu, Shengjie Zhou, Binbin Toh et al. (+2 more)
As LLMs increasingly act through tools, they must reconcile user instructions, parametric knowledge, and dynamic environmental observations before taking actions. We introduce KC-Bench, a controlled multi-turn
benchmark for measuring this capability across world-knowledge conflicts, input inconsistencies, and multi-source temporal conflicts. Its 238 tasks are manually screened from more than 1,000 generated candidates and combine a user simulator, stateful tools, deterministic environment assertions, an open-source natural-
language evaluator, and human trajectory verification. Evaluation of nine models, including DeepSeek-V4-Flash, GLM-5.2, and MiniMax-M3, shows substantial cross-domain variation: no model handles factual correction, identity consistency checking, and temporal conflict resolution reliably across all settings. In the simulated environments, missed conflicts can propagate to tool calls or synthetic protected-data flows. KC-Bench isolates this model-level behavior rather than ranking complete
agent frameworks, and provides a reproducible diagnostic for developing conflict-aware
reasoning and execution safeguards.
Read the full abstract ▾
All authors Yaxing Lyu, Shengjie Zhou, Binbin Toh, Pengyu Zhu, Lijun Li
Artificial Intelligence
The Attention Triangle in Audio-Video Models
Sagi Polaczek, Noa Kraicer, Gal Metzer et al. (+4 more)
Audio-
video diffusion models rely on cross-modal
attention to coordinate text, sound, and visual content, yet this same mechanism can introduce subtle and systematic semantic leakage. We study these models by probing and analyzing the “
attention triangle,” comprising the three cross-
attention edges connecting the text, audio, and
video streams, and examine how semantic information is routed across modalities during generation. Our analysis reveals that routing along the audio-
video edge is bidirectional: audio can influence
video generation, while
video can influence audio generation. This edge is shaped by biases encoded in the model's parameters and emerges as a major contributor to leakage: when
prompts are in tension with learned priors, cross-modal interactions may override the intended conditioning and reroute semantics toward visually canonical but incorrect outcomes. These effects suggest that semantic artifacts arise not merely from
attention spreading beyond its intended target, but from structured, bias-driven interactions along specific pathways. Building on this perspective, we extract
attention-derived signals that expose how semantics are distributed and grounded across modalities, and use them as a diagnostic tool to both analyze and deliberately incur leakage under controlled conditions. This enables us to probe the internal dynamics of cross-modal routing and isolate the role of individual interactions. We further leverage these signals to guide inference-time interventions that encourage more consistent cross-modal
alignment. Extensive experiments support our analysis and demonstrate improved semantic grounding while preserving generation quality.
Read the full abstract ▾
All authors Sagi Polaczek, Noa Kraicer, Gal Metzer, Zhuo Ning, Ali Mahdavi-Amiri, Daniel Cohen-Or, Raja Giryes
Computer Vision
Text2Thermal: Physics-Aware Thermal Image Synthesis from Textual Priors
Tayeba Qazi, Brejesh Lall and Prerana Mukherjee
Thermal infrared imaging offers reliable perception in darkness and adverse weather, but thermal
datasets remain scarce, motivating extensive work on translating abundant RGB images into thermal. Such translation is fundamentally ill-posed as thermal appearance is governed by surface emissivity and object temperature, neither of which is observable in the visible spectrum, so a single RGB image is consistent with many valid thermal outputs. We argue that
language offers a natural means of resolving this ambiguity, and propose **Text2Thermal**, a framework for physics-aware thermal image synthesis from textual priors. Rather than inferring the unobservable radiometric factors from RGB, we supply them explicitly through thermally grounded captions encoding material, weather, time-of-day, and heat-emission state, and adapt a pre-trained Stable
Diffusion backbone to the thermal domain. Because the radiometric content is determined entirely by the
prompt, Text2Thermal synthesizes thermal imagery without requiring a registered RGB image at inference. Where spatial guidance is desired, an optional control signal imparts scene geometry without disturbing the
prompt-specified radiometry. On M3FD and FLIR, Text2Thermal achieves state-of-the-art FID among thermal image synthesis methods, and we additionally report results on the FMB
dataset, while offering text-level control that translation-based approaches cannot provide.
Read the full abstract ▾
Sound
Local chord corruption is not recognizer replay: structure-matched calibration
Weiwen Huang, Yunda Chen, Wangzheng Wu et al. (+1 more)
Synthetic chord substitutions offer controlled tests of music generation, but their effects can differ from those of a complete recognized chord sequence. We propose structure-matched calibration, which constructs synthetic chord sequences that match the changed positions and harmonic-relation composition of recognizer replay. Paired generation compares both target-response magnitude and output-chord agreement with replay. On 29 of 30 MUSDB18-HQ songs, central four-second tritone corruption produces a larger target response than complete replay in MIDI-SAG. On 24 held-out MoisesDB songs, structure matching reduces target-response distance to replay by 81% for MIDI-SAG and 77% for MusicGen-Chord. Distance decreases on every song in both models with CNN–CRF. Joint matching also reduces output-chord mismatch with replay by 8–17 percentage points relative to temporal or relational matching alone.
Read the full abstract ▾
All authors Weiwen Huang, Yunda Chen, Wangzheng Wu, Nengheng Zheng
Machine Learning
WeatherNext 3: Increasing resolution and performance of global weather models with raw observations
Stephan Rasp, Boris Babenko, Dominic Masters et al. (+22 more)
State-of-the-art AI weather models have shown impressive medium-range forecast skill and computational efficiency, but suffer two key shortcomings: their forecasts have lower spatial and temporal resolution than the best physics-based models and they are exclusively initialized with and trained on analysis data. As a result, they cannot directly make use of observations, and any biases in the analysis are inherited by the forecast. WeatherNext 3 addresses these shortcomings and establishes a new state-of-the-art for probabilistic medium-range
forecasting skill. First, WeatherNext 3 generates new forecasts every hour (rather than every 6 hours like traditional global models) by ingesting low-latency geostationary satellite data. Second, WeatherNext 3's temporal and spatial resolution are on par with physics-based global models, with hourly time steps and 0.1 degree resolution for single-level variables, including
solar radiation and cloud cover. Third, WeatherNext 3 moves beyond traditional analysis variables by learning to predict satellite-derived precipitation estimates, as well as tropical cyclone and station observations. Modelling sparse station data allows WeatherNext 3 to make 2m temperature and dewpoint predictions at any location and time, conditioned on local geographical features, with substantially lower error than competing global models, even when evaluated against unseen stations. Together, WeatherNext 3's capabilities move operational AI-based weather
forecasting beyond emulating the traditionally distinct stages of data assimilation,
forecasting and post-processing, which helps to further push the frontier of performance and granularity for global weather prediction.
Read the full abstract ▾
All authors Stephan Rasp, Boris Babenko, Dominic Masters, Andrew El-Kadi, Samier Merchant, Guy Shalev, Ilan Price, Fred Zyda, Remi Lam, Sasha Shysheya, Matthew Willson, Stratis Markou, Shreya Agrawal, Suhani Vora, Mohammed Alewi Hassen, Sunny Mak, Tom R. Andersson, Megan Bela, Akib Uddin, Nofar Peled Levi, Ben Gaiarin, Ferran Alet, Aaron Bell, Peter Battaglia, Alvaro Sanchez-Gonzalez
Artificial Intelligence
HalluPeer: A Taxonomy-driven Benchmark for Detecting Hallucinations in Scientific Peer Reviews
Tzu-Ling Lin, Dong-Ting Yao, Teng-Fang Hsiao et al. (+2 more)
The growing scale of academic peer review has motivated the use of Large
Language Models (LLMs) as review assistants, yet LLMs can generate fluent but unsupported claims that undermine review reliability. Existing
hallucination benchmarks are not designed for peer review, where verification requires grounding claims in long, technical papers. We introduce HalluPeer, a
benchmark for detecting
hallucinations in scientific peer reviews, providing aligned triples of paper content, human-written reviews, and
hallucination-injected reviews, annotated for detection, classification, and localization. Our pipeline induces a peer-review-specific
hallucination taxonomy, identifies review contexts, and injects
hallucinations with automated filtering. Experiments on 12K papers and 38K reviews show that existing detectors struggle to separate
hallucinations from legitimate critique, while evaluation on authentic reviews demonstrates that HalluPeer-defined
hallucination patterns occur in real peer reviews, highlighting the critical need for source-aware verification. Our project page can be found in https://github.com/Lin-TzuLing/HalluPeer.git
Read the full abstract ▾
All authors Tzu-Ling Lin, Dong-Ting Yao, Teng-Fang Hsiao, Wei-Chih Chen, Hong-Han Shuai
Computation and Language
Language, Language Models, and What We're Talking About
Malvina Nissim
Language models are commonly discussed as technical artefacts, but they are obviously shaped by the linguistic worlds conveyed by data during their training. Using Italian
language models as evidence, I want to bring
attention to the nature of the systems which result from training and specialising models on translated and synthetic data, and further curating them, and to the meaning of testing them on equally unnatural data. Are these eventually models of Italian? Are they models of
language? Does NLP still care about
language? These questions yield another, more concrete question: what
language do we actually want
language models to produce? I argue that this question cannot be answered if we do not first consider a clearer distinction between
language models designed as technical products and
language models designed as tools for studying
language itself. The answers then might be diverse, the
languages we are talking about might be diverse, and the picture might not be as pessimistic as we fear.
Read the full abstract ▾
Data Structures and Algorithms
An $m+n^{3/2}$ algorithm for counting spanning trees by $\ell_1$-regularized resistance
Rong-Hua Li and Yichun Yang
We study the basic problem of approximating the number of spanning trees of a graph. For a graph with $n$ vertices, $m$ edges, We propose an
algorithm that approximates the number of spanning trees in $\widetilde O(m+n^{3/2}\eps^{-1})$ time. Our
algorithm improves upon the previously best known $\widetilde O(m+n^{15/8}\eps^{-7/4})$ time
algorithm by Chu, Gao, Peng, Sachdeva, Sawlani, and Wang [FOCS 2018] and the $\widetilde O(m^{3/2}\eps^{-1})$ time
algorithm by Liu, Peng, and Yang [FOCS 2026]. Notably, our
algorithm is based on the novel concept of $\ell_1$-regularized resistance. We propose simple and efficient
algorithm for computing $\ell_1$-regularized resistance and we show that they can be used to approximate the number of spanning trees by combining with the determinant sparsifier framework of Durfee, Peebles, Peng, and Rao [FOCS 2017]. Our
algorithm matches the best known size of the determinant sparsifiers.
Read the full abstract ▾