Robotics
RoboFin3D: A Sim-to-Real Platform for Robotic Surface Finishing
Haowei Wen, Shangtao Li, Vaibhav Sanjay et al. (+3 more)
Grinding and sanding are fundamental processes in industrial robotic surface finishing. However, physical trials are expensive and consume workpieces, making reproducible experiments difficult. We present RoboFin3D, a sim-to-real platform built on Isaac Sim and the Newton physics engine, that provides physics-based grinding and sanding simulation for cheap and repeatable robotic surface finishing experiments. RoboFin3D utilizes a signed distance field (SDF) to model the changing geometry of the workpiece, enabling contact computation, live updates and rendering without an intermediate mesh. It additionally uses a separate surface field to model progressive surface appearance change during sanding. We also introduce WeldGen, a weld sampling module, to generate weld beads on 8,918 real-world workpiece meshes for providing diverse simulation assets. The simulation parameters are calibrated on real experimental results and our evaluation demonstrates our simulation's fidelity against the real world. We also demonstrate that simulation-generated data can be used to improve the performance of perception models. Simulation-only fine-tuning of SAM2 improves IoU for
segmentation of unsanded regions from 77.15% to 84.47%, while combined synthetic and real training reaches 97.41%.
Read the full abstract ▾
All authors Haowei Wen, Shangtao Li, Vaibhav Sanjay, Philip Huang, Jiaoyang Li, Changliu Liu
Computer Vision
APM-Bench: Benchmarking Cross-session Persistent Memory for Egocentric Streaming Video Assistants
Jianguo Huang, Jinming Liu, Qiyao Wang et al. (+9 more)
To serve as real-world personal assistants, streaming
video models need persistent
memory that retains past experiences for later use. Yet existing streaming
benchmarks and methods often focus on individual continuous
videos or short clips, overlooking that real-world interactions are often intermittent and require
memory to persist across interruptions. To fill this gap, we introduce APM-Bench, which reformulates real-world streaming interaction as multi-session life trajectories. It contains 549 sessions, 104 trajectories, and 2,719 candidates, spanning both objective and open-ended questions. Each session is a
video with fine-grained annotations, and sessions within a trajectory revolve around related activities. Models then use persistent
memory to answer questions about past sessions and provide proactive responses while maintaining real-time interaction. This raises challenges: persistent
memory must be storable, selectively retain information, be injected at the right time, and remain efficient. Moreover, finite storage may leave required evidence unavailable, so assistants should recognize missing evidence. Therefore, we systematically evaluate general
video models under different
memory protocols and diverse specialized streaming
memory systems, and test whether models acknowledge insufficient evidence. Our evaluation reveals a clear utility–latency–storage trade-off: existing methods still struggle to simultaneously achieve reliable long-term recall, low overhead, and effective proactive assistance across sessions. APM-Bench provides a comprehensive testbed for developing and comparing persistent
memory systems under realistic streaming conditions. We hope it encourages future work that jointly considers utility, latency, and storage toward more practical persistent
memory for real-world streaming assistants.
Read the full abstract ▾
All authors Jianguo Huang, Jinming Liu, Qiyao Wang, Liang Xu, Jianhang Li, Zhimian Wen, Mingda Li, Shule Lu, Zhicheng Wang, Yuhan Guo, Xin Jin, Wenjun Zeng
Machine Learning
Benchmarking graph-based models for in-silico toxicity prediction in drug discovery
Noel Suarez-Barro, Manuel Lama and Juan C. Vidal
Drug discovery is a costly and high-risk process, where toxicity-related failures remain a major cause of attrition in both preclinical and clinical stages. As a result, accurate early prediction of chemical toxicity is essential to reduce downstream costs and improve compound prioritization. In this context, graph deep learning (GDL) has emerged as a powerful paradigm for toxicity prediction, leveraging molecular graph representations to learn directly from chemical structure with improved expressivity over traditional approaches. Despite the growing number of proposed models, current literature-based comparisons are often difficult to interpret due to inconsistencies in
datasets, preprocessing pipelines, and evaluation protocols. To address this limitation, we introduce a unified and standardized benchmarking framework for GDL-based toxicity prediction. We systematically evaluate more than 20 representative approaches under consistent experimental conditions and across multiple
datasets and partitioning strategies, enabling a fair and reproducible comparison of model performance. In addition, we complement this empirical study with a structured literature analysis to contextualize existing methodological trends and performance claims. Our results provide a clearer and more reliable assessment of the current state of the field, highlighting both the strengths and limitations of existing graph-based approaches. To support transparency and reproducibility, we release our benchmarking framework as open-source software https://gitlab.citius.gal/noel.suarez/benchtox, allowing the community to evaluate and compare models under consistent conditions.
Read the full abstract ▾
Robotics
Risk-Aware Semantic Grounding for Trustworthy LLM-Based Robot Planning
Łukasz Sobczak, Nur Keleşoğlu and Sławomir Piotr Nowak
Large
language models (LLMs) are increasingly used as high-level planners in
robot navigation, but their outputs may become unreliable when instructions are ambiguous, unsupported by the environment, or semantically inconsistent. This paper presents a Risk-Aware Semantic Grounding framework for trustworthy LLM-based
robot planning. Unlike existing LLM-based planners that primarily optimize plan generation, we formulate semantic grounding reliability as a multi-dimensional risk estimation problem. The proposed architecture explicitly models grounding uncertainty through ambiguity,
hallucination and semantic-conflict risks before planning occurs, enabling the system to decide whether to execute the instruction, request clarification, or reject it. To evaluate the approach, we introduce TRUST-NAV, a
benchmark containing both standard
navigation tasks and risk-inducing instruction scenarios. Experimental results show that while conventional LLM planners achieve strong performance on valid
navigation tasks, the proposed framework substantially improves ambiguity detection and semantic conflict rejection. These findings suggest that trustworthy
robot planning should be evaluated not only by task completion, but also by the ability to recognize when execution should not occur.
Read the full abstract ▾
Robotics
Wrench-ACT: Enhancing Robot Policies for Contact Rich Behavior Using Direct Wrench Control
Johannes Hechtl, Yannik Blei, Simon Ball et al. (+5 more)
While contact-rich manipulation requires deliberate regulation of interaction forces, recent approaches to
robot manipulation learning predominantly represent actions as target positions or poses. Even methods that incorporate force sensing either use it solely as an observation or, when predicting forces as part of the output, rely on a hybrid force controller. In this paper, we propose an imitation learning policy that predicts wrenches as its sole action output for direct use by a pure force controller. Our studies suggest that force-domain imitation learning depends critically on data collection, with force-feedback teleoperation improving policy performance by capturing the operator's deliberate force regulation. Using Action Chunking with
Transformers (ACT) as the base architecture, we train single-task models on bilateral wrench demonstrations and evaluate them on five contact-rich manipulation tasks. The wrench policy matches or outperforms position-based baselines across all tasks, with gains varying according to the degree of deliberate force regulation each task requires. Cross-condition ablations show that the bilateral data collection interface and the wrench action space each contribute independently to performance. To support further research, we will release over 1000 wrench-action demonstrations spanning these tasks on a companion website upon publication.
Read the full abstract ▾
All authors Johannes Hechtl, Yannik Blei, Simon Ball, Reihaneh Mirjalili, Michael Krawez, Seongjin Bien, Philipp Schmitt, Wolfram Burgard
Information Theory · Cross-listed from eess.SP
End-to-End Optical Semantic Communication over a Nonlinear WDM Fiber Link
Hussein Jammal, Andrea Bianco and Cristina Rottondi
Emerging optical-network applications increasingly use received data for inference and control rather than exact source reproduction, creating an opportunity to trade bit-level fidelity for greater transmission reach and efficiency. We propose an end-to-end optical semantic communication system for joint image classification and reconstruction over a nonlinear wavelength-division multiplexed (WDM) fiber channel. The system maps each image directly into a fixed-length sequence of channel symbols that preserves task-relevant information, without explicit source compression or channel coding. Experiments on the MNIST
dataset cover launch powers from -9 to +3 dBm, fiber lengths up to 800 km, and 16-, 64-, and 256-Quadrature Amplitude Modulation (QAM) formats. At 0 dBm, classification accuracy remains between 98.92% and 99.31% across all tested link lengths and modulation orders, while requiring fewer transmitted symbols than a Low-Density Parity-Check (LDPC)-coded JPEG baseline at every tested modulation order. These results show that semantic communication can simultaneously extend optical reach and reduce transmission resources by conveying only task-relevant information.
Read the full abstract ▾
Numerical Analysis
Numerical homogenization of a linear multiscale conservation law
Claude Le Bris, Frédéric Legoll and Giulia Merlini
We address the numerical approximation of a scalar conservation law with a highly oscillatory flux, in the linear setting. Taking advantage of the intrinsic numerical viscosity of the scheme employed that yields a
parabolic regularization of the original
hyperbolic equation, we use homogenization theory to derive an effective equation which in turn we solve numerically. Our numerical experiments show the performance of the approach on the example of the Lax-Friedrichs scheme.
Read the full abstract ▾
Artificial Intelligence
How Can Recommendation Feedback Evolve Agent Memory?
Shanwen Mao, Mingming Li, Hao Zhang et al. (+4 more)
Content-generation
agents continuously receive impressions, clicks, conversions, and negative feedback from recommendation systems, providing real-world outcome signals for
memory evolution. However, these signals are delayed and noisy, confounded by audience composition, placement, and recommendation policies, and may result from the combined influence of multiple
memories, making accurate attribution difficult. Existing methods rely primarily on immediate feedback or semantic
retrieval and therefore struggle to reliably translate recommendation outcomes into
memory fitness. To address this challenge, we propose TIDE (Trajectory-Informed Directed
Memory Evolution), an external
memory evolution framework driven by delayed recommendation feedback. We further introduce
Memory Evolution Gain (MEG), which measures the utility improvement of evolved
memory over a no
memory baseline on strictly future tasks. TIDE treats
memory as a capacity-constrained population of experiences: temporal and semantic credit assignment estimates contextual fitness, while responsibility credit distributes outcome signals according to the
memories referenced during generation. These signals are then used to reinforce, crossover, mutate, or evict
memories. On an e-commerce membership marketing content-generation
agent, TIDE achieves a +7.75-percentage-point MEG in offline temporal replay and significantly improves both unique click-through rate (UCTR) and activation rate in an online A/B test. On a delayed-label
benchmark, TIDE achieves the lowest mean absolute error (MAE) and root mean squared error (RMSE) and the highest MEG among the compared methods, demonstrating its effectiveness.
Read the full abstract ▾
All authors Shanwen Mao, Mingming Li, Hao Zhang, Zhiheng Li, Yige Wang, Penghua Yu, Junxiong Zhu
Computation and Language
RunyaNER: Auxiliary Language Selection for Runyankore NER
Prosper Arineitwe Asiimwe, Francois Meyer and Jan Buys
Cross-lingual zero-shot transfer and
multilingual fine-tuning are promising approaches for NLP tasks such as Named Entity Recognition (NER) in low-resource
languages, but in the absence of target
language benchmarks, it is unclear which auxiliary
language selection strategy leads to the best transfer. We introduce RunyaNER, the first publicly available NER
benchmark for the East African
language Runyankore, and use it to investigate the choice of which
languages to use for transfer. Created with a semi-automated pipeline and fully manually verified, RunyaNER contains over 237k annotated words across 30k sentences. We
benchmark pretrained models on RunyaNER, establishing that our
dataset is of sufficient quality and size to produce effective Runyankore NER models. We then use RunyaNER to investigate auxiliary
language selection in cross-lingual zero-shot and
multilingual fine-tuning settings. Our experiments show that while transfer performance is highly sensitive to auxiliary
language selection,
embedding-based measures computed from labelled training spans correlate more strongly with downstream transfer performance than traditional linguistic features based on metadata or typology. By releasing RunyaNER and providing a systematic analysis of auxiliary
language selection strategies, this work contributes both a new
benchmark resource and practical insights for
multilingual transfer in low-resource settings.
Read the full abstract ▾
Digital Libraries
Which reported inputs govern molecular docking reproducibility? A benchmark from reporting audit to independent re-execution
Giap Duc Ha
Computational docking results can be re-executed only when the molecular system and protocol are specified, yet reporting checklists do not quantify how strongly individual method fields affect the reported score. We combined a span-verified audit of 50 open-access papers with controlled one-factor perturbations, a Vinardo scoring-function check and a Vina cross-docking extension covering 12 targets in 7
protein families, and re-execution of 37 published claims on local and independent cloud infrastructure. Search-related fields were sparsely reported, but perturbing box centre, box size, exhaustiveness or random seed produced median absolute score changes of no more than 0.08 kcal mol$^{-1}$; ligand protonation and identity produced median changes of 0.19 and 0.29 kcal mol$^{-1}$, respectively, whereas receptor structure produced the largest change (1.02 kcal mol$^{-1}$; n = 85; P < 0.001), and 22% of 116 unique reported ligand strings remained unresolved or ambiguous after deterministic name normalization. These measurements yielded empirical field weights for the NewScience Evidence score and identified exact receptor structure, machine-resolvable ligand identity and protonation state as primary reporting elements; 29 of 37 local and 27 of 37 cloud re-executions were within 2.0 kcal mol$^{-1}$ of the reported score, but these descriptive rates do not estimate experimental replication or a calibrated probability of reproduction.
Read the full abstract ▾
Sound
Rate-Agnostic Bioacoustics: Heterogeneous Multi-Taxa Classification with Continuous Filterbanks and Fourier Neural Operators
Stefano Ciapponi, Francesco Ardan Dal R{\i}, Nicola Conci et al. (+1 more)
Conventional bioacoustic classification models rely on fixed-rate spectral representations, requiring recordings acquired at heterogeneous sampling rates to be resampled before analysis. We propose a Sampling-Frequency-Independent (SFI) frontend that processes each recording directly at its native sampling rate, coupled with a
Fourier Neural Operator (FNO) backbone featuring progressive temporal-scale fusion. This framework avoids fixed-rate resampling and high-frequency information loss while producing fixed-size representations across sampling rates. Mild training-time sampling-rate (sr) augmentation further improves robustness to unseen rate variations. Evaluated on a multi-taxa corpus comprising 84 classes and 60 sampling rates, the proposed SFI-FNO configuration outperforms fixed-rate and corpus-maximum-rate baselines, achieving .906 accuracy, .921 balanced accuracy, and a Macro-F1 score of .899.
Read the full abstract ▾
All authors Stefano Ciapponi, Francesco Ardan Dal R{\i}, Nicola Conci, Elisabetta Farella
Artificial Intelligence
SkillGym: Training Skill-Use Agents with Automatic Verifiable Environment Generation
Renxi Wang, Mingshan Hee, Fajri Koto et al. (+2 more)
Skills equip LLM
agents with professional knowledge and guidance to complete long-horizon and complex tasks. Although skills have been widely adopted in recent
agent paradigms and harnesses, how to synthesize reliable training data and how to train
agents for skill use remain underexplored. In this work, we propose SkillGym, an automatic pipeline to build verifiable environments, collect trajectories, and train skill-use
agents. SkillGym first crawls a large volume of skills from the internet, then keeps those whose workflows can run reproducibly offline. A builder-reviewer pipeline is used to construct difficulty-controlled tasks, spanning four task types, each with a reference solution and an executable verifier. With this pipeline, we build 6.8k environments and collect 19k verified successful trajectories for supervised finetuning. Finetuning on these trajectories improves LLMs of different families and sizes, from 2B to 122B parameters across four skill-use
benchmarks; Our Qwen3.5-9B SFT model outperforms the 397B untrained model on two of them. Further analysis shows that training teaches
agents to invoke skills, raising the rate of reading the relevant skill from 28% to 96%, and that the gains hold across
reasoning structures, extending to task types that form a minority of the training data and to skills held out from training
Read the full abstract ▾
All authors Renxi Wang, Mingshan Hee, Fajri Koto, Timothy Baldwin, Haonan Li
Computer Vision
Weeding Out Bad Seeds: Initial-Noise-Robust Unlearning for Text-to-Image Diffusion Models
Arian Komaei Koma, Seyed Amir Kasaei, Aida Aryafar et al. (+6 more)
Machine unlearning has emerged as a critical post-hoc safety measure to erase sensitive concepts from Text-to-Image (T2I) models without prohibitive retraining. However, we reveal that current state-of-the-art (SOTA) approaches are brittle due to a severe lack of robustness to noise initialization. We call this phenomenon “probabilistic forgetting”: suppressed concepts re-emerge under specific random initial noise conditions, despite appearing unlearned on other initializations. We trace this failure to the misalignment between standard Gaussian sampling during unlearning and the unlearning objective. Since the target concept manifests only in specific initial noise regions throughout the unlearning phase, uniform random sampling yields sparse, uninformative gradient updates that fail to drive robust erasure. To overcome this issue, we propose an adaptive, concept-conditioned sampling strategy that dynamically concentrates gradient updates on regions where the target concept manifests, down-weighting uninformative areas. We integrate our framework with six distinct SOTA unlearning methods across four
diffusion backbones and evaluate it across safety, object, and artistic-style unlearning, as well as under black-box and white-box
adversarial attacks. Our method reduces the conditional nudity re-emergence rate across random initializations by 67.2% on average over four baselines and lowers attack success rates across both
adversarial evaluations. Across concept domains, Adaptive Noise Sampling strengthens
adversarial robustness and non-target retention while preserving competitive generative quality and target-erasure performance.
Read the full abstract ▾
All authors Arian Komaei Koma, Seyed Amir Kasaei, Aida Aryafar, Matin Ghiasi, Ali Aghayari, Amirhossein Souri, Mohammad Mosayyebi, AmirMahdi Sadeghzadeh, Mohammad Hossein Rohban
Machine Learning
Why Adaptive Optimizers Underestimate Rare Tokens
Sangsidhya Kar
In the softmax output layer, a rare
token receives a small positive logit gradient on most steps and a much larger negative gradient on the few steps when it is the target. SGD simply adds these contributions. Coordinate-wise adaptive methods such as Adam, RMSProp, and sign descent instead divide each update by a running estimate of its magnitude, and that estimate is largest immediately after the
token appears. This imbalance has two effects. At the level of the whole output layer, we characterize which optimizers preserve the mean output
embedding: every method whose update is linear in past gradients does, as do Kronecker-factored and orthogonalized methods such as Shampoo and
Muon. Adam, Adafactor, Lion, and sign descent do not, and for these methods we obtain an exact step-by-step expression for the change. At the level of an individual rare
token, the same normalization shifts the training fixed point. In the unigram model, sign descent lowers the logit of every
token that occurs in fewer than half of the minibatches at a constant expected rate. For RMSProp with periodic arrivals, we can solve the fixed point in closed form: if a
token is absent for at least two consecutive minibatches, its
equilibrium probability is strictly below its data frequency for every learning rate, and the ratio tends to $\kappa/(2(e^{\kappa/2}-1))$. Here $\kappa$ is the mean number of steps between occurrences divided by the second-moment time constant $1/(1-\beta_2)$. In the same model, SGD and AMSGrad retain the unbiased fixed point. We test these predictions both in a unigram model and in a small
language model trained from a known generating distribution. With random arrivals, the bias is larger than the periodic formula predicts; in the
language model, the optimizers with the biased fixed point also fit the generating distribution less well.
Read the full abstract ▾
Computation and Language
E-MoE: Enhanced Mixture-of-Experts for Non-Factorized Diffusion Language Models
Arseny Ivanov, Alexander Kolesov, Alexander Korotin et al. (+2 more)
Masked
diffusion models (MDMs) generate sequences by progressively unmasking several
tokens per denoising step, but their reverse process is typically factorized over positions, limiting sample quality in the few-step regime where
diffusion's speed advantage over autoregressive decoding matters most. A recent line of work introduces a continuous Gaussian latent, trained as a variational autoencoder, to capture correlations across positions, but such approaches are prone to posterior collapse, where the latent is silently ignored. We propose Enhanced Mixture-of-Experts (E-MoE), which builds the reverse process as a mixture of factorized distributions over a discrete shared latent given by the expert-routing decisions of a Mixture-of-Experts (MoE) backbone, without increasing active parameters over the factorized baseline. Across synthetic multi-modal
benchmarks, binarized MNIST, and LM1B, E-MoE improves few-step generation over factorized baselines.
Read the full abstract ▾
All authors Arseny Ivanov, Alexander Kolesov, Alexander Korotin, Ivan Oseledets, Mikhail Goncharov
Distributed Computing
DScale: Scaling Block-Diffusion Speculative Decoding with Adaptive Verification
Rongjian Chen, Minxian Xu, Zhengxin Fang et al. (+2 more)
Growing large
language model applications demand efficient inference. At high concurrency, block-
diffusion speculative decoding suffers from verification padding, rejected candidates, and incompatibility between variable prefixes and fixed-shape graphs. Uniform truncation sacrifices acceptable
tokens. We present DScale, preserving drafter architecture, weights, and full draft length. A separate 112K-parameter predictor requires neither confidence calibration nor hardware speed-curve preparation. Path-aware tiles reduce padding. Dynamic verify-length (DVL) allocation packs scored prefixes into half the native verification capacity. Fixed-address workspaces propagate changing boundaries through verification and acceptance while reusing captured graphs. On A100-40GB with tensor parallelism 1, Qwen3-8B and Qwen3-4B cover four
datasets and concurrency 8-32, reusing each target's frozen predictor.
Geometric-mean throughput gains across these configurations are respectively 43.9% and 48.8% over DFlash, 22.2% and 37.7% over DSpark, and 24.4% and 32.0% over Domino, with lower request latency. Cumulative ablations show that adding the three mechanisms successively increases
geometric-mean throughput, while budget adjustment improves accepted-
token retention. GPU profiling shows that complete decode-step time on GSM8K decreases by 30.8-52.5% relative to DFlash
Read the full abstract ▾
All authors Rongjian Chen, Minxian Xu, Zhengxin Fang, Kejiang Ye, Chengzhong Xu
Software Engineering
Profiling the Energy Consumption of Serverless Functions with Joule Profiler
Jérémy Woirhaye, François Gibier, Anderson Andrei Da Silva et al. (+3 more)
Cloud providers and customers have widely adopted serverless computing as a convenient paradigm for deploying and executing functions on demand. To do so, serverless platforms require provisioning an appropriate execution environment before a single line of the function's code runs. These environments consist of several layers, such as container engines, hypervisors, unikernels, and programming
language runtimes. While the literature has investigated the performance of these serverless platforms, it treats functions as black boxes, and the community lacks key insights into the environmental impacts of packaging applications as serverless functions. This paper therefore empirically studies the energy efficiency of serverless functions deployable on serverless platforms. We design an experimental benchmarking environment that lets stakeholders explore the impacts of the various layers involved in executing serverless functions. We use it to evaluate 1,401 configurations, combining 9 execution environments, 7
language-runtime configurations, 11 workloads, and 3 input sizes, to answer three research questions: Are the most popular programming
languages for serverless functions the most energy-efficient? What factors most affect their energy efficiency? What are the most energy-efficient configurations to deploy them? Our results show that one should first choose the programming
language, then the
language runtime, and only then the execution environment, which matters only for short-lived functions and whose best choice depends on the runtime. Our benchmarking environment, experimental artifacts, raw measurements, and analysis code are publicly available.
Read the full abstract ▾
All authors Jérémy Woirhaye, François Gibier, Anderson Andrei Da Silva, Francescomaria Faticanti, Thomas Ledoux, Romain Rouvoy
Robotics
RawVLA: Embodied Neural Image Signal Processor For Robotic Manipulation
Shuhong Liu, Heng Zhou, Lingfeng Qian et al. (+7 more)
Vision-
language-action (VLA) models typically operate on RGB images produced by a fixed camera image signal processor (ISP), leaving the imaging pipeline outside the learning and evaluation loop. We systematically examine the consequences of this overlooked design choice across five fundamental ISP dimensions: gain, sensor noise, chromatic response, tonal response, and bit depth. Our analysis reveals that RAW-to-RGB processing materially shapes both action prediction and manipulation success, with different ISP dimensions exerting substantially different effects. Guided by these findings, we introduce RawVLA, a streaming neural ISP that adaptively renders RAW observations for frozen VLA policies while concentrating its capacity on the imaging factors relevant to
embodied behavior. We further present RawVLA-Bench, a RAW-domain manipulation
benchmark to expose image processing as an explicit evaluation variable across clean and adverse acquisition conditions. Experiments on RawVLA-Bench show that RawVLA preserves performance under standard conditions while substantially improving robustness under degraded imaging, establishing adaptive RAW processing as an effective interface between physical cameras and
embodied policies.
Read the full abstract ▾
All authors Shuhong Liu, Heng Zhou, Lingfeng Qian, Yuhao Fang, Xianbao Hou, Qianyu Zhou, Lin Gu, Wei Sui, Jianfei Yang, Ziteng Cui
Computer Vision
Principled MAP estimation for inverse problems: bridging the gap between convergence and performance
Alexandre Lagier, Valentine Tosel, Anne Gagneux et al. (+2 more)
Pretrained denoisers provide a powerful way to incorporate image priors into restoration
algorithms. Plug-and-Play and RED approaches exploit fixed-noise-level denoisers within first-order optimization schemes, with convergence guarantees, but often struggle to achieve high-quality reconstruction on severely ill-posed inverse problems. In contrast, recent state-of-the-art approaches leverage denoisers derived from flow- or
diffusion-based generative models and evaluate them along a sequence of decreasing noise levels. While these methods achieve strong empirical performance, their convergence theory remains limited. In this paper, we bridge this gap by specifically designing an
algorithm that combines denoisers at decreasing noise levels with a schedule tailored to ensure convergence. From a
Bayesian perspective, we prove that our method converges to a $\textit{Maximum a Posteriori}$ (MAP) estimate, under suitable assumptions. Subsequently, we apply our method to various ill-posed inverse problems and show that it surpasses convergent methods while competing with state-of-the-art empirical ones.
Read the full abstract ▾
All authors Alexandre Lagier, Valentine Tosel, Anne Gagneux, Mathurin Massias, Ségolène Martin
Software Engineering
Exploring Emotional Intelligence in Software Testing
Cristina Martinez Montes, Pushpamalar Rajendran, Grace Karuri et al. (+1 more)
Background: Emotional Intelligence (EI) is the ability to recognise, understand, and manage one's own and others'
emotions. Software testers deliver judgements about colleagues' work under deadlines they do not control, and prior work on
emotion in software engineering has mostly studied developers. Aims: To explore how software testers describe the part EI plays in their day-to-day work, in communication and conflict within the team, and in responding to requirements
volatility. Method: Semi-structured interviews with 16 software testers in Sweden working in teams that use agile practices, across aviation, automotive, healthcare, IT services, administration, banking and pharmaceuticals, analysed with reflexive thematic analysis informed by Goleman's EI framework. Results: Three themes. Testers described regulating stress under deadline pressure and drawing motivation from recognition, clarity and autonomy; managing the daily delivery of critical findings to colleagues so that trust survives; and responding to requirements change with frustration that turned into decisions about what to leave untested, into advocacy for process change, or into workarounds. Read against developer-focused studies, the themes point to features of the testing role: the work product is a criticism of a colleague's work, success is invisible while failure is attributed, and the tester's window shrinks with every upstream delay. Conclusions: For testers, managing
emotions is a constant job requirement. The results highlight that the importance of EI increases when the development process lacks an independent testing phase. The findings also inform implications for teams and, ultimately, for organisations and future research.
Read the full abstract ▾
All authors Cristina Martinez Montes, Pushpamalar Rajendran, Grace Karuri, Felix Dobslaw
Machine Learning
Physical Muon: Orthogonalization as an Equilibrium Computation
Yuren Hao
Physical neural networks and analog in-
memory computing could reduce the energy cost of neural network training. Realizing this potential, however, requires optimizers that combine effective learning with physical implementability. SGD fits local analog updates but struggles on
transformers, while Adam family is unstable against analog bias.
Muon offers strong training performance, but its Newton–Schulz orthogonalization relies on dense
matrix-
matrix products. To address this obstacle, we introduce Physical
Muon, which computes the orthogonalization as the
equilibrium of a continuous-time flow. Random probes approximate the flow using
matrix-vector products, reciprocal reads, and local rank-1 writes. To test whether this replacement preserves training performance, we evaluate it on a 10.95M-parameter
transformer. The dense flow's mean validation cross-
entropy is 0.0085 above Newton–Schulz across nine seeds per method; the probe implementation is 0.0188 above the control across two seeds.
Circuit simulations further reproduce the flow dynamics and yield comparable training behavior.
Read the full abstract ▾
Machine Learning
Graph-Conditioned On-Policy Agent Distillation from Off-the-Shelf Teachers
Xiaohan Yi, Wen Luo, Yani Huang et al. (+4 more)
On-policy
distillation (OPD) trains compact
language agents with teacher feedback on student-generated trajectories. In multi-turn tasks, compounding errors can move students beyond the teacher's effective supervision. We introduce Graph-Conditioned On-Policy
Agent Distillation (GC-OPD), which enriches an off-the-shelf teacher's scoring context with execution evidence. A graph indexes repeated teacher executions by shared states while preserving complete successful and failed histories. After each student episode, GC-OPD retrieves current-state references or historical alternatives and combines them with student hindsight to score the original thought-action
tokens. Using the same original teachers, GC-OPD improves mean success over vanilla OPD from 24.70% to 48.78% on ScienceWorld (4B student), from 53.36% to 85.26% on ALFWorld Unseen, and from 29.10% to 37.65% on WebShop. At matched student sizes, it also achieves higher mean success than every evaluated OPD baseline using GRPO-trained teachers on ScienceWorld and ALFWorld; the strongest such ScienceWorld 4B baseline reaches 46.66%. GC-OPD requires no task-specific teacher optimization.
Read the full abstract ▾
All authors Xiaohan Yi, Wen Luo, Yani Huang, Junfeng Zhan, Asher Qin, Peilin Zhao, Xi Xiao
Robotics
Video2STL: Grounding VLM-Generated Temporal Specifications for Robot Learning
Merve Atasever, Keyan Azbijari, Cagan Bakirci et al. (+6 more)
Video-based policy learning is particularly promising, as it illustrates target behaviors without requiring action annotations or embodiment-matched demonstrations. A central challenge is deciding what information should be transferred from the
video to the
robot. Existing approaches commonly convert visual observations into scalar similarity or value signals, or ask foundation models to directly generate reward code. These approaches can make the temporal structure of a task difficult to inspect, ground, and reuse. We present
Video2STL, a framework that converts observation-only
videos into parametric Signal Temporal Logic (STL) specifications and uses the resulting formal representation for
robot learning. A
vision-
language model extracts an embodiment-independent semantic event trace and constructs a bank of symbolic temporal specifications. The model determines the task structure, while numerical predicate thresholds and temporal bounds are grounded from successful
robot trajectories. For policy learning, we separate short- and long-timescale temporal information: short-horizon specifications provide dense rewards through rolling-window quantitative robustness, while a causal monitor over a retained long-horizon specification provides one-time progress rewards for valid temporal prefixes. The same representation supports cross-embodiment transfer from human or animal
videos to
robot control. Across four manipulation tasks,
Video2STL achieves $85.8\%$ average success-once and $67.0\%$ success-at-end, compared with $81.5\%/59.5\%$ for native dense PPO and $65.0\%/42.3\%$ for Text2Reward; in quadruped locomotion, Qwen-3.8 and GPT-5.6-based
Video2STL policies achieve $100\%$ success across velocities from $0.3$ to $2.1\,\mathrm{m/s}$ while remaining competitive in high-speed energy efficiency. Project webpage: \href{https://
video2stl.github.io/}{
video2stl}.
Read the full abstract ▾
All authors Merve Atasever, Keyan Azbijari, Cagan Bakirci, Bo-Ruei Huang, Tolga Izdas, Zahra Shahrooei, Richard Yang, Erdem Biyik, Jyotirmoy V. Deshmukh
Sound
Bad: Taming the Bioacoustic Data Deluge with a Bat Activity Detector
Stefano Ciapponi, Santiago Martinez Balvanera, Andrea Cesaretti et al. (+2 more)
Passive Acoustic Monitoring of bats generates massive ultrasonic
datasets (>27 GB/night per node), straining edge storage and battery life. Legacy triggers fail against acoustic confusers, while deep models exceed microcontroller limits. We present a hardware-aware Bat Activity Detector (BAD) specifically designed to discriminate bat calls from hard biological and environmental confusers across variable sampling rates (192-384 kHz). Tailored for the Silicon Labs EFM32PG26 (MVP) in 8-bit integer precision, our model achieves 100 percent hardware offload across all 14 layers (17.2 KB Flash, 73.1 KB RAM). End-to-end preprocessing (74.00 ms for 76 frames) and inference (30.00 ms) of 100 ms clips at 192 kHz require 104.00 ms per clip. On spatially out-of-domain recordings under a realistic low-prevalence regime (r_pos = 0.05), BAD achieves an AUC-ROC of 0.9748 and suppresses 99.4% of non-target noise frames while retaining 65.3% of bat calls - delivering a >33x precision gain over classical Goertzel baselines.
Read the full abstract ▾
All authors Stefano Ciapponi, Santiago Martinez Balvanera, Andrea Cesaretti, Elisabetta Farella, Kate E. Jones
Machine Learning
Hyunjong Ok, Seunggu Kang and Jaeho Lee
Thorough evaluation of
vision-
language models (VLMs) has become prohibitively expensive, as
benchmarks span an ever-broader spectrum of capabilities and new models arrive at a relentless pace.
Benchmark compression methods that preserve model rankings at a fraction of the cost are well studied for
language models, but for VLMs the question remains under-explored. We present PRIMEBench (
Pruning Redundant Items for
Multimodal Evaluation), a
vision-aware hierarchical
benchmark compression framework that substantially reduces evaluation cost while preserving model rankings. This hierarchical framework operates in four stages: data cleaning to remove items answerable without the image and all-correct items, category representative selection to pick one
benchmark per capability category, item
pruning with
Vision-Aware Variance (VAW), and category-count
pruning. VAW combines inter-model variance with a
vision-dependence score computed from
multimodal embeddings alone, while encouraging coverage of diverse items within each
benchmark. On models held out from item selection, it has the highest mean fidelity at the released 5% retention. The hierarchical design lets practitioners stop at any stage to match their compute budget; the released suite removes over 97% of items while preserving model rankings. Beyond compression, our analyses show how VLM evaluation behaves as model panels grow and evolve, providing guidance for designing future
benchmarks that are more efficient, robust to model turnover, and explicit about the limits of evaluation-side
pruning.
Read the full abstract ▾
Computation and Language
From Dissonance to Orchestration: Teacher Intervention in On-Policy Distillation
Yuhao Wang, Ruiyang Ren, Yinan Zhang et al. (+3 more)
On-policy
distillation (OPD) trains a student on its own
reasoning trajectories using feedback from a stronger teacher. Teacher interventions can improve these trajectories, but also change the distribution on which the student learns. Our controlled studies show that rollout quality alone is an incomplete criterion for allocating teacher guidance. Deeper intervention yields diminishing gains in rollout accuracy while increasing off-policy load. In a training probe with a restricted rollout horizon, peak student accuracy and performance retention favor different intervention strengths. The preferred intervention depth and placement also vary across
benchmarks. These findings motivate MAESTRO, which uses local policy disagreement to jointly adapt when the teacher takes over and how long it generates. Its {policy disagreement score} combines teacher-weighted candidate coverage with local distribution similarity and is aggregated within
reasoning paragraphs. Across eight mathematical
reasoning benchmarks, MAESTRO achieves the highest macro-average accuracy among the compared methods for both 0.6B and 1.7B Qwen3 students, with the 1.7B student leading on every
benchmark. MAESTRO also reduces average training response length by 67.3% relative to standard OPD. The code is available at https://github.com/yhao-wang/MAESTRO.
Read the full abstract ▾
All authors Yuhao Wang, Ruiyang Ren, Yinan Zhang, Ruiqing Zhang, Jing Liu, Chunyan Miao
Machine Learning
ScaGNN: a Graph Neural Network for Multiple Scattering Simulations
Rémi Marsal, Stéphanie Chaillat and Alexandre Chapoutot
The boundary element method (BEM) provides an efficient numerical framework for solving multiple scattering problems in unbounded homogeneous domains. By restricting the discretization to the domain boundaries, it substantially reduces computational complexity. The procedure first consists in determining the solution trace on the boundaries of the domain by solving a boundary integral equation. Then, the volumetric solution can be recovered at low computational cost using a boundary integral representation. As the first step of the BEM represents the main computational bottleneck, we present ScaGNN, a learning-based approach designed to approximate the solution trace. It relies on a graph neural network architecture that incorporates a dynamic adaptive edge sampling mechanism for selecting the most relevant interactions to model. Guided by intermediate predictions of expected error and edge length, this mechanism selects, at various stages of the forward pass, the most relevant distant interactions to model. The proposed method is tailored to achieve linear complexity with the number of nodes in the input graph. To train and evaluate our network, we present a
benchmark consisting of several
datasets with different types of multiple scattering problems. Our experiments show that our approach surpasses existing state-of-the-art learning-based methods on the considered tasks and investigate the generalization capabilities to settings with an increased number of obstacles and out-of-distribution obstacle shapes. github.com/LARIAD/ScaGNN
Read the full abstract ▾
Artificial Intelligence
Demistifying Data and Simulator Assumptions in Supervised Causal Discovery
Pingchuan Ma, Rui Ding, Bojun Huang et al. (+1 more)
Supervised causal discovery learns to infer causal structure for a new
dataset from training
datasets paired with structural labels. These training pairs are typically simulated, making the simulator both a source of supervision and a carrier of assumptions about causal graphs, mechanisms, and noise. Understanding the resulting predictions therefore requires examining how these assumptions supplement the information available in observational data, which may be compatible with multiple causal graphs. This paper examines that relationship across representative methods available through June 2026. We organize these methods by prediction target, prediction granularity, encoder, structural decoder, and training regime to relate what each method predicts to how it uses data and simulator-based supervision. Using this framework, we distinguish two questions: whether the target is identifiable under the assumed model class, and whether a trained predictor generalizes beyond its training distribution. Restrictions on mechanisms and noise can make otherwise ambiguous causal directions identifiable, but predictive accuracy under those restrictions does not establish transfer when they change. This distinction motivates evaluation that matches metrics to the identifiable graph target and tests changes in graphs, mechanisms, and noise between training and deployment. Extending such evaluation to real data also requires documenting the external causal evidence and uncertainty behind
benchmark reference graphs. Together, these analyses guide method comparison and identify open questions in transfer, test-time adaptation, and uncertainty assessment.
Read the full abstract ▾
All authors Pingchuan Ma, Rui Ding, Bojun Huang, Shuai Wang
Computation and Language
Learning to Retrieve Missing Evidence for Long-Term Memory QA
Yi-Xuan Deng, Yi Zhang, Wei Liu et al. (+2 more)
Long-term
memory enables
language models to use past interactions in future conversations. However, evidence needed to answer a question may be scattered across distant turns, while the question itself omits clues needed to locate it. Retrieved facts can reveal these clues, motivating
retrieval decisions conditioned on evidence already found. We introduce MERA (Missing-Evidence
Retrieval Augmentation), which separates globally searchable
memory from a question-specific evidence state. Verified evidence guides subsequent
retrieval without restricting access to the global
memory. We train a lightweight planner through reinforcement learning, rewarding queries that recover previously missing evidence. MERA achieves strong answer accuracy across Qwen3-30B and GPT-4o-mini backbones. With Qwen3-30B for evidence processing and answer generation, the trained 0.6B planner achieves 77.40% accuracy on LoCoMo and 71.29% on LongMemEval-S, exceeding a 30B planner without
retrieval-grounded training by 4.10% and 3.96%, respectively. On LoCoMo, later
retrieval rounds increase cumulative evidence recall from 55.5% to 80.5%.
Read the full abstract ▾
All authors Yi-Xuan Deng, Yi Zhang, Wei Liu, Chao Xue, Shuojin Yang
Robotics
Anisotropic Representations Improve Planning in JEPA World Models
Mingu Kang, Yoori Oh, Sookyung Kim et al. (+1 more)
Latent world models learn action-conditioned dynamics in representation space and often score candidate actions by Euclidean distance to a goal representation. Joint training typically regularizes the representation to prevent collapse, but the resulting representation geometry also determines how terminal errors are weighted during planning. We show that accurate prediction and noncollapsed representations do not guarantee a task-aligned latent planning cost: isotropic Gaussian regularization can induce a geometry that ranks feasible outcomes differently from the task cost. To address this mismatch, we introduce AnisoWM with $\Lambda$Reg, which replaces the fixed isotropic Gaussian target with a learnable diagonal covariance under fixed-trace and anisotropy constraints. The prediction objective, predictor architecture, and Euclidean planner remain unchanged; the target is used only during training. Our analysis characterizes the prediction-driven allocation of target variance, its dependence on the training distribution, and the conditions under which the induced metric reduces planning regret. Across four visual control environments, AnisoWM improves planning success over LeWorldModel in all four. Its latent planning cost also shows better agreement with task outcomes. Project website: https://rkdrn79.github.io/AnisoWM-page/
Read the full abstract ▾
All authors Mingu Kang, Yoori Oh, Sookyung Kim, Joonseok Lee