Computation and Language
Two Emojis of Difference: What Multilingual Affective Generation Benchmarks Actually Measure
Fardeen Sadab and Adib Sakhawat
We audit a
multilingual affective generation
benchmark eight instruction-tuned LLMs producing emoji summaries for 17,100 Bangla, English and Hindi sentences, with 6,960 human judgements and find its headline conclusions to be artefacts of the measurement instrument rather than properties of the systems. Treating annotators as a random rather than a fixed factor, no system differs significantly from any other ($F(7,14)=0.59$, $p=0.76$), although the conventional analysis declares 19 of 28 pairwise differences significant. Annotator identity explains far more rating variance than system identity, and the winning system changes whenever any single annotator is removed. The ordering that does emerge tracks output length: mean emoji count explains 78.7% of between-system variance, and a within-item length-matched comparison over 2,599 pairs reverses the leaderboard. We further show that cross-provider anisotropy differences vanish under mean-centring, that per-
language token costs change sign with the normalising unit, and that multi-view row-wise splits inflate macro-F1 by $3.1$ points and change the top-ranked system. In place of preference scoring we propose **emoji-affect decodability**, a reference-based probe whose rankings are stable to $\pm0.003$ macro-F1 across seeds.
Read the full abstract ▾
Computation and Language
IterSynth: Rethinking Deep Search Agents via Role-Decoupled Iterative Synthesis
Xingyu Wu, Yuchen Yan, Zhengxi Lu et al. (+9 more)
Deep search requires LLM
agents to decompose complex queries, search for evidence, and synthesize grounded answers, yet existing ReAct-style
agents suffer from two limitations: role coupling, where one policy must handle planning, evidence use, and synthesis; and context accumulation, where growing search histories introduce noise and obscure useful information. To address these issues, we propose IterSynth, a role-decoupled and summary-based paradigm that alternates between a Planner for identifying information needs and a Synthesizer for integrating evidence into an evolving summary state. This design separates planning from synthesis while using the summary as the persistent state of search, reducing both capability coupling and context noise. To train IterSynth effectively, we further introduce Role-Decoupled Policy Optimization (RDPO) for reinforcement learning, which combines terminal outcome rewards with turn-level rubric evaluations and computes role-specific advantages for more precise credit assignment. Experiments on five long-horizon deep-search
benchmarks such as BrowseComp and Xbench-DS show that IterSynth-8B achieves an average score of 50.7, surpassing the strongest prior $\leq$8B
agent by +4.2%. Moreover, IterSynth serves as a model-agnostic prompting paradigm, delivering substantial zero-shot gains over ReAct and similar prompting paradigms on frontier proprietary models.
Read the full abstract ▾
All authors Xingyu Wu, Yuchen Yan, Zhengxi Lu, Siqi Chen, Xin ZHANG, Aiting Liu, Chao Deng, Jie Liu, Jin Ma, Jian Shao, Jun Xiao, Yongliang Shen
Computer Vision
Pose Adaptive Dynamic FiLM Modulation for Visual Speech Recognition
Matthew Kit Khinn Teng, Haibo Zhang and Takeshi Saitoh
Head-pose variation introduces substantial appearance transformations in visual
speech recognition (VSR), making pose-aware feature modulation desirable. However, performance degradation and unwanted feature interactions may result from using numerous Feature-wise Linear Modulation (FiLM)
circuits with fixed modulation intensity. We propose a Pose Adaptive Dynamic FiLM framework with a Dynamic Residual FiLM (DR-FiLM) modulator that predicts input-dependent weights to adaptively control the strength of pose-conditioned modulation. Experiments on LRS2 and LRS3 demonstrate that unweighted multi-pathway modulation substantially degrades phoneme recognition, increasing PER to 20.33% and 29.42%, respectively, compared with 16.20% and 20.96% for the single ResFiLM configuration. In contrast, the proposed DR-FiLM with dynamic Deep-Res weighting reduces PER to 15.74% on LRS2 and 23.91% on LRS3, substantially mitigating the adverse effects of unweighted modulation. The analysis of the learned weights further reveals a consistent tendency to assign greater weight to the deeper FiLM pathway as head-pose variation increases. These results show that merging pose-conditioned FiLM
circuits is more efficient when the modulation strength is dynamically controlled.
Read the full abstract ▾
Numerical Analysis
Learning Operators of Geometry with an Interface Autoencoder
Aiqing Zhu and Pengzhan Jin
Geometry-dependent PDEs define operators whose inputs and outputs may each consist of an oriented interface and a function on that interface, whereas most existing neural operators are formulated on fixed domains. In this paper, we first establish an approximation
theorem for continuous operators between general state sets. We then instantiate the
theorem with the Interface Autoencoder (IAE), which represents interface–function states in a fixed box using finite projection codes and decodes them by zero-set extraction and restriction. For tensor cosine codes, we prove a uniform $C^0$ reconstruction rate and tube-local gradient convergence. These estimates yield Hausdorff and graph-Hausdorff error bounds, together with a reference-based
topology certificate. The IAE accommodates both cross-space
geometric operators, mapping domain geometries to the associated PDE solution fields, and within-space
geometric operators, mapping between interface–function states. Its effectiveness is demonstrated through numerical experiments on the Poisson equation, interface merging in Hele–Shaw flow, and two-phase Stokes flow with surfactant.
Read the full abstract ▾
Logic in Computer Science · Cross-listed from math.LO
Two applications of the point-free coderivative
Zoltan A. Kocsis
We present two new applications of Simmons' point-free Cantor-Bendixson coderivative operator in intuitionistic logic. First, we use it to give a simplified proof of the recent result of Xu and Ye that the free Heyting
algebra on two generators does not occur as the Heyting
algebra of subterminal objects in any elementary topos. Then we use it to prove that complete Heyting
algebra semantics is not strongly complete for intuitionistic second-order propositional logic: semantic consequence from an arbitrary set of assumptions does not coincide with ordinary syntactic consequence.
Read the full abstract ▾
Computer Vision
Detecting Glaucoma Across Multi-ethnic Myopic and Non-Myopic Populations Using an Uncertainty-Aware Vision Transformer: A Multicentre Model Development and Validation Study
Raghavan Lavanya, Yangqin Feng, Ten Cheer Quek et al. (+36 more)
Background: Artificial intelligence (AI)-based glaucoma detection from colour fundus photographs (CFP) offers scalable screening, but performance may decline on external
datasets because of differences in ground-truth definitions, populations, and coexisting conditions such as high myopia (HM). We developed and validated a
Vision Transformer-based deep learning (DL) model for glaucoma detection across multi-ethnic cohorts with and without HM. Methods: A ViT-B/16 model with predictive uncertainty estimation was developed using 56,483 CFPs (57.1% with myopia; 14.4% with HM). Glaucoma labels were standardised using clinical, imaging, and perimetry data. The model was validated on 16 independent
datasets across three continents, including four
datasets with explicit HM labels. Findings: Internal AUROC was 98.7% (95% CI 98.2-99.1%), with sensitivity 94.5% and specificity 97.3%. Across 16 external
datasets from eight countries, AUROCs ranged from 86.4% to 99.6%. In HM eyes, internal AUROC was 97.8% (95% CI 96.1-99.2%), with sensitivity 94.8% and specificity 93.7%. External HM AUROCs were 86.5% in the Beijing Eye Study and 93.3%, 91.8%, and 85.5% in hospital-based
datasets from Taiwan, Thailand, and South Korea. In an exploratory HM clinical evaluation, the model had higher CFP-only diagnostic accuracy than ophthalmologists and trained graders (92.0% vs 70.0%; p=0.008) and performed comparably to glaucoma specialists using full clinical information. Interpretation: The model showed robust glaucoma detection across myopic and non-myopic multi-ethnic populations and may support AI-assisted screening in settings with high HM prevalence.
Read the full abstract ▾
All authors Raghavan Lavanya, Yangqin Feng, Ten Cheer Quek, Quan V. Hoang, Linda Yi-Chieh Poon, Jost B. Jonas, Ya Xing Wang, Vinay Nangia, Jin Wook Jeoung, Sehie Park, SoYeon Kim, Benjamin Y Xu, Sreenidhi Iyengar Munimadugu, Paul Mitchell, Gerald Liew, Yanin Suwan, Jirayu Hong-amata, Sahil Thakur, Monisha E Nongipur, Tina Wong, Rahat Husain, Ng Si Rui, Yamon Syn, Phey Feng Lo, Nicholas Tan Yi Qiang, Shaista Hussain, Xiaofeng Lei, Zhi Da Soh, Marco Yu, Haslina Hamzah, Zizhou Wang, Yan Wang, Liangli Zhen, Xinxing Xu, Tien-Yin Wong, Tin Aung, Rachel S Chong, Yong Liu, Ching-Yu Cheng
Human-Computer Interaction
Calibrating LLM Judges for Human and AI Conversations
Maike Züfle, Patrícia Schmidtová, Vilém Zouhar et al. (+9 more)
Measuring how successful a conversation is remains difficult, even for humans judging spoken dialogue. We evaluate state-of-the-art LLMs as pointwise and pairwise judges of conversational success on CANDOR, finding pointwise scoring correlates moderately with human ratings, while pairwise comparison suffers from long transcripts and positional bias. Since this leaves judge scores incomparable across models, we propose a small anchor set and a calibration function that calibrates any judge onto a shared, interpretable scale. We further release the Voice Arena Goal
Dataset (VA), 200 task-oriented human-AI and human-
agent conversations with pairwise annotations, revealing a substantial gap between current judges and human-level discrimination. Using VA, we test whether CANDOR-fitted calibration transfers to human-AI conversations, finding it brings judges onto a shared scale despite never observing VA during fitting.
Read the full abstract ▾
All authors Maike Züfle, Patrícia Schmidtová, Vilém Zouhar, Shree Harsha Bokkahalli Satish, Erica Cooper, Nicholas Sanders, Shobhit Banga, Vaibhav Nalawade, Manmeet Kaur, Jan Niehues, Markus Müller, Ondřej Klejch
Artificial Intelligence
Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures
Ruoqi Guo, Yi Liu, Gelei Deng et al. (+6 more)
Detectors of
alignment failures screen deployed
language models and score
alignment benchmarks. Most are generative judges that spend a decoding pass on every criterion, and classifiers that read
token probabilities, such as Llama Guard, still score one fixed label per call. Jev, a model trained with reinforcement learning for calibrated decisions (RLCD), answers many typed questions about one input with calibrated probabilities in a single call. Whether it detects
alignment failures has not been measured. We present RLCDAlignBench, which
benchmarks Jev on ten
alignment failures: sycophancy, jailbreaks, deception,
prompt injection,
hallucination,
privacy violation, social bias, reward hacking, concealing uncertainty, and power seeking. It spans 44
benchmarks and five target models, labelled by each
benchmark's scorer and, on two, by humans. Many of these failures are relational, defined against a reference, such as the user's belief or an injected instruction, that the response alone does not reveal. Our key idea is therefore to vary what Jev is asked separately from what it sees: the question's wording and answer type on one side, the fields of the input on the other. A single generic question reaches a median AUROC of 0.886 zero-shot and beats supervised baselines on most
benchmarks. Question wording matters little, while context matters more, mostly through fields that encode the label. Jev matches the reference scorer's agreement with human labels, surfaces label defects in existing
benchmarks, and costs 63x less than LLM-judge scorers. Code and data: https://github.com/sumleo/RLCDAlignBench.
Read the full abstract ▾
All authors Ruoqi Guo, Yi Liu, Gelei Deng, Yuekang Li, Lida Zhao, Yutao Wu, Simin Chen, Ying Zhang, Leo Yu Zhang
Computation and Language
agentic-ger: terminology recovery in long-form speech using global context
Yanqiao Zhu, Wupeng Wang, Zhifu Gao et al. (+2 more)
Recent advances in
speech language models have improved automatic
speech recognition (ASR) for long-form audio. However, accurately and consistently transcribing domain-specific terminology remains challenging. Motivated by the world knowledge and contextual capability of large
language models (LLMs), we propose Agentic-GER, an LLM-based
agent for terminology correction in long-form
speech. The
agent uses global context from the full transcript to identify suspicious terms and resolve ambiguous hypotheses. It selectively re-transcribes the source
speech to check candidate corrections, and uses accepted edits to guide subsequent decisions. Experiments with four LLMs and two ASR systems on GigaSpeechBench show consistent terminology improvements in both Chinese and English, with and without thinking. On Chinese
speech, Agentic-GER achieves up to a 36.8% relative reduction in biased character error rate (B-CER) over the Whisper baseline.
Read the full abstract ▾
All authors Yanqiao Zhu, Wupeng Wang, Zhifu Gao, Xiangang Li, Xie Chen
Robotics
Coupled State-Space Modelling, Control, and Policy Distillation for Hybrid Rigid-Pneumatic Manipulators
Alan Royce Gabriel Samuel and Pulkit Verma
Hybrid manipulators combine motorized rigid joints with pressure-actuated origami segments. Published arms of this kind are controlled with decoupled per-DOF loops, and the cost of this approximation has not been quantified, because the coupled model needed to measure it has not been built. This paper derives such a model for a chain of $N$ alternating revolute joints and Kresling origami segments, including pneumatic chamber dynamics and crease hysteresis. Using the model, we measure the coupling directly and show that its strength varies joint by joint, and that decoupled control loses precisely on the strongly coupled joints while remaining competitive on the one nearly decoupled joint. Coupled model-based controllers track $2.5\times$ tighter than a decoupled PID baseline at lower torque. However, the model predictive controller (MPC) is too slow for real time, and model-free reinforcement learning stalls far below acceptable success rates on a strict settling metric. We therefore distill the MPC into a small neural policy with behavior cloning and DAgger. The distilled policy settles 93-94$\%$ of goals with zero collisions, within a few points of its teacher, and runs inside the 5 ms control step where the MPC does not. Where the teacher itself fails, we trace the failure to a limit cycle with the bellows' lightly damped mode, and we remove it by selecting goal postures holdable at low pressure.
Read the full abstract ▾
Robotics
Temperament Engineering: Designing Strategic Behavioural Diversity in Robot Swarms
Edmund R. Hunt
No two
robots are truly identical: calibration, battery state, sensor drift and wear give every swarm a distribution of behaviour rather than a single point, usually treated as an imperfection to be minimised. In animal collectives the reverse holds: consistent individual differences in behaviour ('temperament') are shaped by natural selection and often decisive for group performance. This perspective proposes 'temperament engineering', a bio-inspired framework that treats the swarm's distribution of temperaments, rather than the individual controller, as the design object. It borrows five evolutionarily validated axes of animal temperament (shyness-boldness, exploration-avoidance, activity, aggressiveness and sociability) as a design vocabulary, rendering each as a continuous control parameter $\tau \in [0,1]$ above the controller, realisable as a module threshold, a policy-conditioning vector in multi-
agent reinforcement learning, or a constraint on a foundation-model planner. A three-phase workflow maps mission success criteria onto relevant axes, plans the shape of the $\tau$ distribution, and tunes reaction norms governing how temperament responds to environmental cues. The payoff is greatest under decentralisation: where a central planner can reassign behaviour online, a temperament distribution is a planner output, but in a swarm without global knowledge it must be an offline, anticipatory design input. Behavioural and platform heterogeneity are thereby co-design variables, and I sketch tentative
robot-native axes (self-model plasticity, forcefulness, initiative and expressiveness) arising from features
robots have and animals do not. Engineered heterogeneity has been shown to outperform homogeneous swarms in tasks such as aggregation and exploration; establishing when, and how much, heterogeneity repays its cost is the work the field can now take forward.
Read the full abstract ▾
Computation and Language
Rufus-Air: An Open LLM Post-Training Recipe
Chia-Yuan Chang, Renyuan Cheng, Rui Feng et al. (+19 more)
Rufus-Air is an open and reproducible post-training recipe on GLM-4.5-Air-Base (106B-A12B), organized as a serial pipeline of eight stages: SFT,
Reasoning RL, Coding RL, Instruction-Following RL, General
Agent, Coding
Agent, Search
Agent, and RLHF. We document the data, reward design, infrastructure, stage order, and stagewise results needed to reproduce the recipe. Stages progress from basic to advanced capabilities and from hard, verifiable rewards to softer judge-based signals. Training builds on open-source components and public data, much of it used as released, without new human annotation or an in-house
distillation teacher. Our main findings are that (i) diverse, high-quality SFT establishes a strong capability floor; (ii) difficulty filtering keeps RL
prompts within a productive learning range; (iii) reward reliability provides a practical principle for ordering stages; and (iv) infrastructure and engineering choices are part of the recipe, not just an implementation detail. Rufus-Air improves over the official GLM-4.5-Air post-trained release and is competitive with similarly sized open models.
Read the full abstract ▾
All authors Chia-Yuan Chang, Renyuan Cheng, Rui Feng, Xiaotian Han, Yuan He, Hongye Jin, Linwei Li, Shiyang Li, Fenglin Liu, Xin Liu, Priyanka Nigam, Haoyang Wen, Zhenghao Xu, Zhuocheng Xu, Bing Yin, Qingyu Yin, Chao Zhang, Rongzhi Zhang, Zhihan Zhang, Zixuan Zhang, Zixuan Zhang, Tuo Zhao
Robotics
UCON: Uncertainty-aware Navigation with Historical Re-association in Dynamic Environments
Bing Sun, Yue Lin, Yongsheng Yuan et al. (+3 more)
Autonomous
navigation in dynamic environments is hindered by two fundamental challenges: perception instability and uncertainty-optimization mismatch. The former leads to identity switches and unreliable motion estimation, while the latter prevents principled incorporation of motion uncertainty into trajectory optimization. To address these challenges, we propose UCON, an uncertainty-aware
navigation algorithm in dynamic environments. For perception instability, we present a point-level historical re-association mechanism that leverages historical point cloud fragments to recover lost targets while maintaining identity continuity. Subsequently, a Kalman filter is employed to provide anisotropic motion state estimation and covariance propagation. To resolve the uncertainty-optimization mismatch, we transform predicted states and their covariances into uncertainty sectors, which are embedded as differentiable cost terms within a trajectory optimization framework. This achieves consistent uncertainty-aware dynamic obstacle avoidance while maintaining smoothness and feasibility. Extensive simulations and real-world experiments demonstrate that, while maintaining high computational efficiency, UCON achieves superior perception stability and robust
navigation performance in dynamic environments compared to state-of-the-art methods. The code will be open-sourced to facilitate further research.
Read the full abstract ▾
All authors Bing Sun, Yue Lin, Yongsheng Yuan, Yang Liu, Dong Wang, Huchuan Lu
Computation and Language
Controlling Backchannels in Streamable Full-duplex Models
Maike Züfle, Peter Polák, Sefik Emre Eskimez et al. (+3 more)
Backchannels, brief acknowledgements like "uh-huh" produced while the other party may still be talking, are central to natural conversation, but full-duplex spoken dialogue models rarely model them explicitly. We introduce a lightweight backchannel head that predicts, from a full-duplex model's own hidden states, when a backchannel should begin. Once this probability crosses a tunable threshold, a backchannel is force-decoded. Attached to both a 7B (PersonaPlex) and a 1B (F-Actor) model, it generalizes across scale. Probing confirms the hidden states anticipate real human timing, and generation evaluation shows more frequent, better-timed backchannels. Human raters judge the resulting backchannels on par with real ones.
Read the full abstract ▾
All authors Maike Züfle, Peter Polák, Sefik Emre Eskimez, Jan Niehues, Peter Bell, Ondřej Klejch
Robotics
Singularity Analysis for the Perspective-Four and Five-Line Problems
Jorge García Fontán, Abhilash Nayak, Sébastien Briot et al. (+1 more)
This paper deals with image-based visual servoing and pose estimation by observing four and five lines. Our main interest is to determine the relative configurations of the camera and the observed lines that lead to problems in control and stability. Since it is equivalent to finding the singularities of the corresponding Jacobian
matrix, we use tools from computational algebraic geometry to seek configurations such that all of its minors vanish simultaneously. By choosing a suitable basis for this
matrix, we revisit the problem in the case of three lines to show that one type of the singularities is when the camera lies on the hyperboloid of one sheet uniquely defined by the lines. This result is further exploited to prove that the one-dimensional singularities, if any, in the case of $n$ lines appear when the camera lies on the transversals to the observed lines. Thus, by forcing the transversals to be complex, we can avoid the aforementioned type of singularities in the case of four lines although the
algebra shows that there can always be up to 10 inevitable singular locations of the camera for the other type of singularity. For five lines, we find out that there are no singularities in the generic case. The singularities are also characterized for four and five lines with orthogonality and parallelism constraints. Furthermore, a visual servoing library is used to conduct some simulated experiments to substantiate the theoretical results. As expected, we observe problems in control in the vicinity of a singularity as well as increased errors in pose estimation.
Read the full abstract ▾
All authors Jorge García Fontán, Abhilash Nayak, Sébastien Briot, Mohab Safey El Din
Discrete Mathematics · Cross-listed from math.CO
The coarse Erdős-Pósa theorem
Sandra Albrechtsen, Marthe Bonamy, Romain Bourneuf et al. (+1 more)
We prove the coarse Erdős-Pósa
conjecture of Georgakopoulos and Papasoglu. Informally, any graph either contains many fat cycles that are pairwise far apart, or there is a small number of bounded radius balls that together hit all of them. To be more precise, if $G$ is a graph with no $q$-fat model of $k \cdot K_3$ for some $q, k \in \mathbb{N}$, then there is a set $X\subseteq V(G)$ of $\mathcal{O}(k\log k)$ vertices such that every $q$-fat model of $K_3$ in $G$ has distance $\mathcal{O}(q)$ from $X$. In another form more closely resembling Manning's
theorem that characterises quasi-trees: if $G$ is a graph with no $q$-fat model of $k \cdot K_3$ for some $q, k \in \mathbb{N}$, then $G$ is $\mathcal{O}(q)$-quasi-isometric to a graph $H$ that contains a set $X\subseteq V(H)$ of $\mathcal{O}(k\log k)$ vertices such that $H-X$ is a forest. Bootstrapping this result, we further prove that every graph with no $q$-fat model of $k \cdot K_3$ is quasi-isometric to a graph with no $k \cdot K_3$ minor, where the quasi-isometry can be chosen to only have additive distortion. This result also holds for $k = \infty$. We also obtain an Erdős-Pósa
theorem for long induced cycles that are far apart.
Read the full abstract ▾
All authors Sandra Albrechtsen, Marthe Bonamy, Romain Bourneuf, James Davies
Machine Learning
Neural Transport Nested Sampling
David Yallup and Will Handley
Sampling from Boltzmann distributions of molecular systems is an inference problem that has seen significant recent developments fuelled by advances in neural density estimation. We develop a novel sampling
algorithm, Neural Transport Nested Sampling (NTNS), which combines the classical strengths of nested sampling with modern neural flow-based methods. NTNS uses a flow matching velocity as the drift in a Metropolis–Hastings corrected Langevin kernel inside a nested sampling outer loop, requiring only evaluations of the target energy function and providing scalable estimation of the full partition function of high-dimensional particle systems. We
benchmark NTNS on challenging molecular sampling
benchmarks, scaling up to Lennard–Jones clusters of 55 interacting particles, where it reduces both interatomic distance and energy Wasserstein errors to reference MCMC by over an order of magnitude relative to the strongest neural baselines at lower wall-clock cost. To our knowledge, NTNS is also the first neural sampler to return a calibrated, temperature resolved partition function estimate at this scale, recovering the phase structure across temperature from a single run.
Read the full abstract ▾
Systems and Control
System Strength-Constrained Scheduling with Switchable Grid-Forming and Grid-Following Generation Resources
Jiaxin Wang, Fei Teng, Huanhai Xin et al. (+3 more)
Inverter-based resources (IBRs) are increasingly dominating modern power systems, posing significant challenges to cost-effectively maintain system strength for stability. At the same time, the operating behaviors of IBRs are software-defined, including both their steady-state power outputs and control modes, e.g. grid-forming (GFM) and grid-following (GFL). Such flexibility has not been fully explored to efficiently operate future power systems. This paper develops a novel framework that simultaneously optimizes IBR operating behaviors and ensures adequate system strength. A comprehensive solution is provided to integrate system strength constraints into scheduling models, despite their inherent strong non-convexities. We derive a rigorous linear-
matrix-inequality (LMI) reformulation of the system strength constraint, effectively addressing non-explicit formulations and dimension variation issues caused by GFM/GFL mode switching of IBRs. Then, we equivalently convert the original non-convex implicit system strength-constrained scheduling problem into an explicit mixed-integer semi-definite programming (MISDP) problem by incorporating the reformulated system strength constraint along with other operational constraints. We further provide a Rayleigh Cut method, which is compatible with standard mixed-integer linear programming (MILP) solvers, to solve this system strength-constrained scheduling problem. Case studies on a modified IEEE 118-bus system and a practical Jiangsu power system demonstrate the performance of the proposed methods.
Read the full abstract ▾
All authors Jiaxin Wang, Fei Teng, Huanhai Xin, Jing Dai, Tomislav Capuder, Ning Zhang
Computation and Language
Large Language Models for Programming: Actually Fixing or Reimplementing Incorrect Code?
Alexandru Stefan Stoica, Traian Rebedea and Marian Cristian Mihaescu
Recent studies have shown that Large
Language Models can effectively solve problems and fix bugs in diverse programming environments, including competitive programming. Existing approaches primarily evaluate LLM performance in problem solving or bug fixing independently, but do not explore the relationship between these two capabilities. This work focuses on determining how much the LLM deviates from a buggy solution to fix the bug compared to a human-written patch, and if there is a bias towards generating entirely new solutions. We construct a
dataset with all the submissions ($\sim$ 3000) from a couple of users from Codeforces, and we match each buggy submission with its corresponding human fix. By using the similarity between the buggy solution and the human fix as a baseline, we evaluate the quality of LLM-generated bug fixes on 3 OpenAI GPT models (gpt-5-nano, gpt-5-mini, gpt-5.1). We check if the generated solutions solve the problem by using the Codeforces-R1
dataset, an openly available
dataset that has tests generated with the DeepSeek-R1 model. Our findings suggest that LLMs tend to modify more lines than necessary compared to human fixes and, in some cases, generate entirely new solutions. We also observe that LLMs solve more problems correctly when allowed to generate solutions from scratch rather than patch buggy submissions, even when those submissions are close to the human patch. This has important implications for the design of AI-assisted programming tools, particularly in supporting user debugging processes and promoting incremental problem-solving strategies rather than solution replacement.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
Machine Unlearning for Gibbs Supervised Learning Algorithms
Yaiza Bermudez, Samir M. Perlaza and Iñaki Esnaola
In this paper, a method for achieving exact unlearning for Gibbs supervised learning
algorithms is proposed using a variational formulation inspired by empirical risk minimization subject to relative
entropy regularization (ERM-RER). Such a method consists of maximizing the expected empirical risk over the
dataset to be unlearned subject to a regularization by relative
entropy with respect to the original
algorithm. The optimization variable is a probability measure on the models; and the solution is another Gibbs probability measure that represents a new Gibbs supervised learning
algorithm. The method guarantees exact unlearning in the sense that the new Gibbs
algorithm coincides in distribution with the
algorithm that would have been obtained by retraining from scratch on the
dataset to be retained. As a byproduct, a framework for reweighting data points in ERM-RER by strategically choosing both the reference measure and the regularization factor is obtained. In this framework, exact unlearning is the special case in which zero-weight is assigned to the contribution of the data points to be unlearned. More generally, depending on the choice of certain parameters, data points can be up-weighted or down-weighted in ERM-RER problems for particular purposes, e.g., controlling the generalization error of Gibbs
algorithms. This paves the way for new constructive or
adversarial views on classical reweighting data points in ERM-RER.
Read the full abstract ▾
Robotics
WRAP: Fixtureless Wrench-aware Multi-Robot Assembly Planning
Valentin N. Hartmann, Huang Su, Yijiang Huang et al. (+1 more)
Assembly using
robots often requires specially designed fixtures, or relies on top-down only assembly strategies. Using multiple
robots, we can avoid using fixtures and make robotic assembly more flexible. Planning assembly sequences for multiple
robots is challenging due to the high number of possible task assignments and orders. In addition, we need to reason over forces that occur during the assembly process, e.g., to decide if multiple
robots are required for support, or if external support such as a table should be used. We present Wrap, a multi-
robot assembly planner for multi-part assemblies, given the inter-part ordering-dependencies, the part meshes, and their initial state. We formulate a linear program to reason about valid grasps for supporting the forces that occur during assembly. The search leverages the assembly sequence, and greedily finds a feasible solution per assembly step by computing a heuristic via a cheap backwards search, and using the heuristic in the more expensive forward search. We then solve the multi-
robot, multi-goal motion planning problem, and for execution, we split the plan into contact-rich assembly skills, and free space motion. We
benchmark the planner on a variety of multi-part assemblies, and apply the planner to groups of
robots differing in size and kinematics. We validate the work both in a physics simulation, and in real.
Videos and code are available at https://www.vhartmann.com/wrap.
Read the full abstract ▾
All authors Valentin N. Hartmann, Huang Su, Yijiang Huang, Stelian Coros
Emerging Technologies · Cross-listed from quant-ph
Evaluating the Effect of the Order of Optimization Passes in Quantum Circuit Optimization
Xiao-Ting Michelle To, Nils Quetschlich, Amr Elsharkawy et al. (+3 more)
Quantum circuit optimization is critical for mitigating the noise inherent in current
quantum hardware.
Quantum compilers typically sequentially apply multiple optimizations (also called “optimization passes”) to improve the
circuit. The impact of the order in which these passes are executed has yet been largely unexplored. This paper investigates the significance of the order of optimization passes within
quantum circuit compilation, specifically analyzing interactions between different optimization methods and quantifying their mutual influences. Using Qiskit's compiler, we systematically evaluate pairwise combinations of 16 selected optimization passes, measuring
circuit depth and gate count across various
benchmark circuits. Our findings indicate dependencies between certain optimization passes, demonstrating that the order of the passes affects the optimization quality. In some cases, the worse performing sequence can be corrected through repeated pass application. %such that they are as good as the best performing one by extending the sequence. Experiments on multi-pass sequences show that more than two optimization passes may have an impact on each other but that this always links to the previously found pairwise effects. We observe that it is important to initially choose the best order of optimization passes to get the best possible optimization for the given
circuit. The experiments reveal some factors which are important to choose the best, or at least a good, order; among those, the resulting optimization sequence depends the most on the native gate set.
Read the full abstract ▾
All authors Xiao-Ting Michelle To, Nils Quetschlich, Amr Elsharkawy, Martin Schulz, Robert Wille, Dieter Kranzlmüller
Machine Learning · Cross-listed from eess.AS
Transcript-Supervised Post-Training of Generative Speech Enhancement on Real Recordings via Reinforce Adjoint Matching
Julius Richter, Christoph Boeddeker, Yoshiki Masuyama et al. (+4 more)
We adapt Reinforce Adjoint Matching (RAM), a reward-based post-training method, to generative
speech enhancement (SE). Starting from a pretrained SE model, RAM tilts the model's conditional distribution toward outputs with higher reward. During training, the current model generates enhanced
speech on-policy, evaluates each generated endpoint with a potentially non-differentiable reward, and analytically re-noises the endpoint to construct inputs for a reward-guided regression objective. This enables post-training directly on real recordings using weak supervision, such as text transcripts, without requiring paired clean
speech targets or reward gradients. We investigate word error rate (WER)-based post-training and whether recognition performance can be improved without compromising perceptual
speech quality. Experiments on real CHiME-4 recordings reduce WER by 5.08 percentage points relative to pretrained FlowSE without reducing any of the reported non-intrusive
speech quality metrics. A subjective listening test at the default reward scale finds no statistically significant preference between the post-trained and pretrained models.
Read the full abstract ▾
All authors Julius Richter, Christoph Boeddeker, Yoshiki Masuyama, Kohei Saijo, Dominik Klement, Gordon Wichern, Jonathan Le Roux
Artificial Intelligence
RD-JEPA: Predictive latent pretraining for few-trajectory transfer across reaction–diffusion equations
Chenhao Si and Ming Yan
Learning surrogates for time-dependent partial differential equations often requires a new simulation corpus when the governing operator changes. We introduce RD-JEPA, a joint-
embedding predictive architecture for self-supervised pretraining on reaction-
diffusion trajectories. A single model is pretrained on five parameterized systems and then adapted to three held-out systems whose reaction operators and trajectories are excluded from pretraining. Using one, five, or ten complete trajectories from a held-out system, RD-JEPA achieves lower mean relative discrete $\ell^2$ field error and mean absolute spatial first-difference error than five supervised surrogate baselines, an independently trained control that removes the trajectory-dependent predictive latent pathway, and an architecture-matched model trained from scratch. Within the evaluated equations, output resolution, forecast horizons, and choices of adaptation trajectories, the results indicate that prediction of future-state representations can support data-efficient adaptation across related reaction-
diffusion systems.
Read the full abstract ▾
Distributed Computing
Resource-Aware Model Selection for Scalable Indoor Localization on HPC Platforms
Fukuharu Tanaka, Hamada Rizk, Moustafa Youssef et al. (+1 more)
Large-scale indoor localization is increasingly needed in campuses, smart buildings, factories, and digital-twin infrastructures, where wireless conditions, access-point deployments, and spatial layouts evolve over time. Such systems must be accurate, extendable, and maintainable, allowing new buildings, floors, rooms, and service areas to be added without retraining a monolithic model. Modular learning-based localization supports this goal by assigning independent models to buildings, floors, and fine-grained spatial regions. However, this extendability introduces a high-performance inference challenge: each query may require selecting and executing among hundreds or thousands of local models, making exhaustive inference costly in computation, accelerator
memory residency, model loading, and scheduling. This paper presents a resource-aware modular inference framework for WiFi fingerprint-based indoor localization on high-performance and distributed computing platforms. The framework organizes local autoencoder models into a building-floor-spot hierarchy and formulates localization as model selection over a large pretrained model ensemble. To reduce inference cost under resource constraints, we introduce two lightweight execution-
pruning strategies: Hierarchical Candidate
Pruning, which performs coarse-to-fine model selection, and Trajectory-Aware
Pruning, which uses temporal locality in user movement to restrict inference to spatially plausible neighboring models. Experiments on a real-world
dataset demonstrate that the proposed framework delivers scalable inference without sacrificing localization quality. Compared with exhaustive evaluation over 735 spot models, Hierarchical Candidate
Pruning requires only 67 model evaluations, while Trajectory-Aware
Pruning reduces this number to just 10, cutting model executions by 98.6%.
Read the full abstract ▾
All authors Fukuharu Tanaka, Hamada Rizk, Moustafa Youssef, Hirozumi Yamaguchi
Machine Learning
ICE: Task-Aligned Clifford Latent Fields for Multimodal Graph Foundation Models
Xunkai Li, Xu Wang, Yinlin Zhu et al. (+4 more)
Multimodal attributed graphs connect entities, visual content,
language, and observed relations. Learning one foundation across such graphs requires more than compressing each node into a fused Euclidean vector. The representation must preserve entity semantics, construct interaction state from graph neighborhoods, and expose that state to prediction units with different geometry. Our empirical study shows why these requirements are inseparable. Higher-grade channels recover pair relations across the foundation graphs, specialized queries reveal information hidden by a generic readout, and rigid blade isolation removes cross-grade capacity. We therefore introduce ICE (Interaction-aware Clifford Encoder), a
multimodal graph foundation model built on a node-indexed Clifford latent field.
Topology, text, and images enter explicit Cl(3) addresses. Edge-aware
geometric products transform these directions into scalar, bivector, and trivector relations over observed neighborhoods. A protected Grade-1 route preserves entity semantics, while the full grade and depth bank remains available to fresh node and link heads. We establish exact cross-grade reachability, node-permutation equivariance, and a bound on the task residual around the semantic score. Experiments span one shared foundation over eleven graphs, six node-classification
datasets, three link-prediction
datasets, and matched few-shot tasks. ICE ranks first in all 30 reported supervised and few-shot comparisons. Core removals reduce every task summary, and mechanism controls connect the gains to higher-order transport, retained multidepth structure, semantic protection, and direct field access.
Read the full abstract ▾
All authors Xunkai Li, Xu Wang, Yinlin Zhu, Xiong Yongfu, Yi Liu, Rong-Hua Li, Guoren Wang
Computation and Language
Baseline Shape Decides the Verdict: A Controlled Re-Examination of Ternary Language Models at 60K Parameters
Gautam Veldanda
Ternary (1.58-bit) weights are attractive for microcontroller-class
language models, but the sub-1M-parameter regime rests mainly on isolated, single-seed comparisons. One prominent example reports that a routed ternary block (convolution, diagonal SSM and sparse
attention mixed by a per-
token router) beats a parameter-matched full-precision
transformer by 22% at 60K parameters, attributing this to inductive bias. We re-run it under one fixed recipe, three seeds per
cell, 98 byte-level runs on one laptop. (i) Baseline shape dominates: at a 16M-byte budget, param-matched
transformers span 22.6% in validation loss purely by depth/width choice - far more than any architecture effect we measure there - and the best-shaped
transformer ties the routed model, so the published margin is at least partly a baseline-shape effect; the ordering of shapes reverses with budget, so no single fixed shape can be trusted. (ii) At 130M bytes the routed model does win, by 22.2-24.0% over the three
transformer shapes we evaluate there - but a plain gated diagonal-SSM block beats it by a further 9.1%, and the routed model's own router puts most of its weight on its recurrent pathway, so the gain does not require routing. (iii) The ternary penalty differs by architecture at the larger budget (+5.3% best
transformer vs. +19.5% routed, +28.1% gated SSM), but we cannot attribute that to architecture alone: our
transformers keep learned positional
embeddings in full precision, 11-22% of their parameters, so they are less quantized than the models they are compared with. (iv) A 90/10 full-precision-then-ternary schedule beats all-ternary training, but only at a stage-2 learning rate about 10x the pretraining peak; at a conventional fine-tuning rate it looks 15.3% worse, reversing the conclusion. The from-scratch baseline was not itself learning-rate tuned, which bounds (iii) and (iv). Code and run logs released.
Read the full abstract ▾
Artificial Intelligence
Wearable ECG Quality Assessment: A Deep Learning and Ambulatory Context-Awareness Approach
Xiaopeng Mao, Marike Weisbjerg and Sadasivan Puthusserypady
This paper presents and evaluates a Deep Learning-based (DL-based) Signal Quality Assessment (SQA) model to distinguish between clean and noisy ambulatory Electrocardiograms (ECG). The model is trained on Copenhagen Center for Health Technology-Contextualized Arrhythmia Database (CACHET-CADB), which, to the best of our knowledge, is the first ambulatory ECG database with both physical and patient-reported contextual data. The model shows stable performance on different databases such as MIT-databases and the latest PyhsioNet/Cinc Challenge 2021 databases. Subsequently, the paper demonstrates how complicated ECG noise can be investigated by the SQA model and the physical contextual data.
Read the full abstract ▾
Distributed Computing
Concurrent Split Learning Through Stable Client Clustering
Mohammad Kohankhaki, Valentin Rentschler and Anke Schmeink
Training with a fixed global batch limits how many distributed clients can provide examples in any one step. We examine a way to use additional server workers without increasing the batch processed by an individual workload. Global Clustered Parallel Split Learning (GCPSL) assigns clients to fixed clusters, executes a Parallel Split Learning with Global Sampling (GPSL) workload for each cluster concurrently, and periodically fuses the client and server model segments. In simulations with 256 logical clients, dividing the population across more workloads improves direct data participation, while smaller clusters can incur an accuracy cost. A four-H100 implementation of label-aware GCPSL reaches 85% CIFAR-10 validation accuracy in $6.13 \pm 0.15$ minutes over three matched runs, versus $19.09 \pm 0.45$ minutes when the same workloads are serialized. Within the four-GPU allocation, size-balanced and random fixed affiliations reach the target in similar mean times (5.70 and 5.66 minutes); size balancing increases direct participation by 3.25 percentage points. These measurements characterize a trade-off among execution concurrency, assignment information, participation, and accuracy for stable-client split learning.
Read the full abstract ▾
Robotics
RACaP: Agentic Reasoning, Acting, and Coding as Policies for Evolvable Robot Learning
Zexi Li, Yehang Zhang, Haojian Huang et al. (+10 more)
General-purpose
robot agents must learn from experience, transfer to new tasks, and act efficiently. Code as Policies (CaP) methods generate and repair programs at runtime, incurring latency and entangling reusable mechanisms with task-specific decisions. We introduce RACaP, an agentic framework that moves coding to
evolution and uses a
Reasoning-and-Acting (ReAct) loop to call frozen, typed Policy APIs at deployment. A two-phase strategy combines capability curriculum learning with autonomous self-
evolution to improve the APIs, the ReAct harness, and experience
memory. The APIs encode reusable physical mechanisms while exposing arguments for runtime adaptation. ReAct combines task-specific working
memory, long-term experience
memory, and visual feedback to select actions, verify outcomes, and recover from failures without modifying source code. RACaP achieves 54.4% success on LIBERO-90, 45.0% on zero-shot LIBERO-PRO, and 46.0% on LIBERO-Long, compared with at most 4.0% for CaP baselines on long-horizon tasks. On LIBERO-PRO, it achieves 2.5 times the success rate of CaP baselines and a 1.9-fold speedup in median policy time. For efficient on-
robot deployment, rejection-sampled fine-tuning distills GPT-5.6 ReAct decisions into Qwen3-VL-8B-Instruct, yielding a 13.2-fold per-decision inference speedup and reducing repeated physical calls from 16 to 4. These results show that separating reusable code from runtime decisions supports continued
evolution, effective transfer, and efficient long-horizon control.
Read the full abstract ▾
All authors Zexi Li, Yehang Zhang, Haojian Huang, Bohan Zhou, Wenqian Li, Chenxu Wang, Yifan Chang, Yangkai Wei, Tianyi Zhang, Ying-Cong Chen, Kaiwen Zhou, Yinchuan Li, James Cheng