Information Theory
Nonlinear fixed-distance codes via real lifts of moment configurations
Sergey Yekhanin
Let $A_q(n,d)$ denote the largest size of a code of length $n$ and minimum Hamming distance $d$ over an alphabet of $q$ symbols. For fixed $q\ge2$ and $d\ge4$ we construct codes with redundancy $n-\log_q A_q(n,d)\le(d-3)\log_q n+O(\sqrt{\log n})$ for all large $n$. No algebraic structure is imposed on the alphabet, and the codes are not linear. For $d=4$ and $d=5$ the coefficient of $\log_q n$ matches the Hamming bound, so the redundancy is determined up to lower-order terms. At distance four the codes are provably better than every linear code: by the
polynomial-method bound for cap sets, $\mathbb{F}_q$-linear codes with $q>2$ require a strictly larger coefficient in front of $\log_q n$. The construction imposes moment checksums over an auxiliary finite field, as BCH codes do, but one fewer than the distance would normally require. The affine-line
theorem from prior work describes the dependencies left by these checks. We exclude them by placing the code positions inside a specially structured subset of the field, built from Behrend's sphere construction with the help of algebraic number theory.
Read the full abstract ▾
Networking
An Experimental Study on the Functional Correctness of Network Device Configurations Produced by Large Language Models
Anastasios C. Politis
This paper presents a preliminary study on the efficacy of network device configuration produced by Large
Language Models (LLMs). Currently, the study focuses on routing protocol configurations in a predefined small internetwork with Cisco-based routing devices. The capability of three freely available LLMs with standard capabilities (i.e., with no enhanced features) to produce effective setups is investigated.
Prompt engineering methods are excluded in order to assess the "first-response" configurations of the models under consideration. The assessment method is based on the contents of the resulting routing table, aiming at measuring the device functional correctness. For that purpose, the Jaccard index is used to indicate the percentage of correct network prefixes contained in the routing table constructed by the model-based configuration commands. The work provides insights on the maturity and limitations of modern LLMs on aiding network administrators with network device configurations in real deployments.
Read the full abstract ▾
Robotics
Complementary Future Token Pruning for World Action Models
Baekseung Kim, Junhoo Lee, Sohyeon Hong et al. (+5 more)
World action models (WAMs) jointly predict future visual states and
robot actions, but processing dense future-frame
tokens incurs substantial inference latency. We propose CF-Prune, a training-free framework for
pruning future-frame
tokens in pretrained WAMs. Our key insight is that future visual predictions support action generation and therefore need not preserve every visual detail required for high-fidelity
video synthesis. CF-Prune combines instruction and action
attention to identify task-relevant
tokens during the initial denoising forward pass, even when future-frame and action representations remain highly noisy. An
entropy-based phase identification mechanism further retains dense computation during precision phases to mitigate
pruning-induced performance degradation. Experiments on RoboLab, RoboCasa, and real-world manipulation tasks demonstrate consistent inference speedups. At a 35%
pruning ratio, CF-Prune achieves average speedups of 1.19-1.27x while improving task success rates. At a 50%
pruning ratio, it achieves 1.29-1.33x average speedups on both simulation
benchmarks, with overall success rates within 1.0 percentage point of the baseline.
Read the full abstract ▾
All authors Baekseung Kim, Junhoo Lee, Sohyeon Hong, Suhyun Jeon, Minkyu Kim, Seungyeon Kim, Donghoon Han, Nojun Kwak
Artificial Intelligence
Neurosymbolic Learning of Interpretable World Models
Riccardo Andreoni, Massimiliano Ronzani, Chiara Ghidini et al. (+2 more)
World models aim to learn compact representations of an environment from observations, enabling
agents to predict future states and plan their behaviour. However, most existing approaches learn black-box representations, with limited ability to incorporate prior knowledge about the world. We introduce Concept-Grounded World Models (CGWMs), a neurosymbolic world model design that instead learns interpretable concept representations. We learn these concepts from observations using explicit and complete knowledge, expressed in temporal logic, that specifies the valid world states and the temporal relations governing their dynamics. Furthermore, we directly use this knowledge by formulating planning as differentiable
reasoning, optimising the
agent's actions by gradient ascent to satisfy a goal. We experimentally compare CGWM with a purely neural baseline and a neurosymbolic baseline on two game environments. We find that CGWMs ground concepts much more accurately, even over long horizons, resulting in significantly more robust planning both in and out of distribution.
Read the full abstract ▾
All authors Riccardo Andreoni, Massimiliano Ronzani, Chiara Ghidini, Alessandro Daniele, Emile van Krieken
Computation and Language
AtomSearch: Evidence-Grounded Tree Search for Agent Skill Optimization
Jia Tong, Senyou Deng, Min Peng et al. (+1 more)
Agent skills adapt frozen models through editable external instructions. Revising several rules at once makes changes difficult to inspect, while judging each local edit only by its immediate score can discard useful intermediate states. We introduce AtomSearch, which keeps revision actions local while using subsequent skill states to guide search. Contrastive atomic editing links each primitive rule edit to failed and successful executions, a behavioral hypothesis, and an intended scope. Skill-State Tree Search (STS) evaluates short edit compositions and selectively retains them as executable states that can be revisited and extended. Outcome
memory supplies later proposals with observed repair and regression statistics. We evaluate AtomSearch across four tasks and five target models. With deepseek-v4-flash, it exceeds SkillOpt on three of four tasks, including a 9.68-percentage-point gain on LiveMathematicianBench, and SkillOpt's final skills contain 2.3-19.7 times as many characters. In 67% of completed searches, the best validation state passes through an ancestor that was not highest-scoring at its depth. These results show how local rule edits can support the exploration of useful revision paths and yield compact skills, with additional offline evaluations used to explore alternative states.
Read the full abstract ▾
All authors Jia Tong, Senyou Deng, Min Peng, Jianfeng Pan
Artificial Intelligence
When Protection Overrides Consequences: Understanding Protection Mode in Large Language Model Decision-Making
Yuanfan Li, Junyi Chen, Qi Zhou et al. (+3 more)
Frontier
language models excel at complex tasks yet may prioritize protection over larger physical consequences in simple, urgent decisions. GPT-5.6 Sol, for example, moves a girl playing in shallow water before retrieving a submerged camera. We call this Protection Mode and study it with ProtectionBench: 285
prompts, 34 physical families, and nine models. At lowest effort, at least one of four responses prioritizes the subject on 34.74% of Sol
prompts and over 83% of MiniMax M3 and Qwen3.5-27B
prompts; none of four independent human raters does so. Controls show that choices usually track physical risk. We elicit both risks before requesting an action. Some models assess risk incorrectly; others state the correct ordering but still choose the subject. Qwen3.5-27B with thinking shows 100% correct risk ordering but 57.81% subject choice among eligible conversations on eight selected scenes.
Attention audits find no stable reduction in
attention to relevant facts; removing the stated risk direction reduces object-first choice in dots3-note-prev but not detectably in Qwen3.5-27B. Adding a general "people or animals before property" rule increases subject choice by 19-38 percentage points, whereas factual reminders favor the object by 0.7-5.2 points. Removing naturally generated versions of that rule lowers subject choice by 10-15 points. We also examine whether post-training introduces this pattern. Base models already show Protection Mode; post-training changes justifications more than choices.
Read the full abstract ▾
All authors Yuanfan Li, Junyi Chen, Qi Zhou, Rui Yang, ZhangLiujie, Weihang Chen
Cryptography and Security
Quiet Triggers, Loud Footprints: A Tri-Space Measurement Study of Backdoor Stealthiness
Behrad Tajalli, Henk Berendsen, Xiaoyun Xu et al. (+1 more)
Backdoor attacks on deep neural networks are commonly evaluated by attack success rate and benign accuracy, yet their stealthiness remains inconsistently defined and measured. Existing work often studies only one observable aspect of stealthiness, such as trigger imperceptibility, feature-space separability, parameter-space concentration, or evasion of particular defenses. This creates a fragmented picture: an attack may appear stealthy under one metric while leaving conspicuous footprints elsewhere. This paper presents a tri-space measurement study of backdoor stealthiness in image classification. We distinguish latent stealthiness—the ideal but unobservable difficulty of distinguishing a backdoored system from a benign one—from measurable footprints in three spaces: input, feature, and parameter space. Under this framework, we evaluate representative backdoor attacks across four
datasets and three model architectures using a broad suite of footprint metrics. Our results show that stealthiness is not monolithic: attacks that are quiet in one space are often loud in another, and existing attacks rarely achieve consistently small footprints across all three spaces. We further analyze agreement and disagreement among stealthiness metrics and study how footprint measurements interact with attack success rate. Based on observed blind spots in existing measurements, we introduce two diagnostic metrics: Class-Specific Davies–Bouldin Index (CDBI), which captures class-conditional feature overlap, and TAC–UCLC Product (TUP), which identifies channels that are both trigger-responsive and downstream influential. These metrics are intended to augment, not replace, the broader measurement suite. Finally, we provide practical guidance for future stealthiness evaluations.
Read the full abstract ▾
All authors Behrad Tajalli, Henk Berendsen, Xiaoyun Xu, Stjepan Picek
Machine Learning
Learning Graph Energies for Finite-Time Generation
Amartya Banerjee, Xingyu Xu, Caroline Moosmüller et al. (+1 more)
Energy-based models can represent distributions over discrete structures such as molecular graphs, but an energy that is accurate at
equilibrium need not yield accurate samples when the sampler stops after a fixed number of steps. We introduce finite-horizon energy learning, which adapts the acceptance energy of a Metropolis–Hastings sampler to the distribution it returns after a prescribed number of steps, with initialization, proposals, and annealing schedule held fixed. For graph generation, a frozen pretrained model supplies initialization and proposals, and a learned energy governs acceptance. A training-only discriminator scores completed samples, and coupled continuations of the accepted and rejected branches of a proposal give an acceptance-gradient
estimator that is unbiased for a fixed discriminator under stated conditions, without equilibrated negative samples or differentiation through discrete states. Generation uses the learned energy in the original single-trajectory sampler, without discriminator evaluations or reranking. On twelve pairwise binary targets with exactly evaluated terminal laws, learned energies have lower median terminal total variation than the
equilibrium-correct energy in every tested short-horizon setting, and than its numerically tuned scalar multiple in most settings. On MOSES, a learned two-coefficient combination of pretrained Graph Energy Matching (GEM) potentials lowers FCD by 3.7–10.5% relative to scale-calibrated GEM at matched sampling steps, with validity gains at the shortest budget and a sub-point validity trade-off at higher budgets.
Read the full abstract ▾
All authors Amartya Banerjee, Xingyu Xu, Caroline Moosmüller, Harlin Lee
Computation and Language
Does Machine Translation Retain Media Bias?
Silvia V. Gargova, Tim Menzner and Jochen L. Leidner
Within the most recent two decades, machine translation (MT) has been advanced from a research area to a mature, deployed technology for prose text and most
language pairs. However,
language has different dimensions of meaning, and the alluded progress has primarily been demonstrated for propositional meaning. In this small exploratory study, we investigate whether one type of affective meaning, namely different types of linguistically expressed media bias, are retained under automatic translation for two
language pairs, English and German as the source
languages, and Bulgarian as the target
language. We evaluate four state-of-the-art translation methods to answer the question whether and to what degree a loss of non-neutral
language (specifically, 27 types of media bias) can occur as a result of applying MT. Our empirical findings are consistent with the claim that MT does not fully retain existing news bias of its input source text, but also may add extra bias of its own. To the best of our knowledge, this is the first experimental study of MT media bias retention.
Read the full abstract ▾
Logic in Computer Science
Finite Satisfiability of Two-Variable Logic with Arbitrarily Many Successors
Artur Jeż, Jakub Michaliszyn and Piotr Witkowski
We study finite satisfiability of two-variable first-order logic over structures equipped with an arbitrary finite number of independent successor relations of linear orders. The number of successor relations is part of the input, and the vocabulary may contain further unrestricted unary and binary relations. We prove decidability in deterministic doubly exponential space together with a triply exponential bound on the size of a smallest finite model. This settles the unrestricted finite case beyond two successors.
Read the full abstract ▾
Machine Learning
MorphingNet: Symbolic Regression Where the Network Is the Formula
Jincheng Gao, Jiahe Yi and Shuo Sun
We introduce MorphingNet, a network for symbolic regression (SR) whose units change their function continuously. Instead of searching over expressions built from a fixed operator library, MorphingNet trains the form of each function as a parameter, so SR becomes one continuous optimization problem. Its units are either pole-free rational functions or complex exponential–logarithm functions, which move between exponentials, sinusoids, damped oscillations, power laws and logarithms as their parameters change. The network is a readable formula at every step of training, and no operator library is needed to train it; a structure-recovery step afterwards rewrites the trained formula into short elementary expressions. Training is dense linear
algebra, so it is GPU-friendly and scales to large data. MorphingNet achieves state-of-the-art accuracy on SRBench, recovers most generating formulas on synthetic
benchmarks, and on large data is up to two orders of magnitude faster than the strongest search method. By turning the search for a formula into the training of a network, MorphingNet offers a new paradigm for SR and for scientific discovery from data.
Read the full abstract ▾
Logic in Computer Science
A Non-Dichotomy for CSPs of Stable $\omega$-Categorical Structures
Manuel Bodirsky, David Bradley-Williams, Ehud Hrushovski et al. (+1 more)
We construct countable, stable, $\omega$-categorical structures with at most two binary relations whose CSPs exhibit three complexity regimes: NP-complete, decidable but not in NP, and undecidable. The templates arise from a controlled Hrushovski construction of stable $\omega$-categorical graphs $M_\alpha$ for suitable irrational parameters $\alpha>1$. Some of these graphs have NP-complete CSPs. Expanding the graphs $M_\alpha$ by the non-edge relation turns age membership into a restriction of the CSP. For every time-constructible bound $t$, there is such an expansion whose CSP is decidable but not in DTIME$(t)$. For an explicit parameter $\alpha$, the restriction to complete instances belongs to $\mathrm{coNP}$ and the full CSP belongs to $\Sigma_2^{\mathrm P}$. Separating the ages of the $M_\alpha$ using graphs with large girth and prescribed density yields $2^{\aleph_0}$ distinct CSPs of these expansions, all but countably many of which are undecidable.
Read the full abstract ▾
All authors Manuel Bodirsky, David Bradley-Williams, Ehud Hrushovski, Christoph Spiess
Computation and Language
To Reason but Not to Stop: Understanding and Recovering Pruned Large Reasoning Models
Minh-Anh Nguyen, Nguyen T. Ha Lan, Xiyan Fu et al. (+2 more)
Weight
pruning can degrade the accuracy of large
reasoning models (LRMs), yet it remains unclear whether it damages
reasoning itself. We find that much of this degradation stems from a failure to stop rather than to reason. As sparsity increases, pruned LRMs increasingly fail to terminate within the
token budget, often after the correct answer has appeared in their
reasoning, instead falling into repetitive loops, even though they still recognize where the dense model would stop. We further find that the hidden-state difference between terminating and looping continuations is consistent across pruned checkpoints, suggesting a shared direction associated with committing to an answer. Building on this, we propose Termination-Guided Activation Steering (TGAS), a training-free method that adds this direction to the residual stream at inference time. Across six LRMs, three
pruning pipelines, and math and code
benchmarks, TGAS improves termination and overall accuracy while reducing repetitive
reasoning and generation length, showing that this failure is actionable.
Read the full abstract ▾
All authors Minh-Anh Nguyen, Nguyen T. Ha Lan, Xiyan Fu, Dung D. Le, Wei Lu
Computer Vision
Instruction Mining From Images: Constructing a Synthetic Dataset for Multimodal Learning ILSP DCVLR Competition Submission
Eleni E. Kasoura, Dimitrios Damianos, Georgios Paraskevopoulos et al. (+1 more)
This work presents a compact and reproducible pipeline for synthesizing and curating image-based instruction-response pairs for DCVLR. We draw from the Cauldron collection and use Magpie-style instruction and response synthesis with Qwen2.5-VL-7B Instruct to create concise, image-conditioned instruction pairs. The pipeline consists of instruction synthesis, conditioned on input images and controlled via a system
prompt, sanitization, tagging, and filtering of the instructions based on the score obtained by a reward model (DeBERTa-v3). We retain samples with positive scores to maximize the quality of the generated instructions. We observe that score distributions have a median and mean reward score of ~ 1.53 and ~ 1.75 respectively, indicating that most generated instructions are of good quality. The resulting
dataset contains diverse instructions in the math, spatial, and social
reasoning domains.
Read the full abstract ▾
All authors Eleni E. Kasoura, Dimitrios Damianos, Georgios Paraskevopoulos, Vassilios Katsouros
Computer Vision
SAM3RL: Memory Control via Reinforcement Learning for Visual Object Tracking
Tomáš Čížek, Matej Straka, Illia Volkov et al. (+5 more)
Segment Anything Model 3 (SAM 3) is a foundation model for image and
video segmentation that sets the state of the art in visual object tracking. Its tracker, inherited from SAM 2, stores information from past frames in a
memory bank, managed by a simple First-In-First-Out rule, allowing temporal consistency in complex
videos. Several recent methods improve SAM 2 with hand-crafted
memory update rules, each targeting a specific failure mode, such as distractors, occlusions, or object motion. However, their gains transfer only partially to the stronger SAM 3 backbone. We instead present a more general, data-driven approach that frames
memory control as a sequential decision-making task. SAM3RL is an extension of the SAM 3 tracker with a lightweight
memory controller, trained by reinforcement learning, that decides which frames enter the
memory bank in order to maximize tracking performance. SAM3RL sets a new state of the art on 10 of 12 tracking and
video object segmentation
benchmarks, outperforming all hand-crafted rules without any runtime overhead. The same approach applied to SAM 2 gives SAM2RL, which outperforms hand-crafted rules on 9 of the 12
benchmarks, showing the generality of our method across model generations.
Read the full abstract ▾
All authors Tomáš Čížek, Matej Straka, Illia Volkov, Matěj Kripner, Ervin Macić, Jiri Matas, Klara Janouskova, Martin Schmid
Computation and Language
MemDuet: Learning Dual-Process Memory for Long-Context Reasoning
Jiangcheng Song, Haodong Jing, Yulin Mu et al. (+7 more)
Reasoning over infinitely long documents is becoming a reality with recurrent
memory agents. However, increasing context length exacerbates the trade-off between
reasoning performance and inference efficiency. Inspired by Kahneman's account of fast and slow thinking, we propose MemDuet, a dual-process
memory framework that learns to coordinate a small
language model for fast, parallel evidence selection from raw context chunks (System 1) with a large
language model for
memory-update verification and
memory updates in document order (System 2). We train MemDuet in three stages: supervised fine-tuning of System 1 for evidence selection, Group Relative Policy Optimization (GRPO) of System 2 for verification and
memory rewriting, and joint optimization of both policies to coordinate selection and updating for long-context
reasoning. Experiments on diverse long-context
reasoning benchmarks (RULER-HQA, LongBench v2, and 2WikiMultiHopQA) demonstrate a favorable accuracy-efficiency trade-off as context length grows. Averaged across evaluation settings on the three
datasets, MemDuet achieves an end-to-end inference speedup of 9.74x and an output-
token reduction of 73.91% relative to RL-MemAgent.
Read the full abstract ▾
All authors Jiangcheng Song, Haodong Jing, Yulin Mu, Lesong Tao, Jixin Wang, Jin Cui, Tianjing Ren, Runxuan Xie, Yongqiang Ma, Nanning Zheng
Machine Learning · Cross-listed from stat.ML
Convergence Rates of Gaussian Process Thompson Sampling for Efficient Global Optimization
Haowei Wang and Yilin Zheng
Efficient global optimization aims to identify a global optimum of an expensive black-box function within a limited evaluation budget $N$. We investigate the convergence rates of Gaussian process Thompson sampling (GP-TS) under noiseless observations, assuming a fixed objective function in a reproducing kernel
Hilbert space (RKHS). For Matérn kernels with smoothness parameter $\nu$ in dimension $d$, we establish a worst-case expected simple-regret upper bound of $O(N^{-\nu/d}\sqrt{\log N})$ for both discrete GP-TS on sufficiently fine grids and its continuous counterpart. For the continuous implementation, we develop a nested-grid argument to control posterior sample paths over the entire domain. We further establish matching lower bounds of $\Omega(N^{-5/2}\sqrt{\log N})$ for both implementations under a fixed one-dimensional Matérn-$5/2$ kernel, demonstrating that the logarithmic penalty is intrinsic to standard GP-TS in this setting. Motivated by this limitation, we propose Gaussian Process Capped Thompson Sampling (GP-CTS), which caps posterior sample paths using a valid RKHS norm upper bound while preserving optimism. This modification successfully eliminates the logarithmic penalty and achieves the minimax-optimal rate $\Theta(N^{-\nu/d})$ for both discrete and continuous implementations.
Read the full abstract ▾
Computational Engineering
Sounds Cheesy - Bridging the Texture Gap Between Dairy and Plant-Based cheese with Non-Contact Ultrasound and AI
Wenjing Feng, Thomas A. Hazlehurst and Nik Watson
Plant-based cheeses often fail to reproduce the texture of dairy cheese. Closing this gap is slow because the reference methods, texture profile analysis (TPA) and sensory panels, destroy the sample and are poorly suited to screening many formulations in a timely and cost-effective manner. Here we show that non-contact, air-coupled ultrasonic imaging combined with machine learning can characterise cheese texture rapidly and without damaging the sample. Thirteen commercial products (nine dairy, four plant-based; 119 slices, 357 scans) were imaged in through-transmission at 100 kHz to give two-channel amplitude and time-of-flight C-scans, and each slice was then measured by TPA. The C-scans revealed millimetre-scale acoustic domains in ripened dairy cheeses, consistent with their fused-curd microstructure, that were absent from the homogeneous starch and oil
matrix of the plant-based products. TPA showed that the texture gap is one of range and failure behaviour rather than average firmness. Mean hardness was similar for the two categories, but dairy products spanned a 7.5-fold range against 1.9-fold for plant-based products, and the plant-based products failed in a brittle, strain-softening manner rather than by ductile yielding. No single ultrasonic parameter tracked texture across products. However, a compact convolutional neural network predicted full true stress-strain loading and unloading curves from the C-scan images of unseen slices across all thirteen products without product-specific calibration. Clustering the predicted curves produced a texture map on which three plant-based slices sat with the Cheddars and one with Emmental, while soft, mozzarella-like textures remained unoccupied. The approach offers a one-minute, non-contact measurement suited to formulation screening and at-line quality control of cheese.
Read the full abstract ▾
Machine Learning
MolHop: Scaffold-Hopping Molecular Design with Agentic Reinforcement Learning
Yanyi Su, Chenyan Wang, Yulei Gong et al. (+3 more)
Molecular design is often formulated as an optimization problem over existing molecular spaces. However, molecular optimization and the discovery of structurally distinct replacement molecules represent two fundamentally different search problems. LLM-based molecular design
agents typically perform the former, conducting local refinement within the neighborhood of existing structures to improve target properties through structural modifications. In contrast, the latter requires exploration of a broader chemical space to discover molecules with entirely different scaffolds while preserving the functional characteristics of reference molecules. We propose MolHop, an agentic framework for cross-scaffold molecular discovery that enables models to navigate and edit within a pre-organized chemical space. MolHop organizes approximately 1.6 million molecular scaffolds from commercial molecules into a coarse-to-fine hierarchical action space. The
agent selects new exploration regions through scaffold navigation actions and adjusts candidate properties through molecular editing. The framework maintains historical trajectory
memory to support long-horizon search processes. On drug molecule and commercial compound tasks, connecting Grok-4.6 and DeepSeek-Flash-V4.1 to the MolHop framework substantially improves their cross-scaffold joint success rates. We develop MolHop-9B through agentic reinforcement learning, and MolHop-9B outperforms generative baselines including GPT-5.6-sol, Claude-5-Opus, and Gemini-3.1-Pro, while generating candidate molecules with larger scaffold differences from the reference molecules. These results demonstrate that effective molecular discovery beyond the traditional optimization paradigm requires structured chemical and action spaces, enabling
agents to explore new structural regions rather than merely refine existing molecules.
Read the full abstract ▾
All authors Yanyi Su, Chenyan Wang, Yulei Gong, Yeyun Chen, Xiaohui Yang, Jun Cheng
Machine Learning
Beyond DFT electronic band structures via dual-space orbital learning
Minhyuk Kang, Beom Seok Kang, Nikolai Argatoff et al. (+4 more)
Accurate electronic band structures are essential for predicting material properties, but high-fidelity calculations are computationally demanding. We introduce O-kRystal, a dual-space orbital-learning framework that uses a lower-cost Perdew-Burke-Ernzerhof (PBE) calculation as both an energy baseline and a source of structured orbital information. Combining PBE band energies with real- and reciprocal-space orbital
matrices, O-kRystal predicts higher-level corrections for individual electronic states as a function of
crystal momentum and
spin. For states within 5 eV of the band-edge midpoint, it predicts Heyd-Scuseria-Ernzerhof (HSE06) band energies with a mean absolute error of $0.171 \pm 0.009$ eV across nearly 6,000 three-dimensional materials spanning insulating, metallic,
magnetic, and nonmagnetic systems. On a separate
benchmark of six strongly correlated materials, it reduces the corresponding PBE band-energy MAE by 68.7% and resolves orbital-dependent changes in the relative placement of transition-metal d and ligand p states. Despite training only at high-
symmetry points, it maintains comparable accuracy at unseen points along band paths and reconstructs HSE06 densities of states from dense Brillouin-zone predictions. Finally, training O-kRystal on $G_0W_0$ quasiparticle energies for two-dimensional materials demonstrates its applicability across levels of theory and the potential of orbital learning for higher-fidelity, momentum-resolved electronic-structure prediction beyond density functional theory.
Read the full abstract ▾
All authors Minhyuk Kang, Beom Seok Kang, Nikolai Argatoff, Miguel Nouman, Danish Khan, William A. Goddard III, Anima Anandkumar
Systems and Control
On the Mechanism of Multi-Cluster System Separation Under Extreme Events
Nikolaos Sofos, Georgios Tzounas and Federico Milano
Historical blackout events demonstrate that, under complex multi-event contingencies, interconnected power systems can split into multiple areas exhibiting distinct dynamic behavior while remaining physically connected. This work provides a rationale for this phenomenon. Typical N-1 contingency analysis leads to a response dominated by a single unstable mode, supporting the two-cluster
conjecture used by transient stability assessment tools such as the SIME method. However, extreme events, often involving cascading N-k contingencies, can excite multiple unstable modes. We establish a proof of concept based on linear modal expansion to show how such concurrent excitation leads to multiple coherent areas. The resulting behavior is illustrated through simulations on the standard WSCC 9-bus, IEEE 14-bus, and IEEE 39-bus systems, demonstrating the limitations of conventional two-cluster representations under extreme events.
Read the full abstract ▾
Computation and Language
Not All Criteria Matter: Importance-Aware Criteria Weighting for Rubric-Based LLM Evaluation
Haocheng Yang, Licheng Pan, Yiming Dong et al. (+7 more)
Rubric-based evaluation assesses the responses of large
language models (LLMs) by aggregating the verification results of explicit criteria, yet not all criteria matter equally. However, existing methods commonly aggregate the verification results with uniform weighting, which assigns minor and overlapping criteria the same weight as essential ones and thus produces misleading evaluation scores. Although some methods
prompt an LLM to directly assign weights, direct weighting requires a holistic judgment over all criteria that LLMs struggle to make reliably. To address these limitations, we propose Importance-Aware Criteria Weighting (ICW), which derives the weights of criteria from pairwise importance comparisons made by an LLM. Specifically, ICW transforms the holistic judgment over all criteria into a series of pairwise importance comparisons, checks and revises inconsistent comparisons, and derives the weights from the principal eigenvector of the comparison
matrix. Extensive experiments demonstrate that ICW consistently outperforms uniform weighting and competitive weighting methods, and translates into better policy models in downstream reinforcement learning.
Read the full abstract ▾
All authors Haocheng Yang, Licheng Pan, Yiming Dong, Xiaoxi Li, Yuan Lu, Zhenhao Chen, Jiajun Fan, Shuai Shao, Chunyuan Zheng, Hao Wang
Robotics
MUCO: A Mani-Unit-Structured Manipulation Framework for Compositional Long-Horizon Robot Tasks
Xiangyi Wei, Hanzhe Yao, Jingwen Shang et al. (+3 more)
Learning and executing long-horizon
robot manipulation as complete task trajectories raises data-collection costs, lim?its capability reuse, and causes local failures to cascade into later task stages. We introduce manipulation units (MUs) as reusable operations, each defined by a local goal, an initi?ation condition, and observable success and failure criteria. MUs are learned and verified individually. During execution, consecutive MUs remain coupled through shared environ?ment dynamics. We formulate MU-Structured Manipulation (MUSM) and realize it through MU-Centric Orchestration (MUCO). Given
language and
vision, MUCO constructs an MU sequence, matches each MU to compatible policy models in a frozen capability registry, and dispatches the model with the highest calibrated success rate. Visual verification checks MU outcomes against success and failure criteria and governs transitions, enabling retry or fallback to another model from the current state without re-executing verified MUs. Canonical keys enable checkpoint reuse for equivalent MUs across tasks without new demonstrations or updates. We evaluate MUCO on RLBench, RoboTwin 2.0, and five real-world tasks. MUCO achieves higher complete-task success and verified progress, stronger failure containment, and lower error propagation than baselines. Results demonstrate cross-task MU reuse and het?erogeneous policy composition without joint training, shared backbones, or common action representations.
Read the full abstract ▾
All authors Xiangyi Wei, Hanzhe Yao, Jingwen Shang, Zhenhong Wu, Yang Li, Changbo Wang
Computer Vision
Quantifying Annotation Agreement in Object Detection with Optimal Transport
Kirill Prokhorov and Alexandr A. Kalinin
Reliable validation of machine learning models is a crucial step in designing robust and trustworthy systems. Yet validation relies on annotated test sets treated as ground truth, even though annotations can be noisy or ambiguous. In object detection, sources may disagree on object presence, box location, or class label. Standard agreement metrics usually binarize box overlap before computing a summary score, obscuring the degree and structure of disagreement between annotation sets. Here, we study an Optimal Transport (OT)-based metric for measuring agreement between object detection annotations. Instead of binarizing bounding box overlap, this metric assigns graded costs to matched and unmatched labeled boxes. Through theoretical analysis and experiments on real and synthetically perturbed annotations, we show that OT captures graded changes in agreement and distinguishes annotation pairs that thresholded metrics score identically. Our results suggest that OT provides a richer measure of annotation agreement in object detection, especially for domains with many small or ambiguous objects. Such agreement estimates can support more reliable validation when labels are noisy or conflicting.
Read the full abstract ▾
Machine Learning
CARD: Closing the Teacher-Student Loop for Adversarial Robustness Distillation
Zhi Li, Haowei Liu, Hongchen Yang et al. (+5 more)
Adversarial robustness
distillation typically treats a robust teacher as a fixed knowledge source and transfers robustness to a compact student in a one-way manner. This paradigm terminates teacher-student interaction once the student is distilled, thereby discarding potentially useful feedback from the distilled student. However, exploiting such feedback is nontrivial because indiscriminate weak-to-strong transfer may propagate student errors to the teacher. To address this issue, we propose Cyclic
Adversarial Robustness
Distillation (CARD), a closed-loop framework that turns the distilled student into a feedback source for refining the robust teacher and subsequently transfers the teacher gains back to the same student. CARD first performs strong-to-weak
adversarial distillation and then uses reliability-enhanced student feedback to refine the robust teacher. The refinement combines inverse
adversarial student feedback with teacher-student discrepancy maximization, after which the refined teacher is used to continue training the same student under the unchanged base
distillation objective. We further establish a sample-level sufficient condition for reliable weak-to-strong feedback transfer and derive a distribution-level upper bound on the refined teacher's risk. Experiments on CIFAR-10, CIFAR-100, and TinyImageNet-10 across multiple teacher-student architectures and base
distillation methods show that CARD improves
adversarial robustness in most evaluated settings while generally preserving clean accuracy. These results show that the distilled student can provide useful feedback to the teacher, enabling robustness transfer to proceed beyond the conventional one-way teacher-to-student paradigm.
Read the full abstract ▾
All authors Zhi Li, Haowei Liu, Hongchen Yang, Xiaoxuan Wang, Song Gao, Zhenli He, Wei Zhou, Shaowen Yao
Machine Learning
When Non-Adversarial Noise Hurts Learning: Benchmarking Skill Self-Evolution in Agents
Tao Yu, Zhongtian Luo, Yuchen Long et al. (+19 more)
Large
language model
agents increasingly improve by distilling experience into reusable skills, but errors in that experience can persist in learned rules and affect later tasks. Existing evaluations largely examine clean learning or perturbations encountered after skills are frozen, leaving robustness during self-
evolution insufficiently understood. We introduce RSE-Bench, to our knowledge the first
benchmark for evaluating skill self-
evolution under ordinary, non-
adversarial noise. It spans four domains and six
benchmarks, with controlled perturbations to instructions, environmental evidence, execution records, and outcome–record pairings that preserve the underlying tasks and native scoring rules. The protocol separates noise during learning from input-side noise at evaluation, testing frozen skill stores on held-out tasks. We also introduce RSEClaw, a method-agnostic framework supporting consistent noise injection and process diagnostics of actual exposure and skill updates. Across three methods and two backbones, noisy learning retains only $25.5\%$–$42.1\%$ of the aggregate gain achieved by clean self-
evolution, depending on the noise type. Perturbations confined to execution records and outcome–record pairings cause average losses comparable to input-side noise, despite leaving the original executions and evaluations intact. Diagnostics further identify differences in candidate skill text that coexist with small changes in mean held-out performance.
Read the full abstract ▾
All authors Tao Yu, Zhongtian Luo, Yuchen Long, Yiheng Lu, Yuxuan Zhou, Yanpei Gong, Siyi Cao, Yuqing Wu, Haopeng Jin, Zhenghao Zhang, Yujia Yang, Jingmin Zhu, Yunyun Hou, Xinming Wang, Hongzhu Yi, Jiachen Liu, Sirui Wang, Nan Duan, Yan Huang, Liang Wang, Tianjin Huang, Yanyan Zou
Artificial Intelligence
Sparse Transformer: a Controlled Testbed for Mechanistic Interpretability
Anton Korznikov, Alexey Dontsov and Elena Tutubalina
Mechanistic interpretability aims to decompose neural network computations into human-understandable features, yet progress is limited by the absence of ground-truth units to evaluate against. We address this with a Sparse
Transformer (ST): a 5-layer
language model trained on TinyStories whose wide, TopK-sparse MLP forces
neuron specialization. We show that ST
neurons are highly interpretable: they outperform a loss-matched dense
transformer by 43% on AutoInterp, and
circuits of a median of 12
neurons suffice to reproduce individual model predictions. This testbed allows us to directly compare feature learning methods: Transcoder, which approximates the MLP input-output mapping, recovers ST's
neuron vectors with 52.6% higher cosine similarity than Sparse Autoencoder, which only reconstructs outputs. Furthermore, the ST enables a controlled study of polysemanticity: distilling its sparse MLP into a dense counterpart reveals how compression leads to feature superposition. These results show how a known reference basis sharpens evaluation and understanding, a role we hope the ST can serve for the field.
Read the full abstract ▾
Computation and Language
Beyond Benchmark Accuracy: A Diagnostic Test for LLM Chemical Prediction
Yanyi Su, Yu Zeng, Hongshuai Wang et al. (+3 more)
LLMs have achieved strong performance on chemical prediction
benchmarks. However, existing evaluation methods typically provide target entity identity information directly, making it difficult to determine whether model predictions arise from transferable structure-property
reasoning capabilities or rely on target-related contextual information or
memory retrieval. We propose the Identity-Blinded
Reasoning Diagnostic framework to evaluate chemical prediction models when target entity identity information is hidden. In this framework, the target is no longer directly defined by its entity identity, but instead by a known source entity and an explicit structural edit operation. This setting preserves the information required to determine the target while reducing the opportunity for models to access target identity cues. We evaluate this framework across six tasks spanning odor prediction, molecular property prediction, retrosynthesis, and reaction yield prediction. The results show that models generally achieve better prediction performance when source and target entity properties are consistent. Providing explicit source entity labels further strengthens this dependence. Moreover, while keeping the target entity, structural change, and ground-truth label unchanged, replacing only the source entity label causes some model predictions to systematically shift toward the substituted source labels. These results indicate that high
benchmark accuracy in chemical prediction tasks does not necessarily imply that LLMs possess reliable structure-property
reasoning capabilities. Our diagnostic framework provides a controlled evaluation approach for testing whether models can genuinely update predictions according to entity changes. The framework can be extended to other AI for Science tasks, particularly those where targets can be defined through transformations of known entities.
Read the full abstract ▾
All authors Yanyi Su, Yu Zeng, Hongshuai Wang, Chenyan Wang, Zhifeng Gao, Xiaohui Yang
Computer Vision
Multimodal Medical Image Parsing with Task-Specific Low-Rank Adapters
Taha Sabir, Alberto Montero Molina, Thinh Quang Ly et al. (+3 more)
Adapting a single
vision-
language model to medical image parsing requires training choices that reflect the demands of each task. We study task-specific adaptation with Qwen3.5-9B for
FLARE 2026 Task 3, covering six task families and seven imaging modalities. Our system couples a shared, frozen 4-bit backbone with LoRA adapters selected from the input question. We customize adapter ranks and
prompts, rebalance rare classification targets, and supplement regression training with dermatology classification examples. On the fixed internal holdout, the task-specific adapters achieve a
dataset-macro balanced accuracy of 0.7791 for classification, a
dataset-macro micro-F1 of 0.6286 for multi-label classification, a counting mean absolute error (MAE) of 11.73, a
dataset-macro detection F1 of 0.8914, a
dataset-macro regression MAE of 9.78, and a report-generation CRIMSON score of 0.8204. On the organizer's 1,703-example hidden-validation set, the submitted system achieves 0.8496 classification balanced accuracy, 0.5338 sample-averaged multi-label F1, and 14.5950 regression MAE. The final 30.1 GB container averages 3.1 seconds per case, including model loading, and produces identical outputs across repeated verification runs. The benefits vary across tasks, supporting the use of task-specific adapter configurations and image budgets within a shared medical
vision-
language model. Code is available at https://github.com/TahaSabir0/
FLARE26-Hexapus.
Read the full abstract ▾
All authors Taha Sabir, Alberto Montero Molina, Thinh Quang Ly, Veronika Dmitrenko, Mohammad Yaqub, Tausifa Jan Saleem
Artificial Intelligence
How GUI Agents Fail: GraceBench for Execution Stability Diagnosis
Ridong Zhang, Shuxian Liang, Chaoqun Wan et al. (+2 more)
As GUI
agents are increasingly deployed for mobile task automation, their reliability depends not only on final task outcomes, but also on whether they reach these outcomes through stable interaction trajectories. In automation workflows, unnecessary actions, detours, and execution errors can add noise to collected data, introduce irreversible side effects, or undermine trust, even when the
agent eventually completes the task. It is therefore important to systematically diagnose the execution stability, including whether an
agent deviates from a feasible path, enters a loop, becomes stagnant, or recovers from unstable actions. Existing
benchmarks, however, primarily assess final task success or a small set of intermediate milestones, leaving step-level execution behavior unclear. To bridge this gap, we introduce GraceBench, an online evaluation framework that represents the reachable interaction space of mobile applications as UI Transition Graphs (UTGs), providing a structural reference for step-level execution diagnosis. To support reliable
alignment between dynamic UI observations and graph states, GraceBench uses
video-grounded trajectory evaluation over this graph-aligned representation, assessing process stability beyond final success with metrics such as deviation rate, loop burden rate, and recovery ability. GraceBench contains 169 tasks spanning 10 applications and constructs 10 UTGs with 2,909 canonical GUI states and 3,116 observed transitions. Across 3,718 trajectories, GraceBench shows that outcome scores hide execution instability: GPT-5.6 Sol achieves the highest success rate (SR) but the lowest recovery ability, 51.24% of successful runs still contain a deviation or loop, and trajectories with the same success rate (SR) and completion rate (CR) can differ substantially in recovery behavior. Code and data will be released on https://iaie-physicalai.github.io/GraceBench.
Read the full abstract ▾
All authors Ridong Zhang, Shuxian Liang, Chaoqun Wan, Zhen Huang, Xian-Sheng Hua