Machine Learning
Reinforcement Learning on the Discrete Composition Channel of a Crystal Generator: Validated Gains and Reward Hacking
Pawan Prakash, Philipp Höllmer, Addis Fuhr et al. (+4 more)
Inverse materials design is a long-standing goal of computational materials discovery. Generative models for crystalline materials are typically trained to match the distribution of a structure database, while nothing in their training objective points them at specific design goals such as targeted properties. We use group-relative policy optimization (GRPO) to align a generative model based on
stochastic interpolants and discrete flow matching with general black-box reward functions through reinforcement learning. Atom types are generated by a discrete flow and the policy gradient of our generalization of GRPO directly acts on the likelihoods of the atom-type transitions, which differentiates our work from previous reinforcement-learning approaches for
diffusion and flow-based generative models of crystalline materials. We introduce a reward function that raises the yield of metastable, unique and novel structures (mSUN) from 13.4% for the pretrained model to 45.5% for the reinforced model, as evaluated by a community
benchmark. Our reward also improves the performance of a reinforcement learning framework for crystalline materials based on latent denoising
diffusion models. At the same time, we find that directly reinforcing atom-type transition likelihoods enables reward exploitation that has to be prevented with explicit guards. The same analysis also exposes a gap in the community metric. Single-element structures in distinct packings are counted as metastable, unique and novel materials and inflate mSUN without yielding any new compounds. A stability claim is only as good as its reference hull. We report every result split by the number of reference phases behind it and argue that
benchmarks should do the same.
Read the full abstract ▾
All authors Pawan Prakash, Philipp Höllmer, Addis Fuhr, Peter Hirschfeld, P. Ganesh, Stefano Martiniani, Richard Hennig
Networking
Performance Analysis of ISAC Slicing with Sensing-Assisted Communication and Communication-Assisted Sensing
Daniel Campos and Jacek Kibilda
Integrated Sensing and Communication (
ISAC) will allow 6G networks to provide both sensing and communication services through shared infrastructure and spectrum resources. However, network slicing that views these services as distinct slices with distinct objectives and performance requirements will inevitably miss the emergent value of integrating them. By considering Sensing-Assisted Communication (SAC) and Communication-Assisted Sensing (CAS), which create interdependencies between services, we can observe trade-offs in resources dimensioned to support each slice and, ultimately, the
ISAC slicing performance. As such, this paper proposes a performance analysis of an
ISAC slicing framework that accounts for resource allocation and sensor density, as well as SAC and CAS, dimensioned to achieve slice-specific Service-Level Agreement (SLA) satisfaction. Numerical simulations, across different bandwidth allocations, sensor deployments, and demand scenarios, show that
ISAC slicing performance is fundamentally constrained by sensing resolution, shaped by demand, and scaled by sensor deployment. These findings provide insights for the design of future
ISAC slicing mechanisms.
Read the full abstract ▾
Computer Vision
Streaming Multi-Track Timeline Control for 3D Human Motion Generation
Yangsong Zhang, Anujith Muraleedharan, Rikhat Akizhanov et al. (+3 more)
Text-driven human motion generation has advanced substantially, yet most methods assume instructions are available before synthesis. Interactive applications require responding to new instructions while continuing ongoing actions, such as answering a phone while walking. Existing approaches address streaming generation or simultaneous composition without explicitly combining streaming instruction arrival with independently timed, overlapping actions. We introduce streaming multi-track timeline control and propose TimelineControl to incorporate new instructions alongside ongoing actions. Interval-aware conditioning preserves instruction timing, while causal part-structured representations and part-aware denoising coordinate concurrent actions across body regions. We also construct TimelineMotion, a
dataset with overlapping instruction intervals and body-part annotations. Experiments on TimelineMotion and MTT demonstrate improved semantic
alignment and temporal adherence over evaluated streaming baselines, including models retrained on the same data. Ablations and human evaluations validate our design, complemented by spatial conditioning and
humanoid execution demonstrations. Our code, data and models will become publicly available.
Read the full abstract ▾
All authors Yangsong Zhang, Anujith Muraleedharan, Rikhat Akizhanov, Gül Varol, Fabio Pizzati, Ivan Laptev
Artificial Intelligence
Training Numerical Intelligence via Auto-Diagnosis and Skill Discovery
Peter Chen and Wotao Yin
AI
agents are becoming increasingly capable of generating scientific code, but generating code is not the same as improving the
algorithms behind it. For numerical solvers, execution feedback can expose poor performance, but rarely reveals its underlying cause and how to address it. We introduce Auto-Diagnosis and Skill Discovery (ADSD), a framework that links numerical diagnosis to reusable solver self-improvement. ADSD follows a diagnosis-first paradigm that first explains why a solver performs poorly, then uses this diagnosis to guide the discovery of appropriate numerical methods. The resulting knowledge is packaged into reusable solver skills, turning solver improvement from trial-and-error editing into a structured process of diagnosis, discovery, and implementation. Across four challenging numerical domains–power flow equation, AC optimal power flow control, stiff ordinary differential equations, and heterogeneous
diffusion PDEs–ADSD consistently improves solver accuracy, robustness, and efficiency. On GOC-500 power flow, for example, ADSD reduces mean solver error by nearly $71\times$, with improvements further transferring to unseen grid
topologies and operating regimes.
Read the full abstract ▾
Robotics
GOTT: Object-centric Dexterous Manipulation with a Reusable Cross-Embodiment Primitive
Yulin Liu, Lai Wei, Yen-Jen Wang et al. (+4 more)
Foundation models and large-scale human data provide rich sources of manipulation intent, but translating this intent into multi-fingered
robot behavior remains difficult. Dexterous hands still lack a reusable low-level primitive that reliably establishes contact across tasks and embodiments. We propose GOTT, a reach-acquire-move framework built around a single cross-embodiment contact-acquisition primitive. Given a
robot-agnostic object trajectory and a reach specification, GOTT first brings the hand near a task-relevant contact region. The shared closed-loop primitive then establishes stable contact from this approximate initialization, and a pose-conditioned controller tracks the desired object motion. Reach specifications may come from future-aware planning, external models, or human demonstrations, while the primitive and tracking backend remain unchanged. Simulation and real-world experiments show that GOTT is able to establish robust contact across diverse objects, arm-hand platforms, and seen and unseen hand morphologies. It also consistently improves end-to-end task success over open-loop grasp execution.
Read the full abstract ▾
All authors Yulin Liu, Lai Wei, Yen-Jen Wang, Akash Sharma, Pieter Abbeel, Henrik I. Christensen, Haozhi Qi
Machine Learning
Retrieval-Centric Deep Learning in Growing Nonparametric Neural Networks
Maximilian Schlegel, Rajai Nasser, Seijin Kobayashi et al. (+6 more)
We investigate a general-purpose layer for deep learning that, instead of compressing arbitrary-size training data into fixed-size weight
matrices, stores a new pair of key-value representations for every data point during training, and retrieves and recombines these representations through an
attention mechanism at inference time - resulting in a growing neural net (NN). While Irie et al. (arXiv:2202.05798) have put forward this perspective from the classic duality expressing any linear layer in a deep NN trained by gradient descent as linear
attention (LA) over the training data points, replacing LA by more powerful
attention functions, as they suggest, turns out to be non-trivial: we show that naively applying learning rules from the LA case to advanced kernels does not lead to principled optimization. Here we fill this gap and develop functional gradient-based learning rules for kernelized
attention layers, based on radial basis function (RBF) and softmax-like kernels - establishing the principled "
retrieval-centric deep learning" (RCDL) paradigm. Empirically, we demonstrate the promising performance and learning-efficiency of RCDL on image classification and synthetic teacher-student learning tasks. Moreover, we show that replacing LA in the dual form of NNs by advanced LA variants, namely MesaNet/DeltaNet, yields a formal connection to recently proposed optimizers for conventional fixed-size NNs, offering a novel perspective on deep learning optimization.
Read the full abstract ▾
All authors Maximilian Schlegel, Rajai Nasser, Seijin Kobayashi, Yanick Schimpf, Oliver Sieberling, Robert Obryk, Kazuki Irie, João Sacramento, Johannes von Oswald
Cryptography and Security
Beware EviLLM: Enabling Vulnerability Injection via Large Language Models
Zeezoo Ryu, Simon Chung, Muhammad Faraz Karim et al. (+4 more)
Advances in large
language models (LLMs) have enabled AI-driven code generation from natural
language specifications, introducing new attack surfaces for injecting vulnerabilities into software. Prior work has studied this problem only in benign settings where vulnerabilities are introduced inadvertently, or under unconventional threat models where the LLM itself is malicious (backdooring) or the user is the attacker (jailbreaking). In this paper, we study a more realistic threat model: a third-party adversary, with capabilities comparable to existing cybercriminals, compromises the AI code generation pipeline to deliberately introduce vulnerabilities. We call this the EviLLM attack. We have implemented two instances of EviLLM, each of which only requires the underlying LLM to be accessed through a compromised account or browser, and can inject vulnerabilities from 13 CWE classes. As we show in our feasibility study, both attack vectors are already used to implement many existing cyberattacks. Our user study shows that 7 out of 8 and 10 out of 13 participants did not notice the vulnerabilities injected by the two instances of EviLLM, and 13 out of 21 participants "rarely" or "never" considered the risk of an attack like EviLLM.
Read the full abstract ▾
All authors Zeezoo Ryu, Simon Chung, Muhammad Faraz Karim, Anna Raymaker, Karan Singh Jodha, Yash Chaturvedi, Sukarno Mertoguno
Machine Learning
BAT-NO: A Boundary-Condition-Aware Transformer Neural Operator for Crashworthiness Prediction of Vehicle Components
Haoran Li, Yingxue Zhao, Haosu Zhou et al. (+4 more)
High-fidelity finite-element simulations provide accurate crashworthiness predictions, but their cost limits iterative design exploration. Deep learning surrogates can reduce this cost, but many component-level models are developed under a single prescribed boundary condition, limiting generalisation to boundary variations. This work proposes a Boundary-Condition-Aware
Transformer Neural Operator (BAT-NO) for autoregressive prediction of transient displacement fields and scalar crashworthiness responses under variations in geometry and boundary conditions. A B-pillar simulation framework evaluates generalisation across variations in geometry, impact position and velocity, and support stiffness. BAT-NO combines recurrent mesh processing with latent-grid
Fourier operator processing. Boundary-condition information is transferred to the latent grid through a hybrid local–global mechanism. Slice-based
attention models interactions among physically related regions, while direct boundary-to-grid projection preserves local spatial structure. Across the validation sets for the shape-only, shape-and-loading, and shape-loading-boundary cases, BAT-NO achieves the lowest mean final-step mean nodal Euclidean displacement error among the evaluated baselines. In the most challenging case, it reduces the mean error by 32.6% relative to the second-best model. Hyperparameter tuning reduces the validation error from 0.451 to 0.269 mm, with a comparable error of 0.267 mm on 300 unseen test simulations sampled within the investigated design space. An
attention-based scalar decoder jointly predicts six response trajectories with a mean relative error of 2.46%. Most derived crashworthiness indicators have median errors below 3%. These results show that explicit local and global boundary-condition representations improve crashworthiness prediction over expanded component-level design spaces.
Read the full abstract ▾
All authors Haoran Li, Yingxue Zhao, Haosu Zhou, Mustapha Ziane, Pierre Culiere, Tobias Pfaff, Nan Li
Computers and Society
Can LLM Agents Select and Engage with Biological Tools?
Jeffrey Lee, Alyssa Wordland, Kyle Brady et al. (+12 more)
Computational tools for biological research (biological tools, or BTs) are advancing rapidly in both quantity and demonstrated capability. While these technologies offer many benefits for scientific advancement, malicious actors may seek to exploit them to design and develop biological weapons (BWs). Generally, BTs require specialized expertise to operate successfully, presenting a barrier to nefarious use by nonexperts. Large
language model (LLM)
Agents may erode this barrier by enabling actors with limited domain expertise to successfully use BTs. Assessments of how AI could change bioweapons development pathways should examine how LLM
Agents interact with BTs on relevant biological design tasks, but such assessments are limited. In this report, we present an assessment of the abilities of LLM
Agents in the early stages of interaction with BTs. First, we evaluate seven frontier LLM
Agents on their ability to select appropriate BTs for a given task. Second, we assess how these LLM
Agents engage with two BTs, EVEscape and ESM3, through targeted case studies. These case studies probe the enabling capabilities required for autonomous BT operation, a potential entry point to a wide range of risk pathways. We identify and assess technical barriers at the intersection of LLM
Agents and BTs, offering the biosecurity community and AI developers a foundation for further risk and capability assessments as technologies progress.
Read the full abstract ▾
All authors Jeffrey Lee, Alyssa Wordland, Kyle Brady, Grant Ellison, Henry Alexander Bradley, Christopher Rodriguez, CASEY MICHAEL O'DAY BARKAN, SUNISHCHAL DEV, Dawid Maciorowski, Jordan Despanie, Barbara Del Castello, Bria Persaud, Amar Pandya, Ella Guest, Steph Guerra
Computers and Society
Testing Large Language Model Agents on the Use of Biological Tools for Nucleic Acid Synthesis Screening Evasion
Jeffrey Lee, Alyssa Worland, Christopher Rodriguez et al. (+8 more)
This report is a continuation of previous efforts to test the ability of large
language model (LLM)-driven artificial intelligence (AI)
agents to interface with AI-enabled biological tools (BTs). While rapid advancements in BTs in recent years have brought promise to accelerate scientific discovery, they also raise significant biosecurity concerns about potential misuse. The biosecurity community is particularly interested in the extent to which LLMs can lower technical barriers and assist non-expert users in accessing and operating BTs. Despite this interest, few evaluations have focused on LLM-BT interactions in the context of a defined threat model. To address this gap, this report describes a test of frontier LLM-driven AI
Agents on their ability to use BTs to redesign peptides and
proteins to evade nucleic acid synthesis screening measures. Highly relevant to biorisk, this task assesses a potential capability of AI
agents that could enable a breach of a critical early defensive layer designed to prevent a multitude of biological misuse scenarios. The findings presented here intend to offer a foundation for biosecurity researchers and AI developers to conduct or further risk and capability assessments as these technologies progress.
Read the full abstract ▾
All authors Jeffrey Lee, Alyssa Worland, Christopher Rodriguez, Kyle Brady, Grant Ellison, Henry Alexander Bradley, Dawid Maciorowski, Jordan Despanie, Barbara Del Castello, Jason Johnson, Steph Guerra
Information Theory · Cross-listed from math.CO
An Improved Upper Bound for Recovering Pairs
Simone Costa
We prove that every recovering pair $(\mathcal{A},\mathcal{B})$ of nonempty families of subsets of an $n$-element set satisfies $$|\mathcal{A}||\mathcal{B}|\le\left(\frac{223949}{100000}\right)^n=(2.23949)^n.$$ A result of Mond, Souza and Versteegen, combined with the sharp $(9/4)^n$ bound of Fang and Huang for cancellative pairs, gives $(2.2499)^n$ for recovering pairs. We improve this to $(2.23949)^n$. The proof combines two
entropy inequalities. One is derived directly from the recovering property, while the other applies the Fang-Huang bound to families obtained from the original pair by a construction of Mond, Souza and Versteegen. The two inequalities are then combined by a convex combination.
Read the full abstract ▾
Data Structures and Algorithms
Stochastic Network Speed Scaling with Competitive Ratios Independent of the Network
Yash Khanna
In network speed scaling, jobs arrive over time at a network of servers whose speeds can be tuned, every job must be processed by the servers along one of its allowed routes, and the goal is to minimize the total flow time plus the total energy. For
stochastic arrivals, the competitive ratio of Vaze and Nair depends on the network, through the lengths of the routes it uses. We show that this dependence can be removed: we give an
algorithm, which routes the jobs by solving a convex program and runs every server at a fixed speed, whose competitive ratio depends only on the power functions; for $P(s)=s^2$, it is at most the golden ratio $\varphi\approx1.618$. The key idea is a lower bound on the optimal cost which, like the cost of our
algorithm, is a sum over the servers of a function of each server's load, so the analysis reduces to a single server. We also show that the routing rule of Vaze and Nair can be a factor $\Omega(L)$ away from optimal, where $L$ is the length of the longest route.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
Probability flow ODEs in score-based and reflected diffusion models
Rama CONT
Probability-flow ordinary differential equations (PF-ODEs) are widely used as deterministic samplers for score-based
diffusion models. Their usual justification is that the Fokker–Planck equation of a
diffusion can be rewritten as a continuity equation driven by the score function of the forward
diffusion. This identity does not, however, guarantee that the resulting velocity field generates a well-posed flow. We provide theoretical insights into the design of such deterministic samplers for generative models based on
diffusions and reflected
diffusions. We identify sufficient conditions for a regular Lagrangian PF-ODE flow to exist; reverse sampling and invertibility require two-sided divergence control. For learned scores, sampler stability is controlled by an unweighted velocity error, exposing a mismatch with density-weighted score matching and motivating architectural control of Jacobians, divergence, growth, and compression. Under the
manifold hypothesis, positive-time regularization justifies an early-stopped PF-ODE while constants deteriorate near the data endpoint; an explicit sphere example shows that the exact deterministic flow becomes singular as the noise level vanishes even though the
diffusion marginals remain well defined. These theoretical insights translate into concrete design principles for stable, invertible, and constraint-preserving
diffusion samplers. We illustrate the practical relevance of these design principles using controlled numerical experiments.
Read the full abstract ▾
Machine Learning
KVE-KD: Key Visual Evidence-Guided Knowledge Distillation for Vision-Language Models
Jianbin Zhang, Xin Sun, Shanwen Wang et al. (+2 more)
Knowledge
distillation is crucial for deploying
vision-
language models on resource-constrained devices. However, existing methods typically impose uniform supervision across visual
tokens or rely on static
token selection, which confuses task-relevant cues with background noise and degrades cross-modal
reasoning. To address this limitation, we propose Key Visual Evidence-guided Knowledge
Distillation (KVE-KD), a framework that dynamically focuses feature
distillation on task-relevant visual
tokens identified by the teacher model. Specifically, KVE-KD appoints the final pre-generation textual
token as a unified semantic anchor and identifies the target cross-modal fusion layer by analyzing changes in the anchor representation through iterative visual-
token contribution removal. Within this layer, KVE-KD ranks visual
tokens via the anchor-conditioned
attention distribution and selects the most informative visual
tokens as key visual evidence with normalized
entropy. The key visual evidence subsequently guides focused visual feature
distillation, making the student align closely with the teacher's task-relevant visual representations while suppressing irrelevant background information. Extensive experiments on six
benchmarks demonstrate that KVE-KD outperforms state-of-the-art cross-modal
distillation methods, with particularly pronounced gains on tasks requiring complex
reasoning and fine-grained visual understanding. Importantly, these improvements are achieved without introducing any inference-time overhead. The source code is available at https://github.com/zhangjianbin07/KVE-KD.
Read the full abstract ▾
All authors Jianbin Zhang, Xin Sun, Shanwen Wang, Wei Ye, Susanto Rahardja
Computational Engineering
Dexy: A Simple Stablecoin Design Based on an Algorithmic Central Bank
Alexander Chepurnoy, Amitabh Saxena and Luca Gaetano D'Angelo
We consider a new algorithmic stablecoin called Dexy consisting of three components: a central bank, a secondary
market in the form of a customized CP-AMM liquidity pool, and a trusted oracle. The price of the stablecoin in the liquidity pool is stabilized, relative to the oracle price, via central bank interventions. Users mint Dexy stablecoins from the bank using basecoins, the base cryptocurrency asset.
Read the full abstract ▾
Computation and Language
SYNLAT: Syntax-Aligned Text-Latent Compression for Chain-of-Thought Reasoning
Yifeng Zhao, Hongjun Yu, Shibo Wang et al. (+5 more)
Long chain-of-thought (CoT) traces impose substantial output-
token costs. Under constrained budgets, compression must preserve answer-critical information, making boundary placement central.
Token-level and fixed-length boundaries can fragment coherent spans such as phrases, formulas, and local derivations, whereas step-level boundaries can bind content requiring different compression actions. We introduce SynLat, a text-latent CoT framework that aligns compression boundaries with syntactic structure through non-overlapping Syntax-Aligned Units (SAUs). An answer-conditioned Teacher constructs progressive KEEP/LATENT targets for a single compression-conditioned Student, which generates mixed
reasoning from only the question and requested compression level at inference. Across two Qwen3 Student scales, Standard-CoT and Long-CoT groups, and three compression levels, SynLat matches or exceeds the strongest evaluated baseline in all 12 task-group aggregates and strictly leads in 11 under the reported achieved-CR selection protocol. Overall gains reach 3.6/2.6 points at MEDIUM and 7.0/5.5 points at HIGH for Qwen3-8B/14B, with larger advantages under stronger compression, particularly on Long-CoT groups.
Read the full abstract ▾
All authors Yifeng Zhao, Hongjun Yu, Shibo Wang, Yunjiao Zhou, Zixiao Zhu, Zhipeng Ning, Kezhi Mao, Junlang Qian
Software Engineering
Smells and Refactorings for Software Environmental Sustainability: A Systematic Literature Review
Ornela Danushi, Flavio Sampirisi, Jacopo Soldani et al. (+2 more)
Context: The environmental impact of ICT is constantly growing. Enhancing its environmental sustainability requires dealing with energy-hungry software systems, by possibly reducing their footprint. Objective: To better frame the problem and its persistent nature, software can be viewed as carrying structural inefficiencies regardless of how advanced its functionality may be. Identifying these inefficiencies as "green smells" provides a basis for refactoring code to mitigate its ecological impact. We aim at identifying well-known green smells impacting environmental sustainable software and map them to corresponding refactoring aimed at reducing the impact therein. Method: In this article, we conduct a systematic literature review on the articles that discuss green smells and their possible refactorings. We analyse and classify 66 primary studies published up to March 2026. Results: We identify 20 smells impacting environmental sustainability of software. Each smell is associated with one or more refactoring techniques known to mitigate their negative effects on the environmental sustainability of software. Conclusions: The literature witnesses the interest in resolving the green smells affecting software systems. The catalogued green smells and the corresponding refactorings can provide pragmatic value for practitioners in their daily development workflows, while also offering researchers a starting point to establish new research directions in sustainable software engineering.
Read the full abstract ▾
All authors Ornela Danushi, Flavio Sampirisi, Jacopo Soldani, Stefano Forti, Antonio Brogi
Formal Languages and Automata
An example of an automatic sequence with non-regular abelian complexity
Jean-Paul Allouche, Narad Rampersad, Michel Rigo et al. (+2 more)
Answering a question of Madill and Rampersad, we give an example a of a $2$-automatic sequence whose abelian complexity is not $2$-regular.
Read the full abstract ▾
All authors Jean-Paul Allouche, Narad Rampersad, Michel Rigo, Jeffrey Shallit, Manon Stipulanti
Information Theory
Multiple Access in Pinching-Antenna Systems: A Survey, Impairment Analysis, and Evaluation
Wei Jiang and Hans Dieter Schotten
Pinching-
antenna systems attach dielectric pinches to a waveguide, creating line-of-sight radiation points within a few meters of any user. The pinches on one waveguide, however, radiate the same signal, unlike a conventional array, where each element transmits a dedicated signal. Separating the signals of multiple users therefore becomes challenging and requires a new perspective on multiple access. Most existing studies rest on an idealized model, and no survey examines the access schemes under realistic impairments. This article surveys multiple access in pinching-
antenna systems and organizes fifty-six works into a unified taxonomy by spatial degrees of freedom. The users of one waveguide can be separated only in time, frequency, power, or guided mode, while multiple waveguides add the space domain. The article then identifies the impairments critical to this separation, which perturb the effective channel, leak interference across orthogonal resources, or couple the pinches on the uplink, and summarizes them in an impairment-versus-method map. A unified evaluation of time-, frequency-, power-, and space-domain access under identical channel and impairment models reveals that the degradation is method specific. The analytical and numerical results give insight into multiple access in these systems and provide a basis for its impairment-aware design, a necessary step toward their adoption in practical networks.
Read the full abstract ▾
Machine Learning
LLM-enhanced spatio-temporal learning for grid-level docked bike sharing demand prediction
Xuxilu Zhang and Francesc Soriguera
Short-term bike-sharing demand
forecasting is complicated by spatial-temporal non-stationarity and the practical difficulty of incorporating unstructured external text into numerical pipelines. Conventional approaches rely on historical flow sequences and fixed graph structures, thereby constraining their accuracy when anomalous social events perturb normal travel patterns. We propose a
forecasting framework in which a Large
Language Model (LLM) drives a semantic shockwave mechanism that converts free-form urban text, such as municipal event schedules, local news, and transit bulletins, into quantified spatial-temporal perturbation fields. The LLM extracts three physically interpretable parameters per event (intensity, spatial reach, and temporal lag), from which Gaussian decay fields are constructed and injected into a Zero-Inflated Adaptive Spatio-Temporal Graph Convolutional Network (ZI-ASTGCN). To handle the pronounced sparsity of grid-level measurements, the model couples a dual-branch output head with a multi-task zero-inflated loss that jointly trains a gating probability and a conditional flow intensity. Experiments on the operational Barcelona Bicing
dataset show that ZI-ASTGCN outperforms established neural baselines, with particularly strong gains during high-demand periods, validating the utility of physics-grounded semantic signals in spatial-temporal mobility
forecasting.
Read the full abstract ▾
Neural and Evolutionary Computing
Distribution Matching Evolutionary Algorithms for Rare Event Sampling
Yonatan Gideoni and Yarin Gal
A novel discovery is one which is both useful and surprising: a generative model's output is a useful discovery if it has a low probability of being generated (it's surprising) and a high reward (it's useful). Global optimization can directly increase the probability of sampling high rewards but typically requires updating model weights. Such gradient based optimization is expensive and bars using capable closed-source models. Instead, modern search methods for discovery sacrifice the global target, and use evolutionary
algorithms with local reward maximizing objectives, permitting the search to focus only on high probability samples. In this paper, we interpret various evolutionary
algorithms as approximate Markov Chain Monte Carlo, an optimization-free method to sample from complex distributions. This interpretation allows developing Distribution Matching Evolutionary
Algorithms (DME), a class of search methods which sample from a global target distribution without updating weights. Empirically, DME has a higher sample efficiency than existing methods on problems requiring many samples to find a solution.
Read the full abstract ▾
Machine Learning
Where Does Jagged Competence Come From?
Ioannis Tsiokos
Capable systems often show jagged competence: low average error alongside failures on particular inputs. We ask where it comes from in a task built from two known layers. A lower layer A computes five per-slot sums from records; an upper layer B uses the slot-1 sum and a mode carried over from earlier boards to predict the next board's category, so B cannot be computed from the current A alone: B is a strict extension of A. We train small recurrent networks on B and measure, against exact ground truth, what they acquire of A. The central finding is that learning B gives the network a jagged version of A, measured through probe readability and supervised outputs. It is readable where B needs it (slot 1, 97-98% by a linear probe) and becomes less readable where B does not (the other slots, 5-10%); category misreads concentrate near the slot-1 cutoffs; and when A is trained explicitly it comes out only approximately right. The networks show jagged competence in B: natural KL below $3\times10^{-4}$ bits coexists with a maximum law TV of about 0.25 on constructed histories. Matched experiments show that even a good A is not enough: connecting a learned A to B cuts misreads 1.3 to 17-fold, the same exact A gives fewer misreads as one-hot inputs (0-2) than as numerical inputs (10-317), one B update makes an exact A inexact unless the B gradient is blocked, and exact A still leaves some B failures. In this task, uneven acquisition, access and preservation of the lower theory explain part of the jagged competence of a network that learns the theory built on it; some failures remain unexplained. Whether the same holds in larger systems is a test to run.
Read the full abstract ▾
Machine Learning
Memory-State Critic for Asymmetric Actor-Critic with Application to Vision-Based Pursuit-Evasion
Arthur Louette, Alejandro Sánchez Roncero, Gaspard Lambrechts et al. (+4 more)
In partially observable Markov decision processes, the optimal policy generally depends on the history of observations and past actions. Asymmetric actor-critic methods have become popular to learn such policies when additional information, such as the true state of the environment, is available during training. The critic, which is not needed at execution, is given access to the state. A critic conditioned on the state alone is generally ill-defined and yields biased policy gradients. Conditioning on the state and the history, the history-state critic restores both. In this paper, we show that conditioning the critic on the state and the policy's own
memory, i.e., the internal representation of the history through which the policy selects its actions, is already well-defined and gives unbiased policy gradients, removing the need for a second recurrent approximator of the history. We call it the
memory state critic. It follows that a critic based on the policy's
memory need not backpropagate its loss into that
memory, even though the
memory is a lossy encoding of the history. We evaluate the
memory-state critic in a
vision-based pursuit-evasion environment between two quadrotors across two arena types. The pursuer is the learning
agent, and the evader is sampled per episode from a fixed pool of heuristic behaviours. The results show that the
memory-state critic outperforms the history-state critic and converges faster. In addition to being unbiased compared to the state-only critic, it maintains a slight edge in the wall arena, where the actor's history carries information that the privileged state alone does not.
Read the full abstract ▾
All authors Arthur Louette, Alejandro Sánchez Roncero, Gaspard Lambrechts, Pascal Leroy, Julien Hansen, Petter Ögren, Damien Ernst
Computation and Language
OncoNoteBERT: A Foundation Representation Model for Natural Language Processing of Real-World Outpatient Oncology Notes
Wuraola Oyewusi, Eliana Vasquez Osorio, Goran Nenadic et al. (+1 more)
Real-world outpatient oncology notes contain specialised terminology, tumour staging expressions, treatment names, toxicity descriptions, and institution-specific de-identification markers that may not be represented efficiently by general biomedical or adjacent clinical
language models. We developed and evaluated oncology-specific BERT-style encoders using a governed UK outpatient oncology corpus comprising 290,026 notes from 21,564 patients treated for lung and head-and-neck cancer. We compared RadBERT and PathologyBERT with two local strategies: OncoNote-RadBERT, produced by continued masked
language model pretraining, and OncoNoteBERT, trained from scratch with an oncology WordPiece tokenizer. Models were evaluated using masked
language modelling loss and perplexity on the validation set, tokenizer fragmentation metrics, clinical term tokenisation, masked-
token probes, and exploratory representation analysis. Both external encoders fit the oncology corpus poorly in zero-shot evaluation (perplexity 113.04 for RadBERT; 2035.03 for PathologyBERT), while continued pretraining produced the strongest fit (2.10 for OncoNote-RadBERT). OncoNoteBERT achieved perplexity 2.83 but produced the most efficient tokenisation, with lower subword fertility and shorter normalised sequence length. It also returned a clinically acceptable prediction for 12 of 13 masked-
token probes, compared with 7 of 13 for OncoNote-RadBERT. This divergence between corpus-level fit and masked-
token performance was partly attributable to tokenizer fragmentation rather than learned semantics alone. Both locally developed models represented the institutional placeholder as a single learnable
token. These findings show that continued adaptation and bespoke tokenisation provide complementary benefits, and that representation-layer design matters before adjacent-domain encoders are applied to oncology NLP.
Read the full abstract ▾
All authors Wuraola Oyewusi, Eliana Vasquez Osorio, Goran Nenadic, Gareth Price
Robotics
TACET: Context-Appropriate Acoustic-Social Navigation for Quadrupeds
Sungsan Park, Young-Sik Shin and Sanghyun Kim
Quadruped
robots entering hospitals, care homes, and quiet offices must be context-appropriate not only in where they move but in how loudly they move: a legged
robot's locomotion noise, dominated by foot-ground impacts, is itself a social variable. Prior social
navigation respects human space but treats the
robot as acoustically uniform, while quiet-locomotion methods reduce noise to an operator-specified, context-blind level. We present TACET, a context-appropriate acoustic-social
navigation method that infers social context from the
robot's
egocentric view and decides both where it walks and how loudly, coupling a slow fine-tuned
vision-
language reasoner to a fast reactive controller through a single compact behavior
token, <gait, speed, social_cost>. The same
token conditions both a social costmap (where to go) and a quiet locomotion policy (how loudly to move), while a structured out-of-view
memory keeps recently seen people in the reasoner's context after they leave the camera view. On a real quadruped, context-conditioned locomotion lowers locomotion noise by up to 9.3 dBA at matched speed, and across our scenarios the full method keeps personal-space compliance at 100% with low acoustic intrusion (<=2.9 dBA), jointly improving spatial and acoustic performance in the evaluated scenarios. The project page is available at https://rcilab.khu.ac.kr/tacet/.
Read the full abstract ▾
Computation and Language
The Score Is Not the Structure: Brain Alignment and Cross-Lingual Transfer
Saman Rahbar
Similarity scores are often offered as evidence that a model shares structure with the
brain or across
languages. We ask what such a score reads when that structure is removed, or when the instrument measuring it does not work, in two settings. Across seventeen
languages, a grammaticality probe transfers worse between more distant
languages (r = -0.66). But the probe's own accuracy falls along the same axis and is at chance in four
languages, four of the five most distant. Dropping them halves the explained variance, and because it also narrows the range of distances, the design cannot say how much of the gradient is the instrument. Counting the 272
language pairs as independent gives p = 0.0006 for a steering effect that is null when the seventeen
languages are the unit (p = 0.155). In
brain alignment, a training objective raises a
language model's similarity to fMRI responses from 0.10 to 0.34 (reliability ceiling 0.54), yet targets with the
brain correspondence destroyed still reach 0.31. A shuffled target scores about k/n against the real one, for rank k and n sentences, a baseline that can be computed before any model is trained. Both interventions work, yet we detect no distance-graded steering effect and no syntactic benefit from
alignment. Before reading a correspondence score, measure how much of it survives without the correspondence.
Read the full abstract ▾
Computer Vision
Are We Measuring Anticipation? Auditing Privileged Information in Procedural Video Evaluation
Mahsa Mohammadi and Sareh Rowlands
Benchmark scores license claims about the capabilities being evaluated. We audit the inference licensed by an evaluation protocol, rather than the predictive model alone. Using procedural action anticipation as a controlled case study, we study a broader evaluation-validity failure mode: a protocol can remain temporally causal and free of classical target leakage while still supplying a privileged intermediate representation. The failure is not merely optimistic accuracy, but a mismatch between the capability claimed and the construct actually measured. On Breakfast, matched recognizer-history and GT-history regimes score 30.3% and 62.3% (Delta_PH(R_BA) = +32.0, 95% Student-t interval [+24.1, +39.8]). A fixed-checkpoint 2 x 2 intervention isolates a +14.6-point test-time oracle contrast; a matched no-
video provenance probe yields a +26.8-point gap; and a boundary-independent query/history control retains a +19.4-point gap. We refer to this discrepancy as a privileged-information gap, defined relative to a specified non-oracle recovery pipeline, and propose a reusable four-condition audit. Across five evaluation settings the gap is heterogeneous; a standard 50 Salads long-term-anticipation re-implementation provides cautious support beyond the audit-specific next-action construction.
Read the full abstract ▾
Computation and Language
Same Output, Different Gold: Measuring How Reference Choice Moves a Multilingual Benchmark Score
Parth Kulshreshtha, Shivali Dalmia and Abhishek Mukherji
A
benchmark score compares a system output against a reference, and methodological
attention falls almost entirely on the first term. We measure the second. The retained annotation record of a six-
language benchmark for personally identifiable information contains two independent annotator labellings, the aggregate shipped as gold, and a reviewer gold from independent expert re-annotation of a sample. Using it, we hold the scored output fixed and exchange the reference. The score moves by 4.95 F1 points for one output and 2.00 for the other (95% CIs [3.23, 6.27] and [0.26, 3.37]), and by 7.55 in the worst
language. The comparison between two outputs moves as well: the paired interaction between reference and system is +2.95 points (CI [+1.97, +3.87]), survives correction for multiple testing, and changes one
language's margin outright. The cause is an undocumented aggregation default that usually kept one annotator when adjudication did not fire, making the shipped reference a partial copy of an output being scored. We report the resulting reference-sensitivity band, show how to compute one from any retained annotation record, and argue that the quantity belongs beside the score.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
Targeted Active Learning for Preference-Based Treatment Effects on Multivariate Outcomes
Lola Giordani, Mathieu Even, Chloé Geoffroy et al. (+3 more)
Treatment efficacy is traditionally demonstrated on the basis of a single primary outcome. However, clinical decision-making usually requires consideration of multiple outcomes, balancing expected benefits against potential risks. The relative value assigned to these outcomes varies substantially from one patient to another. Given a preference rule over outcome profiles, treatment effects and optimal policies can be defined and estimated. Such a rule is rarely available in practice: it must itself be estimated from pairwise comparisons of outcome profiles, which are costly to collect from clinical experts. We propose an active learning framework that selects which comparisons to query. Standard criteria maximize the information gained on the preference rule itself. We instead target the quantities of interest, and select the query that most reduces uncertainty on the treatment effect and on the optimal policy induced by the learned rule. Under a Gaussian process model of the preference rule, we derive a closed-form approximation of this criterion. On semi-synthetic data built from a Parkinson's disease cohort with 13 clinical outcomes, our criterion achieves lower treatment effect estimation error and lower policy regret than existing criteria at equal query budget.
Read the full abstract ▾
All authors Lola Giordani, Mathieu Even, Chloé Geoffroy, Jean-Christophe Corvol, Raphaël Porcher, Federico Pavone
Computer Vision
Beyond Token Accuracy: Prioritizing What Matters for Visual Reconstruction
Zhicheng Liu, Zhouxiang Zhao, Chenliang Wu et al. (+2 more)
Tokens have become a unified interface for
multimodal foundation models, making visual-
token communication a natural paradigm for efficient image delivery. However, existing methods typically rely on static policies that cannot jointly adapt to image content and channel conditions. Moreover, their
token-level utility objectives do not necessarily translate into improved image reconstruction quality. In this paper, we propose AdapToC, an adaptive, reconstruction-oriented visual-
token communication framework. At the transmitter, an adaptive selector jointly models image content, channel state, and communication budget to perform instance-wise resource allocation. Rather than using a fixed
token rate and protection policy, it dynamically determines how many
tokens should be transmitted and assigns different protection levels according to
token importance and current channel conditions. At the receiver, an adaptive MaskGIT receiver incorporates channel reliability into contextual
token modeling. It distinguishes
tokens with different reliability levels, preserves high-confidence observations, corrects potentially corrupted
tokens, and iteratively reconstructs missing content from the received evidence and global visual context. By co-designing
token quantity, unequal protection, and reliability-aware recovery for image-level reconstruction quality, AdapToC achieves a peak mean PSNR gain of 4.20 dB over the strongest static baseline under matched communication costs and state-of-the-art performance among the evaluated visual-
token communication methods.
Read the full abstract ▾
All authors Zhicheng Liu, Zhouxiang Zhao, Chenliang Wu, Zhaohui Yang, Zhaoyang Zhang