Game Theory
The Economic Security of Exponential EIP-1559
Ben Berger, Edward W. Felten and Robin Fritsch
We consider the problem of parameter selection for EIP-1559, a widely used gas pricing mechanism for blockchains. As opposed to previous work, we aim to achieve economic security, where the chosen parameters guarantee a lower bound on total collected gas fees whenever usage over a given time window exceeds a specified threshold. This bound can be set prohibitively high, thereby economically deterring usage above a desired level. Such guarantees are particularly relevant to long-term objectives such as limiting state growth. We apply our approach to the pure exponential version of EIP-1559 which Ethereum uses and to a variant used by Robinhood Chain and Arbitrum. To achieve economic security, we first characterize the revenue-minimizing gas-usage distribution for the exponential version and for the other variant we construct a distribution whose associated fee revenue provably approximates the minimum. Using these results, we then demonstrate how to set economically secure mechanism parameters for both variants and we discuss the associated tradeoffs.
Read the full abstract ▾
Computation and Language
Learning to Act with Task Progress: Distilling Small Agents from Compact Teacher Supervision
Wenxi Gan
Learning from large-model demonstrations offers a way to train small
agents that can complete recurring tasks without calling a large model at every step. A central design choice is what to retain from teacher trajectories that contain
reasoning, actions, and information about task progress. We introduce Task-Progress
Distillation (TPD), an offline approach that pairs each demonstrated action with a short label describing the current task stage. The student learns these compact targets and selects actions by jointly scoring admissible stage–action pairs, which a deterministic harness executes in the environment. On ALFWorld, a 1.7B student trained with 404 demonstrations achieves 72.4% mean unseen task success with either TPD or action-only supervision, compared with 48.3% for a
reasoning-trained student using constrained action selection. Explicit stages provide an additional benefit at 200 demonstrations, improving success from 48.0% to 67.7% over action-only supervision. With more demonstrations, the action-only student closes the gap, and both approaches reach 76.9% at 808 demonstrations. Shared-history analyses link part of TPD's local advantage to better decisions when moving between subgoals, particularly from object acquisition to processing. These results show that compact supervision can train effective small task
agents, while explicit task progress provides additional guidance at an intermediate demonstration budget.
Read the full abstract ▾
Machine Learning
Average-Reward Reinforcement Learning for Multichain MDPs: A Hierarchical Decomposition Approach
Huizhen Yu and Isaiah Heidt
We study learning optimal policies in average-reward multichain Markov decision processes (MDPs), where the optimal gain may depend on the initial state and recurrence structures vary across policies, creating challenges for reinforcement learning (RL) methods. We propose an asynchronous value-iteration-based RL
algorithm that requires no model knowledge beyond the MDP's transition graph and leverages Bather's decomposition to hierarchically partition the state space into communicating subsystems and transient states. This decomposition induces a recasting of the global decision problem into structured subproblems, which our
algorithm exploits. We show that the
algorithm converges to the optimal gain and produces gain-optimal policies after finite time. Building on this base
algorithm, we develop two further
algorithms: one approximately solves the multichain average optimality equations to obtain near gain-optimal policies, and another targets near bias-optimality by approximating the optimal bias function and solving an induced average-reward multichain MDP using the base
algorithm. We provide almost-sure convergence guarantees for all three
algorithms and empirically compare their tradeoffs, showing that the latter two also consistently improve transient performance relative to the base
algorithm. To our knowledge, these are the first essentially model-free average-reward RL
algorithms for general multichain MDPs without reductions to discounted problems.
Read the full abstract ▾
Computer Vision
Performance at What Cost? A Sustainability-Aware Performance Index for Cell and Nucleus Instance Segmentation
Eiram Mahera Sheikh, Alaa Tharwat and Wolfram Schenck
Pretrained models for
cell and
nuclear instance
segmentation differ substantially in architecture, pretraining data and objectives, parameter count, inference strategy, adaptation requirements, postprocessing pipeline, and computational demand. Large pretrained and foundation models are increasingly adopted because of their strong zero-shot capabilities, but their use also imposes greater energy consumption,
memory requirements, computational demands, adaptation costs, and operational carbon emissions. Whether these additional demands are justified by meaningful gains in
segmentation performance remains unclear. We address this question by introducing the Sustainability-Aware Performance Index (SAPI), a configurable metric that combines
segmentation performance, energy consumption, and model size. We
benchmark 19 pretrained and foundation models across six CellBinDB
datasets under zero-shot inference and evaluate 16 fine-tunable models using few-shot adaptation with both frozen encoder and full-model fine-tuning. We estimate energy consumption for GPU, CPU, and RAM using software-based monitoring tools. Our results show that larger and more computationally demanding models do not consistently achieve proportionate improvements in
segmentation quality. While few-shot adaptation benefits several models, the gains and resource costs vary considerably across architectures,
datasets, and adaptation strategies, causing SAPI-based rankings to differ from rankings based on performance alone. This study provides a practical framework for comparing
segmentation models more comprehensively and supports more computationally accessible and environmentally responsible model selection in biomedical image analysis.
Read the full abstract ▾
Machine Learning
HAN-Mamba: Hierarchical Selective State Space Networks for Multi-Scale Financial Volatility Forecasting
Mihai Bogdan Deaconu and Ioan Daniel Pop
Short-horizon realized
volatility forecasting requires the integration of
market information that evolves at incompatible temporal resolutions, from second-level order book dynamics to weekly regime drift. Our conference work introduced HAN-T, a hierarchical architecture in which scale-specific
Transformer encoders process short, mid, and long-horizon streams and a learned
attention fuser weighs their contributions. This article replaces the quadratic
attention encoders with selective state space (Mamba) encoders while retaining
attention only in the fuser, where the input is a three-
token set rather than a long sequence. The resulting hybrid, HAN-Mamba, summarizes each stream through a recurrent state whose input-dependent gating matches two structural properties of
volatility: persistent but decaying
memory and abrupt regime shifts. On the Optiver Realized
Volatility Prediction
benchmark under time-aware five-fold cross-validation, HAN-Mamba improves mean RMSPE over HAN-T (0.1942 vs. 0.1965) with 33% fewer parameters. Its linear-time encoders further allow the high-frequency context to be extended from 60 to 240 buckets, reducing error to 0.1927 where the
attention variant saturates, and support constant-time streaming updates at inference. Ablations attribute the gains to the encoder swap, confirm that the hierarchical prior transfers across sequence-model families, and show that the permutation-invariant
attention fuser remains the correct mechanism for cross-scale integration.
Read the full abstract ▾
Computer Vision
From Digital Human Interactions to Physics-Based Humanoid Skills: Physics-Grounded Post-Training of Interaction Generators
Kerui Chen, Jianrong Zhang, Kai Lv et al. (+1 more)
Recent methods have made promising progress in generating interactions between two
humanoids, largely relying on physics-based tracking policies to convert digital reference motions into executable trajectories. However, limited tracking capabilities restrict the range of reference motions that can be successfully executed, reducing data utilization. Moreover, even successful tracking does not guarantee physically plausible responses or faithful realization of the intended interactions. In this paper, we introduce DIGHT, a co-adaptive framework that couples a Digital human Interaction Generator with a
Humanoid Tracking policy. Our DIGHT first executes multiple text-conditioned interaction candidates in simulation using a fixed tracker. It then constructs physics-grounded preferences from the resulting rollouts, covering both general executability and interaction fidelity. Rather than collapsing these signals into a single scalar reward for candidate ranking, we align the pretrained generator using physics-decoupled
diffusion direct preference optimization (DPO), preserving criterion-specific supervision without differentiating through the simulator. To improve executability, preference pairs are derived from tracking error, friction, and floating. Additionally, to improve interaction fidelity, we propose to incorporate force feedback from simulator as a measure of contact fidelity and construct preferences over contact occurrence, location, duration, and force magnitude. The aligned generator then supplies reference motions for fine-tuning the tracker, improving compatibility between generation and physical execution. Extensive experiments demonstrate that our approach not only improves the physical plausibility of generated motions but also enables more reliable and faithful
humanoid interactions in simulation.
Read the full abstract ▾
All authors Kerui Chen, Jianrong Zhang, Kai Lv, Hehe Fan
Machine Learning · Cross-listed from stat.AP
Estimating Uncoded Crash Factors with Tabular Foundation and System One Models: Kumo Tabular and Jev
Amir Rafe and Subasish Das
Road safety programs count the coded fields of police crash records, while the officer's narrative, which often records factors the fields omit, is rarely read. A safety office thus cannot tell how much its counts miss or where to review. This study develops and evaluates a system that joins both views of the 5,601,890 Texas crashes from 2017 to 2025 into population estimates with stated validity. An in-context tabular foundation model, Kumo Tabular, reads the coded record of every crash, a calibrated System One model, Jev, reads the narratives of two probability samples, and human judgments recalibrate its probabilities. A multiwave predict-then-debias
estimator joins the three tiers, and a second human tier drawn with recorded probabilities checks the estimates by design. For hydroplaning, medical episodes, fatigue, animals, and phone use, the narrative documents more injury crashes than the coded field, 15,074 against 7,340 for phone use, and the human check agrees with all fifteen estimates within its margin. A re-read list ranked by Kumo Tabular finds confirmed discordance 7 to 58 times as often as random reading. At the planning cost of human coding, one further round of human judgments would cut the root mean square relative half-width from 22.0 to 16.2 percent, against 21.2 for reading every narrative. Two calibrated readers of different views, joined by a sampling design, give a safety office counts, a discordance map, a validated re-read list, and a reading budget, with Kumo Tabular reading the table at 15 times the speed of TabPFN 3.5.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from physics.chem-ph
LLM-Assisted Generation of Transparent, Open-Source Multiphysics Models of Electrochemical Devices
Sebastian Castro, Maya F. Schuchert, Spencer A. McCluskey et al. (+2 more)
Multiphysics continuum models are powerful tools for studying electrochemical devices, enabling in silico reactor design and resolution of local pH, potential, and concentration fields that govern device performance but are difficult to measure experimentally. However, constructing such models requires substantial numerical expertise or reliance on proprietary software. Here, we show that frontier large
language model
agents can remove this implementation burden while keeping the underlying physics under researcher control. Using one-dimensional electrochemical CO2 reduction to CO in a porous gas
diffusion electrode as a test case, we develop a machine-readable, human-specified modeling harness containing governing equations, parameters, numerical methods, logical build stages, and human-verifiable checkpoints. From this specification, the
agent reproducibly constructs complete multiphysics models in open-source Julia. Independently built models, including fully autonomous
agent-built models, agree with an equivalent COMSOL implementation to within 0.7% of the peak CO partial current density, and with one another to within 0.04%. Systematically planted errors demonstrate the importance of explicit specifications for reproducibility and reveal the
agent's capabilities and limitations in debugging model physics. This framework establishes a more transparent approach to multiphysics modeling in which physical descriptions and governing equations, rather than specialized code, become the primary inputs for computational model development.
Read the full abstract ▾
All authors Sebastian Castro, Maya F. Schuchert, Spencer A. McCluskey, Eric W. Lees, Justin C. Bui
Data Structures and Algorithms
Polynomial Kernels for Interval Completion
Zimo Sheng, Tian Bai and Mingyu xiao
An interval graph is the intersection graph of a family of intervals on the real line. Interval Completion asks whether a given graph can be transformed into an interval graph by adding at most $k$ edges. Although the problem is fixed-parameter tractable when parameterized by $k$, whether it admits a
polynomial kernel has long been an open question. We resolve this question by giving the first
polynomial kernel for Interval Completion. Our main contribution is a parameter-preserving
polynomial-time reduction from Interval Completion to Odd Cycle Transversal (OCT). Combining this reduction with the known randomized and deterministic
polynomial kernels for OCT and a
polynomial-time reduction back to Interval Completion, we obtain a randomized kernel with $\widetilde O(k^{18})$ vertices and $\widetilde O(k^{36})$ edges, and a deterministic kernel with $O(k^{36})$ vertices and $O(k^{72})$ edges. Here, $\widetilde O$ suppresses polylogarithmic factors in $k$.
Read the full abstract ▾
Computation and Language
Nobody Truly Agrees on Sentiment: Humans, Bespoke Tools, and LLMs Struggle with Social Media Texts
Himarsha R. Jayanetti, Sivakanesan Dhanushkanda, Shuai Hao et al. (+2 more)
Social media is a rich source of real-time public sentiment, but widely used sentiment analysis tools are often applied without understanding their limitations. In this study, we evaluate the inter-rater reliability of three bespoke sentiment analysis tools (TextBlob, VADER, and Twitter-roBERTa-base) and three large
language models (LLMs: Qwen3-32B, GPT-OSS-120B, Llama-4-Maverick-17B) against six human raters across 100 tweets. We measured agreement using two statistical measures: Cohen's kappa for pairwise comparisons and Fleiss' kappa for multiple raters. Even among the human raters, our results showed only fair agreement, highlighting the subjectivity of sentiment analysis. Higher agreement was observed under the binary sentiment classification (negative vs. non-negative and positive vs. non-positive) than under the three-class classification across both humans and automated tools. The Twitter-roBERTa-base model showed the strongest
alignment with human ratings, outperforming both bespoke sentiment tools and LLMs, particularly in distinguishing negative versus non-negative sentiment. LLMs showed substantial agreement among themselves and moderate to substantial
alignment with humans, performing better in positive vs. non-positive classifications. Our findings underscore that domain-specific fine-tuning remains crucial for reliable social media sentiment analysis, and human-centered evaluation remains essential for establishing gold-standard labels.
Read the full abstract ▾
All authors Himarsha R. Jayanetti, Sivakanesan Dhanushkanda, Shuai Hao, Michael L. Nelson, Michele C. Weigle
Machine Learning
Thinking in Depth: Retrospective Inference for Tabular Foundation Models
Hao-Run Cai, Si-Yang Liu, Zi-Jian Cheng et al. (+8 more)
Tabular foundation models (TFMs) are pretrained across diverse tabular tasks and make predictions on a new table at inference time using its labeled examples as context. Most recent TFMs perform such in-context prediction with stacked
Transformer layers, repeatedly transforming how examples are represented and compared. By tracing individual queries through several strong TFMs, we find that predictive refinement is highly uneven across depth and is often concentrated in later layers. This uneven refinement motivates us to reconsider how intermediate representations are constructed and reused throughout the network. We introduce Retro, a tabular foundation model based on retrospective inference, where later stages can explicitly revisit and recombine intermediate information produced earlier in the network. Retro organizes this process around two complementary operations: which intermediate information to revisit, and how the resulting contextual update should be shaped for each query.
Attention Residuals address the former by adaptively reweighting contributions from different depths, while query-conditioned Gated
Attention addresses the latter by modulating the
attention output element-wise across representation dimensions. Our analysis shows that Retro shifts predictive refinement earlier and more broadly across depth, with different stages revising different subsets of queries in a pattern suggestive of multi-view refinement. Across TabArena, TALENT, and RelArena, Retro ranks among the top three and lies on the Pareto frontier. These results indicate that directly reusing intermediate representations provides a practical way to better exploit depth in TFMs.
Read the full abstract ▾
All authors Hao-Run Cai, Si-Yang Liu, Zi-Jian Cheng, Kun-Yang Yu, Jin-Hao Sheng, Guo Yu, Chonghan Liu, Zhi Zhou, Jun-Peng Jiang, Lan-Zhe Guo, Han-Jia Ye
Machine Learning
PoreML: A Data-Driven Framework for Learning Multiphase Flow in Porous Media
Chunyang Wang, Mingrui Zhang, Yuyan Zhang et al. (+5 more)
Multiphase flow in porous microstructures is central to CO$_2$ storage, fuel-
cell operation, and flip-chip packaging. Predicting these flows remains challenging because wettability and complex pore geometry govern the nonlinear
evolution of fluid interfaces. Machine learning holds substantial promise for advancing the field, but progress is constrained by scarce time-resolved 3D
datasets and a lack of a unified workflow for training and evaluating models. To fill this critical gap, we introduce PoreML, an open-source framework unifying data generation, model training, and evaluation grounded in pore-scale physics. The framework comprises three core components. (a) A modern GPU-native
lattice Boltzmann solver, validated against analytical solutions and published experiments, enables reproducible data generation. (b) A 3.3 TB
dataset contains 560 simulation runs and 158,546 stored time steps across four application-driven scenarios. These trajectories span synthetic structures and geometries derived from micro-CT scans of real materials, covering diverse wetting conditions and viscosity ratios. (c) A unified learning framework evaluates one-step prediction and autoregressive rollouts. Its domain-specific evaluation protocols assess predictive accuracy and physical consistency. We evaluate five models of diverse architecture under these protocols. Two complementary challenges assess transfer to larger domains and from synthetic to micro-CT-derived structures. PoreML provides a shared foundation for machine-learning research on multiphase flow in porous media, with the aim of empowering the community to develop reliable predictive models and advance the field.
Read the full abstract ▾
All authors Chunyang Wang, Mingrui Zhang, Yuyan Zhang, Linqi Zhu, Xin Ju, Edo Sicco Boek, Martin J. Blunt, Gege Wen
Machine Learning
Fault-tolerant foundation models
Trevor McCourt, Ila R. Fiete and Isaac L. Chuang
Emerging computer hardware often trades reliability for energy efficiency; here we show that large-
language models (LLMs) can be trained to tolerate this unreliability, and that rather than degrading, their error resilience actually increases as they grow. Modified neural scaling laws inferred from 40,000 GPU-hours of training runs on simulated faulty digital hardware quantify this trend and suggest that models learn to compute within "good" error-correcting codes, whose relative overhead remains finite no matter how large the model gets. This finding leads us to
conjecture that appropriately trained LLMs may be formally fault-tolerant; if true, running AI inference on low energy, faulty hardware may be a path to substantial energy savings over the status quo.
Read the full abstract ▾
Machine Learning
RSIGym: A Flexible Environment for Recursive Self-Improvement
Fanqing Meng, Lingxiao Du, Haocheng Lu et al. (+6 more)
Recursive self-improvement requires carrying accepted changes into later improvement cycles, while studying
agent-proposed changes also requires substantial research infrastructure. Existing settings often leave
agents to rebuild routine infrastructure or restrict exploration to individual components. We introduce RSIGym, an
agent-native research environment based on Everything as a Service (EaaS). RSIGym exposes training, inference, rollout, evaluation, and sandbox execution through reusable services, with shared budget and permission controls supporting Data, Harness, and Joint improvement tracks. This design enables
agents to investigate individual interventions and jointly optimize data, training settings, and execution harnesses within the same environment. We define RSI-Index as the mean fraction of the remaining performance gap closed across five
benchmarks covering software engineering, terminal interaction, mathematics, scientific
reasoning, and skill-based tasks. Comparing six frontier research models in independent Joint runs, Opus 5 achieves the highest RSI-Index of 0.4809 under a $500 platform-service budget per
benchmark run. Its selected systems improve all five
benchmarks, raising SWE-bench Verified from 17.67% to 50.33% and AIME from 31.67% to 97.78%. Additional experiments examine DSH-harness refinement, budget variation, and restricted network access, while recorded trajectories reveal how
agents diagnose failures and select candidates. We open-source the full RSIGym codebase and results to support reproducibility and further research.
Read the full abstract ▾
All authors Fanqing Meng, Lingxiao Du, Haocheng Lu, Qiguang Chen, Ziqi Zhao, Zijian Wu, Jiayuan Zhuo, Mengkang Hu, Michael Qizhe Shieh
Information Theory · Cross-listed from eess.SP
Antenna Coding by Pixel Antennas: Unlocking A New Dimension for Wireless Communications
Zixiang Han, Shanpu Shen, Yifei Yuan et al. (+3 more)
Conventional wireless communication systems employ
antennas with fixed radiation patterns. Enhancing system performance by increasing the number of
antennas would push the limits of cost and size for communication devices. To overcome this issue, novel
antenna technologies are urgently desired to break through the fundamental performance bottleneck and engineering limits. Pixel
antennas provide a general framework for highly reconfigurable
antennas, which can flexibly adjust radiation patterns via controlling variable lumped elements placed across adjacent pixels, unlocking novel degrees of freedom (DoF) in the beamspace domain. Recently, an emerging
antenna coding technique links wireless system performance to the
antenna configurations. This enables the use of pixel
antennas to enhance system performance by leveraging the DoF from the
antenna side. In this article, we provide a comprehensive overview on
antenna coding by pixel
antennas. Specifically, based on the pixel
antenna model, the concept of
antenna coding is firstly introduced, followed by a discussion on the classifications of
antenna coding. Two cases for channel gain and multiplexing gain enhancement are highlighted to show the effectiveness of
antenna coding in wireless communications. Besides, various optimization approaches for
antenna coding design are investigated. Finally, the challenges and opportunities are outlined, providing guidance for future works.
Read the full abstract ▾
All authors Zixiang Han, Shanpu Shen, Yifei Yuan, Jiangzhou Wang, Ross Murch, Chih-Lin I
Computer Vision
One-Shot Adaptive Segmentation For Scientific Images
Tejaswi V. Panchagnula, Allison M. Davis and Fengqing Zhu
Scientific image
segmentation methods rely on extensive annotation and task-specific training, limiting adaptation across imaging modalities and experimental conditions. We present a training-free, one-shot framework that specializes
vision foundation models using a single annotated reference image. The framework combines DINOv3 representations with background-adaptive feature orthogonalization to suppress artifact-related feature directions, after which cosine similarity localizes candidate regions for SAM
segmentation. We evaluate the framework on red-blood-
cell microscopy, structured-illumination pool boiling, and chest radiography. Relative to the strongest baseline, the proposed method improves mean IoU by 5.91% and 78.62% on the microscopy and pool-boiling
datasets, respectively, while achieving comparable performance on chest radiographs. These results demonstrate that one-shot reference conditioning can adapt general-purpose
vision models to specialized scientific
segmentation tasks.
Read the full abstract ▾
Machine Learning
Eduardo Santos-Escriche, Valerie Engelmayer, Ya-Wei Eileen Lin et al. (+1 more)
Training
Transformer-based architectures with finite data augmentation has become an increasingly popular approach in
geometric machine learning. Despite its empirical success, the interplay between the
Transformer architecture, invariance to different
symmetries, and augmentation budgets remains underexplored. In this paper, we study the ability of a vanilla
Transformer to learn various
symmetries through finite data augmentation for point cloud
datasets. We identify an ordering of increasing learnability across the following
symmetry groups: (i) non-angle-preserving
symmetries, (ii) angle-preserving
symmetries, and (iii) base angle-preserving subgroups, such as translation, rotation, and scale. For the base angle-preserving groups, we further investigate the
Transformer's extrapolation behavior and conduct a structural analysis of the trained models, allowing us to identify interpretable mechanisms that induce invariance. Finally, we extend our analysis to equivariant functions and show that the detected mechanisms for approximate invariance can also provide a key building block for learned equivariance. Our project page is available at https://
transformers-learn-
symmetries.github.io/
Read the full abstract ▾
All authors Eduardo Santos-Escriche, Valerie Engelmayer, Ya-Wei Eileen Lin, Stefanie Jegelka
Machine Learning
SemanticFold: Latent Sequence Compression SeparatesLanguage Modeling, Decodability, and Reasoning
Mingyan Liu and Min Huang
We study whether latent sequence compression of
prompt prefixes preserves the capabilities that large
language models rely on during inference. We introduce SemanticFold, a compression scheme that folds prefix hidden states at learned boundaries, and evaluate it across five model scales: Qwen3-1.7B, Qwen3-8B, SmolLM2-1.7B, Pythia-1.4B, and Pythia-6.9B. We use a fixed-target protocol: a frozen prefix is executed natively or compressed, and both arms teacher-force identical continuation
tokens. This design rules out target-selection explanations for likelihood changes. We examine five endpoint families: fixed-target negative log-likelihood, finite-label
reasoning accuracy, linear probe accessibility, open-ended generation, and systems-level
memory and latency. We find that compression moves these endpoints non-monotonically and that they do not share a single compression threshold. On Qwen3-1.7B at compression ratio R=1.7, compressed-minus-native mean NLL decreases by 0.135 under paired bootstrap with 10000 draws. On SmolLM2 at R=1.2, the mean change is 0.013 higher than native. On both Pythia checkpoints, NLL is effectively unchanged. An NLL decomposition separating sequence shortening from the learned residual transform shows that the favorable Qwen likelihood is attributable primarily to residual adaptation rather than to shortening alone. MLP-only, which applies the transform without shortening, achieves 0.082 lower NLL than Full SemanticFold. Linear probe accuracy and macro AUC change by less than 0.03 in absolute value across conditions, with confidence intervals crossing zero. We conclude that preservation under latent compression has no single scalar certificate:
language-model fit, decodability, and
reasoning behavior answer different questions and can move in different directions under the same compression operation.
Read the full abstract ▾
Computer Vision
Junhyeok Kim, Jinyeong Kim, Jae Wan Park et al. (+1 more)
The standard
Transformer architecture relies on a rigid pattern that alternates
Attention and Feed-Forward Network (FFN) layers. Despite its widespread adoption, the inductive bias imposed by this strict separation has not been systematically examined. In this work, we investigate the necessity of the
Attention-FFN dichotomy in
Vision Transformers (ViTs). To facilitate this analysis, we introduce the AttenFeed module, a unified component that integrates the functional properties of both
Attention and FFN. Based on this module, we devise the unified
Vision Transformer (uViT), which replaces the conventional alternating
Attention-FFN structure with a sequence of AttenFeed modules. We then use uViT as a control group that relaxes the
Attention-FFN dichotomy of the standard ViT and systematically compare the two models across multiple
datasets and model scales. Our experiments reveal that the
Attention-FFN dichotomy can hinder performance at smaller model scales due to the rigid parameter allocation of ViTs. The AttenFeed module and uViT serve as new analytical tools for understanding the
Attention-FFN structure and offer theoretical insights into the heuristically designed architecture of conventional ViTs.
Read the full abstract ▾
All authors Junhyeok Kim, Jinyeong Kim, Jae Wan Park, Seong Jae Hwang
Machine Learning
Continual Graph Multi-Agent Reinforcement Learning
Tommaso Marzi, Ahmed Hendawy, Jan Peters et al. (+3 more)
In Continual Multi-
Agent Reinforcement Learning (CMARL),
agents learn cooperative policies across sequences of tasks, aiming to adapt effectively to new tasks while preserving the ability to solve previously encountered ones. In many applications, tasks differ in their underlying structure, which can represent, for example, distinct operational conditions or target configurations (e.g., different network
topologies in power grids or arrangements in formation control). Existing CMARL methods lack dedicated mechanisms to leverage this structural information when learning new tasks, failing to promote transfer and mitigate forgetting. To fill this gap, we propose Continual Graph Multi-
Agent Reinforcement Learning (CGMARL), a novel framework for CMARL problems in which task sequences are mapped into a series of attributed graphs, each modeling a task-specific structure. In CGMARL, each graph determines the environment dynamics (next states and/or rewards) and the number of
agents for the corresponding task. Then, we present Graph-based Formation (GRAFO), the first CGMARL
benchmark, and show how forgetting arises in this setting. Finally, to address this limitation, we propose Frozen Graph Encoder (FROG), a method that relies on a frozen graph backbone to preserve past structural information in graph-based CMARL policies. Experiments on GRAFO show that pairing FROG with existing CL methods substantially improves performance on multiple CGMARL scenarios.
Read the full abstract ▾
All authors Tommaso Marzi, Ahmed Hendawy, Jan Peters, Carlo D'Eramo, Andrea Cini, Cesare Alippi
Machine Learning
Revisiting Explainable AI through Model-Independent Concept Dictionaries
Thomas Schnake, Doreen Schöppenthau, Alexander Meyer et al. (+3 more)
Modern applications of AI rely on increasingly complex models. Explainable AI (XAI) has emerged as a set of techniques aimed at improving model transparency. However, existing XAI methods typically assume input features to be inherently interpretable, or they rely on intermediate internal abstractions that are difficult to characterize and highly architecture-specific, hindering consistent use across models. To address these limitations, we propose DictXAI, a method that defines concepts directly in the input domain via a dictionary—a large, potentially overcomplete set of predefined elements, each carrying an interpretable meaning. Technically, DictXAI first computes a sparse code of the input and then attributes the model's prediction to the associated dictionary elements. We demonstrate the actionable nature of DictXAI explanations, showing that they can attribute AI malfunctions (e.g., Clever Hans effects) directly to identifiable artifact patterns in the data, while fostering human-AI
alignment on intricate biomedical signals. We further demonstrate our method's ability to operate across a wide variety of dictionaries, including learned image bases, analytically defined waveforms for electrocardiography, and experimentally acquired dictionary elements. Overall, our results show that DictXAI provides more interpretable, actionable, and architecture-agnostic insights than classical XAI or existing concept-based approaches.
Read the full abstract ▾
All authors Thomas Schnake, Doreen Schöppenthau, Alexander Meyer, Jacques Corbeil, Klaus-Robert Müller, Grégoire Montavon
Machine Learning
Shared Gaussianization: What Gaussian Regularizers Certify About Contrastive Learning, and What They Miss
Ruoyu Zhao, Yuting Chen, Jinheng Zhang et al. (+2 more)
What can a distribution-matching regularizer such as SIGReg in LeJEPA certify about contrastive learning? We study shared Gaussianization (SG), a characteristic-function Gaussianity test on the average of two normalized views, scaled by an independent $\chi_d$ radius. Because disagreeing views shorten the average, one test detects both misalignment and non-uniformity. SG vanishes exactly at the aligned, uniform minimizers of population InfoNCE, and under equal marginals it bounds the InfoNCE excess by $4\cdot 3^{3/4}\beta$ times the square root of the SG loss, plus a term linear in the loss. The square-root rate and this dimension-free constant are sharp, and no squared mean-
embedding distance on view pairs achieves a faster rate. With an explicit
alignment term, a rotation-invariant uniformity test gives a linear bound if and only if its spectrum dominates that of InfoNCE's kernel $e^{\beta u^\top v}$; SG's own test does, Gaussian kernels $e^{-\gamma \|u-v\|^2}$ qualify exactly when $\gamma \ge \beta/2$, and moment matching never does. Away from the optimum, the objectives differ. Along an isotropic nuisance channel, pure SG lowers its loss by adding per-view nuisance whenever the shared code is non-uniform. An
alignment weight above the channel's gain makes the nuisance-free solution a strict local minimizer; for LeJEPA, the same rule gives a critical SIGReg weight that decreases with the batch size. At finite batch size, an off-diagonal U-statistic removes a plug-in bias toward misalignment. In controlled latent-variable models, pure SG retains per-view style, an
alignment weight above the measured gain removes it, and for LeJEPA at three batch sizes the measured gain separates the encoders that retain style from those that do not. InfoNCE training also reaches a lower SG$_{0.2}$ loss than SG$_{0.2}$ training from scratch, which points to an optimization gap.
Read the full abstract ▾
All authors Ruoyu Zhao, Yuting Chen, Jinheng Zhang, Zhehao Zou, Tong Che
Machine Learning
Physics-Aligned Electronic Ground-State Learning Improves Generalization
Eike S. Eberhard, Xaver Kainz, Viktor Kotsev et al. (+2 more)
Machine-learned interatomic potentials (MLIPs) excel at in-distribution tasks, accelerating drug and material development, yet they struggle to generalize out-of-distribution. We propose to push the cost-accuracy Pareto frontier by designing observable-agnostic electronic ground-state descriptor models (GSMs) with computational costs situated between MLIPs and Kohn-Sham density functional theory (KS-DFT). We align the learning objectives and architectures of GSMs with the governing equations of KS-DFT by enforcing physical constraints and removing optimization pressure on unphysical or irrelevant degrees of freedom. In our size-extrapolation experiments from QM9 to QM40, our combined contributions OrthoNormal-Loss (ON-Loss) and Grassmann Restricted Occupied-Orbital Training (GROOT) reach a 79.1% energy and 83.4% force mean absolute error (MAE) reduction over previous state-of-the-art density GSMs. For
Hamiltonian GSMs, ON-Loss and Residual Optimal-gauge Conditioning-aware KS-Eq. Training (ROCKET) together reduce the energy and force MAEs of the strongest baseline by 99.8% and 95.9%, respectively. Using a self-consistency rejection criterion, we filter out extrapolation errors on QMugs, rejecting fewer than 0.4% of predictions while reaching an energy MAE of 0.07 mHa. Finally, we demonstrate the efficiency of label-free self-consistency fine-tuning, and transfer GSMs to reactive chemistry in Transition1x, reaching energy errors below chemical accuracy.
Read the full abstract ▾
All authors Eike S. Eberhard, Xaver Kainz, Viktor Kotsev, Abdulrahman Aldossary, Stephan Günnemann
Robotics
Energy-Efficient Gait Adaptation via Hierarchical Reinforcement Learning for Quadrupedal Locomotion Across Diverse Terrains
Ammar Issa, Anubhav Singh, Anton Tsaritsin et al. (+1 more)
While energy efficiency is a critical objective for legged-
robot locomotion control, achieving low energy consumption while maintaining robust performance across different velocity ranges and terrain conditions remains a key challenge. This is particularly true for end-to-end RL policies, where gait generation, motion execution, and energy optimization are tightly coupled, leading to high sensitivity to reward design. In this work, we propose a hierarchical reinforcement learning (HRL) framework that separates a high-frequency policy for stable and robust joint-level motion execution from low-frequency gait adaptation that explicitly minimizes the cost of transport (CoT). The three-stage Isaac-based training procedure enables zero-shot sim-to-real transfer with improved tracking accuracy, robustness, and energy efficiency. The learned hierarchy exhibits automatic speed-dependent gait adaptation, transitioning from pacing at low speeds to trotting at higher speeds. We validate the proposed approach in simulation against representative single-policy and hierarchical locomotion baselines, demonstrating reduced CoT over a broad range of commanded velocities, while maintaining robust locomotion across flat, uneven rough, and inclined terrains. We further demonstrate its practical feasibility through zero-shot deployment on a physical Unitree AlienGo quadruped.
Read the full abstract ▾
All authors Ammar Issa, Anubhav Singh, Anton Tsaritsin, Sergey Kolyubin
Game Theory
Sharper bounds on the thresholds for sensitive and Blackwell optimality
Xavier Allamigeon, Stéphane Gaubert, Julien Grand-Clément et al. (+1 more)
In perfect-information two-player
stochastic games, the notions of Blackwell and sensitive optimality provide generalizations of the classical mean-payoff optimality and discount optimality criteria to account for more farsighted preferences. We provide bounds on the Blackwell threshold $\alpha_{\sf bw}$ and the $d$-sensitive thresholds $\alpha_{\sf d}$, defined as the smallest discount factors above which discount optimal policies coincide with Blackwell optimal policies and $d$-sensitive optimal policies respectively. Our refined bounds improve upon prior work by focusing on “reduced” families of
polynomials and, crucially, our bounds are tight in terms of controlling the degrees and heights of the minimal
polynomials of the Blackwell thresholds. We apply classical root separation based on Mahler's and Cauchy's bounds to our reduced families to derive the strongest upper and lower bounds on $\alpha_{\sf bw}$ in the literature, and we are the first to obtain bounds on $\alpha_{\sf d}$ in the multichain
stochastic setting.
Read the full abstract ▾
All authors Xavier Allamigeon, Stéphane Gaubert, Julien Grand-Clément, Ricardo Katz
Numerical Analysis
BDF2-type integrator for Landau-Lifshitz-Gilbert equation in micromagnetics: IMEX time-stepping and full effective field
Michele Aldé, Dirk Praetorius and Agus L. Soenjaya
We extend the BDF2-type finite-element integrator proposed in [M. Aldé, M. Feischl, D. Praetorius; BDF2-type integrator for Landau-Lifshitz-Gilbert equation in micromagnetics: unconditional weak convergence to weak solutions. (Math. Comp., 2026, doi:10.1090/mcom/4210)] to the Landau-Lifshitz-Gilbert (LLG) equation with lower-order effective-field contributions and current-induced non-conservative torques arising in micromagnetic applications. To incorporate these additional terms while retaining a linear solve at each time step, we employ an implicit-explicit (IMEX) time splitting. Our main
theorem proves unconditional weak convergence of the fully discrete approximations towards weak solutions of the LLG equation. The analysis removes the mild but artificial CFL-type restrictions required at the first and final time steps in [Aldé M., Feischl M., Praetorius D.; Math. Comp., 2026]. Furthermore, in the presence of the Dzyaloshinskii-Moriya interaction (DMI), the convergence is likewise unconditional and does not require the CFL-type restriction imposed in [G. Hrkac, C.-M. Pfeiler, D. Praetorius, M. Ruggeri, A. Segatti, and B. Stiftner. Convergent tangent plane integrators for the simulation of
chiral magnetic skyrmion dynamics. (Adv. Comput. Math., 2019. doi: 10.1007/s10444- 019-09667-z)]. Numerical experiments support the theoretical findings.
Read the full abstract ▾
Computer Vision
TouchScale: 500 Hours of Human Vision and Touch for Visual-Tactile Learning
Dayou Li, Hao Wang, Qianqian Yang et al. (+23 more)
Large-scale
egocentric human interaction data is becoming an important source of physical supervision for
embodied learning, yet
video alone leaves the contact and pressure that characterize physical interaction unrecorded. Recent visual-tactile
datasets provide this missing supervision, but their synchronized tactile data remain far smaller in volume than human
video. Moreover, the largest resources often merge recordings from different sensors or annotation procedures, which makes the effect of data scale difficult to isolate. We therefore introduce TouchScale, a 500-hour
dataset of contact-rich human interaction recorded with a single unified wearable setup. Its approximately 2K predefined task descriptions span everyday activities and structured manipulation, and each recording temporally aligns
egocentric RGB-D
video with wrist RGB
video and dense full-hand bimanual tactile measurements. Compared with prior tactile data, training on the full TouchScale raises zero-shot contact IoU on data from an unseen tactile sensor from 0.134 to 0.383. Pretraining a visual encoder on TouchScale also yields the highest action recognition accuracy on three
benchmarks among the compared visual-tactile
datasets. Used for visual-tactile mid-training of a
robot policy, TouchScale improves the average real-world success rate across four contact-rich manipulation tasks from 22.5% to 57.5%. With the sensor and collection protocol held fixed, both zero-shot tactile prediction and
robot success show an overall upward trend as more TouchScale data is used. These results suggest that human visual-tactile data collected at scale with consistent sensing benefits both perception and
robot manipulation. We will publicly release TouchScale, including all synchronized visual-tactile recordings and reconstructed object models, to support future research on scalable visual-tactile learning.
Read the full abstract ▾
All authors Dayou Li, Hao Wang, Qianqian Yang, Zihao Zhu, Haoquan Fang, Ziyao Zeng, Yan Han, Zihan Wang, Yan Wang, Baoru Huang, Dilin Wang, Kenji Shimada, Yiyue Luo, Manling Li, Teresa Lv, Mustafa Mukadam, Rakesh Ranjan, Ruohan Zhang, Qi He, Changliu Liu, Xu Chen, Marco Pavone, Bangya Liu, Jiachen Li, Masayoshi Tomizuka, Zhiwen Fan
Computer Vision
$\Delta$Representation: Geometry Supervised Representation Learning of Phenotypes via Counterfactual Reasoning for Medical VLMs
Hao Wang, Qiwei Zeng, Jinghao Lin et al. (+6 more)
Medical
vision-
language models (VLMs) have shown increasing potential for radiological image interpretation. Medical VLMs encode radiological images into visual representations that capture both anatomical and phenotypic information for diagnosis. Existing approaches improve pathological phenotype representations through semantic-guided representation
alignment. However, pathological phenotypes arise as lesion-specific visual changes superimposed on underlying normal anatomy. Such semantic
alignment approaches fail to model the phenotype-specific increment relative to the corresponding normal anatomical representation. To address this gap, we propose \textbf{$\Delta$Representation}, a visual phenotype representation learning framework based on counterfactual
reasoning for medical VLMs. It comprises BaseAnatomy, a geometry-supervised representation learning module, and \textbf{$\Delta$Phenotype}, a counterfactual incremental representation learning module. BaseAnatomy provides fine-grained
geometric supervision through spatial relationships across and within anatomical structures. $\Delta$Phenotype computes the representation increment between lesion representations and their corresponding normal anatomical representations, and supervises increments associated with the same phenotype to cluster in the representation space. Experiments on ReXGroundingCT and LIDC-IDRI demonstrate that $\Delta$Representation effectively structures pathological phenotype representations and improves lesion grounding and phenotype characterization accuracy in medical VLMs. Code is available at https://anonymous.4open.science/r/deltarep-CF6D.
Read the full abstract ▾
All authors Hao Wang, Qiwei Zeng, Jinghao Lin, Shuchang Ye, Yuezhe Yang, Yige Peng, Haoyuan Che, Jinman Kim, Lei Bi
Artificial Intelligence
AI Safety Considerations for Agents With Limited Time to Act
Leo Zeitler, Jack Richings and Victoria Nockles
In the wake of the increasingly public discussion about AI
alignment, recent work has tried to propose specific AI architectures that behave safely. However, the proposed arguments that seemingly demonstrate proved
alignment mostly neglect the environment the
agent needs to act in. We discuss theoretical bounds for
agent-agnostic safety guarantees in environments that can only be partially observed and within which an action is required within limited time. We introduce two realistic scenarios, one with an infinite state space and one with signal mixture. In these scenarios, we prove that even a perfect
agent cannot guarantee safe behaviour. It will be argued that for any proof of AI safety or
alignment, the environment and associated safe actions need to be specifically considered together with the
agent.
Read the full abstract ▾
Robotics
Temporal Visuo-Tactile Learning for Dexterous Grasp Stability
Ken Nakahara, Aleksei Buvailik, Prokhor Kotov et al. (+1 more)
Humans can grasp everyday objects with almost perfect success rates using fingertip tactile feedback, yet much of the robotic grasping literature emphasizes
vision-based grasp selection with parallel grippers. In this work, we systematically investigate how high-resolution, dynamic tactile sensing contributes to grasp stability prediction and model-guided grasping in dexterous robotic hands. To this end, we collected a
dataset of 10,000 grasp trials across 200 objects using a multi-fingered robotic hand equipped with four Digit 360 tactile sensors, recording external
vision, proprioception, and tactile streams throughout each grasp. With this
dataset, we trained end-to-end temporal
multimodal models to predict post-lift stability from pre-lift grasp observations and compared sensing modalities and encoding backbones. Experimental results and controlled input ablations show that incorporating touch, and particularly high-resolution, dynamic touch, improves grasp stability prediction. Finally, we deployed the learned predictor as an online stability gate on the real
robot, where visuo-tactile model-guided regrasping improved the success rate among executed lifts by 10.5 percentage points over a non-tactile gate. These results show how rich fingertip sensing and expressive temporal models that capture the dynamics of touch can support learned grasping with multi-fingered hands without explicit contact or force modeling, providing a scalable data-driven path from tactile experience toward stable dexterous manipulation. The
dataset is publicly available at https://lasr-lab.github.io/dexterous-grasp-stability/.
Read the full abstract ▾
All authors Ken Nakahara, Aleksei Buvailik, Prokhor Kotov, Roberto Calandra