Machine Learning
Understanding Decision-Making Mechanisms in Neural Routing Solvers
Fatemeh Askari, Mazdak Teymourian, Mohammad Izadi et al. (+1 more)
Neural Combinatorial Optimization (NCO) has achieved strong empirical success, yet the internal mechanisms driving model decisions remain largely unexplored. In this paper, we investigate three representative autoregressive NCO models spanning two encoder-decoder configurations: AM and POMO (heavy-encoder, light-decoder), and LEHD (light-encoder, heavy-decoder). Through behavioral analyses, representation probing, and causal interventions, we examine how these models construct solutions and use internal representations during decoding. Our results suggest that AM and POMO predominantly follow a persistent
geometric pattern throughout solution construction, whereas LEHD contains linearly accessible information about multiple future actions. Causal experiments further provide evidence for the role of future-node representations in LEHD's decision-making. We also observe that LEHD relies strongly on the current-node representation for immediate local decisions, while the start-node representation plays a broader navigational role over the subsequent route. Cross-instance
alignment analyses additionally indicate that LEHD maps current-node representations into a relatively shared latent region, which may provide a stable reference for evaluating subsequent decisions. Across the Traveling Salesman Problem and the Capacitated Vehicle Routing Problem, these results reveal distinct decision-making patterns across these architecturally distinct solvers and provide a foundation for more interpretable analyses of NCO solvers. Code and additional visualizations are provided in the https://github.com/NCO-Interpretability/NCO-Interpretability.
Read the full abstract ▾
All authors Fatemeh Askari, Mazdak Teymourian, Mohammad Izadi, Mahdieh Soleymani Baghshah
Artificial Intelligence
SMat-Attention: Structured Long-Context Sequence Modeling
Emile Anand, Abdullah Ateyeh, Archer Wang et al. (+1 more)
Long-context sequence models face a fundamental tradeoff: softmax
attention uses flexible
token-level interactions at quadratic cost, whereas linear
attention obtains linear-time training and constant-time decoding by compressing history into a fixed-size state. In this work, we ask whether we can connect these regimes through a tunable notion of structure. To this end, we introduce Structured
Matrix Attention (SMat-
Attention) via a family of causal masks with structured long-range routing whose row supports have VC-dimension $d$. In our construction, $d=1$ recovers the standard causal mask, and increasing $d$ permits richer subset-routing patterns. We give chunkwise forward and backward
algorithms to enable hardware-efficiency. For sequences of length $T$, the hard-routing construction takes $O(T^{2-3/d}+T)$ work, despite the mask being dense, for our prescribed family. In fixed-horizon streaming, decoding after the distant prefix takes constant time per
token using $O(T^{1-1/d})$ cached states. SMat-
Attention therefore makes VC-dimension an explicit knob governing access-pattern complexity, prefill cost, and decoding
memory. Empirically, subset-routing and rule-assisted multi-key
retrieval experiments illustrate the masks' routing expressiveness. Extensions to Mamba-2 and Gated DeltaNet using learned routing with top-$k$ query reads retain subquadratic prefill, improve recall accuracy over the backbones in several settings, and achieve comparable small-scale
language-modeling performance.
Read the full abstract ▾
All authors Emile Anand, Abdullah Ateyeh, Archer Wang, Marin Soljačić
Machine Learning
Introducing the CZAR Loss: A Tailored Objective Function for Financial Log-Return Predictions
Joel Pfeffer, J. M. Diederik Kruijssen, Florian Stecker et al. (+1 more)
In quantitative finance, standard regression losses are misaligned with the economics of return prediction. As the conditional mean of financial log-returns is close to zero, symmetric losses such as the mean squared and mean absolute errors make the constant zero forecast a near-optimal solution, penalizing models with genuine but noisy directional skill. This applies both during training, where predictions shrink toward zero, and during evaluation, where trivial forecasters can lead loss-based rankings. Under a Gaussian linear prediction model, we show that all symmetric monotonic losses share a universal breakeven directional accuracy against the zero predictor, which rises sharply and becomes unobtainable as the prediction noise approaches the standard deviation of the returns. We introduce the CZAR (Composite Zero-Agnostic Return) loss function, a piecewise quadratic loss built around five key requirements: convexity in the prediction, asymmetry with true return direction that vanishes at zero, near-linear penalization of undershoots and wrong-direction predictions, divergence for large errors, and an adaptive loss floor for evaluation. CZAR is provably convex in the prediction at fixed true value, has closed-form gradient and Hessian suitable for custom objectives in gradient-boosted libraries, and its four hyperparameters reduce to a single choice through correlated defaults. In idealized tests, the minimum directional accuracy required for a CZAR-evaluated forecaster to outperform the zero predictor under mean log loss remains near the 50% chance level, whereas the corresponding threshold for symmetric losses rises sharply with prediction noise. This advantage persists under heavy-tailed return distributions. In a LightGBM experiment on intraday BTC log-returns, CZAR-trained models reduce the `zero-returns bias' and improve directional accuracy on large-magnitude returns.
Read the full abstract ▾
All authors Joel Pfeffer, J. M. Diederik Kruijssen, Florian Stecker, Steven N. Longmore
Computation and Language
Mnemon: Raw Records, Fast Judgments, Slow Thoughts
Guangren Wang
Long-term
memory lets an LLM assistant use a history it can no longer reread, and most
memory systems build it by rewriting conversations into facts, graphs or typed
memories at write time. We argue that the work of
memory divides, as thinking does, into two systems. Most of it is fast System 1 work: many small, independent yes/no judgments about records, such as whether a record is needed or no longer current, which a decision model makes by the dozen in a third of a second. Only a little is slow System 2 work: writing a few search queries, naming what the reply needs and composing the answer, which an LLM does well but slowly. We present Mnemon, a
memory agent built on this division. It keeps conversations as raw, dated records; an LLM (System 2) plans searches over them, a decision model, Jev (System 1), judges what the searches return, and rules with explicit budgets turn the judgments into a small View for an unchanged answering model. A background pass consolidates each record once into topic timelines, value histories and standing instructions linked to the records, so that questions about a whole conversation reach evidence their own searches miss. Because nothing is decided about a record when it is written, the same
agent can read any store that returns dated records. With gpt-4.1-mini answering, as in a public re-evaluation of 14 systems, Mnemon scores 91.7% on LoCoMo, the highest among them, and 83.8% on LongMemEval-S, from under 4k
tokens of context per question, with the lowest effective cost index on LoCoMo. With a
reasoning model answering, it reaches 92.2% on LoCoMo and 94.4% on LongMemEval-S, the latter on par with the best published results. From 100K to 10M
tokens of history on BEAM, its cost per question grows by a factor of 1.11. On the same records, Jev separates gold evidence better than two LLMs and is 3-11 times faster.
Read the full abstract ▾
Machine Learning
ABC: Advantage-Based Control Variates for Reinforcement Learning with Verifiable Rewards
Hsiao-Ru Pan, Florent Draye and Bernhard Schölkopf
Recent progress in reinforcement learning with verifiable rewards (RLVR) has highlighted the effectiveness of simple critic-free policy-gradient methods such as Group Relative Policy Optimization (GRPO). In contrast, actor-critic methods rely on learned value functions whose approximation error can introduce bias through commonly used advantage
estimators such as temporal-difference error. Motivated by this observation, we revisit trajectory-level control variates through an advantage-value formulation, which we call Advantage-Based Control Variates (ABC). This formulation reveals that the covariance structure is closely related to the return decomposition used in Direct Advantage Estimation (DAE). Finally, we combine ABC with DAE into a single actor-critic
algorithm and evaluate it in an offline-to-online RLVR setting, where the critic is first trained on previously collected trajectories and adapted during online learning. On mathematical
reasoning tasks, ABC achieves performance competitive with GRPO using substantially fewer online optimization steps.
Read the full abstract ▾
Artificial Intelligence
Mirror-Score: Calibrated, Inference-only Scoring Exposes the Limits of Sequence-compatibility Ranking in D-peptide Design
Jiada Li
D-peptides combine protease resistance with high target specificity, but computational design of D-peptide binders remains immature. Mirror-Peptidizer introduced an in silico mirror-image screening pipeline using target reflection, backbone generation, and ProteinMPNN sequence design, but its raw ProteinMPNN negative log-likelihood (NLL) ranking was not validated against measured affinities, and only 4 of 9 tested MDM2 designs bound detectably. We introduce Mirror-Score, a calibrated, inference-only scoring framework for heterochiral D-peptide/L-
protein complexes, and a public
benchmark of 31
crystal complexes across four target families, including 18 with literature-verified affinities. Raw ProteinMPNN NLL is not a valid affinity ranker: its pooled Spearman correlation with affinity is 0.19, and correlations reverse between MDM2/CHIP (+0.62) and gp41 (-0.70). We therefore evaluate Boltz-2 mirror-space cofolding confidence. For the complete viral-entry family (7 structures representing 3 peptides), interface predicted local distance difference test (pLDDT) achieves structure-level leave-one-out Spearman rho = 0.90 (p = 0.006) and correctly orders all three peptides by affinity, whereas NLL fails (structure-level rho = 0.18). Because only three independent chemotypes are represented, this result indicates directional consistency rather than a statistically validated predictor. Cross-family calibration does not transfer at current sample sizes, supporting family-matched calibration as the practical deployment mode. We also specify a prospective design protocol for the antimicrobial-resistance targets LasR and LecB from Pseudomonas aeruginosa, including mirrored structures, ligand-derived hotspot maps,
diffusion-model-ready inputs, and Mirror-Score ranking. Code,
benchmark data, structures, and analysis scripts are openly available at https://github.com/Jiadalee/Mirror-Score.
Read the full abstract ▾
Artificial Intelligence
GeoWind2Plan: Mission-Time 3D Urban Wind Prediction for Energy-Efficient UAV Planning
Shaoxiang Qin, Yucheng Zhao, Fuyuan Lyu et al. (+6 more)
In urban low-altitude flight, buildings reshape ambient wind into spatially varying 3D flow, making unmanned aerial vehicle (
UAV) energy depend on local wind exposure as well as path length. However, building-resolved wind information is rarely available when a mission must be planned. Computational fluid dynamics (CFD) can produce high-fidelity urban flow fields, but each simulation is tied to a fixed inflow boundary condition and can take hours to days, which is incompatible with urban
UAV missions that typically last minutes to tens of minutes. We present GeoWind2Plan, a geometry-to-wind-to-planning framework for mission-time 3D urban wind prediction and energy-efficient
UAV planning. Given only a background wind vector, 3D building geometry, and a start-goal pair, GeoWind2Plan transforms the building geometry into a reference-wind frame, predicts mission-relevant 3D wind patches with a localized geometry-conditioned neural operator, stitches them into a queryable local wind field, and optimizes a feasible 3D path and speed profile using a physically grounded
UAV energy model. Rather than pursuing CFD-perfect reconstruction, GeoWind2Plan targets decision-useful wind prediction: trajectories are planned with predicted wind and evaluated under high-fidelity CFD wind. Across held-out urban domains, wind speeds, and mission wind-angle regimes, GeoWind2Plan performs corridor-localized wind inference in about 3 seconds, compared with roughly 8 hours for CFD. Under CFD evaluation, trajectories planned with GeoWind2Plan reduce energy by 6.9%, 12.7%, and 4.5% in tailwind, headwind, and crosswind missions relative to wind-agnostic planning, recovering 87.9%, 85.7%, and 75.0% of CFD-reference savings. These results show that fast, corridor-localized 3D urban wind prediction can make wind-aware
UAV energy planning practical at mission time.
Read the full abstract ▾
All authors Shaoxiang Qin, Yucheng Zhao, Fuyuan Lyu, Di Zhou, Jiachen Yao, Xue Liu, Anima Anandkumar, Liangzhu Leon Wang, Xiongye Xiao
Computers and Society
What if automating AI R&D triggers an intelligence explosion?
Alan Chan, Christoph Winter, Andrew Barto et al. (+19 more)
In contrast to even a year ago, AI systems now write most of the code inside the companies that build them. As more of the AI research and development (R&D) pipeline is automated, could AI progress radically accelerate in an "intelligence explosion," where years of advances are compressed into months or less? Preliminary evidence suggests that it could. In this work, we assess this evidence, analyze an intelligence explosion's potential impacts, and propose policy responses. AI systems are on track to automate most AI R&D work within a few years, and possibly all of it. If this triggers an intelligence explosion, it could dramatically bring forward AI's benefits, but also pose extreme risks: capabilities growth could accelerate far beyond what society can keep up with, humanity could lose control over superhuman AI systems, and checks on power within and between states, companies, and branches of government could be severely eroded. Although there remains much uncertainty about these possibilities, the high stakes warrant serious further
attention. Policymakers should urgently obtain more visibility into the automation of AI R&D, develop ways to steer and constrain an intelligence explosion, and prepare society to adapt to an intelligence explosion's impacts.
Read the full abstract ▾
All authors Alan Chan, Christoph Winter, Andrew Barto, Jakub Pachocki, Geoffrey Hinton, Eric Horvitz, Yoshua Bengio, Dawn Song, Jack Clark, Hilary Greaves, Anton Korinek, Samuel Hammond, Thore Graepel, Ben Bariach, Philip H. S. Torr, Sheila A. McIlraith, Jeff Clune, Sam Manning, Girish Sastry, Tom Davidson, Daniel Eth, Sören Mindermann
Numerical Analysis
Slip Wall Boundary Conditions in Curved Domains for Finite Element ALE Hydrodynamics
Nabil Atallah, Kevin Sweet, Paul Moujaes et al. (+3 more)
We present a high-order finite element arbitrary Lagrangian-Eulerian (ALE) method for hydrodynamics with slip-wall boundary conditions on analytically curved domains. The method combines distinct Lagrangian, remesh, and remap phases while preserving the
geometric features of curved boundaries and allowing tangential motion of boundary nodes. In the Lagrangian phase, we use weak boundary condition enforcement to impose the slip-wall condition without freezing tangential motion. In the mesh optimization phase, we adapt TMOP (target-
matrix optimization paradigm) to analytic walls by replacing selected boundary coordinate degrees of freedom with curve or surface parameters. The Newton solve then moves boundary nodes tangentially with respect to the prescribed geometry while carrying the drift introduced by the Lagrangian phase. In the remap phase, we transfer the solution from the old mesh to the optimized mesh by a conservative advection-based remap over pseudo-time. We present numerical results in two and three dimensions demonstrating the method on high-order curved meshes and showing that it preserves boundary fidelity while producing the expected hydrodynamic solution features.
Read the full abstract ▾
All authors Nabil Atallah, Kevin Sweet, Paul Moujaes, Jan Nikl, Ketan Mittal, Vladimir Z. Tomov
Artificial Intelligence
PowerZooJax: A JAX-based Power System Benchmark for Reinforcement Learning
Zhanhua Pan, Xiao Liu, Zhilong Cao et al. (+2 more)
Power system operation is a safety-critical sequential decision-making problem, making it a natural testbed for reinforcement learning (RL). However, existing RL environments for power systems are often narrow in scope and computationally limited by CPU-based simulation workflows, making large-scale evaluation difficult. We introduce PowerZooJax, a JAX-based
benchmark suite for RL in power system operation. It provides five constrained Markov decision process tasks spanning generation, transmission, distribution, distributed energy resources, and data center microgrid. By rewriting power flow, economic dispatch,
market clearing, and device dynamics as JAX computation graphs, PowerZooJax keeps the entire training and evaluation loop on the GPU. Experiments show substantial speedups over CPU-based simulations and demonstrate standardized evaluation of policy returns, safety violations, and out-of-distribution stress conditions. Our open-source
benchmark is available at: https://github.com/powerzoojax/PowerZooJax.
Read the full abstract ▾
All authors Zhanhua Pan, Xiao Liu, Zhilong Cao, Jianhong Wang, Dawei Qiu
Computational Complexity · Cross-listed from math.ST
From Weak to Strong Testing in Gaussian Models
Ansh Nagda and Alexander S. Wein
We study the computational complexity of hypothesis testing in the spiked Wigner model, a prototypical model for detecting low-rank structure in a large random
matrix. Below the "BBP"
eigenvalue transition, it is expected that strong detection — with both type I and II errors vanishing — requires exponential time. Assuming this as a
conjecture, we determine the limits of
polynomial-time weak detection, exactly characterizing the possible tradeoffs between type I and II errors. Specifically, the optimal tradeoff is achieved by a particular linear spectral statistic. Thus, the question of weak detection is entirely reduced to that of strong detection. The proof builds on ideas of Nagda-Raghavendra (2025) and Moitra-Wein (2025). The low-degree likelihood ratio (LDLR) plays a key role: any test that slightly beats the LDLR can be boosted to have an even higher success probability. This leads us to establish a computational analogue of the Neyman-Pearson lemma for a subclass of additive Gaussian models: for a given super-
polynomial runtime, the best possible tradeoff between type I and II errors is either the one achieved by thresholding the LDLR, or the trivial tradeoff that results from strong detection.
Read the full abstract ▾
Machine Learning
Improving scalable oversight with co-trained monitors
Joseph H. Rudoler, Kevin Tan, Benedict Tessler et al. (+2 more)
Worker-monitor setups are a promising approach to AI oversight, but training workers against fixed monitors can incentivize monitor evasion. We study whether this failure mode can be avoided by co-training the monitor alongside the worker, and explore both supervised and self-supervised approaches. In the supervised setting, we prove a characterization: monitoring is possible with vanishing error and query rates exactly when the class of possible monitor functions has finite Littlestone dimension. This connects worker monitoring with an established literature on
adversarial online learning. For self-supervision, we propose a co-training procedure based on test-time
distillation: the monitor uses additional test-time compute to generate training labels, then trains its standard-compute policy on those labels. For majority-vote labels, we give a finite-sample sharpening guarantee under adaptive worker distributions with action coverage, that shows that the monitor's verdicts converge to its initial modal verdicts. We stress-test the former in code-security settings where the worker is trained adversarially to fool the monitor. Our results suggest that adaptive monitors are better at keeping pace with evolving worker strategies, while fixed monitors are more vulnerable to evasion.
Read the full abstract ▾
All authors Joseph H. Rudoler, Kevin Tan, Benedict Tessler, Timothy Kong, Enric Boix Adserà
Machine Learning
Neural networks for spectral optimization
Alexis de Villeroché, Beniamin Bogosel, Stéphane Breuils et al. (+2 more)
Given a functional dependent on the spectrum of a differential operator, we address the problem of finding a domain which optimizes this functional. PDE solvers might be used to tackle this optimization. It is however computationally expensive. We propose two neural network models which learn the spectrum directly from the geometry of the domain and can be used to optimize the domain from one or more
eigenvalues. We investigate two representations. The first encodes the domain through
Fourier coefficients and a light MLP, which is efficient on
star-shaped geometries, achieving a precision of 0.2%. Through a rescaling of the coefficients the designed models satisfy the scaling law of the
eigenvalues. Additionally, averaging the outputs of the trained surrogates over rotations and reflections induces invariance for these transformations. The second is a model that takes the landscape function, the indicator function and the gradient of the landscape function. A Gram-Schmidt process produces orthogonal eigenfunctions as output of the model along with the associated
eigenvalues. The landscape model reaches 1% mean relative error on the first ten
eigenvalues, compared with 4% for an FNO model. Replacing the landscape by an SDF worsened both prediction and optimization errors. The trained model also generalizes from synthetic shapes to domains given as classical image
dataset. The resulting surrogates of both approaches recover classical spectral optima such as the disk for the first
eigenvalue or the conjectured minima of higher
eigenvalues. This confirms that our models produce accurate differentiable estimates of
eigenvalues, which can be used in shape optimization problems involving spectral quantities.
Read the full abstract ▾
All authors Alexis de Villeroché, Beniamin Bogosel, Stéphane Breuils, Dorin Bucur, Jacques-Olivier Lachaud
Machine Learning · Cross-listed from hep-ph
Hybrid Neural Simulation-Based Inference for Robust Applications and Limited-Budget Scenarios
Sean Benevedes, Mani Dehghan, Aishik Ghosh et al. (+1 more)
We develop two hybrid techniques that approach the performance of neural simulation-based inference (NSBI) analyses while substantially reducing the computational cost of inference and preserving some or all of the reliability guarantees of parametric methods. The first approach is broadly applicable, while the second is tailored to a class of particle physics analyses that admit a semi-parametric NSBI formulation. With only a modest compromise in raw sensitivity, these methods represent an important step toward computationally efficient NSBI in offline analyses and also open the door to the exploration of trigger-level applications in the future. Based on our comparison studies, we recommend the use of our first approach, Latent Categories, for robust and efficient inference.
Read the full abstract ▾
All authors Sean Benevedes, Mani Dehghan, Aishik Ghosh, Tae Hyoun Park
Artificial Intelligence
SAGE: A Statistical Acceptance Gate for Self-Evolving Agents
Yihao Wang, Linhan Xia, Rui Liu et al. (+6 more)
Large
Language Model (LLM)-based
agents increasingly self-evolve by editing a persistent skill document that encodes their workflow, tool-use rules, and decision logic. This loop has two steps, an optimizer that proposes a candidate edit and a gate that accepts or rejects it. Prior work has concentrated on the optimizer, while the gate still follows a naive rule that keeps any edit which improves an aggregate validation score. We show that this rule fails in two ways. First, it admits permanent regressions, since an edit can raise the average while breaking items the skill already solves. Second, it is vulnerable to the Optimizer's Curse, since the best observed score on a finite and noisy validation set is upward biased. To solve the above two limitations, we propose a statistical acceptance gate for self-evolving
agents (SAGE). Compared with previous work, SAGE has two contributions. First, SAGE proposes a per-item paired comparison that evaluates the current skill and the edited skill on identical validation items, which exposes regressions that an aggregate score hides and penalizes them asymmetrically. Second, SAGE also employs a one-sided paired test that commits an edit only when its wins are statistically reliable against its losses, and it abstains otherwise. SAGE is a conservative refinement of the standard gate that recovers the baseline exactly at a boundary setting. It commits only a subset of the baseline's edits, filtering out those whose gains are unreliable or purchased by breaking already-solved items. Across five
benchmarks and four backbone LLMs under an equal-budget protocol, SAGE lowers the regression rate in 19 of 20 settings and matches the baseline in the remaining one, for example from 36.5% to 0% on LiveMath and from 42.8% to 0% on OfficeQA with DeepSeek-V4. SAGE also attains the highest final score in all 20 settings, raising LiveMath from 34.15 to 48.78.
Read the full abstract ▾
All authors Yihao Wang, Linhan Xia, Rui Liu, Zhaofeng Zhang, Hongyu Wu, Yang Yang, Jinglu He, Yu Guo, Kai Lei
Cryptography and Security
Multi-Class, Multi-Tier Network Intrusion Detection: A Comprehensive and Reproducible Benchmark
Yufeng Xin, Bryant Goseland and Mohamed Rahouti
Machine learning (ML) and deep learning (DL) have dominated Intrusion Detection System (IDS) research in recent years. Unfortunately, many existing studies have produced inflated results and unreliable
benchmarks due to critical oversights and mistakes in the ML and DL pipeline, from data collection and labeling to feature engineering and model training and evaluation. CIC-IDS2017 is a standard
benchmark for network intrusion detection. Still, many published results on this
dataset are difficult to compare due to labeling errors, inconsistent flow extraction, potential leakage, and performance evaluation metrics dominated by benign traffic. In this paper, we present a comprehensive
benchmark with corrected PCAP-level labeling and a complete evaluation pipeline with diverse ML models. We evaluate eleven tabular classifiers at three nested levels: binary attack detection, nine-class attack-family attribution, and fifteen-class fine-grained classification. A soft-voting ensemble of Random Forest, XGBoost, and LightGBM obtains the best fine-tier macro-F1 of 0.955, with coarse and binary macro-F1 scores of 0.980 and 0.999, respectively. We further conducted a feature selection study based on an analysis of feature importance. This comprehensive
benchmark pipeline is configurable and open-source, enabling new feature extraction and model plugins for new
datasets. Future work should use this pipeline as a reference point for richer features, rare-class analysis, and model generalization towards new
datasets and attack classes.
Read the full abstract ▾
Machine Learning · Cross-listed from math.OC
Dual-Anchor Acceleration Is Near-Optimal for Stochastic Monotone Root-Finding
TaeHo Yoon and Nicolas Loizou
Among distinct optimal acceleration mechanisms for deterministic monotone root-finding problems and fixed-point problems, dual-anchoring has recently been shown to admit a more robust direct
stochastic extension than standard anchor acceleration. However, without additional strong monotonicity, the existing
stochastic dual-anchoring guarantee has two limitations: first, it requires cocoercivity in expectation, and second, it attains only $O(\epsilon^{-3})$ oracle complexity, leaving a gap to the near-optimal $\tilde{O}(\epsilon^{-2})$ complexity achieved by other methods. In this work, we address both of these limitations by combining dual-anchoring with
stochastic resolvent approximation and optimized variance control. For unbiased
stochastic oracles with variance bounded by $\sigma^2$, where sample operators are monotone and uniformly $L$-Lipschitz, our
algorithm finds a point with $\epsilon$-residual with a near-optimal oracle complexity of $O ( (LD / \epsilon) \ell + (\sigma^2 / \epsilon^2) \ell^2)$, where $\ell = \log (1 + LD / \epsilon)$ and $D$ is the initial distance to a solution. This result improves the best known oracle complexity in the noise-dominated regime under these samplewise assumptions, reducing the poly-logarithmic factor from cubic to quadratic.
Read the full abstract ▾
Machine Learning
TORQUE: Optimizing What (not) to Quantize Before and After Rotation
Ran Ben Basat, Michael Mitzenmacher and Shay Vargaftik
Uniform random rotations are an effective preprocessing step for quantization: they make normalized coordinate distributions approximately Gaussian, enabling the use of codebooks optimized offline. We introduce TORQUE, a framework that improves on previous quantization works that use random rotations by jointly optimizing how many and which coordinates to preserve at high precision both before and after rotation, under a fixed overall expected bit budget. Intuitively, before rotation, preserving large input coordinates at high precision can reduce overall error by preventing the rotation from spreading their values across many coordinates. Likewise, after rotation, preserving a small fraction of the largest-magnitude coordinates at high precision allows the remaining values to be quantized more accurately using codebooks optimized offline for the resulting truncated Gaussian distribution. We derive a quantization error upper bound and prove that top-$k$ pre-rotation retention minimizes it for each $k$. This reduces the search over coordinate subsets to an optimization over $k$, enabling a fast optimizer that uses offline codebooks and parallel parameter selection for practical implementation. We demonstrate an improved tradeoff between reconstruction accuracy and storage cost through numerical evaluation under the Gaussian model and experiments on nearest-neighbor
retrieval, KV-cache compression, and activation compression.
Read the full abstract ▾
Robotics
SAKI: Skill Assembly and Kinematic Imitation from Human Videos for Long-Horizon Mobile Manipulation
Yijie Lu, James Zhao and Weiming Zhi
Learning from human
videos offers a promising route to acquiring diverse manipulation skills. Extending this capability beyond tabletop settings to long-horizon mobile manipulation requires adapting and composing demonstrated interactions across changing scenes and
robot configurations. We present Skill Assembly and Kinematic Imitation (SAKI), a framework connecting human-
video skill acquisition, cross-demonstration assembly and closed-loop whole-body execution. SAKI prepares reusable object-centric skills that preserve task-critical interactions while allowing transfer paths to adapt. Given a goal and supplied task dependencies, it selects and orders skills, binds their object roles to the current scene, and carries scene estimates and
robot configuration between successive skills. Whole-body kinematic imitation generates coordinated base, arm and gripper motion. During execution, persistent object estimates maintain task references across viewpoint changes, while visual feedback updates remaining trajectories. Real-
robot experiments demonstrate skill reuse across layouts and the composition of independently demonstrated interactions into continuous mobile tasks, including tidying and wiping. Ablation results show that task-conditioned reference preparation substantially improves long-horizon task completion with whole-body optimisation and visual feedback held fixed. Check https://aus.bot/research/saki/ for
video demos!
Read the full abstract ▾
Machine Learning
Preferent Compression Bounds Are Tight
Dario Paccagnan and Marius Tirlea
The lack of rigorous safety and performance certificates remains a key bottleneck to the deployment of modern learning-based methods. Sample compression has recently emerged as a powerful tool for deriving such certificates, with particularly sharp bounds available for
algorithms satisfying a so-called preference property – also known as stability in the learning theory literature. These bounds find direct application across domains as different as the Scenario Approach, Pick-to-Learn, and Support Vector methods. However, whether they are tight has remained an open problem. In this paper we resolve this question affirmatively and show that the state-of-the-art bound for preferent compressions is provably tight. We establish this by exhibiting an explicit construction based on the uniform distribution and order statistics that attains the bound in the limit. Along the way, we also provide a considerably shorter and more accessible proof of this bound, requiring only elementary counting arguments and no infinite-dimensional duality.
Read the full abstract ▾
Computer Vision
CoDimRecon: Agentic Reconstruction of Sim-Ready 3D Scenes with Deformable Curves, Surfaces, and Volumes
Shuzhao Xie, Lelin Wang, Guying Lin et al. (+2 more)
Reconstructing simulation-ready 3D scenes from real-world observations enables robotics, gaming, and immersive applications, yet existing methods largely assume rigid objects. This leaves an important gap for deformables, whose simulation-ready geometry depends on dimensionality (curves, surfaces, or volumes) and whose behavior may require models beyond elasticity. We present CoDimRecon, an agentic framework that reconstructs editable scenes containing rigid, articulated, and deformable objects from multi-view RGB observations. Scene-level
geometric priors ground scale and layout, while object-level generated meshes guide the
agent toward detailed, compact geometry; articulated rigid objects are decomposed into movable parts with explicit joints. For deformables, category-wise
agent sessions reconstruct curves as centerlines with radii, surfaces as
manifold shells with thickness, and volumes as watertight solids for volumetric meshing. Reusable simulator skills initialize compatible physical models and parameters, while
agent-guided behavioral tests expose mismatches and trigger targeted revisions of motion, geometry, numerics, or material modeling. On evaluated Replica and ScanNet++ scenes, CoDimRecon achieves competitive compositional reconstruction accuracy while additionally producing deformable assets for rod, shell, and solid simulation. We further demonstrate
robot interactions across all three representations, including a controlled paper-folding case in which behavioral testing motivates plastic bending.
Read the full abstract ▾
All authors Shuzhao Xie, Lelin Wang, Guying Lin, Zhi Wang, Minchen Li
Computer Vision
Persistence Forcing: Exploiting Feature Specialization in Pixel-Space Diffusion
Chong Wang, Zixuan Fu, Shiqi Huang et al. (+3 more)
Pixel-space
diffusion Transformers (DiTs) directly operate on high-dimensional visual data, yet their hidden representations typically undergo uniform refinement across depth. Natural images, however, are inherently organized at different levels of granularity. Global structure can often be represented compactly, whereas local textures and fine details require richer representations. Motivated by this, we introduce heterogeneous refinement in pixel-space DiTs, assigning different feature groups distinct refinement budgets across depth. Consequently, an ordered feature specialization emerges: sparsely refined features predominantly encode global visual structure, whereas more frequently refined features increasingly specialize toward localized, high-frequency details. We refer to these two groups as persistent and active features, respectively. Building on this emergent specialization, we introduce Persistence Forcing (PerF), which explicitly exploits this persistent–active feature organization for pixel-space image generation. This enables persistent features to continuously condition actively refined features, allowing stable global information to guide the ongoing refinement of finer visual details. During generative sampling, this interaction further induces a meaningful guidance direction that promotes coherent global structure and naturally complements classifier-free guidance. On ImageNet $256\times256$, PerF-L achieves FID of $1.91$, approaching $1.86$ of JiT-H with only half the parameters, while PerF-H further achieves FID of $1.63$ and $1.76$ on ImageNet $256\times256$ and $512\times512$, respectively.
Read the full abstract ▾
All authors Chong Wang, Zixuan Fu, Shiqi Huang, Siyuan Yang, Hao Cheng, Bihan Wen
Robotics
In-Context Learning for Robots: Methods and Applications
Haojian Huang, Zexi Li, Junhao Guo et al. (+36 more)
General-purpose
robots must infer what a new task requires and translate that understanding into appropriate physical action. In-context learning (ICL) for
robots supports this process by using demonstrations and interaction to direct existing competence with neural parameters held fixed during deployment. We organize this literature review around the interfaces connecting contextual evidence to execution, distinguishing four families: context-conditioned policies,
geometric demonstration transfer, world-model-based control, and skill- and
agent-based execution. Comparing these interfaces clarifies their transfer assumptions and the roles of training, correspondence, and
memory in making context useful. Across manipulation and
navigation, we examine how these mechanisms preserve taught requirements as objects, environments, and execution conditions change. This analysis links method design to evaluation practices that distinguish responsiveness to teaching, physical transfer, and benefits from retained experience. The resulting agenda connects compositional task acquisition and faithful transfer with physical recursive self-improvement, in which experience improves the ability to learn subsequent tasks.
Read the full abstract ▾
All authors Haojian Huang, Zexi Li, Junhao Guo, Yehang Zhang, Wenxuan Peng, Bohan Zhou, Weilin Ruan, Leyi Wu, Chenxu Wang, Jianchong Su, Binghui Xie, Wosong Chen, Yingjie Xu, Tianhao Zhou, Suzeyu Chen, Pukun Zhao, Jiaqi He, Xinyi Li, Runze Li, Peiran Dong, Shaoxiang Dang, Jing Huang, Yingbing Chen, Yifan Chang, Tianyi Zhang, Shiyuan Deng, Haozhi Wang, Yangkai Wei, Wenqian Li, Han Yang, Kaiwen Zhou, Huaping Liu, James Cheng, Rui Shao, Donglin Wang, Yaochu Jin, Jianye Hao, Ying-Cong Chen, Yinchuan Li
Social and Information Networks
Group dynamics of engagement with AI topics on Bluesky
Bradley Huynh, Moyi Tian and Nancy Rodríguez
Social media increasingly shapes everyday life, serving as both a central venue for discussion of major events and a space where online collective behavior can spill over into real-world activity, while artificial intelligence (AI) is likewise becoming increasingly influential across society. Understanding how different online communities respond to AI-related events, and disentangling the mechanisms underlying the development of such engagement, are therefore increasingly important for studying information spreading and the societal reception of AI. Our work addresses the limited connection between empirical studies of AI-related online engagement and mathematical modeling of group-level spreading dynamics. We develop a framework to collect and organize empirical Bluesky activity into distinct user groups, then use a network-based dynamics model to investigate the mechanisms underlying their engagement. We use the release of DeepSeek R1 as a case study under two complementary grouping schemes: AI-related communities and academic disciplines. For each group, we fit a network-based Susceptible-Infected-Recovered (SIR)-type model augmented with an exogenous engagement term, allowing us to quantify the relative strengths of endogenous network-driven spreading and direct external response. Across groups, we find that strong direct responses to the event do not necessarily coincide with strong network-driven propagation, revealing distinct engagement patterns that may be obscured by aggregate activity alone.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from hep-ph
Infrared Subtraction with Artificial Intelligence
Wenjie He, Xiaohui Liu, Yandong Liu et al. (+1 more)
We present AI-developed local infrared subtraction, building on projection to Born and EFT matching. The framework separates an integrable radiation term from a finite contribution at Born kinematics, referred to as the Born contact. The contact is determined using the EFT singular distribution in a resolution observable such as N-jettiness $\tau_N$. Under human physics guidance, an LLM develops two implementations. One uses a neural network for phase space projection and fits the contact by matching to EFT cumulants. The other uses an analytic construction that keeps the Born momenta fixed while integrating over radiation. It combines the EFT $\delta(\tau_N)$ coefficient with finite 4-dimensional radiation integrals to calculate the contact term directly. This gives a local subtraction formula without a slicing parameter, while reusing existing lower-order radiation calculations and EFT singular predictions. As a demonstration, we reconstruct the full NLO correction for massless 3- and 4-jet production in electron-positron annihilation. The attempt to the NNLO dijet production is also made by recursively using the NLO P2B construction with the LLM designing machine-learning controls to reduce the variance of the contact integral. The tested predictions are in good agreement with EERAD3. The numerical calculation and projection-network training use a 2020 Apple M1 MacBook, without GPU acceleration, illustrating the feasibility of the construction with modest computing resources. The appendices develop an extension of the local subtraction to 3-jet NNLO, giving explicit radiation maps and a proposed contact formula. We also show how to integrate over NNLO radiation while keeping the Born momenta fixed, for any number of massless final-state jets. Our results demonstrate how AI can help higher-order calculations by constructing infrared subtraction and improving its numerical integration.
Read the full abstract ▾
All authors Wenjie He, Xiaohui Liu, Yandong Liu, Zhan Wang
Machine Learning
Making Cross-Continental Federated Learning Repeatable with FLIP: a Multi-Application Study
Rafael Garcia-Dias, Alexandre Triay Bagur, Chayanin Tangwiriyasakul et al. (+20 more)
Federated learning (FL) in healthcare remains challenging, as the overhead of rebuilding governance guarantees for every collaboration stops most projects at the proof-of-concept stage. Here we present FLIP (
Federated Learning Interoperability Platform), an open-source, multi-application platform that makes FL training and evaluation repeatable. FLIP implements common FL workflows as a set of composable services: cohort queries against per-site structured databases, on-demand DICOM
retrieval from institutional PACS, per-site project approval, and reusable FL job types. To demonstrate FLIP, we ran two distinct use cases,
federated fine-tuning and
federated evaluation, on synthetic chest X-ray cohorts across two client nodes based in the United Kingdom (UK) and Thailand. In FLIP, each institution independently approves its participation in each project and operates its own node under local IT security processes. This study makes an operational rather than an algorithmic claim. It does not compare
federated with centralised training; for that question, we refer the reader to existing systematic reviews and meta-analyses. The central result is evidence that such platforms enable international FL collaboration and improve repeatability, auditability, and site-specific governance. We also present a comprehensive comparison of existing platforms to help researchers and operators choose the right platform for their use case.
Read the full abstract ▾
All authors Rafael Garcia-Dias, Alexandre Triay Bagur, Chayanin Tangwiriyasakul, Virginia Fernandez, Parhom Esmaeili, Piyalitt Ittichaiwong, Yang Li, Lawrence Adams, Wason Buncharoen, Martin Chapman, Benjamaporn Chayanond, Sadthavud Chunrod, Tanawat Fongsri, Kass Gibson, Supat Plungprasertkul, Supawit Tangpanithandee, Kanyakorn Veerakanjana, Vicky Goh, Michela Antonelli, Joe Zhang, Kongkiat Kespechara, Sebastien Ourselin, M. Jorge Cardoso
Computation and Language
Causal and Interpretable Structures in LLM Compositional Tasks
Gurbir Arora, Toni J.B. Liu, Jiajun Bao et al. (+2 more)
Large
language models are able to solve tasks whose answers depend on not only individual input
tokens, but also on relations among them. How is such relational information represented and processed across
transformer layers? We study activations from ensembles of
prompts that require inferring relationships between three
tokens corresponding to a cyclic concept (months, hours, weekdays, and musical notes) to correctly predict the next
token. Across model families (Llama, Qwen, Gemma, and Mistral) and cyclic concepts, we find a consistent layerwise progression in how the joint dependence among the
tokens is geometrically organized and causally used: intermediate layers use a joint representation based on the inferred relationship between two
tokens, while later layers use a joint representation associated with all three
tokens to correctly complete the task. We also find other relationships between
tokens that are geometrically structured but remain causally inert in the next-
token prediction. Crucially, when taken together, these
geometric and causal investigations reveal the representation-level mechanism that progressively organizes and composes the relational information to form the answer. More surprisingly, restricting the models to such causally relevant joint representations improves next-
token prediction accuracy.
Read the full abstract ▾
All authors Gurbir Arora, Toni J.B. Liu, Jiajun Bao, Raphaël Sarfati, Christopher J. Earls
Machine Learning · Cross-listed from astro-ph.IM
SIFARI: Self-Supervised Interferometric Fitting for Astronomical Radio Imaging
Shunyuan Mao, Andrea Isella, Paris Perdikaris et al. (+2 more)
Radio-interferometric images are reconstructed from sparsely sampled visibilities, and CLEAN-based imaging can struggle with spatial filtering, complex morphologies, and uncertainty quantification. Alternative methods that fit visibilities directly can address some of these limitations but often require manual choices of image priors and model hyperparameters. We present SIFARI (Self-Supervised Interferometric Fitting for Astronomical
Radio Imaging), a self-supervised neural network workflow that represents sky brightness as a continuous function of position and fits measured visibilities without an external image training set or explicit spatial regularizer. An empirical rule sets the
Fourier feature scale from the visibilities before training, controlling how readily the network fits fine structure. Sampling network weights with
Stochastic Weight Averaging-Gaussian (SWAG) gives approximate brightness uncertainty estimates, which we combine with a thermal-noise floor to construct spatially resolved signal-to-noise maps. In synthetic ALMA tests, SIFARI yields an effective point-source response about eight times narrower than the natural-weighting CLEAN restoring beam and recovers more extended flux than CLEAN when short baselines are missing. It also achieves higher image fidelity than the restored CLEAN images in all three morphology
benchmarks. Applied to ALMA observations of PDS 70, SIFARI recovers the bright outer ring together with faint compact emission in the central cavity. For long-baseline-only WISPIT 2 data, SIFARI supplies a sky model for phase self-calibration where the CLEAN model is inadequate. The restored, self-calibrated SIFARI image has approximately 30% lower RMS noise than the CLEAN image made from the original visibilities without self-calibration.
Read the full abstract ▾
All authors Shunyuan Mao, Andrea Isella, Paris Perdikaris, Li-Ta Lo, Hui Li
Computer Vision
Yunzhe Xu and Zhe Liu
Vision-and-
Language Navigation (VLN) has largely focused on a single
agent following a single instruction, yet many real-world applications require teams of
robots to tackle tasks beyond the capabilities of any individual
agent. We present Systematic Multi-
Agent Vision-and-
Language Navigation, providing, to our knowledge, the first systematic formalization of multi-
agent VLN as a constrained coordination problem: each mission consists of subtasks carrying dependency and resource constraints (presence locks and holding chains). A verified four-stage crafting pipeline instantiates the task as MAVLN, comprising 11,724 episodes across 145 scenes with teams of up to four
agents under three instruction regimes, accompanied by tailored constraint-aware metrics. We further present TRISS, a coordination-ready
navigation system coupling an LLM-based subtask scheduler, a shared topological
memory that turns each
agent's exploration into team knowledge, and a conflict-aware execution mechanism that realizes simultaneous intentions as collision-free routes. Extensive experiments establish TRISS as a comprehensive baseline and reveal substantial room for improvement across scheduling, planning, and execution, highlighting the challenges of coordinating under MAVLN task constraints. Project page: https://xyz9911.github.io/mavln.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from hep-th
Solver Agent: an Agentic AI Framework for Theoretical Physics Computations Applied to F-theory Uplifts of O3-planes and S-folds
Eliott Morgensztern, Cesar Fierro Cota and Alessandro Mininno
We introduce Solver
Agent, an AI framework based on large
language models for calculations and proofs in mathematics and theoretical physics. The solution process is tracked through a persistent ledger that records assumptions, derivations, and computations. A central
agent delegates tasks to specialized sub-
agents, while independent
agents verify both intermediate steps and the final result. This setup improves the traceability, reproducibility, and verification of computer-assisted calculations. Applying Solver
Agent, we study global F-theory uplifts of Type IIB orientifolds and their S-fold generalizations. We establish sufficient conditions for Weierstrass models over projective threefolds with terminal $\mathbb{Z}_k$ quotient singularities ($k\in\{2,3,4,6\}$) to give $\mathbb{Q}$-factorial projective elliptically fibered Calabi-Yau fourfolds with isolated Gorenstein terminal quotient singularities. These geometries realize O3-planes and S-folds, where local D3-brane probes of the latter yield four-dimensional $\mathcal{N}=3$ superconformal field theories. Using stringy invariants, we derive fixed-point contributions to Hodge data and Euler characteristics, and show that these Euler corrections determine the localized D3-brane charges required for tadpole cancellation. We illustrate these results using toric hypersurface constructions, where a single three-dimensional polytope determines both the Type IIB Calabi-Yau threefold and the F-theory base; here, the orientifold double cover naturally forms a bisection of an alternative genus-one-fibered uplift with discrete $\mathbb{Z}_2$ gauge
symmetry. Finally, we provide methods for toric computations and four-form flux analysis in four-dimensional $\mathcal{N}=1$ compactifications with non-abelian gauge sectors.
Read the full abstract ▾