Optics
Contact lens with stretchable distributed-feedback laser for intraocular pressure monitoring
S.A. Ivanov, I.M. Fradkin, E.S. Musikhina et al. (+8 more)
Continuous monitoring of intraocular pressure (IOP) is essential for the diagnosis and management of glaucoma, yet existing clinical methods rely on intermittent in-clinic measurements that miss critical diurnal fluctuations. Smart contact lenses are an attractive platform for continuous IOP tracking, and optical strain sensors are particularly promising thanks to their high sensitivity and natural readout. Most such optical sensors infer strain from the period of a regular structure - a grating or photonic
crystal - whose deformation is read out optically. However, the precision of all sensors based on the period of regular structures is fundamentally bounded by the uncertainty principle, which severely limits performance at the millimeter length scales available inside a contact lens. Here, we address this limitation by integrating a distributed-feedback (DFB)
laser, based on a surface-modulated ultrathin F8BT dye layer, into a soft polydimethylsiloxane (PDMS) contact lens. Operating at a
symmetry-protected bound state in the continuum at the {\Gamma} point, the device produces a narrow lasing line whose wavelength shifts directly with grating strain - a quantity not constrained by the spatial uncertainty principle. The DFB structure is fabricated by UV
holographic lithography and transferred onto the lens by a simple float-off process, yielding a stretchable, transparent,
polymer-compatible sensor that is intrinsically scalable. Tested on a custom artificial eye model whose pressure-induced deformation is comparable in scale to that reported for the human eye, the sensor achieves a sensitivity of 0.027 nm/mmHg and a calibration residual of 1.2 mmHg under phantom conditions, a level relevant to tonometric monitoring, with substantial headroom currently limited mainly by auxiliary readout equipment.
Read the full abstract ▾
All authors S.A. Ivanov, I.M. Fradkin, E.S. Musikhina, R.V. Kirtaev, A.A. Khrebtov, A.A. Vyshnevyy, A.A. Marchenko, V.R. Solovei, I.P. Radko, A.V. Arsenin, V.S. Volkov
Machine Learning
Causal Routing for Unlearning
Bardh Prenkaj, Andrea D'Angelo, Davide Mottin et al. (+4 more)
LLMs cannot forget the way we delete a file. Strangely, we are asked to remove something that was never put anywhere in particular. What the model took from a piece of text is now smeared across billions of weights. Existing methods rewrite all of them to change one thing, and none of them say which part produced that change. To address this, we introduce Causal Routing for Unlearning (CRU) by asking where the concept is expressed in the model and suppressing only that part. One untrained forward pass over the forget set ranks
neurons by how their activations vary. Then, small routing modules on those
neurons gate and suppress only the concepts that need to be forgotten. In CRU, the base model is frozen, and any change in behavior is caused only by the gated
neurons; hence, why the routing is causal. Due to our parameter efficiency (only ~0.01% as many parameters as the base model), unlearning a concept costs 14 GiB, whereas the baselines require 71 GiB. On TOFU, CRU is indistinguishable from the retained model (p > 0.05, KS test) and is never Pareto-dominated, whereas every compared baseline matches its forgetting on the larger-forget batches only by collapsing utility. On RWKU, it achieves an
adversarial-probe recall of 0.052, compared to 0.250 for the strongest baseline, meaning the knowledge is gone, not merely harder to reach. Thus, deciding on the intervention at query time, rather than fixing it beforehand, is the axis along which we argue that unlearning should proceed.
Read the full abstract ▾
All authors Bardh Prenkaj, Andrea D'Angelo, Davide Mottin, Federico Fontana, Davide Gabrielli, Paola Velardi, Stefano Faralli
Machine Learning
Deep kernel hedging
Jean-Loup Dupret, Donatien Hainaut and Edouard Motte
We introduce a deep kernel hedging framework that combines the flexibility of deep learning with the structural inductive bias of kernel methods. The hedging functional is restricted to a reproducing kernel
Hilbert space whose kernel is parameterized through a neural network
embedding of the input features. The framework minimizes a regularized empirical risk under convex loss functions and can accommodate path-dependent information through truncated time-augmented signature features. We derive a generalized representer
theorem for the joint hedging problem, reducing the empirical optimization to a finite-dimensional problem. To further reduce the computational cost associated with large kernel
matrices, we develop a scalable random
Fourier feature approximation and establish convergence guarantees. The random
Fourier parameters are sampled once and remain fixed throughout training, while the deep kernel adapts to
market data through the learned neural representation. We evaluate the performance of the proposed deep kernel approach on both synthetic and real data and compare it with standard kernel methods and classical deep hedging architectures. Numerical results indicate competitive and robust hedging performance, particularly in low-data regimes, which highlights the benefits of combining expressive neural representations with the inductive bias of kernel methods.
Read the full abstract ▾
Software Engineering
From Noisy Telemetry to Actionable Warnings: GPU Failure Prediction in Industrial Clusters
Yongqian Sun, Run Zhu, Wenwei Gu et al. (+9 more)
GPU clusters are critical infrastructure for AI services, but accurate and actionable GPU failure prediction remains a problem in production settings. We study ticket-linked telemetry from a ByteDance GPU cluster and identify three obstacles: workload-confounded telemetry, heterogeneous fault precursors, and the gap between window-level predictions and actionable alerts. These findings motivate Falcon, a fault-specific warning framework combining missingness-aware temporal and peer-relative features, fault-specific learner selection, and an event policy based on thresholding, persistence, and cooldown. On the test set, Falcon achieves the highest F1 among four baselines and reaches 70.6% F1 on the best-performing fault type. Detected cases provide median lead times of 17.34-35.57 hours. We further report a production deployment, where Falcon is calibrated toward high-precision alerts to reflect false-positive costs. Together, these results show that fault-specific modeling improves early warning from noisy production GPU telemetry.
Read the full abstract ▾
All authors Yongqian Sun, Run Zhu, Wenwei Gu, Mengyao Li, Shenglin Zhang, Guanjin Wang, Yang Zhang, Xin Wu, Linlin Han, Feng Wang, Xiaozhou Liu, Yu Zhang
Computer Vision
VL-AcneSeg: A Vision-Language Framework for Region-Aware Acne Lesion Segmentation
Sukju Oh, Soo Ick Cho, Dae Hun Suh et al. (+1 more)
Acne assessment is crucial for clinical decision-making, yet traditional grading and counting are subjective and fail to account for lesion size. While area-based assessment has emerged as a promising alternative, acne
segmentation has continued to rely on general-purpose architectures. To address this gap, we propose VL-AcneSeg, a
multimodal framework for acne lesion
segmentation that leverages CLIP and region-level text
prompts to incorporate spatial priors, enabling lesions to be localized across the whole face. Because region-level
prompts indicate which facial areas contain lesions, we report a single global
prompt, which requires no such information, as our primary setting. On our internal clinical
dataset, VL-AcneSeg achieves a Dice score of 0.5082 and an IoU of 0.3407 under this protocol, the highest among all compared methods, including recent
vision-
language segmentation methods that are themselves given region-level
prompts; region-level prompting raises these to 0.5296 and 0.3602. Moreover, lesion area measurements derived from our
segmentation correlate with IGA scores at a level comparable to expert annotations (Pearson r = 0.719 versus 0.658). Notably, our framework maintains consistent performance across external validation
datasets, performing reliably even on uncontrolled smartphone images without requiring additional training or fine-tuning. By pairing a protocol that requires no lesion-location information with area-based severity estimation, this work provides a foundation for objective acne assessment outside the clinic. Our implementation is publicly available at: https://github.com/sukjuoh/VL-AcneSeg
Read the full abstract ▾
All authors Sukju Oh, Soo Ick Cho, Dae Hun Suh, Sukkyu Sun
Combinatorics
Three Standard Deviations Suffice While One Does Not
Victor Reis and Zhao Song
Spencer's 1985 “six standard deviations suffice”
theorem shows that every $A \in [-1,1]^{n \times n}$ has a sign vector $x \in \{-1,1\}^n$ with $\|Ax\|_\infty \le 6\sqrt{n}$. We show the upper bound $\sqrt{3\operatorname{arsinh}(10)}\sqrt{n}+4 < 2.9992 \sqrt{n} + 4$ by directly rounding the minimizer of a potential function to a vertex of the cube. We also show that, for every power of two $n \ge 2^{50}$, there exists a
matrix $A \in \{-1,1\}^{n \times n}$ such that $\|Ax\|_\infty >1.0000002\sqrt{n}$ for every choice of signs $x \in \{-1,1\}^n$. The construction simply replaces a $2^{-22}$ fraction of the columns of a Hadamard
matrix with independent random sign vectors. This is the first improvement over the $\sqrt{n}$ lower bound of Olson and Spencer (1978), which uses a Hadamard
matrix.
Read the full abstract ▾
Computer Vision
Precise Editing and Flexible Referencing for Interactable Worlds
Xinyao Liao, Xianfang Zeng, Zhu Liang et al. (+5 more)
We present EditWorld, a
video world model for precise editing and flexible referencing in interactable worlds. Existing
video world models primarily focus on
navigation, letting users explore generated worlds but offering limited control over how existing world content is modified. EditWorld extends world modeling from exploration to precise modification by streaming editing instructions and reference images during autoregressive generation. To support these capabilities, EditWorld introduces Gated Causal
Attention for temporally varying editing conditions and reference images, together with a Sparse Context mechanism that maintains a bounded historical context for long-horizon inference. We further adopt joint autoregressive and bidirectional training with annealed self-resampling, and construct a dedicated data synthesis and annotation pipeline that provides supervision for world editing. We also present WBench-Editing to systematically evaluate streaming world editing capabilities. EditWorld achieves the best overall performance on WBench-Editing with an overall score of 73.8 and an editing score of 80.0, substantially outperforming existing methods on editing-related metrics. https://github.com/leoisufa/EditWorld
Read the full abstract ▾
All authors Xinyao Liao, Xianfang Zeng, Zhu Liang, Zhoujie Fu, Qianxun Xu, Jiachi Liu, Gang Yu, Guosheng Lin
Software Engineering
The Last Mile Is the File: OfficeEditBench for Preservation-Aware Office Editing
Zhiwen Wu and Chengxu Wu
A small Office edit creates two obligations: propagate every required update and leave protected state untouched. Updating too little leaves dependencies inconsistent; updating too much changes content the user did not authorize. We introduce OfficeEditBench, a 170-task
benchmark for change-scoped maintenance of spreadsheets, presentations, and documents. Task contracts specify required updates, protected state, native structures, and applicable interaction requirements. Across 510 archived task-system outcomes from WorkBuddy, Doubao, and Codex, we distinguish file delivery, target completion, and verifier-defined acceptance. Hard package-valid delivery ranges from 92% to 100%, yet no selected output satisfies the complete contract. Case analysis highlights why local correctness is insufficient: an updated value can lose its generating formula, a revised rule can fail to reach related conclusions, and a new deadline can omit a retained prerequisite. These mechanisms connect artifact-level checks to the continued maintainability of Office files. We analyze maintenance failures while distinguishing frozen automatic verdicts from human acceptability. OfficeEditBench provides a testbed for completing required changes while preserving the logic and scope of existing work.
Read the full abstract ▾
Statistical Mechanics
Fluctuations and multifractality in stochastic models of interface growth and population dynamics
Maximilien Bernard
This thesis studies how disorder and fluctuations shape large-scale growth phenomena in three related settings: fluctuating interfaces, random spring chains, and random multiplicative growth. The first part concerns interface growth and a phenomenon denoted anomalous scaling, where local and global exponents differ.To clarify its origin, we study two models in which this mismatch has different causes. The first is a heterogeneous elastic line, where we show that the apparent anomaly is a purely statistical effect. The second is the
stochastic porous medium equation, a strongly nonlinear model in which the anomaly is genuine. The second part concerns Anderson localization, which appears here through the spectral properties of the heterogeneous elastic lines. We study chains with both random masses and random spring constants, with particular emphasis on the strong-disorder regime, where standard weak-disorder expansions break down. We develop a new combinatorial method to probe this regime. The last part concerns random multiplicative growth with redistribution. In such models, changes in wealth, population, or mass, for instance, are proportional to the amount already present, so that small differences are amplified over time. This naturally generates broad distributions and provides a simple mechanism for the emergence of inequality and concentration, with applications to population dynamics, wealth distribution, city growth, and ecology. We in particular study models in which each site has its own quenched growth rate, representing a persistent advantage or disadvantage, and is also subject to transient fluctuations. Redistribution competes with these mechanisms by homogenizing the system. This competition leads to rich phase diagrams.
Read the full abstract ▾
Machine Learning
Shengchao Hu, Peng Wang, Qiyang Zhou et al. (+5 more)
Recent advances in
Vision-
Language-Action (VLA) models point toward general-purpose robotic intelligence by unifying perception, instruction, and control. Despite impressive progress, existing VLA models often adapt poorly due to tri-modal misalignment among
vision,
language, and action, which weakens action grounding and hurts generalization and fine-tuning efficiency. In this work, we present
Alignment-Guided Flow
Transformer (AGFT), a novel framework that explicitly enforces tri-modal
alignment through a dedicated
alignment loss, bridging the representational gap across modalities and enhancing task adaptation. While prior research has predominantly emphasized bi-modal
vision–
language alignment, we systematically formalize and study tri-modal
alignment in VLA models, and provide both ablations and analysis to isolate its role in improving adaptation and robustness. To further accelerate deployment, we adopt a flow-matching objective, enabling substantially fewer inference steps than
diffusion-based policies while maintaining accuracy. Theoretically, we establish a quantitative connection between the tri-modal
alignment gap and the optimization tightness of flow matching; empirically, experiments on the extensive
benchmark show that AGFT achieves superior success rates and lower inference latency compared to SOTA baselines, underscoring tri-modal
alignment as a key ingredient for scaling robust VLA manipulation.
Read the full abstract ▾
All authors Shengchao Hu, Peng Wang, Qiyang Zhou, Guodong Zheng, Yuqi Huang, Li Shen, Ya Zhang, Dacheng Tao
Machine Learning
PhysioTRACE: Provenance-Aware Stress Tests for Physiological Foundation Models
Ayana Mussabayeva, Anuar Aimoldin, Olivier Oullier et al. (+2 more)
Physiological foundation models encode how a signal was recorded alongside the physiology it reflects. When recording conditions are associated with diagnosis, this acquisition provenance can become a shortcut, yet the usual evidence, shifted transfer and provenance decodability, does not show whether a predictor uses it. We introduce PhysioTRACE, a four-axis behavioral audit for frozen encoders that separates what a probe can decode from what a fixed task head relies on. Recover scores how decodable provenance is; Stress reverses only the provenance-target association on the same held-out records; Intervene removes a train-localized provenance component; and Verify certifies that removal only if it beats matched random projections within a declared utility margin. Each audit thus ends in one of three verdicts: no reliance, or reliance with the remedy certified or refused. Across
EEG and ECG, five training objectives, and five frozen foundation models, the relation between Recover's calibrated score and out-of-distribution utility changes sign between
datasets, so neither can stand in for a reliance test. On paired
EEG views where the shortcut is known by construction, the audit detects it (the exposed head loses about 0.2 AUROC when the association is reversed, while a control head is unaffected) and certifies removal of a rank-two component that restores control-level behavior without measurable utility loss, for both encoder objectives tested. On real ECG device metadata it returns all three verdicts: it certifies a remedy that removes 91% of one model's excess vulnerability, finds no reliance where device and diagnosis are barely associated, and refuses the remedy for a second model whose localized direction also carries task signal. Robustness to how inputs were recorded therefore needs a behavioral test, and PhysioTRACE provides one that can pass, fail, or refuse a remedy.
Read the full abstract ▾
All authors Ayana Mussabayeva, Anuar Aimoldin, Olivier Oullier, Xue Liu, Kun Zhang
Number Theory
Plectic Lie Algebra Action on Hilbert modular varieties
Yuanyang Jiang and Lue Pan
We construct some part of the plectic Galois action on the locally analytic $p$-adically completed
cohomology of
Hilbert modular varieties, predicted by the plectic
conjecture of Nekovář-Scholl. As a byproduct, we prove a vanishing result for the completed
cohomology of
Hilbert modular varieties below middle degree. To do this, we make use of the partial Sen operators constructed earlier by a
geometric method.
Read the full abstract ▾
Neurons and Cognition
Automatic Generation of Expert-Level Neuron Segmentation Masks from Fluorescence Microscopy Images for Non-Invasive Deep Learning Analysis of Phase-Contrast Images
Gerard Villarroya-Piqué, Víctor M. González, Esther Serrano-Pertierra et al. (+3 more)
Background & Objective Accurate
segmentation of
neurons in microscopy images of neuronal cultures is crucial for research on neurodegenerative diseases and neurotoxicity. Manual annotation of such images is time-consuming, subjective, and inconsistent across experts. Deep learning (DL) models offer an effective alternative, but require high-quality training
datasets composed of microscopy images with accurately segmented
neurons, typically created by experts. Neuronal cultures can be imaged using either phase-contrast or fluorescence microscopy. While live
neurons are easily detected in fluorescence images, this modality requires staining, which affects
cell viability. Conversely, phase-contrast imaging is non-invasive but makes
neuron identification more challenging. Methods In this work we present a robust computer
vision pipeline for the automatic generation of expert-level
neuron segmentation masks from fluorescence microscopy images. These masks are used to train DL models for
neuron identification in phase-contrast images. Our method relies on paired fluorescence and phase-contrast images captured simultaneously at the same magnification and coordinates, ensuring
alignment across modalities. Once trained, the DL models can segment
neurons in phase-contrast images alone, eliminating the need for fluorescence staining. Results We validate our approach by comparing the automatically generated masks with expert annotations using multiple agreement metrics, including IoU, Accuracy, and Gwet's AC1. Such metrics are calculated not only for the identification but also for the
segmentation of instances. Conclusions This study presents a classical computer
vision algorithm for generating
neuron segmentation masks, which can be used for downstream applications such as non-invasive
cell viability analyses by means of DL.
Read the full abstract ▾
All authors Gerard Villarroya-Piqué, Víctor M. González, Esther Serrano-Pertierra, M. Teresa Fernandez-Sanchez, Antonello Novelli, Angel Rio-Alvarez
Cryptography and Security
CoDeL: Co-Evolutionary Defense against Indirect Prompt Injection in LLM-based Agents
Xiao Yang, Yangchen Ou, Yuhan Gao et al. (+3 more)
Large
language model (LLM)-based
agents increasingly rely on external tools and content, exposing them to indirect
prompt injection (IPI). This threat has motivated a wide range of defenses, among which training-based defenses are often regarded as most reliable. However, existing training-based defenses are typically optimized on a static distribution of explicit injections. They learn surface-form cues rather than the boundary between serving the user and obeying an injected objective, and therefore fail when malicious intent is folded into a plausible workflow and deferred for several turns. We present CoDeL, a defense that hardens
agent against an attack distribution it reshapes as it trains. The defender is updated each round via LoRA-based GDPO under a decoupled reward over safety, task progress, and format compliance, so refusing injections and completing the user's task jointly define fitness. To keep supplying it with the failures worth learning from, a co-evolving prober searches over injection rounds, attack methods, and payloads for injections that still penetrate the current defender, guided jointly by attack success and attack latency so that it preferentially mines breaches the defender notices too late. Each defender update invalidates part of the attack population and forces the next round onto a new frontier, turning the defender's own failures into a moving curriculum. Extensive experiments on three IPI
benchmarks, nine baselines, and two base models show that CoDeL reduces attack success rate (ASR) by 88.5% and outperforms other baselines largely (+38.0%). Codes are available.
Read the full abstract ▾
All authors Xiao Yang, Yangchen Ou, Yuhan Gao, Le Wang, Zonghao Ying, Aishan Liu
Computational Complexity
A Quadratic Lower Bound on Determinantal Complexity
Mrinal Kumar and Ben Lee Volk
We prove an $\Omega(n^2)$ lower bound on the determinantal complexity of the power sum
polynomial $\sum_{i=1}^n x_i^n$ over the field of complex numbers. A similar result was claimed in a recent paper of Sheshadri (arXiv:2606.13628), via an AI-assisted and AI-written proof. Assuming its correctness, this was the first super-linear lower bound for this fundamental algebraic problem for any explicit
polynomial. However, the authors of this note were unable to follow the details and verify the argument in arXiv:2606.13628, in spite of considerable effort on their part. The proof we provide here is short, (almost) self-contained and seemingly simpler.
Read the full abstract ▾
Audio and Speech Processing
CharDuplex: Building Character-Consistent Full-Duplex Spoken Dialogue Models
Donghang Wu, Yisi Liu, Chen Chen et al. (+2 more)
Full-duplex
speech models are moving voice interaction beyond conventional turn-taking, yet natural conversation is shaped not only by when an
agent speaks, but also by how it behaves as a conversational character. We present CharDuplex, a character-driven full-duplex
speech model that combines real-time spoken interaction with persona-conditioned behavior. We first adapt GLM-4-Voice to an always-on dual-stream architecture and train the model for full-duplex conversation. Then a fully automated pipeline constructs character-conditioned dialogue data from open-source character descriptions for character-conditioned supervised fine-tuning. The model is further refined with the proposed FDGym, where an LLM-simulated user dynamically interacts with the model, enabling reinforcement learning over evolving multi-turn interactions. On SpeechRole-Eval, CharDuplex achieves the highest average score among the evaluated open-source models, while remaining competitive with closed-source systems. It also demonstrates competitive general
speech intelligence and strong full-duplex interaction capabilities. CharDuplex demonstrates a practical training recipe for building full-duplex voice assistants that are not only interactive, but also character-consistent.
Read the full abstract ▾
All authors Donghang Wu, Yisi Liu, Chen Chen, Hexin Liu, Eng Siong Chng
Artificial Intelligence
When Does Structured Knowledge Help Neural Theorem Proving?
Sareh Nabi, Roland Vogl and Marzieh Nabi
Does structured mathematical knowledge help LLMs prove
theorems in Lean 4? If so, for which models, and does the answer vary by problem? Formal libraries such as Mathlib encode 285,000+ verified
theorems with syntactic dependencies, but the semantic layer mathematicians rely on for discovery (analogies, generalizations, cross-domain bridges) remains implicit. We introduce MathAgent, which builds this layer as a knowledge graph, MathKG, and uses it to augment LLM
theorem provers. MathKG connects 364 Mathlib
theorems and definitions by 9,434 typed semantic edges inferred via LLM-based relation extraction anchored to verified Mathlib declarations. We run a controlled ablation across four augmentation modes (no context, knowledge-graph context, Mathlib
retrieval, both) and five models: Qwen3-8B/32B, their Lean-specialized derivatives Goedel-Prover-V2-8B/32B, and Claude Sonnet 4.6, on miniF2F, plus PutnamBench and MathOlympiadBench for Sonnet. Three findings emerge. (i) Specialization dominates augmentation: Lean fine-tuning adds 33-38 percentage points of solve rate in every mode, and a specialized 8B model beats a $4\times$ larger general one by 29-35 points, while no augmentation mode improves solve rate by more than 3 points. (ii) Augmentation is capability-conditioned: knowledge-graph context helps small models but hurts large ones, with the specialized model gaining more relative to its general base at every scale. (iii) Yet the augmentation modes solve different problems: an oracle selecting the best mode per problem solves 6% to 58% more than the unaugmented prover, a complementarity effect that strengthens on harder problems (32% more on PutnamBench). These results motivate adaptive strategies that select augmentation by model capability and problem. Code, data, and artifacts are available at https://github.com/sarehnabi/mathagent
Read the full abstract ▾
Artificial Intelligence
Escaping Local Views: Discovering Latent Concepts for Interpretable Multi-Agent Reinforcement Learning
Yijie Sun, Sanquan Sun, Yanda Zhu et al. (+3 more)
Efficient cooperation is challenging due to the usual partial observability of each
agent in multi-
agent reinforcement learning. Recurrent networks encode local interaction histories, but their hidden representations provide limited insight into the information underlying individual decisions. To address these challenges, we propose a novel interpretable framework, called escaping local views (ELV), which introduces semantically structured latent concepts to render policy decisions transparent. Specifically, each
agent extracts low-dimensional semantic concepts from its local observation and action-observation trajectory. These concepts are jointly encoded into a contextual latent variable via a variational autoencoder (VAE), which builds a bridge between local views and global semantics. To explicitly model the decision of each
agent, we employ a dual-path
attention mechanism in which one module estimates the salience of individual concepts relative to the global context, while the other captures higher-order cooperative patterns with pairwise concept interactions. Furthermore, we incorporate a concept prediction module that derives an intrinsic reward from next-concept prediction errors, which incentivizes
agents to explore regions of semantic novelty. Experiments in multiple environments verify that ELV not only achieves competitive performance but also explicitly provides how
agents reason about their decisions.
Read the full abstract ▾
All authors Yijie Sun, Sanquan Sun, Yanda Zhu, Yuanyang Zhu, Yaohua Hu, Chunlin Chen
Machine Learning (Statistics)
Understanding Generalization Requires Universal Induction
Aram Ebtekar, Marcus Hutter and Danica J. Sutherland
Classical statistical theory is insufficient to explain the successes of general-purpose AI models, because it depends on handcrafted inductive biases that it cannot justify. No Free Lunch (NFL)
theorems force any learner that beats chance on some environments to underperform on others. We might hope that past experience informs which environments to expect, but NFL applies equally to meta-learning. Thus, any method that makes meaningful predictions necessarily begins with an inductive bias external to the data. Choosing to bias toward short programs yields Solomonoff induction (SI), whose performance is competitive against all computable learners - albeit up to "constants" that become large when comparing against specialized methods that exploit background information. We therefore relativize SI to an information vantage point, biasing toward short programs with access to all preexisting information. This reframes the inductive bias: instead of seeking some absolute notion of simplicity, we favour accessibility with respect to our vantage point. An
algorithm can only outpredict the relativized SI to the extent that its code contains additional information about the data, and no
algorithm can generate such information. While SI is incomputable and hence not a practical
algorithm, it provides a formal optimum for inference in the limit of infinite compute, and there is evidence to suggest that frontier AI systems roughly approximate it. Thus, the only known answer to meta-NFL is rooted in algorithmic information theory, which we should expect to play a fundamental role in explaining the generalization behaviour of modern (and future) AI systems.
Read the full abstract ▾
Machine Learning
ZonoGPT: Towards An Abstract Domain for Verifying Large GPT Models
Hai Duong, Thanh Le and ThanhVu Nguyen
Transformer-based models are widely used for
reasoning, coding, and
multimodal agentic tasks. To provide formal assurance of desirable behaviors, such as robustness, safety, and
fairness, neural network verification techniques prove required properties and provide auditable guarantees before deployment. However, prior work remains limited to small or restricted
Transformers, and maintaining precision across deep models remains challenging. In this work, we introduce ZonoGpt, an abstract domain for verifying large
transformers that maintains a space complexity independent of network depth. ZonoGpt uses a structured zonotope and a generator reduction mechanism to efficiently preserve correlations. To maintain precision, it introduces block-specific fused transformations for
Attention and LayerNorm that retain feature relations, along with an affine transform for GELU that preserves generator relations. These mechanisms enable ZonoGpt to be the first approach to verify standard architectures, scaling to official HuggingFace models up to GPT-2 Medium (24 blocks, 300M+ parameters) and successfully verifying 1,339 instances across text and
vision tasks.
Read the full abstract ▾
Cryptography and Security
Breaking Windows Malware Detection: A Comprehensive Evaluation of Problem-Space Adversarial Robustness
Mashal Zainab, Salijona Dyrmishi, Hamid Bostani et al. (+2 more)
Problem-space evasion attacks have exposed critical weaknesses in machine learning-based malware detectors; yet, their evaluation remains fragmented across models,
datasets, and attack methodologies, often neglecting domain-specific requirements such as executability and functionality preservation. We address this gap with a unified, large-scale evaluation of nine state-of-the-art evasion attacks against eight Windows malware detectors, including seven open-source models and one commercial detector, under executability-preserving conditions. Our study analyzes attack effectiveness, complementarity, transferability, and
adversarial hardening to evaluate robustness along complementary dimensions. We show that detector vulnerability depends strongly on both model representation and attack type: raw-byte detectors are particularly susceptible to several classes of problem-space manipulation, but no detector family is uniformly robust across all attacks. Importantly, effectiveness is not explained by transformation-space size alone: the strongest attacks can achieve substantially higher success while using fewer distinct transformations and concentrating on a small set of high-impact manipulations. We further show that two complementary attacks are sufficient to cover approximately 99% of the
adversarial examples produced by the remaining evaluated attacks. Transferability exhibits a different pattern from direct attack success: attacks with low direct success can produce highly transferable evasions. Finally,
adversarial hardening is highly attack- and model-dependent: robustness gains often fail to transfer across attacks and can even increase susceptibility to unseen attacks. These findings highlight limitations in current malware robustness evaluations, establish a comprehensive empirical baseline, and clarify relationships between effectiveness, transferability, and defense robustness.
Read the full abstract ▾
All authors Mashal Zainab, Salijona Dyrmishi, Hamid Bostani, Lorenzo Cavallaro, Maxime Cordy
Computation and Language
RGDT-Bench: Benchmarking LLM Reasoning for Rule-Governed Decisions and Their Justifications
Jianpeng Zhao, Haihua Xu, Haoyang Zhang et al. (+7 more)
We study
reasoning in Rule-Governed Decision Tasks (RGDTs), where models apply external rules to case facts and justify decisions, as required in policy, contract, and compliance settings. Beyond the deductive capability emphasized by standard mathematical and logical
reasoning tasks, RGDTs require interpreting rules and their applicability, assessing conditions from evidence, combining judgments under rules and exceptions, and providing checkable justifications. These demands motivate a
benchmark assessing both decisions and their stated grounds. We introduce RGDT-Bench, providing 202.1K condition-level supervision slots across four task tracks and eight supported task-probe combinations that vary access to supporting information. Label-blind extraction and deterministic checks produce labels for warrant completeness: source-referenced coverage and consistency of stated decision grounds. The
benchmark attributes failures to four process layers: rule use, condition, evidence, and aggregation, and checks the final outcome. Among evaluable correct responses, warrant incompleteness averages 40.2% across six evaluated LLMs and supported task-probe combinations. Such warrant incompleteness poses potential safety risks and remains difficult to detect: the best of seventeen existing evaluators reaches only 57.69% (random: 50%) task-averaged area under the receiver operating characteristic curve (AUROC). To address this difficulty, we train a simple reward model with warrant supervision. It achieves 69.24% task-averaged AUROC among correct answers, exceeding the matched outcome-supervised baseline by 10.37 pp (percentage points) and the best existing evaluator by 11.55 pp. Beyond completeness assessment, the model outperforms both outcome-supervised baselines across nearly all response-selection comparisons, supporting RGDT-Bench's warrant supervision for RGDT
reasoning.
Read the full abstract ▾
All authors Jianpeng Zhao, Haihua Xu, Haoyang Zhang, Shuang Qian, Yixiang Tang, Xintao Wang, Kun Sun, Pei Wu, Shuhan Zhong, Pengyang Wang
Computation and Language
When Words Fall Short: Iterative Synergy Between Verbalized Reasoning and Hidden Features for LLM Confidence Estimation
Yekun Xu, Ante Wang, Jingyi Ren et al. (+3 more)
Confidence estimation is crucial for developing trustworthy large
language models (LLMs), with most methods following
estimator-based or verbalization-based paradigms. While recent research increasingly focuses on improving verbalized self-reports of confidence, we challenge the prevailing view that this approach surpasses independent confidence
estimators. Our empirical study shows that a dedicated confidence
estimator can substantially outperform verbalized confidence, indicating that LLMs' internal representations contain richer confidence signals. Building on this finding, we propose Iterative Policy-
Estimator Training (IPoET), a framework that synergizes the complementary strengths of verbalized
reasoning traces and informative representations. IPoET alternates policy optimization with
estimator updating, integrating
estimator-derived confidence feedback into policy learning and refreshing the
estimator on new policy rollouts. Experiments across diverse
datasets and Qwen and Llama backbones demonstrate that, by iteratively exploiting richer hidden features and adapting to the evolving policy distribution, IPoET consistently outperforms both
estimator- and verbalization-based baselines in-domain and achieves superior or comparable results across all out-of-domain metrics. For more details, refer to https://github.com/xyk829/ipoet.
Read the full abstract ▾
All authors Yekun Xu, Ante Wang, Jingyi Ren, Xuanyi Chen, Weizhi Ma, Yang Liu
Machine Learning
SPACE-LoRA: Allocating Activation-Subspace Protection for Continual Learning
Seunghyun Yoo, Kiseok Kim, Hyeontae Joo et al. (+2 more)
This study addresses the catastrophic forgetting problem that occurs when sequentially learning successive tasks using Low-Rank Adaptation (LoRA) from a lifelong learning perspective. While existing approaches have primarily constrained parameter updates or learning subspaces to reduce interference with past knowledge, they have not fully considered additive interference. This occurs when a newly added residual adapter on top of a fixed past model generates non-zero responses along input directions important for old tasks, thereby altering previous predictions. To this end, we propose Subspace Protection with Allocated Capacity for Efficient Continual Adaptation (SPACE-LoRA). SPACE-LoRA directly suppresses the responses of the new residual branch along input activation directions that are important for old tasks and adaptively determines the protection coverage for each module based on past-task sensitivity estimated via a common Fisher sensitivity-based coverage target. Under a fixed LoRA rank, this approach adaptively adjusts module-specific protection coverage while suppressing interference along input directions sensitive to old tasks. We assess the effectiveness of activation-subspace protection in mitigating catastrophic forgetting and examine the role of sensitivity-guided protection in continual learning across diverse tasks. Code is available at https://anonymous.4open.science/r/SPACE-LoRA-7864.
Read the full abstract ▾
All authors Seunghyun Yoo, Kiseok Kim, Hyeontae Joo, Junyeop Bang, Hwangnam Kim
Hardware Architecture
Coarse-to-Fine Macro Placement via Evolutionary Search and Critical Macro Tuning
Biao Liu, Zhiping Jin, Kaixuan Sun et al. (+3 more)
Macro placement is a critical stage in chip physical design that substantially affects downstream implementation quality. Recent search-based methods improve existing layouts through partial reconstruction, but quality-biased or spatially restricted macro selection can limit the diversity of reconstruction proposals, potentially hindering escape from local optima. Moreover, coarse-grid representations restrict placement precision. To address these challenges, we propose C2FPlace, a Coarse-to-Fine macro Placement framework that integrates population-based evolutionary search with fine-grained refinement. During coarse-grained optimization, tournament selection chooses promising parents from randomly sampled groups of layouts, and
stochastic partial rip-up and re-place generates offspring by sampling macro subsets across the entire layout. A two-phase schedule samples reconstruction ratios from a higher range early in the search and a lower range later, supporting broad exploration followed by more conservative refinement. During fine-grained optimization, critical macro tuning enables positional adjustments beyond the coarse grid to obtain additional half-perimeter wirelength (HPWL) reduction. Experiments on the ISPD2005
benchmark show that C2FPlace reduces HPWL by 17.82% over EGPlace and 17.86% over RollPlace on average. On the ICCAD2025
benchmark, C2FPlace achieves the best average ranking among the compared methods under the evaluated power, performance, and area (PPA) metrics. Our codes are available in \href{https://github.com/lxxxxb/C2FPlace}{https://github.com/lxxxxb/C2FPlace}.
Read the full abstract ▾
All authors Biao Liu, Zhiping Jin, Kaixuan Sun, Zengrui Lu, Qingquan Zhang, Bo Yuan
Computer Vision
Modeling Whole-Slide Images as Dynamic Tumor Microenvironment Fields
Lei Wu, Jiashuai Liu, Di Zhang et al. (+9 more)
Due to the gigapixel-scale nature of whole-slide images (WSIs), weakly supervised WSI analysis is commonly formulated as a multiple instance learning (MIL) problem, where patch-level features are aggregated into slide-level representations. However, diagnostic and prognostic evidence often arises from spatially coherent tumor microenvironment regions and their interactions, rather than isolated patches alone. Existing patch-level or static region-based methods usually overlook how tissue regions should be adaptively formed and subsequently evolved through microenvironment interactions across heterogeneous boundaries. In this paper, we propose Concept-Guided Tumor Microenvironment
Evolution (TMEvolve), a reaction-
diffusion-inspired framework that models WSIs as latent tumor microenvironment fields over discrete patch graphs. TMEvolve instantiates this view as a learnable graph-discretized
evolution process over patch neighborhoods. It first forms adaptive soft tissue regions as coherent microenvironment units, then performs pseudo-time
evolution through two complementary local dynamics: intra-region
diffusion, which stabilizes latent states within coherent tissue compartments, and concept-guided boundary flux, which propagates visual feature signals and
language-derived concept signals across heterogeneous region interfaces. The evolved microenvironment regions are finally aggregated for slide-level prediction. We evaluate TMEvolve on six
datasets across three weakly supervised WSI tasks: survival prediction, gene expression prediction, and histological subtype classification. TMEvolve consistently improves over representative MIL methods, pathology foundation models, and concept-guided baselines. Ablation studies and visualizations further support the effectiveness and interpretability of TMEvolve, highlighting the value of dynamic region modeling and boundary interaction.
Read the full abstract ▾
All authors Lei Wu, Jiashuai Liu, Di Zhang, Zhangpeng Gong, Yingkang Zhan, Yi Niu, Jiusong Ge, Chunze Yang, Kai Yi, Mireia Crispin-Ortuzar, Chen Li, Zeyu Gao
Cryptography and Security
ReproBench: Benchmarking LLM Agents on Reproducing Vulnerability From Scratch
Liang He, Sheng Wu, Haomiao Hao et al. (+3 more)
Large
language model (LLM)
agents are increasingly evaluated on cybersecurity tasks such as vulnerability reproduction, exploitation, and patching. However, existing cybersecurity
benchmarks predominantly operate under a post-environment evaluation paradigm, i.e., handing the
agent source code, a container, or an executable binary. This setup bypasses the critical environment reconstruction step, leaving a fundamental question for real-world vulnerability analysis: can an
agent autonomously reconstruct the required execution environment and reproduce a vulnerability entirely from scratch? To address this gap, we present ReproBench, an evidence-grounded
benchmark designed to evaluate
agent capabilities in end-to-end vulnerability reproduction starting from solely a CVE identifier. ReproBench decomposes the full reproduction workflow into six distinct phases, and assesses performance on each phase independently using verifiable experimental artifacts: downloaded firmware images, unpacked binaries, granular analysis logs, and validated crash samples, among others. We instantiate ReproBench with 30 real-world IoT firmware vulnerabilities, which serve as ideal test cases for our from-scratch evaluation setting. Our evaluation demonstrates that 45.3% of test runs resort to vulnerability simulation - a prevalent remediation workaround adopted across all evaluated LLM
agents - while only 5.3% of CVE-model pairs achieve successful reproduction of real-world vulnerabilities. Despite the low overall success rate, these non-trivial successful cases confirm that state-of-the-art LLM
agents already possess the capacity for fully autonomous end-to-end vulnerability reproduction. Concurrently, our in-depth analysis of failed cases identifies core bottlenecks impeding LLM
agents throughout the reproduction pipeline, offering actionable insights for subsequent research.
Read the full abstract ▾
All authors Liang He, Sheng Wu, Haomiao Hao, Hongduo Zhao, Jia Yan, Purui Su
Artificial Intelligence
CORTEX: Learning to Share and Specialize in Dense Language Models
Chuiyang Meng, Ming Tang and Vincent W.S. Wong
Large
language models are trained on heterogeneous data mixtures, where different knowledge domains require both shared knowledge and specialization. Existing modular approaches typically impose explicit components or discover modules through interpretability analysis after training. In this work, we propose CORTEX, a learning dynamics-inspired framework that learns internal modularization within dense
language models. CORTEX partitions trainable
matrices into parameter groups and learns module assignments from domain-conditioned gradient and cross-domain gradient similarity. We introduce the selective lesion score and module-domain mutual information to characterize the target-domain lesion effects and
alignment, and analyze how module assignment affects the trade-off between assignment bias and update magnitude. Experiments with 160M, Qwen3-8B, and Qwen3-32B backbone models show that CORTEX achieves the highest synthetic-domain exact match and largest average perplexity reduction, while remaining competitive on real-domain evaluations and forming identifiable modules.
Read the full abstract ▾
Networking
WiFi Backscatter for Green Internet of Things: Concepts, Research Trends, and Practical Challenges
Weiqi Wu, Shuo Wang and Zhaoyuan Xu
WiFi backscatter has emerged as a promising technology for green Internet of Things (IoT) connectivity by enabling battery-free devices to communicate through widely available WiFi signals. Despite substantial progress in recent years, a considerable gap remains between research prototypes and practical deployment. This paper provides an overview of WiFi backscatter from the perspective of practical and green IoT systems. We first introduce the fundamentals and key enabling techniques, together with potential IoT applications. We then outline recent research trends toward higher throughput, concurrent communication, simplified deployment, commercial compatibility, and joint communication and sensing. Furthermore, we identify the key challenges that still hinder practical deployment, such as limited transmitter-to-tag operating range and packet loss in frequency-shifted backscatter. We believe that addressing these challenges will be critical to enabling WiFi backscatter to become a practical communication technology for future green IoT systems.
Read the full abstract ▾
Computation and Language
Unbiased Top-$k$ Estimation for On-Policy Distillation
Linjian Meng, Siyuan Gan, YuHan Li et al. (+5 more)
On-policy
distillation (OPD) is becoming an important component of large
language model (LLM) post-training for transferring the
reasoning capability of a strong teacher LLM to a weaker student LLM. OPD trains the student by minimizing the reverse KL divergence between the teacher and the student via rollouts generated by the student's policy. However, estimating the gradient of the reverse KL divergence in OPD remains a challenge. Using only the sampled
token from the student-generated rollout is computationally cheap but provides limited distributional supervision, which will degrade accuracy. In addition, using the full vocabulary provides complete distributional supervision but is computationally expensive. Therefore, recent works propose Top-$k$ OPD (TK-OPD) that use selected top-$k$
tokens, which provides richer distributional supervision than sampled-
token estimation at substantially lower computational cost than full-vocabulary estimation. Unfortunately, using only the selected top-$k$
tokens induces bias, leading to accuracy degradation, as the probability mass outside the selected top-$k$
tokens is discarded. To address the bias of TK-OPD, we propose Tail-Corrected Top-$k$ On-Policy
Distillation (TT-OPD). It preserves the advantages of TK-OPD, including rich distributional supervision and low computational cost, while providing an unbiased
estimator of the gradient of the reverse KL divergence. The key insight of TT-OPD is to use not only the selected top-$k$
tokens, but also the sampled
token from the student-generated rollout, thereby recovering the discarded probability mass in expectation, avoiding the bias. Experimental results demonstrate that TT-OPD significantly outperforms other tested OPD variants.
Read the full abstract ▾
All authors Linjian Meng, Siyuan Gan, YuHan Li, Xiran Wang, Ziyang Ding, Ditang Gou, Yiming Wu, Zhen Zhao