Artificial Intelligence · Cross-listed from q-fin.TR
When a Correct Reward Is Not Enough: Diagnosing and Guiding PPO in an Analytically Solved Broker-Trader Game
Siu Tung Wong and Carlo Campajola
Reinforcement learning (RL) is increasingly used for financial optimal-control problems when complex dynamics make analytical strategies difficult to obtain. There are financial mathematics literactures which provides many solved models whose equations and controls could evaluate and guide learning; we ask whether RL can exploit these results. We place a proximal policy optimisation (PPO)
agent in an analytically solved continuous-time broker–trader game. PPO replaces the broker and chooses its trading speed while interacting with an informed trader and
stochastic uninformed order flow. We derive a finite-step reward from the broker's continuous-time payoff and verify its discrete implementation through grid refinement and an exact one-step identity. With zero uninformed flow, a validation-selected PPO–FFNN approaches the reference action. With
stochastic uninformed flow, the tested PPO–FFNN and PPO–LSTM remain inaccurate, although supervised learning confirms that their actors can represent the action. Monte Carlo diagnostics show that their critics do not reliably rank nearby actions; potential-based reward shaping also gives no reliable improvement. Under partial information, a causal certainty-equivalent controller based on the broker's observable history remains close to the reference, while PPO has larger errors and lower payoffs. Finally, we freeze the analytical policy and train PPO to adjust it after the execution cost changes. Halving the cost yields a repeatable improvement that closes \(2.22\%\) of the gap to the changed-cost reference. The analytical solution therefore provides both a
benchmark for diagnosing RL and a useful starting policy for adaptation.
Read the full abstract ▾
Machine Learning
A Path Integral Surrogate for Multi-Step Gradient Inversion in Federated Learning
Agnivo Ghosh and Saumik Bhattacharya
Federated learning lets many clients train a shared model together without ever sending their private data to a central server. Each client shares only a model update, and this update should reveal far less about the client than its raw training examples would. This premise is what protects the
privacy of the clients. Gradient inversion attacks challenge it directly by trying to reconstruct a client's private input images from the single update it shared. Under FedAvg, a client's update accumulates several local training steps, so the server sees only the two endpoints of a hidden weight trajectory. Recent gradient inversion attacks fit a surrogate model along the path between these two endpoints but they still read its gradient at a single point. We propose the Path-Integral Surrogate Model Extension (PI-SME) which treats the accumulated update as a path integral of the gradient field and approximates it by Gauss–Legendre quadrature over several nodes along a learnable Bézier path. On CIFAR-100 and FEMNIST images across a range of trajectory lengths and class-restricted batches PI-SME reconstructs the private inputs more faithfully than the strongest surrogate baseline on several inversion metrics and the matching loss.
Read the full abstract ▾
Cryptography and Security · Cross-listed from quant-ph
Quantum Fire with Delegated Cloning
Rohit Chatterjee, Ananta Mukherjee, Vir Pathak et al. (+1 more)
Quantum fire is a recently introduced cryptographic primitive consisting of efficiently preparable
quantum states, called flames, that admit efficient cloning but resist efficient telegraphing, namely reconstruction via classical communication without preshared
entanglement. In all prior constructions of
quantum fire, cloning is a public operation that requires no separate key and every holder of a flame state can clone it. For applications to access control, however, an issuer may wish to delegate cloning to designated
quantum servers while withholding this capability from other flame holders. To address this, we introduce delegatable
quantum fire, in which cloning requires a separate key. We give two constructions in the classical-oracle model. Our first construction uses a classical secret key which enables cloning, and any user with the entire key may clone successfully. Our second construction, which we call torch-fire, uses
quantum cloning keys, called torches, which enable cloning while remaining unaffected in the process but cannot otherwise be split or delegated to enable additional cloning. An efficient adversary given $m$ torches cannot, except with negligible probability, enable more than $m$ noncommunicating parties to each clone a fresh, independently issued challenge flame. The adversary may jointly process its resources before separating the parties and distribute arbitrarily entangled registers among them. Both constructions are in the oracle model, relying on public classical oracles that allow queries in
quantum superposition.
Read the full abstract ▾
All authors Rohit Chatterjee, Ananta Mukherjee, Vir Pathak, Supartha Podder
Artificial Intelligence
HazardWeaver: Scientific Route Selection for Hazard Analysis Agents
Wangshu Zhu, Xueqi Cheng, Liang Wu et al. (+1 more)
Understanding and assessing natural hazards is essential for disaster preparedness and risk reduction. Recent advances in large
language models have spurred growing interest in AI
agents for hazard analysis, particularly their ability to integrate scientific data, models, and tools into automated workflows. However, effective automation requires
agents to determine which scientific methods are appropriate for a given event and executable with the available data and tools. As new evidence and execution results become available, these conditions can change, requiring
agents to reconsider their choices. We formulate this problem as state-dependent scientific route selection and introduce HazardWeaver. Specifically, HazardWeaver first leverages the Hazard Knowledge Compiler to extract evidence-linked conditions governing scientific applicability, then its Hazard Capability Graph represents executable scientific capabilities and checks compatibility between their inputs and outputs. Using these complementary representations, the Hazard Weaver
Agent component selects applicable and executable routes, carries out their workflows, and revises its decisions as the analysis state changes. To evaluate both the scientific outputs and the decisions that produce them, we introduce the Hazard Weaver
Benchmark, comprising 141 instances across seven single-hazard domains and four multi-hazard interaction classes. The
benchmark accommodates multiple valid scientific routes and evaluates output correctness, route validity, and justified abstention. Extensive experiments on this
benchmark show that HazardWeaver outperforms existing
agent systems, with the largest gains on tasks with multiple eligible scientific routes. Our code is publicly available at https://github.com/LabRAI/HazardWeaver.
Read the full abstract ▾
All authors Wangshu Zhu, Xueqi Cheng, Liang Wu, Yushun Dong
Cryptography and Security
Constant-Rate Certified Deletion
Kai-Min Chung, Tzu-Hsiang Huang, Wei-Hsiang Hung et al. (+1 more)
We present a unified framework for upgrading a broad class of cryptographic primitives to support constant-rate certified deletion. Previous constructions require a linear number of
qubits per encrypted bit of certified-deletable plaintext. In contrast, we obtain the first constant-rate constructions in the plain model that achieve certified deletion while preserving everlasting security. Our approach applies to a wide range of "all-or-nothing"-type primitives based on BB84-style encodings, including commitment schemes, public-key encryption, attribute-based encryption, and fully homomorphic encryption. Beyond this class, we also obtain constant-rate certified deletion for primitives built from subspace coset states, such as blind delegation, secure software leasing, functional encryption, and differing-inputs iO, and CCA-PKE. Importantly, our framework does not introduce any additional assumptions beyond those required by the underlying certified deletion primitives. Finally, under the hardness of SIS, we show that public verifiability can be incorporated into BB84- and coset-based certified deletion. In combination with our constant-rate constructions, this yields publicly verifiable certified deletion schemes with constant rate.
Read the full abstract ▾
All authors Kai-Min Chung, Tzu-Hsiang Huang, Wei-Hsiang Hung, Shota Yamada
Sound
Rubric-Based Optimization for Text-to-Music Generation
Ping Wang, Guang Yang, Shao-Rong Su et al. (+3 more)
Post-training text-to-music generation requires reward signals that capture multiple aspects of musical quality beyond what any single automatic metric can measure. We study structured, rubric-based rewards from pretrained audio-
language models (ALMs) as training signals for both autoregressive and
diffusion-based music generators. An ALM scores each generated clip against the rubric; we rank candidates generated for the same text
prompt by their scores and convert these rankings into preference pairs for DPO on both MusicGen-small and ACE-Step v1, and additionally use the rubric scores directly as scalar rewards for DiffusionNFT on ACE-Step v1. On MusicCaps, rubric-based optimization improves CLAP, SongEval, and Audiobox-Aesthetics simultaneously, with the strongest gains obtained by DiffusionNFT on ACE-Step. By contrast, on MusicGen-small, building preferences from any one of these automatic evaluators produces clear cross-metric trade-offs: the targeted evaluator improves while other independent evaluators deteriorate. We further study tempo, key, and instrumentation, where precise objective rewards are available. Directly optimizing these specialized rewards reliably improves the target attributes, whereas ALM rubrics provide only partial transfer for tempo and instrumentation and no measurable improvement for key. Together, these results suggest a practical division of labor: ALM rubrics are effective for broad perceptual qualities that are difficult to formalize, while specialized objective rewards remain preferable when reliable measurements are available.
Read the full abstract ▾
All authors Ping Wang, Guang Yang, Shao-Rong Su, Junkai Wu, Pang Wei Koh, Noah A. Smith
Data Structures and Algorithms
Faster Sublinear Maximal Independent Set Size
Peter Kiss and Arash Kooroshnezhad
We give a sublinear-time
algorithm for estimating the size of a maximal independent set in a graph using adjacency-query access with expected running time $\tilde{O}(n^{1+1/3})$, improving over the previous $\tilde{O}(n^{1+1/2})$ bound of Mahadabi et al. [MRTV26]. As a consequence of a reduction of [MRTV26], this also improves the running time for sublinear metric Steiner forest. We further show that a bi-criteria estimate of the $k$-center objective in general metrics can be obtained via a reduction to maximal independent set size estimation.
Read the full abstract ▾
Robotics
AVL-JEPA: Preventing Causal Dynamics Information Collapse In Joint Embedding Predictive Architecture World Models
Yikang Qiao, Ling Zhang, Ziying Song et al. (+1 more)
Joint
embedding predictive architectures (JEPAs) predict future latent representations without reconstructing observations, enabling world models to focus on high-level semantic dynamics. However, a JEPA can preserve high dimensional visual information while discarding information about the physical consequences of actions. We call this failure mode causal dynamics information collapse and propose action-grounded
vision-invariance latent (AVL) to prevent this collapse. We first use the executed action as an auxiliary dynamics anchor that encourages the model to preserve dynamics information, and then use a
vision-invariance pathway which aligns perturbed and clean latent predictions without discarding dynamics information, forcing the model to fully understand and utilize causal dynamics information. We validate AVL on four robotic control tasks (TwoRoom, PushT, OGBench Cube, and Reacher), showing that it substantially improves success rates under visual perturbations while preserving clean-environment performance. We further evaluate physical consequence
alignment, clean-noisy dynamics consistency, and the causal effect of targeted transition subspace erasure. Collectively, these results indicate that dynamic information causally relevant to planning is preserved from collapse under AVL.
Read the full abstract ▾
All authors Yikang Qiao, Ling Zhang, Ziying Song, Duan Huang
Cryptography and Security
Threat-Preserving Representation Sensitivity in Agent-Security Benchmarks
Neeraj Karamchandani, Piyush Nagasubramaniam, Xinhong Xie et al. (+2 more)
Security
benchmarks for LLM-based
agents often report the attack success rate (ASR) as a measure of model robustness and use these scores to compare different models and defense mechanisms, assuming that they describe the security of the
agent. In this paper, we explore whether it also influences the
benchmark's measurement. To measure the effect of the
benchmark representation, we introduce threat-preserving representation sensitivity (TPRS), which measures how much the ASR changes when we change the
agent-visible representation while holding the underlying task, harmful action, security policy, ground truth, environment, and the evaluation criteria fixed. On
Agent Security Bench (ASB), replacing threat-related tool names with threat-neutral names raises the committed attack success rate by 11.67 percentage points on GPT-5-mini and by 13.21 points on Claude Haiku 4.5. On MCPTox, replacing the original neutral tool name with an explicit threat-related name lowers the ASR by 11.00 percentage points on GPT-5-mini and 4.11 points on Claude Haiku 4.5. On AgentDojo, adding threat-related wording to the attack-relevant tool changes ASR by only 0.50 percentage points on GPT-4o-mini, yet the benign utility falls by 5.36 points on tasks requiring that tool. We ran an experiment on MCPTox where we observed that a threat-neutral name matched on
token count, length, and casing reproduces most of the shift produced by the threat-explicit name (8.54 of 11.00 points on GPT-5-mini). The results show that a security score measured under one representation may fail to generalize across threat-preserving representations of the same security problem. Robustness claims should therefore be supported by performance across a controlled set of threat-preserving representations rather than relying on a single representation-dependent score.
Read the full abstract ▾
All authors Neeraj Karamchandani, Piyush Nagasubramaniam, Xinhong Xie, Sencun Zhu, Dinghao Wu
Information Theory · Cross-listed from quant-ph
Robustness of quantum spectrum estimation: weak Schur sampling under noisy inputs
Vladyslav Visnevskyi and Laura Mančinska
We initiate the study of weak Schur sampling (WSS) under noisy inputs. Many optimal
quantum learning
algorithms rely on this measurement, for instance in
quantum spectrum estimation (QSE) and
quantum state
tomography (QST). The standard analysis of WSS, QSE and QST assumes that the $n$ input copies of the target state $\rho$ are identical, i.e. $\rho^{\otimes n}$. We study what happens when they are not, a more realistic noisy scenario that breaks the very permutation
symmetry on which WSS is built. In the simplest model the input is a noisy product state: the copies are independent but not necessarily identical and each is $\epsilon$-close in trace distance to the $d$-dimensional target state $\rho$. A naive argument via the data-processing inequality allows the per-copy errors to accumulate to $n\epsilon$ on the measurement outcome. We show that for QSE via WSS this does not happen: the expected estimation error in total variation is at most $\epsilon+\eta(n,d)$, where $\eta(n,d)=O(d/\sqrt n)$ is the noiseless error, and the additive noise term $\epsilon$ is optimal. The output error does not grow with $n$ even though the input error does; in this sense WSS is robust. Beyond noisy product states, for arbitrary input $\omega$ we show that the error is at most $\eta(n,d)+\frac{1}{n}\|\omega-\rho^{\otimes n}\|_{W_1}$, where $W_1$ is the
quantum Wasserstein distance of De Palma et al. In particular, our results imply, for the first time, noise-robustness of Keyl and Werner's seminal
algorithm for QSE, more than two decades after its introduction. Finally, we show that the noise cannot be too bad: within our model of robustness the promise on the input cannot be weakened to closeness of single-copy marginals or to a global trace-distance budget alone, as in both cases some inputs defeat every measurement and
estimator.
Read the full abstract ▾
Data Structures and Algorithms · Cross-listed from quant-ph
Anupam Prakash, Shree Hari Sureshbabu, Dylan Herman et al. (+1 more)
A
quantum orthogonal
polynomial transform (QOPT) is an algorithmic primitive that maps a superposition of standard basis states $\sum_k \alpha_{k} \ket{k}$ coherently to a basis of normalized univariate
polynomials orthogonal with respect to a probability measure $\mu(x)$. We provide new discrete and continuous QOPTs for
polynomial families in the Askey scheme extending the results for the
quantum Hermite transform (Jain et al., STOC'26). Our efficient QOPT
algorithms require time $O(\text{polylog}(N, 1/\epsilon))$, where $N$ is the grid size and $\epsilon$ is the error, for the discrete Charlier, Meixner and Krawtchouk transforms and for the integer-order Laguerre transform in the continuous setting. The efficient QOPTs are obtained by uncovering the links between Askey scheme
polynomials and Gaussian
quantum optical gates and developing a compilation framework for $SU(2)$ and $SU(1,1)$ optical gates on Cartesian grids extending the framework developed by Iyer et al. (arXiv:2602.15180). Further, we reduce the continuous Jacobi transform to the discrete Hahn transform and provide an $O\!\left(N\operatorname{polylog}((N+\alpha+\beta+1)/\epsilon)\right)$-time Hahn transform, a quadratic speedup over the naive implementation. This is based on a more efficient compilation of the Clebsch–Gordan transform for coupling $\mathrm{SU}(2)$ representations with
spins $(j_{1}, j_{2})$. Finally, we develop a new framework for Laguerre transforms for all orders $\nu>0$ by fast-forwarding the corresponding radial oscillator using a 3-term chirp decomposition and an efficient
algorithm for the
Quantum Hankel Transform on a logarithmic grid.
Read the full abstract ▾
All authors Anupam Prakash, Shree Hari Sureshbabu, Dylan Herman, Shouvanik Chakrabarti
Information Theory · Cross-listed from quant-ph
From Symmetry to Secrecy: Covariant Classical–Quantum Wiretap Channels
Masahito Hayashi and Farzin Salek
For classical–
quantum wiretap channels with a transitive covariant input action, both output ensembles admit a description as
unitary group orbits of fixed seed states. We use this structure to construct finite-block preprocessing schemes whose private information is an
entropy difference evaluated at two distributions related by group convolution. Applying the construction to product groups allows correlations across any fixed number of channel uses. We give a sufficient condition for the associated uniform-input bound to equal the single-use private information. Constant-composition channel codes and universal$_2$ hashing achieve the resulting rates, with trace-distance leakage controlled by sandwiched Rényi information. For uniform outer randomization, the representation structure reduces the comparison-state optimization to Eve's invariant states. For the hybrid binary channel considered by Tikku, Berta and Renes, numerical optimization at three and four uses gives rates above our numerical estimate of the optimized noisy-repetition
benchmark wherever that estimate is positive on the tested grid. The improvement comes from noise distributions beyond the family of independent physical flips and a symmetric logical flip. We also prove nonadditivity at an explicit channel parameter using a two-use encoder, an analytic single-use converse, and certified
entropy bounds. Finally, we relate the hybrid model to binary phase-shift keying with a fixed receiver measurement.
Read the full abstract ▾
Computer Vision
Rethinking What to Cache in Few-Step Diffusion Transformers: Solver-Aware Target Selection
Shuo Yang, Lihao Fang, Yi Zhang et al. (+5 more)
Diffusion Transformers (DiTs) can generate high-quality images and
videos, but generating each sample requires multiple costly DiT forward passes. Two common ways to accelerate DiT sampling are step
distillation, which reduces the number of sampling steps, and caching, which skips some DiT evaluations by reusing a tensor computed at an earlier step. Most caching methods decide in advance which tensor to reuse. After
distillation, adjacent sampling steps are farther apart. Reusing a tensor across this larger gap introduces more error, so choosing what to cache becomes especially important. We therefore introduce AutoTarget, a method that chooses the cached tensor for a given model, solver, and reuse schedule. AutoTarget uses a small set of runs without cache reuse to measure the error caused by reusing each candidate tensor, then selects the candidate with the lowest error. We also analyze how an error at one reuse step affects the final sample. For Euler sampling, we identify cache targets that produce the same trajectory and show why a stored solver update may not. Experiments on distilled image and
video DiTs show that the best cache target changes with the model, image resolution, and solver. AutoTarget reduces DiT evaluations and retained cache storage. Generation quality remains close to the corresponding uncached run. On the tested PixArt-LCM and FLUX.1-schnell settings, its calibration ranking matches the ranking from held-out cached runs. To help others reproduce the method, we provide its core implementation on GitHub at https://github.com/wali1024-offical/AutoTarget.
Read the full abstract ▾
All authors Shuo Yang, Lihao Fang, Yi Zhang, Haixiang Wang, Xincheng Ye, Shufan Chen, Jipeng Guo, Youqing Wang
Numerical Analysis
Error Estimates in Physics-Informed Neural Networks to Heat-Wave Fluid-Structure Interactive System
Pelin G. Geredeli, Mohammad Mahabubur Rahman and Deepanshu Verma
We study a physics-informed neural network (PINN) approximation of a coupled PDE system that models the interaction between fluid and elastic dynamics. The canonical heat-wave model considered here couples a
parabolic and a
hyperbolic equation through transmission conditions on a fixed boundary interface, and serves as a prototype for the Stokes-elastic systems that arises in real world applications. This coupling makes the error analysis more delicate than that for a single PDE. We bound the error between the exact and PINN solutions by the associated PINN residuals, and we moreover prove that the generalization error is controlled by the training error, the number of quadrature points, and the size of the network. {To the best of our knowledge}, these are the first error estimates for a PINN approximation of a coupled fluid-structure interaction PDE system. We also show that numerical experiments with respect to a given test problem.
Read the full abstract ▾
Artificial Intelligence
Alham Fikri Aji, Faiz Rizki Ramadhan, Zayd M. K. Zuhri et al. (+14 more)
We introduce HyperBrowseComp, a
multilingual and
multimodal browsing
benchmark comprising 423 manually authored and human-validated questions across 13
languages, written by native or highly proficient speakers. Questions are designed to be extremely challenging. Each question targets a concise, publicly verifiable answer whose discovery requires locating obscure evidence, following multi-step clue chains, or inspecting heterogeneous sources such as
videos, scanned documents, images, or maps. Easier questions are filtered out by evaluating them with models without internet access to reduce the likelihood that they can be answered with parametric knowledge alone. We evaluate several models using provider-native search and a shared external
retrieval harness under a common
agent protocol. To contextualize model performance and effort, we also conduct a human evaluation on a sample of the questions. HyperBrowseComp provides a challenging testbed for persistent information seeking across
languages and evidence modalities, with difficulty arising from discovering and connecting evidence on the open web.
Read the full abstract ▾
All authors Alham Fikri Aji, Faiz Rizki Ramadhan, Zayd M. K. Zuhri, Seung Hun Eddie Han, Ryandito Diandaru, Qinrong Cui, Jan Christian Blaise Cruz, Badrinath Chandana, Peerawat Chomphooyod, Ahmed Attia, Jonibek Mansurov, Emilio Villa-Cueva, Canh Duong Nguyen, Imran Turganov, Minghao Wu, Peerat Limkonchotiwat, Irina Nikishina
Programming Languages
OpenMP Meta-Lowering: A Declarative Approach to Performance Portable Parallel Code Generation
Luca Parigi and Giuseppe Tagliavini
The increasing diversity of parallel hardware challenges existing compilation flows. While OpenMP provides a portable abstraction for shared-
memory parallelism, existing compilers tightly couple the frontend semantics with fixed lowering strategies. This design limits performance portability across different runtimes and architectures. In this paper, we present a modular approach to parallel code generation based on the Multi-Level Intermediate Representation (MLIR) framework. Our approach combines an OpenMP frontend with a domain-specific
language (DSL) that specifies how OpenMP constructs are lowered for a target. We call this approach OpenMP meta-lowering, treating lowering as a programmable component rather than compiler-specific logic. This design provides explicit control over code outlining, data sharing, and runtime interfacing across diverse targets. We evaluate our approach on PolyBench/C-OMP across general-purpose and embedded multicore targets. Our results show that the proposed method matches the performance of state-of-the-art compiler toolchains with negligible code-size overhead (< 0.7%). Preserving OpenMP constructs until late lowering stages enables both general-purpose and OpenMP-specific MLIR optimizations. By decoupling lowering from compiler internals, our approach expresses the same OpenMP subset in 5,182 lines of code, ~32% fewer than the corresponding lowering code in Clang and ~76% fewer than in GCC, while supporting the pmsis runtime costs only a few specification lines, enabling rapid support for new runtimes without modifying the compiler.
Read the full abstract ▾
Artificial Intelligence
Learning to Assess Heartbeat Observability for mmWave Heart-Rate Sensing
Yuxuan Hu, Shilin Shan, Jianfei Yang et al. (+1 more)
Contactless heart-rate sensing with millimeter-wave (mmWave) radar requires assessing whether individual measurements support reliable estimation. We study learning to assess heartbeat observability, defined as the readability of the heartbeat component in an acquired phase spectrum, for selective heart-rate estimation. Coherent superposition of scatterer returns can suppress this component even under similar macroscopic observation geometry, motivating assessment directly from acquired measurements. To obtain training supervision across different observability conditions, we develop a controllable multi-scatterer frequency-modulated continuous-wave (FMCW) simulator. Agreement between the dominant heartbeat-band peak and the known heart rate provides an automatic observability label for each simulated measurement. We propose HEAR (Heartbeat Estimation with Assessed Reliability), a compact dual-task
Transformer that jointly predicts an observability score and heart rate. Its input combines spectral magnitudes with frequencies relative to the respiration fundamental, providing context for respiratory harmonics. Trained solely on simulated observations, HEAR transfers zero-shot to two public real-world
datasets collected at 60 and 120 GHz from 134 subjects. The same learned score supports selective prediction with both HEAR's own heart-rate head and multiple existing
estimators. On the 120 GHz
dataset, score-based selection reduces the HR head's mean absolute error from 17.9 BPM at full coverage to 1.6 BPM at 50% coverage. The complete pipeline achieves an end-to-end processing latency of 50.8 ms on an edge device. Project page: https://yuxuanhu9.github.io/HEAR/.
Read the full abstract ▾
All authors Yuxuan Hu, Shilin Shan, Jianfei Yang, Feng Xu
Computation and Language
Writerslogic at the CLEF 2026 SimpleText Track: Multi-Candidate LLM Simplification and Stacked Complexity Spotting
David L. Condrey
We describe the Writerslogic team's participation in the CLEF 2026 SimpleText shared task, addressing Task 1 (text simplification) and Task 2 (complexity spotting). For Task 1, we develop a multi-candidate generation pipeline using GPT-4o-mini that produces five simplification candidates per sentence at varying temperatures, then selects the best candidate using a reference-free scoring heuristic that rewards compression, source word retention, Cochrane Plain
Language Summary vocabulary usage, and lexical simplicity. On Task 1.1 (sentence-level simplification), our Claude Sonnet 4 submission achieves SARI 47.43 and BLEU 14.21, the top-ranked sentence-level system (3rd on the combined Task 1 leaderboard, behind two document-level submissions). For Task 2, we fine-tune a DeBERTa-v3-large NLI model on 350K labeled (source, sentence) pairs, framing
hallucination detection as natural
language inference. The model reads the most relevant source sentence as premise and the candidate as hypothesis, directly learning to distinguish grounded from hallucinated content. On Task 2.1 (binary overgeneration identification), our fine-tuned DeBERTa system achieves 0.8081 document-level macro F1 (0.8085 in our best ensemble), the top-ranked entry within the identification track and 2nd among teams overall, behind AIIR Lab (0.8197). On Task 2.2 (multi-class error classification), our best submission reaches 0.804 multiclass accuracy, ranking 2nd among unique teams behind AIIR Lab (0.827). We evaluate both tasks on English and
multilingual biomedical text from Cochrane systematic reviews.
Read the full abstract ▾
Computation and Language
Writerslogic at PAN 2026: Process over Content for Robust Detection under Domain Shift
David L. Condrey
We describe the Writerslogic systems for three PAN at CLEF 2026 shared tasks (
Reasoning Trajectory Detection, Voight-Kampff Generative AI Detection, and Multi-Author Writing Style Analysis), unified by a shared analytical framework: feature robustness under distribution shift is governed by support overlap between training and test distributions, not by training-set effect size. This yields a taxonomy (domain-anchored, domain-portable, domain-invariant) that explains why generator-specific features die under domain shift while vocabulary fingerprints (hapax ratio, Yule's K, Heaps' exponent), compression measures, and character n-grams survive. On
Reasoning Trajectory Detection, where training was entirely mathematics and 84 percent of test was unseen domains, the framework guided system design to 1st place in source detection (0.85 macro F1 via Opus-Sonnet agreement) and 3rd place in safety classification (0.66 macro F1 via query-refusal decomposition). For Voight-Kampff, we built a calibrated ensemble of DeBERTa-v2 (ONNX), multi-seed LightGBM with 44 domain-portable stylometric features, and SVM on n-gram TF-IDF, combined via learned stacking with isotonic calibration; the best configuration achieved 0.891 on the PAN 2026 test set with balanced sub-metrics (0.853 to 0.902 across all evaluation dimensions). For Multi-Author Writing Style Analysis, we describe a system fusing spectral clustering over character n-gram similarity graphs, normalized compression distance for local boundary detection, and SmolLM-135M perplexity for neural change-point detection; a platform mix-up meant our run never reached the official evaluation, so we report the design and its a priori predictions. Across all three tasks, features measuring generation process properties are designed to outperform features measuring generated content properties under domain shift.
Read the full abstract ▾
Artificial Intelligence
Knowledge or Calculator? Decomposing the Skill Premium in Verifiable Financial Agent Workflows
Jermyn Zhen Yong Bek, Zhuang Qiang Bok and Zhongtian Sun
Financial AI
agents must do more than retrieve facts: investment workflows require correct quantitative execution, reliable use of procedural resources, and auditable structured outputs. We introduce FinSkillBench, an evaluation suite of 2,603 point in time episodes across 12 subtasks in portfolio construction, risk management, and fundamental analysis, with hidden regenerable ground truth and task specific deterministic verifiers. Executing 17,820 episodes across 9 models and 3 resource conditions, the paired analysis across 8 models shows that curated skill packages raise mean scores by +16.2 points (0.366 to 0.528), whereas skills generated within a single episode add only +0.5 points while consuming more
tokens and turns. We then decompose the curated premium by granting human authored procedural documents and executable domain tools separately: documents alone add +5.6 points, tools alone add +19.5 points, and their combination is subadditive. The premium is strongly workflow dependent: executable tools dominate numerically intensive workflows, documentation matters more when procedural or output schema guidance is the bottleneck, and interpretive tasks benefit from both. The effects are sign stable across 10 scoring variants and cluster bootstrap analyses, and an independently implemented second harness reproduces the directional pattern while showing that effect magnitudes depend on how tools and data are exposed. Overall, a measured "skill premium" is a property of the full model, resource, and harness system rather than of the underlying model alone.
Read the full abstract ▾
Robotics
A Unified Framework for Empowerment and Predictive Control
Wooyoung Chung, Tristan Shah, Volodymyr Makarenko et al. (+1 more)
Sampling-based model predictive control (MPC) is a powerful approach to trajectory optimization, but its performance depends on an informative cost function that often requires substantial domain knowledge to design. An alternative is to derive objectives directly from the system dynamics. Empowerment, defined as the channel capacity between an
agent's inputs and its future state, provides such a goal-agnostic objective and has been shown to produce useful behaviors across a range of domains. However, existing empowerment-based controllers have two key limitations: empowerment is estimated using a virtual probing policy distinct from the executed control policy, obscuring its connection to the resulting behavior; and its computation typically requires second-order derivatives of the dynamics, limiting compatibility with standard MPC methods. We formulate empowerment using a single policy for both probing and acting, directly linking the empowerment objective to the executed behavior. The resulting objective requires only first-order derivatives and can be optimized with standard MPC solvers, either alone or in combination with a task-specific cost. We evaluate the proposed approach on classical control tasks and show that combining empowerment with task costs matches or exceeds the success rate achieved by either objective alone. Our formulation provides a practical bridge between standard MPC and intrinsically motivated control.
Read the full abstract ▾
All authors Wooyoung Chung, Tristan Shah, Volodymyr Makarenko, Stas Tiomkin
Cryptography and Security
A Secure dToF LiDAR SoC with Dual-Domain Fingerprinting and Event-Driven AFE Circuit Achieving Sensor-Level Attack Resilience
Risa Nonaka, Ryoya Matsuno, Shota Nagai et al. (+10 more)
Recent studies have shown that most commercial direct time-of-flight (dToF)
LiDARs can be spoofed by injecting high-frequency
laser pulses into the receiver, which can erase pedestrians from the point cloud. This paper presents the first dToF
LiDAR system-on-chip (SoC) with integrated sensor-level hardware security against spoofing attacks. We propose Dual-Domain Fingerprinting (DDF), which emits
laser pulse pairs whose time interval and amplitude ratio are both randomized and authenticates received echoes in this two-dimensional space, so that spoofed signals are rejected before they corrupt the ranging result. An Event-Driven AFE (ED-AFE) activates the ADC only around pulse peaks: it digitizes three samples around each peak with a triggered ADC at 1-GHz sampling and applies
parabolic interpolation, achieving 1-cm distance resolution with a 99% reduction in ADC power. A time-modulated
laser driver controls the
laser amplitude from 10% to 100% by modulating the charge time of a
laser capacitor, providing the microsecond-order amplitude modulation required by DDF. A
LiDAR system with a 16-channel 65-nm CMOS prototype SoC demonstrates up to 120-m ranging and an AFE power of 3.1 mW per channel, 60% lower than prior art. In a proof-of-concept experiment in which the dual-domain authentication is applied to measured sensor data, 73% of the point cloud is protected under spoofing attack, compared with 0% without DDF.
Read the full abstract ▾
All authors Risa Nonaka, Ryoya Matsuno, Shota Nagai, Satomi Miyagi, Yuki Hayakawa, Ryo Suzuki, Kazuma Ikeda, Ozora Sako, Rokuto Nagata, Ryo Yoshida, Shimpei Ando, Wenlun Zhang, Kentaro Yoshioka
Discrete Mathematics · Cross-listed from math.OC
Grid Theory and Polynomiality in Dynamic Lot-Sizing
El-Mehdi Mehiri, Nabil Absi and Elodie Suzanne
Why are some dynamic lot-sizing problems
polynomial? We address this question by introducing Grid Theory, a structural framework based on cumulative production and the additive structure of production bounds. For a general single-item dynamic lot-sizing model with lower and upper production bounds, there exists an optimal extreme solution in which, within each regeneration interval, all but at most one production quantity lie on a boundary value. This induces additive grids, and the Main Grid
Theorem establishes that an optimal cumulative production trajectory can be restricted to these discrete sets. Although the resulting grids may be exponentially large, we introduce the notion of additive dimension to capture production-bound profiles whose boundary sums admit a low-dimensional representation. We show that bounded additive dimension yields a polynomially constructible grid envelope and a
polynomial time grid-based dynamic programming
algorithm. The framework extends to separable concave costs and establishes
polynomial solvability of several families, including constant capacities, minimum order quantities, a fixed number of capacity levels, fixed-degree
polynomial capacities, periodic capacities, and piecewise
polynomial capacities. In particular, polynomiality may hold even when the number of distinct capacity values grows with the planning horizon. Grid Theory thus identifies additive structure, rather than the number of distinct resource values, as a sufficient mechanism for
polynomial solvability.
Read the full abstract ▾
Machine Learning
Cephalonauts One: A deep fMRI dataset for decoding naturalistic speech in the human brain
Antoine Collas, Louis Jalouzot, Géraud Ilinca et al. (+11 more)
Cephalonauts One is a whole-
brain 3 Tesla (3T) functional
magnetic resonance imaging (fMRI)
dataset recorded while subjects listened to audio podcasts. Three healthy subjects underwent multiple scanning sessions, each consisting of five 15-minute runs, while listening to podcasts in their native
language. With 30 hours of fMRI data per subject, the current release is the deepest available fMRI
dataset using naturalistic
speech stimuli. The
dataset pairs
brain activity with the corresponding podcast audio, transcript annotations, and derived stimulus
embeddings. Furthermore, we introduce a
brain decoding
benchmark formulated as audio segment
retrieval: given fMRI activity from a held-out session, the decoder must identify the corresponding time-aligned podcast audio segment among candidate segments. We provide standardized splits, evaluation metrics, and baseline decoders for this task. Finally, a scaling analysis shows that decoding performance improves continuously with the amount of training data per subject.
Read the full abstract ▾
All authors Antoine Collas, Louis Jalouzot, Géraud Ilinca, Corentin Caris, Romain Valabrègue, Ahmed Hassayoune, David Goncalves, Madeleine Hueber, Thaddée Delebarre, Julien Savatovsky, Clara Fonteneau, Charles Maussion, Bertrand Thirion, Alexis Thual
Machine Learning
Get a GRIP, this will be a long TRIP: A Quantifiable Long-Range Framework for Verifying Over-squashing
Ferran Hernandez Caralt, Simon Heilig, Adrián Bazaga et al. (+3 more)
Empirical claims about the connection between over-squashing and long-range interactions in GNNs, can only be trusted if the
benchmarks used to validate them genuinely require long-range interactions. The de-facto standard, the Long Range Graph
Benchmark, has been repeatedly shown to be saturated by tuned short-range models, with existing synthetic alternatives being tied to specific
topologies. As such, there is a lack of principled certificate of long-rangedness on arbitrary graphs. This state reflects the absence of a precise characterization of long-ranged
benchmarks. We address this fundamental gap by introducing four verifiable axioms: Predictability, Tightness, Strictly $k$-Range, and
Topology-Invariance, that any task claiming to test $k$-hop interactions must satisfy. We formally prove that violating any one of them admits failure modes that undermine conclusions drawn from the task. Based on these axioms, we introduce TRIP (Truly Ranged Interactions Problem) and its generalisation GRIP (Generally Ranged Interactions Problem), constructive procedures that turn any graph into a provably long-ranged task by drawing features from stable distributions. Moreover, by construction, GRIP admits a closed-form, per-range Maximum-Likelihood oracle that yields the first a priori per-range lower bound on test error available on any
benchmark. Using our framework, we: (i) audit 4 common long-range
benchmarks and identify their failures modes with respect to our axioms; (ii) on TRIP-instantiated
topologies, we find a popular notion of
curvature is uncorrelated with GNN performance, supporting topological-vs-computational bottleneck distinction; and (iii) we show that a novel
benchmark's over-squashing measures factors beyond pure long-rangedness. Code to use the framework and reproduce experiments is released https://github.com/ferranhernandezc/graph-grip.
Read the full abstract ▾
All authors Ferran Hernandez Caralt, Simon Heilig, Adrián Bazaga, Asja Fischer, Moshe Eliasof, Pietro Liò
Machine Learning
Objects Without Morphisms: What LLMs for Mathematics Do Not Represent
Yanli Wang, Suijin Wang, Xiaopeng Yuan et al. (+1 more)
Large
language models (LLMs) have reached expert-level performance on competition mathematics largely through the volume of search placed around them: candidate solutions are sampled in quantity and retained only when an external criterion accepts them. Such a procedure improves the outcome that survives it while leaving untouched what the model represents. We examine that question where no external criterion exists: translating statements between the dialects of neighbouring subfields, where fidelity turns on the level of generality at which content is asserted. The source leaves that level implicit in its vocabulary, so a faithful translation must recover it from the relation between the theories. We introduce an instrument that codes truth, content and scope in separate blind queues, with a judge-free measure of whether a rewrite states the hypothesis implicit in its source, and establish its sensitivity with a planted-positive control. Across seven models from four families, translating towards the general framing widens the domain of quantification in 60.6% of rewrites and narrows it in none; translating towards the concrete framing narrows it in 28.3% and widens it in 0.3%. The hypothesis that would prevent it is stated in 21.6% of model rewrites and 4.2% of human statements. Capability does not govern the asymmetry: it appears in every model tested, and the most capable widens least. It replicates on the half of the
benchmark held out by a pre-registered rule, and on statements written by mathematicians. Instructing a model to state every hypothesis it requires raises that rate but not its sensitivity to direction. We argue that these systems have acquired an object-level correspondence between subfield vocabularies without the constraint under which a translation between theories carries hypotheses to hypotheses.
Read the full abstract ▾
All authors Yanli Wang, Suijin Wang, Xiaopeng Yuan, Haohan Wang
Discrete Mathematics · Cross-listed from math.CO
Counterexamples to the Strong Roberson Conjecture
Arnar Á. Kristjánsson
We refute the Strong Roberson
Conjecture, which asserts that adding any graph outside a class closed under minors and disjoint unions strictly increases the distinguishing power of homomorphism counts from that class. More precisely, we construct connected graphs $H$ for which counts from graphs excluding $H$ as a minor determine the number of homomorphisms from $H$ to any target graph. We also refute the analogous
conjecture with immersions in place of minors. We give explicit infinite families of excluded graphs, including cubic bipartite graphs that yield counterexamples for both relations. The proof introduces a method for deriving exact homomorphism count dependence from modular equivalences. We obtain these equivalences for infinitely many
primes using
prime-order
automorphisms of graphs that exclude their orbit quotients as minors or immersions.
Read the full abstract ▾
Artificial Intelligence
Recursive Harness Self-Improvement for Frontier Reasoning Data Synthesis
Wenlong Zhang, Zhengbo Jiao, Chenxu Zhang et al. (+5 more)
Generating progressively harder
reasoning problems requires synthesis procedures that adapt as the task distribution evolves. Existing task-level recursion reuses generated problems as seeds but leaves the construction harness unchanged. We present task-harness co-
evolution, a framework for recursive harness self-improvement (RSI) in
reasoning-data synthesis. Online self-improvement converts intermediate solver failures into reusable skills during generation. Post-task self-improvement revises skills,
prompts, and workflows after each batch, adopting candidates only when they generate harder valid tasks within a bounded cost increase. Model weights and verification criteria remain fixed. Across mathematics, coding, and science, mean solver accuracy decreases from 100.0% to 54.8% over fourteen
evolution rounds. Ablations show that combining both update schedules produces harder tasks than fixed-harness recursion or either schedule alone. The resulting data improves downstream SFT and GRPO performance. In particular, a 27B student fine-tuned on 10K synthesized mathematics examples achieves 62.5% mean-16 accuracy on APEX, competitive with selected frontier-model references. These results support adapting the synthesis harness alongside the tasks to generate increasingly challenging data with downstream training value.
Read the full abstract ▾
All authors Wenlong Zhang, Zhengbo Jiao, Chenxu Zhang, Lekang Jiang, SiYuan Ma, Qituan Zhang, Guo Chen, Linfeng Zhang
Machine Learning
ZeroMAG: Zero-Shot Multimodal Adapter Generation for Plug-and-Play EEG Foundation Models
Yubo Wang, Jingying Ma, Xinliang Zhou et al. (+8 more)
EEG foundation models (EFMs) capture reusable knowledge from large-scale
EEG data, while many
EEG recordings also include companion physiological signals that provide complementary information beyond the
EEG-only interface. The challenge is to preserve this pretrained knowledge while extending the EFM to heterogeneous
multimodal recordings through an adaptation inferred from unlabeled target data. We introduce ZeroMAG, a zero-shot
multimodal adapter generation framework that extends a frozen
EEG encoder and prediction head using unlabeled target recordings, without target labels or target-side optimization. The target
datasets are held out from all model training and selection in the ZeroMAG pipeline. ZeroMAG organizes companion modalities around a configuration-invariant adapter, constructs a modality-subject-task condition from unlabeled recordings and task context, and generates adapter weights in a function-constrained latent space learned from source adapters. Across six held-out target
datasets and three EFM backbones, ZeroMAG improves balanced accuracy by 7.22 percentage points over
EEG-only inference and 4.89 points over direct weight regression, while coming within 0.50 points of supervised
multimodal adaptation on average. Ablations further show that removing functional supervision from either representation learning or conditional generation degrades generated-adapter performance, confirming the contribution of both components.
Read the full abstract ▾
All authors Yubo Wang, Jingying Ma, Xinliang Zhou, Yangxuan Zhou, Jiquan Wang, Sha Zhao, Yiyuan Yang, Yi Ding, Ziyu Jia, Chenyu Liu, Cuntai Guan
Computer Vision
DuoMatching: Joint-Marginal Distribution Matching for Few-Step Video Generation
Jiahao Zhan, Yan Wang, Yongrui Ma et al. (+5 more)
Streaming
video generation has benefited from distribution matching
distillation (DMD), which matches the joint distribution of
video frames to a
video teacher's approximation of the real
video distribution. Although this joint matching mitigates drift during autoregressive rollouts, limitations remain in visual quality and semantic
alignment. To address these limitations, we propose DuoMatching, a distribution matching framework that approximates the real
video distribution through a unified joint-marginal formulation. On top of existing joint matching formulations, the additional marginal matching objective provides dedicated frame-level supervision from an image generator, transferring complementary visual and semantic priors from it. To apply this frame-level supervision in
video generation, we introduce LatentBridge to resolve the latent representation mismatch between the
video student and the image teacher. Latent Variation Sampling further distributes such frame-level supervision across distinct temporal segments, reducing redundancy. Experiments demonstrate that DuoMatching improves visual quality, composition, and semantic
alignment while largely preserving motion dynamics. Human evaluations show overall preference rates above 80% against all evaluated baselines. The project page is available at https://johnzhan2023.github.io/DuoMatching/.
Read the full abstract ▾
All authors Jiahao Zhan, Yan Wang, Yongrui Ma, Qunliang Xing, Ruchang Yao, Runtao Liu, Shijie Zhao, Tianfan Xue