arXiv:2501.01062v4 Announce Type: replace
Abstract: DAG-based BFT consensus has attracted growing interest in distributed data management systems for consistent replication in untrusted settings due to its high throughput and resilience to asynchrony. However, existing protocols still suffer from high communication overhead and long commit latency. In parallel, introducing minimal hardware trust has proven effective in reducing the complexity of BFT consensus.
Inspired by these works, we present Fides, an asynchronous DAG-based BFT consensus protocol that, to our knowledge, is among the first to leverage TEEs to enhance both scalability and efficiency. Fides tolerates a minority of Byzantine replicas and achieves $O(\kappa n^2 + n^3)$ metadata communication complexity through a customized TEE-assisted Reliable Broadcast (T-RBC) primitive with linear communication complexity in one-step broadcast. Building on T-RBC, Fides redefines the DAG construction rules by reducing the reference requirement from $2f+1$ to $f+1$ between consecutive vertices. This new structure weakens DAG connectivity and invalidates traditional commit rules, so we formally abstract the problem and derive new theoretical bounds of liveness. We further propose a four-round commit rule that achieves the theoretically minimal commit latency. Besides, we design two additional primitives, T-RoundCert and T-Coin, to efficiently certify DAG references and replace the costly cryptographic common coin used in prior protocols. Comprehensive evaluations on geo-distributed and local testbeds show that Fides substantially outperforms state-of-the-art protocols, including Tusk, Bullshark, Mysticeti, RCC, Damysus, Achilles and HybridSet, achieving lower latency and higher throughput while preserving strong safety and liveness guarantees.
Science Journals
arXiv:2606.04047v1 Announce Type: new
Abstract: In recent years, the detection of anti-patterns in microservice architecture has gained traction, particularly to identify instances of Microservice Architectural Degradation. In such tasks, the microservice architecture is often modeled as a network of microservice dependencies. Recent works have explored how to assess the evolution of such architectural networks by considering the architecture of consecutive releases of the project. Particular anti-patterns related to the structure of the service network include Wrong cuts and Knot services.
Community detection is a way to identify groups of services in a network that strongly depend on each other. If such groups cannot be mapped to business processes in the system, or if the same service belongs to multiple communities, this could indicate architectural degradation due to an inappropriate division of responsibilities or unoptimized communication. Temporal community detection methods have been proposed to analyze community structure that evolves in time.
We performed temporal community detection within the microservice architecture of six releases of the train-ticket benchmark and analyzed the composition of the discovered communities and their activities over time. We observed a stable architecture with a clear separation of services into two communities, which we could identify with two business processes performed by the system. We found services belonging to several communities, as well as services within the same community with both incoming and outgoing connections. The membership strength metric provided by the leveraged algorithm enables fine-grained assessment of the microservice communities.
arXiv:2606.04471v1 Announce Type: new
Abstract: This paper addresses the Self-Optimizing Control (SOC) problem in industrial continuous processes and proposes a Reinforcement-Learning (RL)-based SOC approach to improve dynamic performance under high-frequency disturbances. In the proposed framework, the SOC controlled variable structure is embedded in the Actor network, and reward functions are designed based on economic indicators. Through interaction with the environment, the RL agent optimizes controlled variables while implicitly considering implementability and steady-state uniqueness. Online fine-tuning is further introduced to alleviate model mismatch. Experiments on a continuous stirred-tank reactor with disturbances compare the proposed RL-based SOC method with the Objective-Guided Controlled Variable Learning Approach based on steady-state data. The results show that the RL method achieves improved dynamic performance under real-time disturbances, generates smooth controlled variable outputs without explicit regularization, reduces hyperparameter-tuning complexity, and enhances adaptability through online adjustment. Overall, the proposed RL-based SOC approach provides an effective solution for nonlinear process control and offers a promising reference for future studies involving multiple disturbances, multiple operating conditions, and model-free scenarios.
arXiv:2606.04269v1 Announce Type: new
Abstract: Deformable object manipulation (DOM) is challenging due to high-dimensional, partially observable states that evolve through long-horizon, topology-changing interactions with multiple valid manipulation modes. We introduce Instant-Fold, an in-context imitation learning framework for DOM. Given a single human demonstration, our policy infers and executes diverse manipulation modes directly from the demonstration, including variations in spatial execution and ordering, without requiring gradient updates. Our approach first learns deformation-aware visual representations via temporal contrastive pretraining, after which a flow-matching transformer policy conditioned on the demonstration predicts actions to execute the intended manipulation mode. Trained entirely in simulation, Instant-Fold generalizes across diverse folding modes and transfers zero-shot to real-world settings without additional data collection or finetuning. Videos are available at https://instant-fold.github.io.
arXiv:2606.04570v1 Announce Type: new
Abstract: Higher-Order Ambisonics (HOA) encoding from sparse, irregular microphone arrays remains a critical challenge for consumer spatial audio capture in immersive communication and XR. We propose Flow-HOA, a generative framework that jointly optimizes a multi-dimensional objective encompassing time-domain, spectral, and spatial fidelity while producing a deployable, time-invariant bank of Finite Impulse Response (FIR) encoding filters. Using conditional flow matching, the model learns to map a simple prior distribution to the target distribution of FIR filter coefficients. Training is guided by a composite loss that balances time-domain waveform fidelity, multi-resolution spectral consistency, sub-band energy preservation, and spatial directivity constraints. Objective evaluations on synthetically simulated data demonstrate improved performance over strong model-based baselines in both signal fidelity and spatial accuracy metrics. Subjective listening tests on real microphone array recordings further confirm that Flow-HOA yields higher overall sound quality with reduced artifacts, demonstrating generalization from synthetic training data to real-world capture conditions.
arXiv:2602.19101v2 Announce Type: replace
Abstract: Value alignment of Large Language Models (LLMs) requires us to empirically measure these models' actual, acquired representation of value. Among the characteristics of value representation in humans is that they distinguish among value of different kinds. We investigate whether LLMs likewise distinguish three different kinds of good: moral, grammatical, and economic. By probing model behavior, embeddings, and residual stream activations, we report pervasive cases of value entanglement: a conflation between these distinct representations of value. Specifically, both grammatical and economic valuation was found to be overly influenced by moral value, relative to human norms. This conflation was repaired by selective ablation of the activation vectors associated with morality.
arXiv:2512.17678v2 Announce Type: replace
Abstract: Selecting compact and informative gene subsets from single-cell transcriptomic data is essential for biomarker discovery, improving interpretability, and cost-effective profiling. However, most existing feature selection approaches either operate as multi-stage pipelines or rely on post hoc feature attribution, making selection and prediction weakly coupled. In this work, we present YOTO (you only train once), an end-to-end framework that jointly identifies discrete gene subsets and performs prediction within a single differentiable architecture. In our model, the prediction task directly guides which genes are selected, while the learned subsets, in turn, shape the predictive representation. This closed feedback loop enables the model to iteratively refine both what it selects and how it predicts during training. Unlike existing approaches, YOTO enforces sparsity so that only the selected genes contribute to inference, eliminating the need to train additional downstream classifiers. Through a multi-task learning design, the model learns shared representations across related objectives, allowing partially labeled datasets to inform one another, and discovering gene subsets that generalize across tasks without additional training steps. We evaluate YOTO on two representative single-cell RNA-seq datasets, showing that it consistently outperforms state-of-the-art baselines. These results demonstrate that sparse, end-to-end, multi-task gene subset selection improves predictive performance and yields compact and meaningful gene subsets, advancing biomarker discovery and single-cell analysis.
arXiv:2606.04904v1 Announce Type: cross
Abstract: Pairwise interactions among general nonlinear oscillators can be reduced, via phase reduction, to a Kuramoto-type phase coupling $\sin(- \theta_j+\theta_k )$. For higher-order interactions, multiple phase couplings exist -- such as $\sin(-2\theta_j+\theta_k+\theta_l )$ and $\sin(-\theta_j+2\theta_k-\theta_l)$. Since different nonpairwise coupling functions produce qualitatively different dynamics, it is important to understand which phase couplings should be included in coupled phase oscillator models. In this Letter, we establish selection rules for higher-order phase coupling functions. These selection rules, which can be applied without the need of explicit phase reduction, are solely based on the symmetry of the isolated oscillator velocity field and the $n$-body interaction functions. As phase reduction established the mechanistic basis for the Kuramoto model, our results provide a theoretical link between physical systems and higher-order phase models.
arXiv:2605.30021v2 Announce Type: replace
Abstract: Many open-ended instructions have multiple valid answers that users can benefit from seeing, but post-training often narrows an LLM's output space toward a small set of canonical responses. We introduce REDIPO, an offline DPO data-construction pipeline for recovering distinct valid answer modes while preserving the alignment benefits of the instruct model. For each prompt, REDIPO samples responses from both base and instruct models, rewrites base-model responses with the instruct model, filters candidates for safety and instruction-following quality, and builds preference pairs that favor marginally diverse responses among candidates with similar instruction-following reward. Across Qwen3-4B, OLMo-3-7B, and LLaMA-3.1-8B, REDIPO improves NoveltyBench distinct_k by 134%, 33%, and 44% relative to the instruct checkpoints, while DivPO changes diversity by 0%, -6%, and -4% on the same models. These gains largely maintain MTBench, IFEval, and Arena-Hard performance, and reduce direct-category HarmBench attack success rate. Ablations show that marginal-diversity pair selection and base-response rewriting drive the diversity gains, while filtering and quality-bounded pairing help maintain alignment. Overall, our results show that diverse valid answers from base-model generations can be reintroduced through carefully constructed preference data while retaining the alignment benefits of post-training. We release our code and data at https://github.com/vsamuel2003/ReDiPO.
arXiv:2606.04557v1 Announce Type: new
Abstract: Large Language Models can reason over long contexts, yet prefilling millions of tokens is wasteful as much of the content remains static across queries. Cartridges address this by distilling document collections into reusable key-value (KV) caches that eliminate prefilling while preserving accuracy. A critical limitation of this approach is that cartridges are monolithic and non-compositional: encoding an entire collection into a single KV block does not scale, and naively mixing cartridges trained in isolation collapses performance to near chance. We introduce Cartridges at Scale (CAS), a training framework for scalable multi-cartridge learning with dynamic distractor mixing and a memory-efficient budget manager that rotates hundreds of per-document cartridges between GPU and persistent storage. Our approach scales to collections exceeding a million tokens, improving over a monolithic cartridge by 10-31 points at comparable token budgets. Oracle cartridge accuracy falls within 2-6 points of full in-context learning even at high compression. When paired with retrieval for cartridge selection, CAS matches or exceeds conventional RAG accuracy while consuming 3-4x fewer prompt tokens.
arXiv:2606.04259v1 Announce Type: new
Abstract: A Hermitian matrix pair $(A,B)$ is called definite if some real linear combination of the matrices $A$ and $B$ is a positive definite matrix. Detection of the definiteness is not straightforward. We propose a basic subspace algorithm for detecting a large definite matrix pair $(A,B)$ with indefinite $B$. The proposed subspace algorithm is based on iterative testing of small projected Hermitian matrix pairs formed by using subspaces of small dimensions. Furthermore, we propose a specialized algorithm with parameter $m$, and its preconditioned variant. In the specialized algorithm with $m=3$ we choose the subspaces like in the indefinite locally optimal block preconditioned conjugate gradient (LOBPCG) method. Numerical experiments demonstrate the efficiency of our specialized algorithm, applied on medium-sized pairs, as well as, on large and banded pairs. Our algorithm very quickly detects (in)definiteness; much faster than some other algorithms.
arXiv:2606.04858v1 Announce Type: cross
Abstract: In this article, we propose an algorithmic approach to determine the integer points located near a transcendental curve. This approach is closely related to a celebrated work by Bombieri and Pila and to the so-called Coppersmith's method. We establish the underlying theoretical foundations, prove the algorithms, study their complexity and present practical experiments; we also compare our approach with previously existing ones. From a practical point of view, we focus on an instance of our general problem, called the Table Maker's Dilemma, whose solving makes it possible to evaluate a given function with correct rounding. Our experiments show a significant speedup. In particular, our results show that the development of a correctly rounded mathematical library for the binary128 format is now possible at a much smaller cost than with previously existing approaches.
arXiv:2606.04261v1 Announce Type: new
Abstract: Curating training data is among the most consequential yet labor-intensive parts of modern AI development: practitioners iteratively propose, implement, evaluate, and revise data policies against noisy benchmark feedback. We ask whether generalist coding agents can automate this data-curation loop. We introduce *Curation-Bench*, an agent-centric benchmark that fixes the model, training recipe, and evaluation suite while giving agents command-line access to inspect data, implement policies, submit them to a fixed training/evaluation pipeline, and revise. In a vision-language instruction-tuning instantiation, out-of-the-box agents reach strong published data-selection baselines within ten iterations. However, trajectory analysis reveals a persistent *execution-research gap*: agents mainly tune local policy variants rather than explore new policy families, even when given strategy guides and paper references. Scaffolds requiring each iteration to cite, instantiate, and adapt a prior method shift agents toward method-guided exploration. The scaffolded agent autonomously composes -- without human design input -- a data-selection policy that outperforms strong published baselines at one-tenth their data budget. Overall, current agents can run the curation loop, but reliable data research requires scaffolded method adaptation, not open-ended prompting alone. Code and benchmark are open-sourced.
arXiv:2606.04049v1 Announce Type: new
Abstract: We develop a general operator-theoretic route that turns Kato-type quasilinear evolution systems on a Banach scale $(Z,X)$ into finite-dimensional interacting approximations. The construction proceeds in two steps. First, one introduces a regularized family $(A_\varepsilon,f_\varepsilon)$ indexed by a scale parameter $\varepsilon>0$, for which the drift $A_\varepsilon[t,z]z+f_\varepsilon[t,z]$ takes values in an output space $Y$ suitable for discretization. Second, one discretizes this regularized dynamics by a sampling-reconstruction pair $(P_N,R_N)$ and obtains an interacting ODE on a finite-dimensional state space $V_N\simeq\R^{dN}$. Our main abstract theorem provides a quantitative estimate of the discrepancy $y_\varepsilon^N-y$ between the lifted discrete solution and the exact one, separating the regularization error $\chi(\varepsilon)$ from the discretization error $(1+L_\varepsilon)N^{-\gamma}$, where $L_\varepsilon$ measures the size of the regularized drift in the output norm. This makes explicit the trade-off between the regularization scale $\varepsilon$, the discretization scale $N$, and the possible deterioration of $L_\varepsilon$ as $\varepsilon\to 0$. As a running example, we focus on quasilinear PDEs on bounded Lipschitz domains with boundary conditions. We show that Burenkov's variable-step mollifiers provide a boundary-compatible kernelization: they regularize differential operators into explicit integral-interaction operators supported inside the domain and preserve boundary traces of sufficiently regular fields. In this setting one can choose an output space $Y$ for which $L_\varepsilon$ remains uniformly bounded, leading to algebraic convergence rates in $N$ for quasi-uniform discretizations.
arXiv:2606.04473v1 Announce Type: new
Abstract: We present ChessMimic, a system of three small encoder-only transformers - for move, thinking-time, and outcome prediction - conditioned on the position, recent move history, player rating, and clock state. We fit a separate instance of each model per 100-Elo rating band, trading parameter efficiency for sharper per-skill calibration. On a held-out month-wide slice of Lichess Rated Blitz games ChessMimic's human move prediction accuracy outperforms Maia-2 in every Elo band. Compared to Maia-3, our 9M parameter model's accuracy sits between Maia-3-5M and Maia-3-23M without the additional complexity of Geometric Attention Bias. In addition to the move matching model, we also train a game outcome model that conditions not only on the position, but also player ratings, time control, and remaining clock times. The outcome model achieves an AUC of 0.78 out of sample, beating Maia-2 as well as logistic regressions based on material, ratings, and clock time. Finally, we train a clock model that predicts human thinking times. The clock model provides a usable but non-SOTA per-ply think-time signal under ALLIE-style filters (Pearson r = 0.41, Spearman rho = 0.50, MAE 4.10 s, against ALLIE's reported r = 0.70), with the residual gap concentrated in per-position bucket sharpness rather than bucket-marginal calibration. A public demo is at 1e4.ai and we release code, per-band weights, and the C++ data-filter pipeline code in GitHub.
arXiv:2606.04475v1 Announce Type: new
Abstract: A mobile phone vibrating on a hard surface often sounds qualitatively unlike ordinary audiovisual recordings when reproduced through laptop loudspeakers. We propose that part of this perceptual distinctiveness can be described as a nested periodicity: a first-order cepstral structure reflecting the vibration period and its multiples, and a second-order cepstral structure reflecting repeated spacing within the first-order cepstrum. Treating the perceptual effect as real and using a deliberately transparent synthetic signal chain, we model six stages: mechanical generation, surface and air propagation, microphone capture, encoding and decoding, laptop-speaker playback, and re-recording or post-processing. The synthetic analysis shows that the first-order cepstral periodicity is preserved across the chain, whereas a cleaner bimodal or quasi-bimodal second-order cepstral signature is most evident at the mechanical source and at laptop-speaker playback. The result supports, but does not prove, the hypothesis that laptop reproduction can re-emphasize a latent contact-vibration periodicity that is less cleanly expressed in intermediate recorded and encoded forms. We frame second-order cepstral bimodality as an exploratory descriptor of contact-vibration playback rather than as a completed perceptual metric. Required validation includes recordings of real devices, controlled playback transfer functions, perceptual judgments, and comparisons against ordinary speech, music, and environmental recordings.
arXiv:2606.04476v1 Announce Type: new
Abstract: In this paper, we study the gradient descent dynamics for jointly training both layers of a one-hidden-layer ReLU network to fit a linear target function. Concretely, we consider a realizable setting where inputs are drawn i.i.d. from a Gaussian distribution and labels follow a planted linear model. This stylized framework captures salient features of end-to-end training in inverse problems and certain auto-encoder models. Despite its apparent simplicity, the dynamics remain poorly understood, in part because the loss landscape contains multiple non-strict saddle points, making it unclear why gradient descent from random initialization reliably escapes bad stationary regions. We provide a detailed characterization of the optimization landscape and prove that gradient descent from a moderately small random initialization-simultaneously training both layers-converges to a global minimizer at a linear rate with order-wise optimal sample complexity. Our analysis tracks the trajectory through three phases: an alignment phase in which hidden weights progressively align with the planted direction while the output weights maintain the correct sign pattern; a growth phase in which the norms of both layers increase while preserving alignment; and a local refinement phase in which the aligned neurons rapidly converge to the planted direction, yielding fast local convergence. To rigorously show that GD avoids non-strict saddles, we develop trajectory-level control arguments for the end-to-end dynamics. In addition, we establish novel uniform concentration results that hold along the entire trajectory, and are essential for obtaining order-wise optimal sample complexity. We corroborate our theory with extensive experiments across a range of configurations.
arXiv:2606.04477v1 Announce Type: new
Abstract: Vision-based tactile sensors (VBTS) recover high-resolution contact geometry but typically rely on opaque elastomer layers that prevent visual transparency, while RGB-D cameras provide global depth perception yet degrade significantly at close range. To address this limitation, we present TransTac, a transparent ultraviolet (UV)-encoded binocular VBTS that integrates visual observation and marker-based tactile reconstruction within a single compact device. The system employs a transparent elastomer embedded with UV-reflective markers and a prior-guided Delaunay stereo matching algorithm for robust sparse triangulation.
To reliably detect densely distributed semitransparent markers, we develop a lightweight detector that enables stable localization under contact and deformation. The proposed prior-guided Delaunay matching improves correspondence robustness by approximately 21% compared with global assignment baselines while maintaining high reconstruction accuracy. In semantic evaluation, TransTac achieves up to 83.3% zero-shot recognition accuracy on tactile images, exceeding opaque tactile baselines by approximately 50 percentage points. Embedding analysis further reveals substantially stronger cross-modal alignment with natural images, with class-center similarity increasing from around 0.2 to over 0.77. Controlled near-distance experiments quantify the degradation of RGB-D depth reliability and demonstrate extended geometric coverage enabled by visuo-tactile integration. Finally, a compact prototype is implemented with an approximate hardware cost of $70.
arXiv:2606.05161v1 Announce Type: new
Abstract: Audio-language models (ALMs) often follow text that conflicts with audio, even when the audio evidence is clear. This raises a basic question: is the audio-supported answer unavailable, or is it represented but overridden by the conflicting text? We examine this question using a same-audio counterfactual that keeps the audio fixed, removes only the conflicting text, and measures the resulting shift in model preference. Across five ALMs and four conflict tasks, 64.1% of conflict samples show a sign flip: the same-audio branch prefers the audio-supported answer, whereas the joint branch prefers the text-supported answer. This pattern suggests that the relevant audio evidence is encoded but loses in arbitration. Activation patching further localizes the reversal to answer-position computation, and patching effects closely track output candidate-score differences (Spearman rho=0.93). Using this diagnostic, we propose Gated Audio Counterfactual Logit Correction (GACL), a training-free decoding rule that interpolates between joint and same-audio scores. Under a strict 5 pp faithfulness-drop budget, GACL improves nAUC by 17.8 points over the best contrastive baseline and transfers without retuning to vision-text arbitration (up to +40.5 pp).
arXiv:2606.04108v1 Announce Type: new
Abstract: Single-view 3D generative models have achieved impressive visual quality, yet they are not designed to satisfy structural or functional requirements, and in practice, often fall short. Symmetry is one such requirement: violations, even subtle ones, on symmetry can render a model physically unusable. We present SymTRELLIS, a method that enforces arbitrary finite point group symmetries (rotational, reflectional, and polyhedral) during the flow-based 3D generation of TRELLIS.2, without retraining the underlying VAE or flow model. Our key idea is to approximate the latent-space action of spatial transformations as a learned linear operator on voxel latents, implemented as a lightweight spatial-transform latent mapper trained on generic, non-symmetric 3D data. At generation time, we enforce symmetry by averaging predicted flow velocities across all symmetry-equivalent transformations at each ODE step, a process we call velocity symmetrization. The symmetry specification can be estimated automatically from an initial TRELLIS.2 generation or supplied by the user, enabling deliberate fold manipulation beyond what the input image suggests. On a curated benchmark of 266 strictly symmetric objects spanning 2- to 20-fold rotations and polyhedral symmetry groups, SymTRELLIS substantially reduces all symmetry error metrics compared to TRELLIS.2, Hunyuan3D-2.1, and TripoSG, while maintaining reconstruction accuracy comparable to the base model.
arXiv:2606.04479v1 Announce Type: new
Abstract: Recent text-to-image (T2I) models can render highly legible and well-structured text within images, enabling applications including document generation and slide generation. However, it remains unclear whether such systems faithfully preserve reasoning ability when complex solutions must be expressed directly through rendered text, or whether they merely imitate surface-level patterns. We investigate this question by evaluating reasoning fidelity in visual text generation, where models must express complete reasoning processes as images. Our evaluation includes long text rendering, factual knowledge probing, context understanding, and multi-step reasoning. Across these settings, we find that current T2I models frequently produce semantic errors, logical inconsistencies, and incorrect intermediate steps, even when the rendered text appears visually clear. These failures contrast with the strong reasoning performance of text-only models on the same tasks. Our findings reveal a substantial gap between visual text generation and procedural reasoning, motivating more reliable visual text reasoning.
arXiv:2605.28210v2 Announce Type: replace
Abstract: Drawing on Ullmann-Margalit's concept of opting (transformative, irrevocable, and shadowed by foreclosed alternatives), we show that current AI systems raise a profound ethical problem that existing AI ethics has not fully captured: the illusion of opting, in which persons and groups encounter the deceptive appearance of meaningful consequential choice while the agency needed to become genuinely capable of choosing is weakened. Against approaches that treat AI primarily as an optimizer of already given ends, we argue that AI systems should be evaluated by whether they protect and cultivate meta-capacity against the illusion of opting: the socially and institutionally scaffolded agentive capacity through which means and ends can be formed, contested, revised, and owned. This reframing is especially urgent for disadvantaged populations, who are least able to absorb the costs of the illusion of opting when AI-mediated pathways misdirect behavior and action. We propose three normative imperatives for AI-mediated consequential decisions: existential honesty, which acknowledges the limits of prediction; ecological rationality, which situates guidance within heterogeneous lived ecologies; and counterfactual reparation, which acknowledges and repairs foreclosed alternatives when AI-mediated decision-making pathways fail.
arXiv:2606.04780v1 Announce Type: new
Abstract: Persistent LLM agents require memory representations that make the formation of person understanding explicit across long term interaction. Existing agent memory methods emphasize information retention and retrieval, yet give limited account of how accumulated interaction evidence is abstracted into person understanding. We view this process as schema formation, where situated evidence is abstracted into reusable patterns and stable person level claims. We introduce PersonaTree, a structured lifecycle memory framework that realizes this view as a three level persona tree with explicit support paths from evidence to claims. PersonaTree maintains the tree through conservative writing, confidence guided consolidation, and query conditioned path retrieval, returning only the evidence depth required by each query. Across six person understanding and persistent memory benchmarks with three answer backbones, PersonaTree ranks first in 12 of 18 compact scores and reaches the top two in 16 settings. Ablations show that hierarchy improves abstract person understanding on KnowMe, while support path retrieval improves RealPref alignment under a comparable context budget.
arXiv:2606.04483v1 Announce Type: new
Abstract: Existing jailbreaks against aligned LLMs are discrete artifacts whose surface forms are easy to fingerprint and patch. We argue that the real failure mode is not any specific prompt, but an entire register of natural human writing that safety training has under-covered. Building on this insight, we introduce the first jailbreak family that uses real fanfiction subgenres as universal attack carriers: a creative-writing meta is conditioned on passages from one of twelve Archive of Our Own (AO3) subgenres, and the harmful behavior is embedded as the climax of the resulting scene. The construction requires no attacker LLM and no per-target adaptation. On eight aligned LLMs over the union of HarmBench and JailbreakBench, this attack lifts mean ASR from 0.278 to 0.731 under a four-judge ensemble; a factorial decomposition shows the gain is carried by register rather than length or structure. Two active defences widen rather than narrow the vernacular-to-baseline ratio, indicating that template-targeting defences merely steer attackers toward register-based attacks like ours. We also propose SAGA-A4, a static four-turn extension that attains mean ASR 0.924, substantially exceeding three existing multi-turn methods.
arXiv:2606.04787v1 Announce Type: new
Abstract: Despite the widespread use of PID controllers in engineering practice, designing optimal PID parameters has long been regarded as a challenging problem in both theory and practice, particularly when faced with uncertain nonlinear dynamical systems. Based on the authors' PID control theory established recently for MIMO nonlinear uncertain systems (Zhao and Guo, 2022), which provides a concrete PID parameter set for global stability of PID controlled systems, this paper further proposes a near-optimal PID tuning method, where only input-output (zeroth-order) data on the control performance is available. The tuning method is formulated as a constrained optimization problem and solved by an iterative learning algorithm, referred to as HRS-KW algorithm, that combines a hysteretic random search with the Kiefer-Wolfowitz algorithm, aiming at utilizing the advantages of both global exploration and local gradient acceleration. This method operates without requiring precise structural knowledge of the system dynamics, yet its almost sure convergence to an epsilon-optimal solution for the PID parameters can be guaranteed in theory while ensuring closed-loop system stability. Simulation results illustrate that our HRS-KW algorithm outperforms other related optimization methods, exhibiting better convergence to the prescribed epsilon-optimal performance set.