arXiv:2604.22489v3 Announce Type: replace-cross
Abstract: Parametric decay instability (PDI) of Alfv\'en wave is thought to play an important role in the dissipation of the large-amplitude Alfv\'en waves and in the heating of magnetized plasmas. Temperature anisotropy is frequently observed by spacecraft, including Parker Solar Probe (PSP), in the near-Sun solar wind, yet its impact on PDI in the near-Sun solar wind has been understudied. We calculate the maximum growth rates of PDI, $\gamma_{\max}/\omega_{0}$, where $\omega_0$ is the frequency of the parent wave, by solving the linear dispersion relation of Chew-Goldberger-Low (CGL) equations under several expanding background models. To assess the effect of temperature anisotropy, the growth rate is compared with that derived from ideal magnetohydrodynamics (MHD). From $R_0$ ($ = 1.02R_\odot$) to $30R_0$, we consider three expansion cases: (i) spherically symmetric adiabatic expansion with constant wind speed, (ii) Multi-source observation- and model-constrained expansion, and (iii) a PSP-constrained profile of $(\beta_{\parallel},\xi)$, where $\beta_\parallel=8\pi p_{\parallel0}/B_0^2$ is the parallel plasma beta and $\xi=T_{\perp0} / T_{\parallel0}$ is the temperature anisotropy, that includes Parker-spiral effects. We find that temperature anisotropy increases $\gamma_{\max}/\omega_{0}$ for $\beta\lesssim 0.1$ in the near-Sun solar wind: in the case of (iii), temperature anisotropy with $T_{\perp0} > T_{\parallel0}$ increases $\gamma_{\max}/\omega_{0}$ by factors of $\sim 1.5$ over $R\simeq 1$--$10\,R_0$, whereas temperature anisotropy with $T_{\parallel0}>T_{\perp0}$ decreases $\gamma_{\max}/\omega_{0}$ at larger $R$. Our results suggest that the temperature anisotropy plays an important role in the onset of PDI even in low-$\beta$ regimes, such as the near-Sun solar wind.
Science Journals
arXiv:2605.31487v2 Announce Type: replace
Abstract: Deploying computer vision models in Warehouse Facilities traditionally requires extensive resources for camera mounting, image collection, annotation, training, and deployment - a process often needing repetition in each new environment due to camera mounting constraints and environmental variability. This paper explores an innovative approach to streamline this process by conducting the standard procedure solely in a laboratory setting, focusing on vertical material handling systems and anomaly detection in forks of the systems. Through extensive experimentation, we have found that combining optimal camera placement, strategic image triggering, careful model selection and model ensemble enables effective generalization from laboratory conditions to diverse warehouse facilities environments, potentially transforming warehouse automation implementation by simplifying warehouse facilities deployment to just camera mounting, image collection, and model deployment, thereby saving significant resources and time typically spent on image annotation and model retraining. This is an experimental research study and not a production deployment.
arXiv:2606.01993v1 Announce Type: new
Abstract: Abundant procedural knowledge on the Web holds great potential for helping agents solve long-horizon tasks. However, such knowledge is often multimodal, heterogeneous, noisy, and implicitly assumes human executors, making it difficult to use directly as the skills required by agents. To bridge the gap between human-oriented guides and agent-executable skills, we formalize this problem as guide-to-skill learning: converting in-the-wild guides into executable skills and continuously improving them from trajectories observable to the agent. To evaluate the capability of existing agents on this task, we introduce MMG2Skill-Bench, the first benchmark designed for this problem. We further propose MMG2Skill, a closed-loop framework that compiles guides into editable skills, conditions a fixed vision-language model (VLM) agent on these skills during execution, and revises the skills from trajectory-level root-cause feedback without using benchmark scores. Across GUI control, open-ended gameplay, and strategic card play with six VLM backbones, MMG2Skill consistently outperforms vanilla baseline agents in every model-domain setting, achieving macro-average gains of +12.8 to +25.3 percentage points across backbones. Ablation studies show that directly prompting agents with raw guides can degrade performance, while both structured skill construction and trajectory-driven revision are necessary for the observed improvements. On success-inferable tasks, analyzer-based early stopping further prevents late-stage performance regressions and saves 25%-53% of attempts when the success signal is properly calibrated.
arXiv:2512.18336v2 Announce Type: replace
Abstract: This paper explores the impact of dynamic entropy tuning in Reinforcement Learning (RL) algorithms that train a stochastic policy. Its performance is compared against algorithms that train a deterministic one. Stochastic policies optimize a probability distribution over actions to maximize rewards, while deterministic policies select a single deterministic action per state. The effect of training a stochastic policy with both static entropy and dynamic entropy and then executing deterministic actions to control the quadcopter is explored. It is then compared against training a deterministic policy and executing deterministic actions. For the purpose of this research, the Soft Actor-Critic (SAC) algorithm was chosen for the stochastic algorithm while the Twin Delayed Deep Deterministic Policy Gradient (TD3) was chosen for the deterministic algorithm. The training and simulation results show the positive effect the dynamic entropy tuning has on controlling the quadcopter by preventing catastrophic forgetting and improving exploration efficiency.
arXiv:2509.02558v2 Announce Type: replace
Abstract: Retrieval benchmarks for large language models (LLMs) should reflect the long, reasoning-intensive queries typical of retrieval-augmented generation (RAG). We present a systematic study of BRIGHT, a reasoning-focused retrieval benchmark, along with strong, reproducible reference methods integrated into Anserini, Pyserini, and RankLLM. We evaluate lexical, sparse, dense, and fusion-based retrievers, as well as LLM rerankers, under long-query settings. In reproducing BRIGHT's lexical baseline, we identify a key under-documented detail: query-side BM25 (BM25Q), which applies BM25 weighting to the query itself. On long, multi-sentence queries, BM25Q consistently outperforms standard BM25, making it the strongest lexical baseline for reasoning-oriented retrieval. We further audit the BRIGHT corpus, uncovering data quality issues that impact evaluation, and offer mitigation. Finally, we study the generalizability of BM25Q across five additional benchmarks, finding its gains largely specific to BRIGHT, while fusion with standard BM25 provides the most consistent improvements across datasets.
arXiv:2606.02018v1 Announce Type: cross
Abstract: Compile-time optimization is important for improving the efficiency and reliability of quantum circuits on current noisy hardware. While many existing methods simplify circuits using structural patterns or quantum-state information, most of them target only unitary circuits and do not support dynamic circuits with mid-circuit measurements and classical feedforward. In this work, we present Branch-Aware Quantum Constant Propagation (BQCP), a compile-time analysis for dynamic circuits. BQCP extends Quantum Constant Propagation (QCP) by tracking the classical information produced by mid-circuit measurements together with the corresponding post-measurement quantum states across different execution branches. This enables path-sensitive reasoning inside conditional blocks and more precise information propagation than QCP. To keep the analysis scalable, we bound both the size of the quantum-state representation and the number of tracked branches. Using the information inferred by the analysis, we apply semantics-preserving simplifications to circuit operations. We prove the soundness of both the analysis and the simplifications. Experimental results on both application-driven and synthetic benchmarks show that, on dynamic circuits, our method consistently achieves larger reductions than other existing passes including QCP.
arXiv:2606.01710v1 Announce Type: new
Abstract: Vision-Language models (VLMs), such as CLIP, achieve powerful zero-shot classification. However, their predictions remain sensitive to spurious correlations, where contextual cues dominate over semantic content. Earlier solutions typically rely on fine-tuning or prompt engineering, which either undermine the advantages of pre-trained models or are prone to hallucination. In this work, we propose Density-Aware Translation (DAT) that refines image-text similarity scores using a local geometric density term derived from group reference sets. Our approach is motivated by the phenomenon that CLIP embeddings exhibit a modality gap and lie on an anisotropic shell in the feature space: common patterns cluster near the mean, while rare patterns are pushed outward. This geometry creates uneven alignment, where spurious correlations are amplified while semantically meaningful but rare cues are marginalised. To address this, we employ a relative measure to rescale similarities based on embedding density, suppressing overconfident scores in diffuse regions while preserving dense, semantically consistent matches. Experimental results on benchmark datasets demonstrate consistent improvements in worst-group and average accuracy, highlighting density-aware translation as a simple and effective calibration mechanism for reliable zero-shot classification using multimodal models.
arXiv:2606.01717v1 Announce Type: new
Abstract: Instruction tuning aligns large language models, including multimodal ones, with diverse user intents, but scaling to heterogeneous mixtures is hindered by gradient interference and bandwidth-heavy synchronization. We ask whether these two bottlenecks can be addressed jointly by training parts of the mixture independently and reconciling them once in parameter space. We develop a local quadratic theory inside a shared flat basin that yields three results: weight merging produces a curvature-weighted variance reduction; PCA-aligned conflict splitting maximizes this gain along high-curvature directions; and merging additionally acts as spectral filtering with implicit norm regularization. These results directly motivate MERIT, a decentralized merge-ready instruction-tuning pipeline that estimates dataset-level gradient conflicts, partitions the mixture along the top PCA conflict axes, fine-tunes each partition independently with no inter-partition communication, and merges once via token-weighted averaging. On Qwen2.5-VL-3B with 136 Vision-FLAN tasks, MERIT improves the 8-benchmark average from 54.3 (joint training) to 57.0. The same recipe scales to a 7B model on a 1.6M-example, 176-source mixture -- matching or exceeding centralized joint training with minimal cost overhead -- and transfers to text-only FLAN. Our code is available at https://github.com/naver-ai/merit.
arXiv:2606.01564v1 Announce Type: cross
Abstract: As beyond-diagonal reconfigurable intelligent surfaces (BD-RISs) gain increasing attention in high-frequency wireless communications, accurate and scalable channel-estimation methods become essential. This paper develops a parametric channel-estimation and beamforming framework that deconstructs the composite BD-RIS channel into its generating directional factors, revealing the tensor structure induced jointly by propagation geometry and beyond-diagonal scattering. We propose two tensor-based estimators: Fourth-Order Tucker Channel Estimation (FORTE), which models the partially structured channel as a fourth-order Tucker tensor, and Fourth-Order PARAFAC Channel Estimation (FORPE), which captures the fully structured channel through a fourth-order PARAFAC model. By exploiting partial and full channel geometry, the proposed methods achieve higher estimation accuracy than Least Squares and Block Tucker Kronecker Factorization benchmarks. In particular, FORTE outperforms FORPE due to its more compact representation, attaining an NMSE of about 10^{-4} at 5 dB SNR. In contrast, FORPE provides essentially unique estimates of the composite-channel factor matrices, whereas FORTE identifies their subspaces. The proposed deconstruction also provides a structured representation useful for sensing-oriented parameter extraction and tensor-structured system optimization. Finally, the Tensor Optimization Framework for Beamforming, Combining, and Scattering (TenFormer) achieves spectral efficiency comparable to the benchmark design while significantly reducing computational complexity through parallel tensor-structured optimization.
arXiv:2601.23220v2 Announce Type: replace
Abstract: Despite recent Multimodal Large Language Models (MLLMs)' linguistic prowess in medical diagnosis, we find even state-of-the-art MLLMs suffer from a critical perceptual deficit: geometric blindness. This failure to ground outputs in objective geometric constraints leads to plausible yet factually incorrect hallucinations, rooted in training paradigms that prioritize linguistic fluency over geometric fidelity. This paper introduces Med-Scout, a novel framework that "cures" this blindness via Reinforcement Learning (RL) that leverages the intrinsic geometric logic latent within unlabeled medical images. Instead of relying on costly expert annotations, Med-Scout derives verifiable supervision signals through three strategic proxy tasks inspired by the systematic reading and reasoning patterns of clinicians: Hierarchical Scale Localization, Topological Jigsaw Reconstruction, and Anomaly Consistency Detection. To rigorously quantify this deficit, we present Med-Scout-Bench, a new benchmark specifically designed to evaluate geometric perception. Extensive evaluations show that Med-Scout significantly mitigates geometric blindness, outperforming leading proprietary and open-source MLLMs by over 40% on our benchmark. Furthermore, this enhanced geometric perception generalizes to broader medical understanding, achieving superior results on radiological and comprehensive medical VQA tasks.
arXiv:2606.01875v1 Announce Type: cross
Abstract: Waterproof Editor provides an educational environment specifically targeted to teaching with proof assistants or programming languages. It arose from Waterproof, educational software targeted at helping students acquire the skill of giving mathematical proofs. Its original features such as enabling rich formatting and providing clear input areas are now abstracted away in an npm package and can be used in different educational contexts. We invite interested parties to use this component in their educational software, and offer to assist with this.
arXiv:2606.01803v1 Announce Type: new
Abstract: The explosive growth of Text-to-Image (T2I) models, from large-scale versions to lightweight, real-time ones, now faces diminishing marginal returns from single-model scaling. Agentic T2I methods emerged to alleviate this bottleneck by using multiple models. However, existing agentic T2I methods suffer from three key challenges: reliance on expensive handcrafted priors or human annotations, rigid single-path decision mechanisms, and a neglect of inference efficiency. To address these challenges, we introduce OctoT2I, a novel agentic framework that reformulates the T2I task as a joint optimization of generation quality and inference efficiency. OctoT2I implements a stateful, multi-round routing strategy that adaptively selects the most suitable tool based on its knowledge and memory. This strategy is enabled by a knowledge base built from scratch by our novel Self-Evolving Mechanism. This mechanism, which requires no human supervision, first autonomously defines foundational Conceptual Dimensions (eg, style, color, count) and then intelligently explores their combinations via an iterative" Propose--Solve--Evaluate--Learn"(PSEL) loop. The PSEL loop efficiently discovers each tool's capability frontier, driving continuous improvement without external guidance. Extensive experiments demonstrate that OctoT2I achieves competitive performance (0.96) on GenEval while delivering a 90.3% inference speedup and a 56.6% energy-efficiency gain over the leading baseline (Flow-GRPO), striking an exceptional balance between performance and efficiency. Code and models will be made available.
arXiv:2606.01809v1 Announce Type: new
Abstract: In the planar, dynamic All-Pairs Shortest Paths (APSP) problem, a planar, weighted digraph $G$ undergoes a sequence of edge weight updates and the goal is to maintain a data structure on $G$, that can quickly answer distance queries between any two vertices $x,y \in V(G)$.
The currently best algorithms for this problem require $\tilde{O}(n^{2/3})$ worst-case update and query time, while conditional lower bounds show that either update or query time $n^{0.5-\delta}$ is needed for any constant $\delta > 0$.
In this article, we present the first algorithm with near-optimal $\tilde{O}(\sqrt{n})$ worst-case update and query time for the offline setting, where the update sequence is given initially. This result is obtained by giving the first offline dynamic algorithm for maintaining dense distance graphs (DDGs) faster than recomputing from scratch after each update.
Further, we also present an \emph{online} algorithm for the incremental APSP problem with $\tilde{O}(\sqrt{n})$ worst-case update/ query time. This allows us to reduce the online dynamic APSP problem to the online decremental APSP problem, which constitutes partial progress even for the online version of this notorious problem.
arXiv:2606.02392v1 Announce Type: new
Abstract: We ask whether dependency topology correlates with functional load-bearing organization as recoverable geometry -- not as a metaphor, but as a measurable structural property detectable by multilayer network analysis. Across seven independent substrates, we show that hub persistence and rank divergence under the Functional Proximity Law recover operational organization that domain experts describe as logic: axiomatic load-bearing structure in formal mathematics, control and contract structure in legacy software, conserved hub grammar across approx. 600 million years of neural evolution, catalytic role organization in a published prebiotic autocatalytic network, carry-path dominance in a 4-bit digital circuit, betweenness persistence in the ISCAS85 c432 standard benchmark (n=196), and a directional formal-systems replication in the Coq Corelib (n=17). A key methodological finding: degree-based hub persistence is weak between physical wiring and simulation state-correlation layers (r=0.21 in c432), while betweenness-based persistence is stronger (r=0.77 in the 4-bit ALU post-hoc; r=0.34 in c432). The ISCAS85 pre-registered primary hypothesis was CONFIRMED (degree r=0.426, p=0.002, Spearman r=0.551). The formal-systems claim is supported by two proof-assistant corpora: Lean 4 mathlib4 (CONFIRMED, r=0.777, p=0.004) and Coq Corelib (PARTIAL, direction confirmed, r=0.288, p=0.287, n=17, underpowered). All seven experiments were pre-registered before analysis.
arXiv:2606.01165v1 Announce Type: cross
Abstract: Ramesh's 2023 dissertation introduces the categorical notions of introspective theories and geminal categories, which formalize "self-internalizing" structures sharing the form of L\"ob's theorem ($\Box A \vdash A$ implies $\vdash A$). We reorganize the theory of geminal categories in a self-contained manner by introducing "code structures on fibrations," which serve as a categorical abstraction of G\"odel coding. This framework leads to a significant simplification of the proof of L\"ob's theorem for geminal categories, as well as to a new categorical counterpart of the G\"odel-L\"ob axiom ($\Box(\Box A \to A) \to \Box A$). This formulation offers an accessible framework for Ramesh's approach and suggests connections to modal type theories, where similar meta- and object-level interactions arise.
arXiv:2512.18333v2 Announce Type: replace
Abstract: This paper proposes a new Reinforcement Learning (RL) based control architecture for quadrotors. With the literature focusing on controlling the four rotors' RPMs directly, this paper aims to control the quadrotor's thrust vector. The RL agent computes the percentage of overall thrust along the quadrotor's z-axis along with the desired Roll ($\phi$) and Pitch ($\theta$) angles. The agent then sends the calculated control signals along with the current quadrotor's Yaw angle ($\psi$) to an attitude PID controller. The PID controller then maps the control signals to motor RPMs. The Soft Actor-Critic algorithm, a model-free off-policy stochastic RL algorithm, was used to train the RL agents. Training results show the faster training time of the proposed thrust vector controller in comparison to the conventional RPM controllers. Simulation results show smoother and more accurate path-following for the proposed thrust vector controller.
arXiv:2606.01719v1 Announce Type: new
Abstract: Machine learning models trained on sensitive data can inadvertently leak population-level information about their training distributions -- a threat known as distribution inference attack (DIA). An adversary with black-box access can infer sensitive demographic properties, such as subgroup proportions, without observing any training data directly. While defenses such as differential privacy and property unlearning have been proposed, the link between fairness constraints and distributional leakage remains unexplored. We propose Fair Fine-tuning (FFt): a trained model is fine-tuned on samples from the complementary distribution under an Equalized Odds (EO) constraint. We provide a complete theoretical characterization, proving the tight bound $\text{Adv}(\mathcal{A},M_f) \le \Delta_{\text{EO}} \cdot W$, where $W$ quantifies how distinguishable the two training distributions are by their sensitive-attribute composition. We also establish a necessary condition for FFt to reduce adversarial advantage and prove tightness of the bound. We evaluate across six datasets spanning tabular (ACS Income, COMPAS, German Credit), image (UTKFaces), and NLP (Bias in Bios) modalities. Rehearsal-based FFt consistently reduces the adversarial accuracy gap below the detection threshold $\tau!=!0.1$ across all settings; on ACS Income, the gap falls from $\sim!15%$ to under $4%$. Our work provides the first formal bound connecting a model's measured EO disparity directly to its adversarial advantage in the DIA game, opening a new avenue for unified fairness-and-privacy defenses.
arXiv:2605.28335v2 Announce Type: replace
Abstract: Federated Learning (FL) enables multiple clients to collaboratively train models without sharing raw data, but it is highly vulnerable to Byzantine attacks. Existing robust approaches can neutralize these threats but incur substantial computational overhead during high-dimensional gradient aggregation, an overhead that scales poorly with model size and increasingly dominates the training cost as modern models grow larger. To address this computational bottleneck, we propose Projected Dimensionality Reduction (PDR), a universal acceleration framework for vector-level distance-based robust aggregators, which performs robust aggregation by compressing gradients into a drastically smaller subspace via sparse random projection to efficiently compute reliability weights. This approach reduces the server computational complexity to an optimal $ \mathcal{O}(Mp) $, where $ M $ is the number of clients and $ p $ is the model dimension, matching the theoretical lower bound required merely to read the gradients. We establish convergence guarantees under standard FL assumptions in prior Byzantine-robust FL analyses. By leveraging the Subspace Embedding Theorem, we show that PDR achieves optimal convergence rates of $ \mathcal{O}(1/\sqrt{T}) $ for non-convex functions and $ \mathcal{O}(1/T) $ for strongly convex functions, where $ T $ denotes the number of iterations. Crucially, we mathematically demonstrate that this massive acceleration comes almost for free, merely inflating the inherent Byzantine error floor by a bounded, tunable factor of $ \frac{1+\epsilon}{1-\epsilon} $. Experimental results on benchmark datasets confirm that integrating PDR with existing aggregators yields orders of magnitude speedups in time efficiency while maintaining highly competitive convergence performance.
arXiv:2502.00753v4 Announce Type: replace-cross
Abstract: Smoothness is crucial for attaining fast rates in first-order optimization. However, many optimization problems in modern machine learning involve non-smooth objectives. Recent studies relax the smoothness assumption by allowing the Lipschitz constant of the gradient to grow with respect to the gradient norm, which accommodates a broad range of objectives in practice. Despite this progress, existing generalizations of smoothness are restricted to Euclidean geometry with $\ell_2$-norm and only have theoretical guarantees for optimization in the Euclidean space. In this paper, we address this limitation by introducing a new $\ell*$-smoothness concept that measures the norm of Hessians in terms of a general norm and its dual, and establish convergence for mirror-descent-type algorithms, matching the rates under the classic smoothness. Notably, we propose a generalized self-bounding property that facilitates bounding the gradients via controlling suboptimality gaps, serving as a principal component for convergence analysis. Beyond deterministic optimization, we establish sharp convergence for stochastic mirror descent, matching state-of-the-art under classic smoothness. Our theory also extends to non-convex and composite optimization, which may shed light on practical usages of mirror descent, including pre-training and post-training of LLMs.
arXiv:2605.14355v3 Announce Type: replace
Abstract: As AI agents improve, the central question is no longer whether they can solve isolated well-defined financial tasks, but whether they can reliably carry out financial professional work. Existing financial benchmarks offer only a partial view of this ability, as they primarily evaluate static competencies such as question answering, retrieval, summarization, and classification. We introduce Herculean, the first skilled benchmark for agentic financial intelligence spanning four representative workflows, including Trading, Hedging, Market Insights, and Auditing. Each workflow is instantiated as a standardized MCP-based skill environment with its own tools, interaction dynamics, constraints, and success criteria, enabling consistent end-to-end assessment of heterogeneous agent systems. Across frontier agents, we find agents perform relatively well on Trading and Market Insights, but struggle substantially on Hedging and Auditing, where long-horizon coordination, state consistency, and structured verification are critical. Overall, our results point to a key gap in current agents in turning financial reasoning into dependable workflow execution in high-stakes financial workflows.
arXiv:2606.00682v1 Announce Type: cross
Abstract: Layered halide perovskites host exceptionally strong excitons, whose optical signatures are usually interpreted as absorptive resonances on a smooth dielectric background. Strong excitons, however, can also reshape the dielectric response itself and drive the real permittivity negative, opening a reflective band: the visible, excitonic analogue of an infrared Reststrahlen band. Whether bare (PEA)$_2$PbI$_4$ slabs reach this regime has remained unclear. Here we show that low-temperature transmission of (PEA)$_2$PbI$_4$ slabs, driven by the intralayer-exciton manifold, evolves with increasing thickness from an excitonic dip into a broad near-zero-transmission interval with compressed Fabry-P\'erot-like fringes. Transfer-matrix analysis with an effective Lorentz-oscillator dielectric response reproduces this crossover, reconstructs a finite negative-Re($\varepsilon$) window, and implies near-ultrastrong exciton-photon coupling. Calculated field maps show suppressed in-plane field penetration within this interval and a driven longitudinal response near the high-energy ($\varepsilon=0$) edge. These results identify (PEA)$_2$PbI$_4$ slabs as a cavity-free visible-frequency excitonic Reststrahlen material.
arXiv:2606.00799v1 Announce Type: cross
Abstract: A classic theorem of Weyl (1921) states that a Weyl metric -- a natural generalisation of a pseudo-Riemannian metric -- is uniquely determined by its conformal and projective structures (i.e. by its conformal structure and its set of unparametrised geodesics). An equivalent formulation of Weyl's result is that a torsion-free linear connection compatible with a pseudo-Riemannian conformal structure is uniquely determined by its projective structure. We discuss analogous results for suitably defined notions of conformal structure for Galilei and Carroll geometry, i.e. for spacetime geometries arising as the `non-relativistic' and `ultra-relativistic' limits of Lorentzian geometry.
arXiv:2512.22702v2 Announce Type: replace
Abstract: Deep learning models have grown popular in time series applications. However, the large quantity of newly proposed architectures and the often contradictory empirical results make it difficult to assess which design choice and model component drives performance. In this position paper, we argue that current benchmarking practices fail to identify the factors responsible for performance differences, thus slowing down progress in the field. In particular, differences in crucial design dimensions are overlooked when comparing architectures, ultimately leading to inconsistent outcomes. To support our position, we show that such differences-often treated as mere implementation details-can have a greater impact than adopting specific sequence modeling layers. We discuss how overlooked aspects (such as globality and locality) can (1) fundamentally change the class of the forecasting method and (2) drastically affect empirical results. Our findings suggest rethinking our benchmarking practices and focusing on the foundational aspects of the forecasting problem when designing and comparing architectures. As a concrete step, we propose an auxiliary forecasting model card, i.e., a template with a set of fields to characterize existing and new forecasting architectures based on key design choices.
arXiv:2504.05710v2 Announce Type: replace-cross
Abstract: We prove that it is impossible to construct perfect-complete quantum public-key encryption (QPKE) with classical keys from quantumly secure one-way functions (OWFs) in a black-box manner, resolving a long-standing open question in quantum cryptography. Specifically, in the quantum random oracle model (QROM), no perfect-complete QPKE scheme with classical keys, and classical/quantum ciphertext can be secure. This improves the previous works which require either unproven conjectures or imposed restrictions on key generation algorithms. This impossibility extends to QPKE with quantum public key in natural settings, which is tight to all known QPKE constructions with quantum public key.
arXiv:2605.27458v2 Announce Type: replace
Abstract: Transformer has significantly propelled the development of artificial intelligence, and certainly the development of agents as well. We categorize attention structures of Transformer into two types based on the source of the input information: homogenous and heterogenous attention structures. Heterogenous attention structures, with co-attention as a typical example, process information from different sources. Heterogenous attention structure is the foundation for Transformer models to achieve more complex functions and integrate more modal information. Whether for research purposes or policy requirements, the interpretation of Transformer models with heterogenous attention structures is an important task. The fusion of information from different sources brings new challenges. Our work mainly includes two parts: method and experimentation. In terms of method, we propose an interpretation method for Transformer models with heterogenous attention structures. In terms of experimentation, based on our experimental analysis paradigm, we interpret the operating mechanisms of representative models, conduct semantic interpretation and logical interpretation.