Test-time prompt tuning for vision-language models has demonstrated impressive generalization capabilities under zero-shot settings. However, tuning the learnable prompts solely based on unlabeled test data may induce prompt optimization bias, ultimately leading to suboptimal performance on downstream tasks. In this work, we analyze the underlying causes of prompt optimization bias from both the model and data perspectives. In terms of the model, the entropy minimization objective typically focuses on reducing the entropy of model predictions while overlooking their correctness. This can result in overconfident yet incorrect outputs, thereby compromising the quality of prompt optimization. On the data side, prompts affected by optimization bias can introduce misalignment between visual and textual modalities, which further aggravates the prompt optimization bias. To this end, we propose a Doubly Debiased Test-Time Prompt Tuning method. Specifically, we first introduce a dynamic retrieval-augmented modulation module that retrieves high-confidence knowledge from a dynamic knowledge base using the test image feature as a query, and uses the retrieved knowledge to modulate the predictions. Guided by the refined predictions, we further develop a reliability-aware prompt optimization module that incorporates a confidence-based weighted ensemble and cross-modal consistency distillation to impose regularization constraints during prompt tuning. Extensive experiments across 15 benchmark datasets involving both natural distribution shifts and cross-datasets generalization demonstrate that our method outperforms baselines, validating its effectiveness in mitigating prompt optimization bias.

These authors contributed equally to this work. For decades, the dominance of English has created a substantial barrier in global science, disadvantaging non-native speakers. The recent rise of generative AI (GenAI) offers a potential technological response to this long-standing inequity. We provide the first large-scale evidence testing whether GenAI acts as a linguistic equalizer in global science. Drawing on 5.65 million scientific articles published from 2021 to 2024, we compare GenAI-assisted and non-assisted publications from authors in non-English-speaking countries. Using text embeddings derived from a pretrained large language model (SciBERT), we measure each publication's linguistic similarity to a benchmark of scientific writing from U.S.-based authors and track stylistic convergence over time. We find significant and growing convergence for GenAI-assisted publications after the release of ChatGPT in late 2022. The effect is strongest for domestic coauthor teams from countries linguistically distant from English. These findings provide large-scale evidence that GenAI is beginning to reshape global science communication by reducing language barriers in research. The rapid rise of generative AI (GenAI) has sparked an important debate regarding its role in science--raising questions of whether it homogenizes writing and erodes authorship norms (1,2) or whether it acts as a "linguistic equalizer" that lowers barriers for non-native English speakers (3,4). This debate is especially salient because English has long dominated global science, which gives native speakers a structural advantage (5-7) by creating larger writing burdens and unique peer review bias risks for researchers from non-Anglophone countries (8-12). As a result, many of these researchers have historically spent time in the U.S. or the UK to learn how to write in English or have hired (expensive) language experts (13, 14). Against this backdrop, the release of ChatGPT in late 2022, a chatbot based on a large language model (LLM), marked a turning point. This widely accessible, low-cost, and human-like tool offers a potential means of reducing longstanding linguistic imbalances (15, 16).

Ground-based cloud image segmentation is a critical research domain for photovoltaic power forecasting. Current deep learning approaches primarily focus on encoder-decoder architectural refinements. However, existing methodologies exhibit several limitations:(1)they rely on dilated convolutions for multi-scale context extraction, lacking the partial feature effectiveness and interoperability of inter-channel;(2)attention-based feature enhancement implementations neglect accuracy-throughput balance; and (3)the decoder modifications fail to establish global interdependencies among hierarchical local features, limiting inference efficiency. To address these challenges, we propose MPCM-Net, a Multi-scale network that integrates Partial attention Convolutions with Mamba architectures to enhance segmentation accuracy and computational efficiency. Specifically, the encoder incorporates MPAC, which comprises:(1)a MPC block with ParCM and ParSM that enables global spatial interaction across multi-scale cloud formations, and (2)a MPA block combining ParAM and ParSM to extract discriminative features with reduced computational complexity. On the decoder side, a M2B is employed to mitigate contextual loss through a SSHD that maintains linear complexity while enabling deep feature aggregation across spatial and scale dimensions. As a key contribution to the community, we also introduce and release a dataset CSRC, which is a clear-label, fine-grained segmentation benchmark designed to overcome the critical limitations of existing public datasets. Extensive experiments on CSRC demonstrate the superior performance of MPCM-Net over state-of-the-art methods, achieving an optimal balance between segmentation accuracy and inference speed. The dataset and source code will be available at https://github.com/she1110/CSRC.

Free-boundary diffeomorphism optimization is a core ingredient in the surface mapping problem but remains notoriously difficult because the boundary is unconstrained and local bijectivity must be preserved under large deformation. Numerical Least-Squares Quasiconformal (LSQC) theory, with its provable existence, uniqueness, similarity-invariance and resolution-independence, offers an elegant mathematical remedy. However, the conventional numerical algorithm requires landmark conditioning, and cannot be applied into gradient-based optimization. We propose a neural surrogate, the Spectral Beltrami Network (SBN), that embeds LSQC energy into a multiscale mesh-spectral architecture. Next, we propose the SBN guided optimization framework SBN-Opt which optimizes free-boundary diffeomorphism for the problem, with local geometric distortion explicitly controllable. Extensive experiments on density-equalizing maps and inconsistent surface registration demonstrate our SBN-Opt's superiority over traditional numerical algorithms.

The surge in intelligent applications driven by large language models (LLMs) has made it increasingly difficult for bandwidth-limited cloud servers to process extensive LLM workloads in real time without compromising user data privacy. To solve these problems, recent research has focused on constructing cloud-edge consortia that integrate server-based LLM with small language models (SLMs) on mobile edge devices. Furthermore, designing collaborative training mechanisms within such consortia to enhance inference performance has emerged as a promising research direction. However, the cross-domain deployment of SLMs, coupled with structural heterogeneity in SLMs architectures, poses significant challenges to enhancing model performance. To this end, we propose Co-PLMs, a novel co-tuning framework for collaborative training of large and small language models, which integrates the process of structure-agnostic mutual learning to realize knowledge exchange between the heterogeneous language models. This framework employs distilled proxy models (DPMs) as bridges to enable collaborative training between the heterogeneous server-based LLM and on-device SLMs, while preserving the domain-specific insights of each device. The experimental results show that Co-PLMs outperform state-of-the-art methods, achieving average increases of 5.38% in Rouge-L and 4.88% in EM.

Learning to optimize (L2O) parametric approximations of AC optimal power flow (AC-OPF) solutions offers the potential for fast, reusable decision-making in real-time power system operations. However, the inherent nonconvexity of AC-OPF results in challenging optimization landscapes, and standard learning approaches often fail to converge to feasible, high-quality solutions. This work introduces a \textit{homotopy-guided self-supervised L2O method} for parametric AC-OPF problems. The key idea is to construct a continuous deformation of the objective and constraints during training, beginning from a relaxed problem with a broad basin of attraction and gradually transforming it toward the original problem. The resulting learning process improves convergence stability and promotes feasibility without requiring labeled optimal solutions or external solvers. We evaluate the proposed method on standard IEEE AC-OPF benchmarks and show that homotopy-guided L2O significantly increases feasibility rates compared to non-homotopy baselines, while achieving objective values comparable to full OPF solvers. These findings demonstrate the promise of homotopy-based heuristics for scalable, constraint-aware L2O in power system optimization.

This study addresses the challenge of integrating complex, high-dimensional deep semantic features with simple, interpretable structural cues for lyrical content classification. We introduce a novel Synergistic Fusion Layer (SFL) architecture, a deep learning model utilizing a gated mechanism to modulate Sentence-BERT embeddings (Fdeep) using low-dimensional auxiliary features (Fstruct). The task, derived from clustering UMAP-reduced lyrical embeddings, is reframed as binary classification, distinguishing a dominant, homogeneous cluster (Class 0) from all other content (Class 1). The SFL model achieved an accuracy of 0.9894 and a Macro F1 score of 0.9894, outperforming a comprehensive Random Forest (RF) baseline that used feature concatenation (Accuracy = 0.9868). Crucially, the SFL model demonstrated vastly superior reliability and calibration, exhibiting a 93% reduction in Expected Calibration Error (ECE = 0.0035) and a 2.5x lower Log Loss (0.0304) compared to the RF baseline (ECE = 0.0500; Log Loss = 0.0772). This performance validates the architectural hypothesis that non-linear gating is superior to simple feature concatenation, establishing the SFL model as a robust and trustworthy system for complex multimodal lyrical analysis.

This article explores the design and experimentation of a neural network architecture capable of dynamically adjusting its internal structure based on the input data. The proposed model introduces a routing mechanism that allows each layer to influence how its outputs are propagated through the network, enabling iterative and adaptive computation. This concept is loosely inspired by the idea of thought processes and dynamic reasoning, where information flow is conditioned not only on the data itself, but also on the internal state of the system. It is important to note that this work does not aim to compete with state-of-the-art language models in terms of performance. Instead, it presents a conceptual prototype-an architectural framework that opens up a new direction for exploring adaptable and potentially more interpretable networks. The goal is not optimization of existing benchmarks but rather the proposal of a system that can learn not only representations, but also the structure of computation itself. Due to practical constraints in computing resources and data, this study remains a preliminary investigation. Nevertheless, initial observations show promise, and the architecture's full potential can only be evaluated in future experiments under more favorable computational conditions.

Transformers rely on positional encoding to compensate for the inherent permutation invariance of self-attention. Traditional approaches use absolute sinusoidal embeddings or learned positional vectors, while more recent methods emphasize relative encodings to better capture translation equivariances. In this work, we propose RollPE, a novel positional encoding mechanism based on traveling waves, implemented by applying a circular roll operation to the query and key tensors in self-attention. This operation induces a relative shift in phase across positions, allowing the model to compute attention as a function of positional differences rather than absolute indices. We show this simple method significantly outperforms traditional absolute positional embeddings and is comparable to RoPE. We derive a continuous case of RollPE which implicitly imposes a topographic structure on the query and key space. We further derive a mathematical equivalence of RollPE to a particular configuration of RoPE. Viewing RollPE through the lens of traveling waves may allow us to simplify RoPE and relate it to processes of information flow in the brain.

Split computing distributes deep neural network inference between resource-constrained edge devices and cloud servers but faces significant communication bottlenecks when transmitting intermediate features. To this end, in this paper, we propose a novel lightweight compression framework that leverages Range Asymmetric Numeral Systems (rANS) encoding with asymmetric integer quantization and sparse tensor representation to reduce transmission overhead dramatically. Specifically, our approach combines asymmetric integer quantization with a sparse representation technique, eliminating the need for complex probability modeling or network modifications. The key contributions include: (1) a distribution-agnostic compression pipeline that exploits inherent tensor sparsity to achieve bandwidth reduction with minimal computational overhead; (2) an approximate theoretical model that optimizes tensor reshaping dimensions to maximize compression efficiency; and (3) a GPU-accelerated implementation with sub-millisecond encoding/decoding latency. Extensive evaluations across diverse neural architectures (ResNet, VGG16, MobileNetV2, SwinT, DenseNet121, EfficientNetB0) demonstrate that the proposed framework consistently maintains near-baseline accuracy across CIFAR100 and ImageNet benchmarks. Moreover, we validated the framework's effectiveness on advanced natural language processing tasks by employing Llama2 7B and 13B on standard benchmarks such as MMLU, HellaSwag, ARC, PIQA, Winogrande, BoolQ, and OpenBookQA, demonstrating its broad applicability beyond computer vision. Furthermore, this method addresses a fundamental bottleneck in deploying sophisticated artificial intelligence systems in bandwidth-constrained environments without compromising model performance.