HoWToBench: Holistic Evaluation for LLM's Capability in Human-level Writing using Tree of Writing

Evaluating the writing capabilities of large language models (LLMs) remains a significant challenge due to the multidimensional nature of writing skills and the limitations of existing metrics. LLM's performance in thousand-words level and open-ended writing is inadequately assessed by traditional reference-based metrics or modern LLM-as-a-judge methods. We propose Tree-of-Writing (ToW), to resolve the implicit inconsistency often found when LLM-as-a-judge aggregates all sub-features in text evaluation. ToW incorporates a tree-structured workflow by explicitly modeling the aggregation weights of sub-features. We also present HowToBench, a large-scale Chinese writing benchmark encompassing 12 genres and 1302 instructions across three task categories: contextual completion, outline-guided writing, and open-ended generation. ToW successfully mitigates the biases, achieving a 0.93 Pearson correlation with human judgments. Furthermore, we detect that both overlap-based text generation metrics and popular LLM-as-a-judge practices are vulnerable to textual disturbances, while ToW is robust to them. We also uncover a negative correlation between input length and content-related scores in the Guide task, showcasing that it cannot be simply improved by input-side information piling.

Infrastructure First: Enabling Embodied AI for Science in the Global South

Embodied AI for Science (EAI4S) brings intelligence into the laboratory by uniting perception, reasoning, and robotic action to autonomously run experiments in the physical world. For the Global South, this shift is not about adopting advanced automation for its own sake, but about overcoming a fundamental capacity constraint: too few hands to run too many experiments. By enabling continuous, reliable experimentation under limits of manpower, power, and connectivity, EAI4S turns automation from a luxury into essential scientific infrastructure. The main obstacle, however, is not algorithmic capability. It is infrastructure. Open-source AI and foundation models have narrowed the knowledge gap, but EAI4S depends on dependable edge compute, energy-efficient hardware, modular robotic systems, localized data pipelines, and open standards. Without these foundations, even the most capable models remain trapped in well-resourced laboratories. This article argues for an infrastructure-first approach to EAI4S and outlines the practical requirements for deploying embodied intelligence at scale, offering a concrete pathway for Global South institutions to translate AI advances into sustained scientific capacity and competitive research output.

Fundamental Analysis of Scalable Fluid Antenna Systems: Identifiability Limits, Information Theory, and Joint Processing

Unlike fixed-position arrays with static observation entropy, the scalable fluid antenna system (S-FAS) can dynamically adjust its aperture to form different observation spaces with configuration-dependent entropy budgets. This reconfigurability requires an information-theoretic framework beyond traditional algebraic identifiability analysis. This paper establishes an observation entropy framework for S-FAS, which unifies the derivation of identifiability limits, the diagnosis of processing bottlenecks, and system design optimization. For an S-FAS with mutual coupling suppression, we derive a complete capacity hierarchy among compressed, extended, and jointly stacked configurations. The entropy framework reveals that sequential two-stage processing suffers from an information bottleneck that restricts achievable capacity, while the noise entropy ratio can be used to distinguish fundamental performance limits from algorithmic deficiencies. A joint MUSIC algorithm is proposed to approach the theoretical joint capacity bound. Extensive Monte Carlo simulations, validated by both algebraic and information-theoretic criteria, verify the derived capacity hierarchy and identifiability boundaries.

Vision2Web: A Hierarchical Benchmark for Visual Website Development with Agent Verification

Recent advances in large language models have improved the capabilities of coding agents, yet systematic evaluation of complex, end-to-end website development remains limited. To address this gap, we introduce Vision2Web, a hierarchical benchmark for visual website development, spanning from static UI-to-code generation, interactive multi-page frontend reproduction, to long-horizon full-stack website development. The benchmark is constructed from real-world websites and comprises a total of 193 tasks across 16 categories, with 918 prototype images and 1,255 test cases. To support flexible, thorough and reliable evaluation, we propose workflow-based agent verification paradigm based on two complementary components: a GUI agent verifier and a VLM-based judge. We evaluate multiple visual language models instantiated under different coding-agent frameworks, revealing substantial performance gaps at all task levels, with state-of-the-art models still struggling on full-stack development.

Rotatable Antenna-Empowered Wireless Networks: A Tutorial

Non-fixed flexible antenna architectures, such as fluid antenna system (FAS), movable antenna (MA), and pinching antenna, have garnered significant interest in recent years. Among them, rotatable antenna (RA) has emerged as a promising technology for enhancing wireless communication and sensing performance through flexible antenna orientation/boresight rotation. By enabling mechanical or electronic boresight adjustment without altering physical antenna positions, RA introduces additional spatial degrees of freedom (DoFs) beyond conventional beamforming. In this paper, we provide a comprehensive tutorial on the fundamentals, architectures, and applications of RA-empowered wireless networks. Specifically, we begin by reviewing the historical evolution of RA-related technologies and clarifying the distinctive role of RA among flexible antenna architectures. Then, we establish a unified mathematical framework for RA-enabled systems, including general antenna/array rotation models, as well as channel models that cover near- and far-field propagation characteristics, wideband frequency selectivity, and polarization effects. Building upon this foundation, we investigate antenna/array rotation optimization in representative communication and sensing scenarios. Furthermore, we examine RA channel estimation/acquisition strategies encompassing orientation scheduling mechanisms and signal processing methods that exploit multi-view channel observations. Beyond theoretical modeling and algorithmic design, we discuss practical RA configurations and deployment strategies. We also present recent RA prototypes and experimental results that validate the practical performance gains enabled by antenna rotation. Finally, we highlight promising extensions of RA to emerging wireless paradigms and outline open challenges to inspire future research.

Action Draft and Verify: A Self-Verifying Framework for Vision-Language-Action Model

Vision-Language-Action (VLA) models have recently demonstrated strong performance across embodied tasks. Modern VLAs commonly employ diffusion action experts to efficiently generate high-precision continuous action chunks, while auto-regressive generation can be slower and less accurate at low-level control. Yet auto-regressive paradigms still provide complementary priors that can improve robustness and generalization in out-of-distribution environments. To leverage both paradigms, we propose Action-Draft-and-Verify (ADV): diffusion action expert drafts multiple candidate action chunks, and the VLM selects one by scoring all candidates in a single forward pass with a perplexity-style metric. Under matched backbones, training data, and action-chunk length, ADV improves success rate by +4.3 points in simulation and +19.7 points in real-world over diffusion-based baseline, with a single-pass VLM reranking overhead.

Point-to-Mask: From Arbitrary Point Annotations to Mask-Level Infrared Small Target Detection

Infrared small target detection (IRSTD) methods predominantly formulate the task as pixel-level segmentation, which requires costly dense annotations and is not well suited to tiny targets with weak texture and ambiguous boundaries. To address this issue, we propose Point-to-Mask, a framework that bridges low-cost point supervision and mask-level detection through two components: a Physics-driven Adaptive Mask Generation (PAMG) module that converts point annotations into compact target masks and geometric cues, and a lightweight Radius-aware Point Regression Network (RPR-Net) that reformulates IRSTD as target center localization and effective radius regression using spatiotemporal motion cues. The two modules form a closed loop: PAMG generates pseudo masks and geometric supervision during training, while the geometric predictions of RPR-Net are fed back to PAMG for pixel-level mask recovery during inference. To facilitate systematic evaluation, we further construct SIRSTD-Pixel, a sequential dataset with refined pixel-level annotations. Experiments show that the proposed framework achieves strong pseudo-label quality, high detection accuracy, and efficient inference, approaching full-supervision performance under point-supervised settings with substantially lower annotation cost. Code and datasets will be available at: https://github.com/GaoScience/point-to-mask.

IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse

Long-context agentic workflows have emerged as a defining use case for large language models, making attention efficiency critical for both inference speed and serving cost. Sparse attention addresses this challenge effectively, and DeepSeek Sparse Attention (DSA) is a representative production-grade solution: a lightweight lightning indexer selects the top-k most relevant tokens per query, reducing core attention from $O(L^2)$ to $O(Lk)$. However, the indexer itself retains $O(L^2)$ complexity and must run independently at every layer, despite the fact that the resulting top-k selections are highly similar across consecutive layers. We present IndexCache, which exploits this cross-layer redundancy by partitioning layers into a small set of Full layers that run their own indexers and a majority of Shared layers that simply reuse the nearest Full layer's top-k indices. We propose two complementary approaches to determine and optimize this configuration. Training-free IndexCache applies a greedy search algorithm that selects which layers to retain indexers by directly minimizing language modeling loss on a calibration set, requiring no weight updates. Training-aware IndexCache introduces a multi-layer distillation loss that trains each retained indexer against the averaged attention distributions of all layers it serves, enabling even simple interleaved patterns to match full-indexer accuracy. Experimental results on a 30B DSA model show that IndexCache can remove 75% of indexer computations with negligible quality degradation, achieving up to 1.82$\times$ prefill speedup and 1.48$\times$ decode speedup compared to standard DSA. These positive results are further confirmed by our preliminary experiments on the production-scale GLM-5 model (Figure 1).

GLM-OCR Technical Report

GLM-OCR is an efficient 0.9B-parameter compact multimodal model designed for real-world document understanding. It combines a 0.4B-parameter CogViT visual encoder with a 0.5B-parameter GLM language decoder, achieving a strong balance between computational efficiency and recognition performance. To address the inefficiency of standard autoregressive decoding in deterministic OCR tasks, GLM-OCR introduces a Multi-Token Prediction (MTP) mechanism that predicts multiple tokens per step, significantly improving decoding throughput while keeping memory overhead low through shared parameters. At the system level, a two-stage pipeline is adopted: PP-DocLayout-V3 first performs layout analysis, followed by parallel region-level recognition. Extensive evaluations on public benchmarks and industrial scenarios show that GLM-OCR achieves competitive or state-of-the-art performance in document parsing, text and formula transcription, table structure recovery, and key information extraction. Its compact architecture and structured generation make it suitable for both resource-constrained edge deployment and large-scale production systems.

SinGeo: Unlock Single Model's Potential for Robust Cross-View Geo-Localization

Robust cross-view geo-localization (CVGL) remains challenging despite the surge in recent progress. Existing methods still rely on field-of-view (FoV)-specific training paradigms, where models are optimized under a fixed FoV but collapse when tested on unseen FoVs and unknown orientations. This limitation necessitates deploying multiple models to cover diverse variations. Although studies have explored dynamic FoV training by simply randomizing FoVs, they failed to achieve robustness across diverse conditions -- implicitly assuming all FoVs are equally difficult. To address this gap, we present SinGeo, a simple yet powerful framework that enables a single model to realize robust cross-view geo-localization without additional modules or explicit transformations. SinGeo employs a dual discriminative learning architecture that enhances intra-view discriminability within both ground and satellite branches, and is the first to introduce a curriculum learning strategy to achieve robust CVGL. Extensive evaluations on four benchmark datasets reveal that SinGeo sets state-of-the-art (SOTA) results under diverse conditions, and notably outperforms methods specifically trained for extreme FoVs. Beyond superior performance, SinGeo also exhibits cross-architecture transferability. Furthermore, we propose a consistency evaluation method to quantitatively assess model stability under varying views, providing an explainable perspective for understanding and advancing robustness in future CVGL research. Codes will be available upon acceptance.