Function2Scene: 3D Indoor Scene Layout from Functional Specifications

Most text-driven 3D indoor scene synthesis methods generate rooms from object-centric prompts, asking what furniture should be placed rather than how the space is used. Yet in real interior design, a layout is judged by how well it supports its occupants, e.g., their activities and physical needs. We introduce Function2Scene, a framework for generating 3D indoor layouts from functional specifications, i.e., natural-language design briefs describing who will use a room and what they need to do there. Given such a specification, our system parses occupant personas and activities, derives a customized set of functional design constraints from a taxonomy of 17 criteria spanning spatial, ergonomic, activity, and environmental considerations, and uses these constraints to guide layout generation. Rather than relying on an LLM to directly produce a final scene, Function2Scene performs iterative evaluation and refinement through a tool-augmented check-and-repair loop, combining geometric measurements, LLM-based contextual reasoning, and VLM-based visual assessment. Experiments on 30 professionally written interior-design cases show that Function2Scene produces layouts that better satisfy functional requirements than recent LLM-based scene synthesis baselines, with our results preferred in 94.3% of pairwise comparisons. Our work reframes text-driven indoor scene synthesis from placing plausible objects to designing spaces that support human use.

A 100 GHz Wideband Reconfigurable Intelligent Surface Based on Orthogonal Polarization and Sub-Array Partitioning Concepts

The sub-terahertz frequency band offers extremely large bandwidth and enables ultra-high data rates for future wireless applications. However, severe propagation loss and blockage significantly limit coverage at these frequencies. Reconfigurable intelligent surfaces can dynamically shape EM wave propagation and provide a promising solution for coverage enhancement. Realizing such surfaces using standard printed circuit board technology is attractive due to its low cost and scalability, but it remains challenging around 100 GHz because of fabrication limits, limited switch availability, large switch size compared with the unit cell, switch parasitic effects, and high control complexity. In this work, we demonstrate a wideband PCB-based reconfigurable intelligent surface operating around 100 GHz. The design combines an orthogonal-polarization slot-coupled patch structure with subarray partitioning to mitigate switch-induced parasitic effects, reduce the required number of RF switches, and simplify the control architecture. The reconfigurability is achieved using AlGaAs SP3T bare-die switches integrated through optimized bond-wire interconnections. For proof of concept, a six-subarray structure with 4 by 4 elements per subarray is designed for different beamforming angles, and a 12 by 8 prototype is fabricated and experimentally characterized. The measured results show a gain enhancement of about 10 dB from 86 to 100 GHz and about 5 dB from 100 to 106 GHz, while maintaining a low power consumption of 0.165 W. These results validate the feasibility of practical wideband PCB-based reconfigurable intelligent surfaces for sub-terahertz wireless systems.

EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation

The rapid evolution of generative video foundation models has propelled the field toward professional-grade cinematic synthesis. To achieve such demanding quality, the community transitions towards Reinforcement Learning (RL) and agentic workflows. However, reliable evaluation has emerged as a critical bottleneck. Existing benchmarks predominantly evaluate ''whether it is right'' (basic prompt-following) while fundamentally neglecting ''whether it is good'' (cinematic quality, acting, and aesthetics). Furthermore, current automated metrics lack the domain-specific rigor required to provide trustworthy signals, creating a severe credibility gap between human aesthetic perception and machine scoring. To bridge this gap, we introduce EvalVerse, a comprehensive, pipeline-aware, and expert-calibrated evaluation framework. We treat video generation assessment not merely as an engineering task, but as a core scientific problem: the systematic digitization of subjective cinematic expertise. First, we organize domain knowledge into an evaluation taxonomy aligned with the professional filmmaking workflow (pre-production, production, and post-production). Second, we distill human expert judgments into a curated dataset with large-scale human annotations. Third, we inject this knowledge into Vision-Language Models (VLMs) through an expert-calibrated fine-tuning strategy, enabling the VLM to perform explicit Chain-of-Thought reasoning. Compared to previous works, EvalVerse not only retains compatibility with foundational ''rightness'' metrics, but also significantly expands the criteria to ''goodness'' and broaden the task coverage to complex multi-shot sequencing and audio-visual integration. Consequently, by providing granular diagnostic signals, EvalVerse transcends a static leaderboard and establishes a fundamental infrastructure for future work, such as reward models and evaluator agent.

Move-Then-Operate: Behavioral Phasing for Human-Like Robotic Manipulation

We present Move-Then-Operate, a Vision language action framework that explicitly decouples robotic manipulation into two distinct behavioral phases: coarse relocation (move) and contact-critical interaction (operate). Unlike monolithic policies that conflate these heterogeneous regimes, our architecture employs a dual-expert policy routed by a learnable phase selector, introducing a structural inductive bias that isolates phase-specific dynamics. Phase labels are automatically generated via an MLLM-based pipeline conditioned on lightweight contextual cues such as end-effector velocity and subtask decomposition to ensure alignment with human motor patterns. Evaluated on the RoboTwin2 benchmark, our method achieves an average success rate of $68.9\%$, outperforming the monolithic $π_0$ baseline by $24\%$. It matches or exceeds models trained on $10\times$ more data and reaches peak performance in $40\%$ fewer training steps, demonstrating that architectural disentanglement of move and operate phases is a highly effective and efficient strategy for mastering high-precision manipulation.

MapSR: Prompt-Driven Land Cover Map Super-Resolution via Vision Foundation Models

High-resolution (HR) land-cover mapping is often constrained by the high cost of dense HR annotations. We revisit this problem from the perspective of map super-resolution, which enhances coarse low-resolution (LR) land-cover products into HR maps at the resolution of the input imagery. Existing weakly supervised methods can leverage LR labels, but they typically use them to retrain dense predictors with substantial computational cost. We propose MapSR, a prompt-driven framework that decouples supervision from model training. MapSR uses LR labels once to extract class prompts from frozen vision foundation model features through a lightweight linear probe, after which HR mapping proceeds via training-free metric inference and graph-based prediction refinement. Specifically, class prompts are estimated by aggregating high-confidence HR features identified by the linear probe, and HR predictions are obtained by cosine-similarity matching followed by graph-based propagation for spatial refinement. Experiments on the Chesapeake Bay dataset show that MapSR achieves 59.64% mIoU without any HR labels, remaining competitive with the strongest weakly supervised baseline and surpassing a fully supervised baseline. Notably, MapSR reduces trainable parameters by four orders of magnitude and shortens training time from hours to minutes, enabling scalable HR mapping under limited annotation and compute budgets. The code is available at https://github.com/rikirikirikiriki/MapSR.

Pre-Execution Safety Gate & Task Safety Contracts for LLM-Controlled Robot Systems

Large Language Models (LLMs) are increasingly used to convert task commands into robot-executable code, however this pipeline lacks validation gates to detect unsafe and defective commands before they are translated into robot code. Furthermore, even commands that appear safe at the outset can produce unsafe state transitions during execution in the absence of continuous constraint monitoring. In this research, we introduce SafeGate, a neurosymbolic safety architecture that prevents unsafe natural language task commands from reaching robot execution. Drawing from ISO 13482 safety standard, SafeGate extracts structured safety-relevant properties from natural language commands and applies a deterministic decision gate to authorize or reject execution. In addition, we introduce Task Safety Contracts, which decomposes commands that pass through the gate into invariants, guards, and abort conditions to prevent unsafe state transitions during execution. We further incorporate Z3 SMT solving to enforce constraint checking derived from the Task Safety Contracts. We evaluate SafeGate against existing LLM-based robot safety frameworks and baseline LLMs across 230 benchmark tasks, 30 AI2-THOR simulation scenarios, and real-world robot experiments. Results show that SafeGate significantly reduces the acceptance of defective commands while maintaining a high acceptance of benign tasks, demonstrating the importance of pre-execution safety gates for LLM-controlled robot systems

CausalTAD: Injecting Causal Knowledge into Large Language Models for Tabular Anomaly Detection

Detecting anomalies in tabular data is critical for many real-world applications, such as credit card fraud detection. With the rapid advancements in large language models (LLMs), state-of-the-art performance in tabular anomaly detection has been achieved by converting tabular data into text and fine-tuning LLMs. However, these methods randomly order columns during conversion, without considering the causal relationships between them, which is crucial for accurately detecting anomalies. In this paper, we present CausalTaD, a method that injects causal knowledge into LLMs for tabular anomaly detection. We first identify the causal relationships between columns and reorder them to align with these causal relationships. This reordering can be modeled as a linear ordering problem. Since each column contributes differently to the causal relationships, we further propose a reweighting strategy to assign different weights to different columns to enhance this effect. Experiments across more than 30 datasets demonstrate that our method consistently outperforms the current state-of-the-art methods. The code for CausalTAD is available at https://github.com/350234/CausalTAD.

Transformer-based Hybrid Beamforming with Dynamic Subarray for Near-Space Airship-Borne Communications

This paper proposes a hybrid beamforming framework for massive multiple-input multiple-output (MIMO) in near-space airship-borne communications. To achieve high energy efficiency (EE) in energy-constraint airships, a dynamic subarray structure is introduced, where each radio frequency chain (RFC) is connected to a disjoint subset of the antennas according to channel state information (CSI). The proposed joint dynamic hybrid beamforming network (DyHBFNet) comprises three key components: 1) An analog beamforming network (ABFNet) that optimizes the analog beamforming matrices and provides auxiliary information for the antenna selection network (ASNet) design, 2) an ASNet that dynamically optimizes the connections between antennas and RFCs, and 3) a digital beamforming network (DBFNet) that optimizes digital beamforming matrices by employing a model-driven weighted minimum mean square error algorithm for improving beamforming performance and convergence speed. The proposed ABFNet, ASNet, and DBFNet are all designed based on advanced Transformer encoders. Simulation results demonstrate that the proposed framework significantly enhances spectral efficiency and EE compared to baseline schemes. Additionally, its robust performance under imperfect CSI makes it a scalable solution for practical implementations.

Two-Layer Reinforcement Learning-Assisted Joint Beamforming and Trajectory Optimization for Multi-UAV Downlink Communications

Unmanned aerial vehicles (UAVs) are pivotal for future 6G non-terrestrial networks, yet their high mobility creates a complex coupled optimization problem for beamforming and trajectory design. Existing numerical methods suffer from prohibitive latency, while standard deep learning often ignores dynamic interference topology, limiting scalability. To address these issues, this paper proposes a hierarchically decoupled framework synergizing graph neural networks (GNNs) with multi-agent reinforcement learning. Specifically, on the short timescale, we develop a topology-aware GNN beamformer by incorporating GraphNorm. By modeling the dynamic UAV-user association as a time-varying heterogeneous graph, this method explicitly extracts interference patterns to achieve sub-millisecond inference. On the long timescale, trajectory planning is modeled as a decentralized partially observable Markov decision process and solved via the multi-agent proximal policy optimization algorithm under the centralized training with decentralized execution paradigm, facilitating cooperative behaviors. Extensive simulation results demonstrate that the proposed framework significantly outperforms state-of-the-art optimization heuristics and deep learning baselines in terms of system sum rate, convergence speed, and generalization capability.

AXIOM: Benchmarking LLM-as-a-Judge for Code via Rule-Based Perturbation and Multisource Quality Calibration

Large language models (LLMs) have been increasingly deployed in real-world software engineering, fostering the development of code evaluation metrics to study the quality of LLM-generated code. Conventional rule-based metrics merely score programs based on their surface-level similarities with reference programs instead of analyzing functionality and code quality in depth. To address this limitation, researchers have developed LLM-as-a-judge metrics, prompting LLMs to evaluate and score code, and curated various code evaluation benchmarks to validate their effectiveness. However, these benchmarks suffer from critical limitations, hindering reliable assessments of evaluation capability: Some feature coarse-grained binary labels, which reduce rich code behavior to a single bit of information, obscuring subtle errors. Others propose fine-grained but subjective, vaguely-defined evaluation criteria, introducing unreliability in manually-annotated scores, which is the ground-truth they rely on. Furthermore, they often use uncontrolled data synthesis methods, leading to unbalanced score distributions that poorly represent real-world code generation scenarios. To curate a diverse benchmark with programs of well-balanced distributions across various quality levels and streamline the manual annotation procedure, we propose AXIOM, a novel perturbation-based framework for synthesizing code evaluation benchmarks at scale. It reframes program scores as the refinement effort needed for deployment, consisting of two stages: (1) Rule-guided perturbation, which prompts LLMs to apply sequences of predefined perturbation rules to existing high-quality programs to modify their functionality and code quality, enabling us to precisely control each program's target score to achieve balanced score distributions. (2) Multisource quality calibration, which first selects a subset of...