Multimodal Large Language Models (MLLMs) have shown promise in single-agent vision tasks, yet benchmarks for evaluating multi-agent collaborative perception remain scarce. This gap is critical, as multi-drone systems provide enhanced coverage, robustness, and collaboration compared to single-sensor setups. Existing multi-image benchmarks mainly target basic perception tasks using high-quality single-agent images, thus failing to evaluate MLLMs in more complex, egocentric collaborative scenarios, especially under real-world degraded perception conditions.To address these challenges, we introduce AirCopBench, the first comprehensive benchmark designed to evaluate MLLMs in embodied aerial collaborative perception under challenging perceptual conditions. AirCopBench includes 14.6k+ questions derived from both simulator and real-world data, spanning four key task dimensions: Scene Understanding, Object Understanding, Perception Assessment, and Collaborative Decision, across 14 task types. We construct the benchmark using data from challenging degraded-perception scenarios with annotated collaborative events, generating large-scale questions through model-, rule-, and human-based methods under rigorous quality control. Evaluations on 40 MLLMs show significant performance gaps in collaborative perception tasks, with the best model trailing humans by 24.38% on average and exhibiting inconsistent results across tasks. Fine-tuning experiments further confirm the feasibility of sim-to-real transfer in aerial collaborative perception and reasoning.

Hallucination in large language models (LLMs) is a fundamental challenge, particularly in open-domain question answering. Prior work attempts to detect hallucination with model-internal signals such as token-level entropy or generation consistency, while the connection between pretraining data exposure and hallucination is underexplored. Existing studies show that LLMs underperform on long-tail knowledge, i.e., the accuracy of the generated answer drops for the ground-truth entities that are rare in pretraining. However, examining whether data coverage itself can serve as a detection signal is overlooked. We propose a complementary question: Does lexical training-data coverage of the question and/or generated answer provide additional signal for hallucination detection? To investigate this, we construct scalable suffix arrays over RedPajama's 1.3-trillion-token pretraining corpus to retrieve $n$-gram statistics for both prompts and model generations. We evaluate their effectiveness for hallucination detection across three QA benchmarks. Our observations show that while occurrence-based features are weak predictors when used alone, they yield modest gains when combined with log-probabilities, particularly on datasets with higher intrinsic model uncertainty. These findings suggest that lexical coverage features provide a complementary signal for hallucination detection. All code and suffix-array infrastructure are provided at https://github.com/WWWonderer/ostd.

Masked diffusion models (MDMs) are a promising alternative to autoregressive models (ARMs), but they suffer from inherently much higher training variance. High variance leads to noisier gradient estimates and unstable optimization, so even equally strong pretrained MDMs and ARMs that are competitive at initialization often diverge after task-specific training, with MDMs falling far behind. There has been no theoretical explanation or systematic solution. We derive the first decomposition of MDM training variance into three sources: (A) masking pattern noise, (B) masking rate noise, and (C) data noise, while ARMs are only affected by (C). This explains the fundamental training gap. Building on this foundation, we design six variance-reduction methods, including two core methods: (1) P-POTS, a Pareto-optimal t sampler that minimizes training variance by sampling harder t values more often with appropriately smaller update steps, and (2) MIRROR, which uses negatively correlated samples to reduce (A). Experiments show that compared to standard MDM training, our methods improve accuracy by 7-8% on complex reasoning tasks, while simultaneously reducing run-to-run variability to near ARM levels, substantially narrowing the gap with strong ARM baselines; in most settings, even the best baseline runs remain below the worst run of our method.

Building codes contain critical information for ensuring safety, regulatory compliance, and informed decision-making in construction and engineering. Automated question answering systems over such codes enable quick and accurate access to specific regulatory clauses, improving efficiency and reducing errors. Retrieval-Augmented Generation (RAG) systems are essential for this task as they combine the precision of information retrieval with the generative capabilities of language models. However, tabular data are challenging to extract as they often involve complex layouts, merged cells, multi-row headers, and embedded semantic relationships that are not easily captured by traditional natural language processing techniques and Vision Language Models (VLMs). This paper explores and compares two methods for extracting information from tabular data in building codes using several pre-trained VLMs. First, a direct input method is used, where the image of the page is input directly into the VLMs, which are then tasked with answering questions based on the image. Second, an indirect input method is introduced, which involves converting an image of a page containing tables into the LaTeX code and then answering inquires based on the LaTeX-based input. The experiments find that the direct input method generally resulted in higher accuracy than the indirect input method. To further improve the performance, we fine-tuned each VLM using Low Rank Adaptation (LoRA) on a domain-specific tabular dataset. The fine-tuned models exhibited substantial improvements, with Qwen2.5-VL-3B-Instruct achieving relative accuracy gains exceeding 100%. Our results highlight the potential of parameter-efficient fine-tuning methods to adapt powerful VLMs for understanding complex structured data in specialized fields, such as building code interpretation and regulatory compliance.

This investigation presents an empirical analysis of the incompatibility between human psychometric frameworks and Large Language Model evaluation. Through systematic assessment of nine frontier models including GPT-5, Claude Opus 4.1, and Gemini 3 Pro Preview using the Cattell-Horn-Carroll theory of intelligence, we identify a paradox that challenges the foundations of cross-substrate cognitive evaluation. Our results show that models achieving above-average human IQ scores ranging from 85.0 to 121.4 simultaneously exhibit binary accuracy rates approaching zero on crystallized knowledge tasks, with an overall judge-binary correlation of r = 0.175 (p = 0.001, n = 1800). This disconnect appears most strongly in the crystallized intelligence domain, where every evaluated model achieved perfect binary accuracy while judge scores ranged from 25 to 62 percent, which cannot occur under valid measurement conditions. Using statistical analyses including Item Response Theory modeling, cross-vendor judge validation, and paradox severity indexing, we argue that this disconnect reflects a category error in applying biological cognitive architectures to transformer-based systems. The implications extend beyond methodology to challenge assumptions about intelligence, measurement, and anthropomorphic biases in AI evaluation. We propose a framework for developing native machine cognition assessments that recognize the non-human nature of artificial intelligence.

Fully Homomorphic Encryption (FHE), particularly the CKKS scheme, is a promising enabler for privacy-preserving MLaaS, but its practical deployment faces a prohibitive barrier: it heavily relies on domain expertise. Configuring CKKS involves a tightly coupled space of ring dimensions, modulus chains, and packing layouts. Without deep cryptographic knowledge to navigate these interactions, practitioners are restricted to compilers that rely on fixed heuristics. These "one-shot" tools often emit rigid configurations that are either severely over-provisioned in latency or fail to find a feasible solution entirely for deeper networks. We present FHE-Agent, an agentic framework that automates this expert reasoning process. By coupling a Large Language Model (LLM) controller with a deterministic tool suite, FHE-Agent decomposes the search into global parameter selection and layer-wise bottleneck repair. The agents operate within a multi-fidelity workflow, pruning invalid regimes using cheap static analysis and reserving expensive encrypted evaluations for the most promising candidates. We instantiate FHE-Agent on the Orion compiler and evaluate it on standard benchmarks (MLP, LeNet, LoLa) and deeper architectures (AlexNet). FHE-Agent consistently achieves better precision and lower latency than naïve search strategies. Crucially, it automatically discovers feasible, 128-bit secure configurations for complex models where baseline heuristics and one-shot prompts fail to produce a valid setup.

The security of code generated by large language models (LLMs) is a significant concern, as studies indicate that such code often contains vulnerabilities and lacks essential defensive programming constructs. This work focuses on examining and evaluating the security of LLM-generated code, particularly in the context of C/C++. We categorized known vulnerabilities using the Common Weakness Enumeration (CWE) and, to study their criticality, mapped them to CVEs. We used ten different LLMs for code generation and analyzed the outputs through static analysis. The amount of CWEs present in AI-generated code is concerning. Our findings highlight the need for developers to be cautious when using LLM-generated code. This study provides valuable insights to advance automated code generation and encourage further research in this domain.

Vision-Language models (VLMs) achieve strong performance on multimodal tasks but often fail at systematic visual reasoning tasks, leading to inconsistent or illogical outputs. Neuro-symbolic methods promise to address this by inducing interpretable logical rules, though they exploit rigid, domain-specific perception modules. We propose Vision-Language Programs (VLP), which combine the perceptual flexibility of VLMs with systematic reasoning of program synthesis. Rather than embedding reasoning inside the VLM, VLP leverages the model to produce structured visual descriptions that are compiled into neuro-symbolic programs. The resulting programs execute directly on images, remain consistent with task constraints, and provide human-interpretable explanations that enable easy shortcut mitigation. Experiments on synthetic and real-world datasets demonstrate that VLPs outperform direct and structured prompting, particularly on tasks requiring complex logical reasoning.

W e present VDC-Agent, a self-evolving framework for Video Detailed Captioning that requires neither human annotations nor larger teacher models. The agent forms a closed loop of caption generation, principle-guided scoring (score and textual suggestions), and prompt refinement. When caption quality regresses, a self-reflection path leverages the previous chain-of-thought to amend the update. Running this process on unlabeled videos produces trajectories of (caption, score) pairs. W e convert the trajectories into preference tuples and filter out samples with JSON parsing errors, resulting in VDC-Agent-19K, which contains 18,886 automatically constructed pairs.

AI-Integrated programming is emerging as a foundational paradigm for building intelligent systems with large language models (LLMs). Recent approaches such as Meaning Typed Programming (MTP) automate prompt generation by leveraging the semantics already present in code. However, many real-world applications depend on contextual cues, developer intent, and domain-specific reasoning that extend beyond what static code semantics alone can express. To address this limitation, we introduce Semantic Engineering, a lightweight method for enriching program semantics so that LLM-based systems can more accurately reflect developer intent without requiring full manual prompt design. We present Semantic Context Annotations (SemTexts), a language-level mechanism that allows developers to embed natural-language context directly into program constructs. Integrated into the Jac programming language, Semantic Engineering extends MTP to incorporate these enriched semantics during prompt generation. We further introduce a benchmark suite designed to reflect realistic AI-Integrated application scenarios. Our evaluation shows that Semantic Engineering substantially improves prompt fidelity, achieving performance comparable to Prompt Engineering while requiring significantly less developer effort.