Generative AI techniques have been proposed for various aspects of coding for tasks ranging from coding assistants [1] to optimisation [2] and vulnerability detection [3] for which promising results are being heeded. Indeed, for many cases traditional types of code verification (be it at compile/development time [4] or runtime [5]) often out perform generative AI-based techniques, yet such tools are often rigid and less flexible compared to how generative AI techniques can be used. Given potential future 1 advancements of generative AI techniques, and given the flexible interface with which tools can interact with generative AI tools, it is useful to evaluate'how good are generative AI techniques at undertaking such tasks?' Indeed, extensive work in the domain has already been proposed surrounding this question, of which an extensive amount of literature has focused on the state-of-the-art large language models. Whilst it may be reasonable to make use of commercially/publicly available LLMs that are operated by a service provider, they indeed raise issues of privacy and confidentiality which some entities may rather not disclose certain intellectual property to (e.g.

Effective data selection is critical for efficient training of modern Large Language Models (LLMs). This paper introduces Influence Distillation, a novel, mathematically-justified framework for data selection that employs second-order information to optimally weight training samples. By distilling each sample's influence on a target distribution, our method assigns model-specific weights that are used to select training data for LLM fine-tuning, guiding it toward strong performance on the target domain. We derive these optimal weights for both Gradient Descent and Adam optimizers. To ensure scalability and reduce computational cost, we propose a $\textit{landmark-based approximation}$: influence is precisely computed for a small subset of "landmark" samples and then efficiently propagated to all other samples to determine their weights. We validate Influence Distillation by applying it to instruction tuning on the Tulu V2 dataset, targeting a range of tasks including GSM8k, SQuAD, and MMLU, across several models from the Llama and Qwen families. Experiments show that Influence Distillation matches or outperforms state-of-the-art performance while achieving up to $3.5\times$ faster selection.

We introduce Speech-IFeval, an evaluation framework designed to assess instruction-following capabilities and quantify catastrophic forgetting in speech-aware language models (SLMs). Recent SLMs integrate speech perception with large language models (LLMs), often degrading textual capabilities due to speech-centric training. Existing benchmarks conflate speech perception with instruction-following, hindering evaluation of these distinct skills. To address this gap, we provide a benchmark for diagnosing the instruction-following abilities of SLMs. Our findings show that most SLMs struggle with even basic instructions, performing far worse than text-based LLMs. Additionally, these models are highly sensitive to prompt variations, often yielding inconsistent and unreliable outputs. We highlight core challenges and provide insights to guide future research, emphasizing the need for evaluation beyond task-level metrics.

Medical large vision-language models (LVLMs) have demonstrated promising performance across various single-image question answering (QA) benchmarks, yet their capability in processing multi-image clinical scenarios remains underexplored. Unlike single image based tasks, medical tasks involving multiple images often demand sophisticated visual understanding capabilities, such as temporal reasoning and cross-modal analysis, which are poorly supported by current medical LVLMs. To bridge this critical gap, we present the Med-MIM instruction dataset, comprising 83.2K medical multi-image QA pairs that span four types of multi-image visual abilities (temporal understanding, reasoning, comparison, co-reference). Using this dataset, we fine-tune Mantis and LLaVA-Med, resulting in two specialized medical VLMs: MIM-LLaVA-Med and Med-Mantis, both optimized for multi-image analysis. Additionally, we develop the Med-MIM benchmark to comprehensively evaluate the medical multi-image understanding capabilities of LVLMs. We assess eight popular LVLMs, including our two models, on the Med-MIM benchmark. Experimental results show that both Med-Mantis and MIM-LLaVA-Med achieve superior performance on the held-in and held-out subsets of the Med-MIM benchmark, demonstrating that the Med-MIM instruction dataset effectively enhances LVLMs' multi-image understanding capabilities in the medical domain.

Relational databases are central to modern data management, yet most data exists in unstructured forms like text documents. To bridge this gap, we leverage large language models (LLMs) to automatically synthesize a relational database by generating its schema and populating its tables from raw text. We introduce SQUiD, a novel neurosymbolic framework that decomposes this task into four stages, each with specialized techniques. Our experiments show that SQUiD consistently outperforms baselines across diverse datasets.

The advent of large language models (LLMs) presents new opportunities for travel demand modeling. However, behavioral misalignment between LLMs and humans presents obstacles for the usage of LLMs, and existing alignment methods are frequently inefficient or impractical given the constraints of typical travel demand data. This paper introduces a novel framework for aligning LLMs with human travel choice behavior, tailored to the current travel demand data sources. Our framework uses a persona inference and loading process to condition LLMs with suitable prompts to enhance alignment. The inference step establishes a set of base personas from empirical data, and a learned persona loading function driven by behavioral embeddings guides the loading process. We validate our framework on the Swissmetro mode choice dataset, and the results show that our proposed approach significantly outperformed baseline choice models and LLM-based simulation models in predicting both aggregate mode choice shares and individual choice outcomes. Furthermore, we showcase that our framework can generate insights on population behavior through interpretable parameters. Overall, our research offers a more adaptable, interpretable, and resource-efficient pathway to robust LLM-based travel behavior simulation, paving the way to integrate LLMs into travel demand modeling practice in the future.

Applying Reinforcement Learning (RL) to Video Large Language Models (Video-LLMs) shows significant promise for complex video reasoning. However, popular Reinforcement Fine-Tuning (RFT) methods, such as outcome-based Group Relative Policy Optimization (GRPO), are limited by data preparation bottlenecks (e.g., noise or high cost) and exhibit unstable improvements in the quality of long chain-of-thoughts (CoTs) and downstream performance.To address these limitations, we propose VerIPO, a Verifier-guided Iterative Policy Optimization method designed to gradually improve video LLMs' capacity for generating deep, long-term reasoning chains. The core component is Rollout-Aware Verifier, positioned between the GRPO and Direct Preference Optimization (DPO) training phases to form the GRPO-Verifier-DPO training loop. This verifier leverages small LLMs as a judge to assess the reasoning logic of rollouts, enabling the construction of high-quality contrastive data, including reflective and contextually consistent CoTs. These curated preference samples drive the efficient DPO stage (7x faster than GRPO), leading to marked improvements in reasoning chain quality, especially in terms of length and contextual consistency. This training loop benefits from GRPO's expansive search and DPO's targeted optimization. Experimental results demonstrate: 1) Significantly faster and more effective optimization compared to standard GRPO variants, yielding superior performance; 2) Our trained models exceed the direct inference of large-scale instruction-tuned Video-LLMs, producing long and contextually consistent CoTs on diverse video reasoning tasks; and 3) Our model with one iteration outperforms powerful LMMs (e.g., Kimi-VL) and long reasoning models (e.g., Video-R1), highlighting its effectiveness and stability.

This study presents FiLLM, a Filipino - optimized large language model, designed to enhance natural language processing (NLP) capabilities in the Filipino language. Built upon the SeaLLM - 7B 2.5 model, FiLLM leverages Low - Rank Adaptation (LoRA) fine - tuning to optimize memory efficiency while maintaining task - specific performance. The model was trained and evaluated on diverse Filipino datasets to address key NLP tasks, including Named Entity Recognition (NER), Part - of - Speech (POS) tagging, Dependency Parsing, and Text Summarization. Performance comparisons with the CalamanCy model were conducted using F1 Score, Precision, Recall, Compression Rate, and Keyword Overlap metrics. Results indicate that Calamancy outperforms FILLM in several aspects, demonstrating its effectiveness in processing Filipino text with improved linguistic comprehension and adaptability. This research contributes to the advancement of Filipino NLP applications by providing an optimized, efficient, and sc alable language model tailored for lo cal linguistic needs.

Text-to-image (T2I) generation models can inadvertently produce not-safe-for-work (NSFW) content, prompting the integration of text and image safety filters. Recent advances employ large language models (LLMs) for semantic-level detection, rendering traditional token-level perturbation attacks largely ineffective. However, our evaluation shows that existing jailbreak methods are ineffective against these modern filters. We introduce GhostPrompt, the first automated jailbreak framework that combines dynamic prompt optimization with multimodal feedback. It consists of two key components: (i) Dynamic Optimization, an iterative process that guides a large language model (LLM) using feedback from text safety filters and CLIP similarity scores to generate semantically aligned adversarial prompts; and (ii) Adaptive Safety Indicator Injection, which formulates the injection of benign visual cues as a reinforcement learning problem to bypass image-level filters. GhostPrompt achieves state-of-the-art performance, increasing the ShieldLM-7B bypass rate from 12.5\% (Sneakyprompt) to 99.0\%, improving CLIP score from 0.2637 to 0.2762, and reducing the time cost by $4.2 \times$. Moreover, it generalizes to unseen filters including GPT-4.1 and successfully jailbreaks DALLE 3 to generate NSFW images in our evaluation, revealing systemic vulnerabilities in current multimodal defenses. To support further research on AI safety and red-teaming, we will release code and adversarial prompts under a controlled-access protocol.

Existing mathematical reasoning benchmarks are predominantly English only or translation-based, which can introduce semantic drift and mask languagespecific reasoning errors. To address this, we present AI4Math, a benchmark of 105 original university level math problems natively authored in Spanish. The dataset spans seven advanced domains (Algebra, Calculus, Geometry, Probability, Number Theory, Combinatorics, and Logic), and each problem is accompanied by a step by step human solution. We evaluate six large language models GPT 4o, GPT 4o mini, o3 mini, LLaMA 3.3 70B, DeepSeek R1 685B, and DeepSeek V3 685B under four configurations: zero shot and chain of thought, each in Spanish and English. The top models (o3 mini, DeepSeek R1 685B, DeepSeek V3 685B) achieve over 70% accuracy, whereas LLaMA 3.3 70B and GPT-4o mini remain below 40%. Most models show no significant performance drop between languages, with GPT 4o even performing better on Spanish problems in the zero shot setting. Geometry, Combinatorics, and Probability questions remain persistently challenging for all models. These results highlight the need for native-language benchmarks and domain-specific evaluations to reveal reasoning failures not captured by standard metrics.