Recent advances in large-scale vision and language models have led to significant progress in zero-shot learning tasks. Methods such as CoOp and CoCoOp have shown that replacing handcrafted prompts with learnable vectors, known as prompt learning, can result in improved performance. However, these models often struggle to generalize to entirely unseen categories. While traditional zero-shot learning techniques benefit from various data augmentation strategies, prompt learning has primarily focused on text-based modifications, leaving the potential of image-based augmentation largely unexplored. In this work, we explore how image-level augmentations, particularly those that introduce attribute-specific variations, can support and enhance prompt learning. Our analysis examines the interaction between these augmentations and soft prompt frameworks, revealing their potential to improve generalization. We also identify a limitation in existing methods, such as CoCoOp, which do not provide explicit guidance for learning prompts that focus on semantically meaningful visual features. To address this, we propose Adding Attributes to Prompt Learning, AAPL, a novel method that introduces adversarial token embeddings to decouple superficial visual variations introduced by augmentation from class-relevant semantic representations. This decoupling enables the learned prompts to concentrate on visually discriminative features that align with the target categories. These authors contributed equally to this work. Keywords: prompt learning, vision-language models, image augmentation, adversarial learning loss, few-shot classification, zero-shot classification, cross-dataset transfer, domain generalization 1. Introduction Recent advances in large-scale vision-language models (VLMs), such as CLIP [1], have demonstrated strong image-text alignment via contrastive learning, yielding remarkable performance in zero-shot classification [2, 3, 4]. Despite these successes, such models rely on fixed, hand-crafted prompts that are unstable, highly sensitive to subtle textual variations, and often demand substantial manual effort, thereby limiting their adaptability across diverse tasks and domains.

In this study, a modular, data-free pipeline for multi-label intention recognition is proposed for agentic AI applications in transportation. Unlike traditional intent recognition systems that depend on large, annotated corpora and often struggle with fine-grained, multi-label discrimination, our approach eliminates the need for costly data collection while enhancing the accuracy of multi-label intention understanding. Specifically, the overall pipeline, named DMTC, consists of three steps: 1) using prompt engineering to guide large language models (LLMs) to generate diverse synthetic queries in different transport scenarios; 2) encoding each textual query with a Sentence-T5 model to obtain compact semantic embeddings; 3) training a lightweight classifier using a novel online focal-contrastive (OFC) loss that emphasizes hard samples and maximizes inter-class separability. The applicability of the proposed pipeline is demonstrated in an agentic AI application in the maritime transportation context. Extensive experiments show that DMTC achieves a Hamming loss of 5.35% and an AUC of 95.92%, outperforming state-of-the-art multi-label classifiers and recent end-to-end SOTA LLM-based baselines. Further analysis reveals that Sentence-T5 embeddings improve subset accuracy by at least 3.29% over alternative encoders, and integrating the OFC loss yields an additional 0.98% gain compared to standard contrastive objectives. In conclusion, our system seamlessly routes user queries to task-specific modules (e.g., ETA information, traffic risk evaluation, and other typical scenarios in the transportation domain), laying the groundwork for fully autonomous, intention-aware agents without costly manual labelling.

Generative artificial intelligence (GenAI) has become a transformative approach in bioinformatics that often enables advancements in genomics, proteomics, transcriptomics, structural biology, and drug discovery. To systematically identify and evaluate these growing developments, this review proposed six research questions (RQs), according to the preferred reporting items for systematic reviews and meta-analysis methods. The objective is to evaluate impactful GenAI strategies in methodological advancement, predictive performance, and specialization, and to identify promising approaches for advanced modeling, data-intensive discovery, and integrative biological analysis. RQ1 highlights diverse applications across multiple bioinformatics subfields (sequence analysis, molecular design, and integrative data modeling), which demonstrate superior performance over traditional methods through pattern recognition and output generation. RQ2 reveals that adapted specialized model architectures outperformed general-purpose models, an advantage attributed to targeted pretraining and context-aware strategies. RQ3 identifies significant benefits in the bioinformatics domains, focusing on molecular analysis and data integration, which improves accuracy and reduces errors in complex analysis. RQ4 indicates improvements in structural modeling, functional prediction, and synthetic data generation, validated by established benchmarks. RQ5 suggests the main constraints, such as the lack of scalability and biases in data that impact generalizability, and proposes future directions focused on robust evaluation and biologically grounded modeling. RQ6 examines that molecular datasets (such as UniProtKB and ProteinNet12), cellular datasets (such as CELLxGENE and GTEx) and textual resources (such as PubMedQA and OMIM) broadly support the training and generalization of GenAI models.

A recent advancement in Multimodal Large Language Models (MLLMs) research is the emergence of "reasoning MLLMs" that offer explicit control over their internal thinking processes (normally referred as the "thinking mode") alongside the standard "non-thinking mode". This capability allows these models to engage in a step-by-step process of internal deliberation before generating a final response. With the rapid transition to and adoption of these "dual-state" MLLMs, this work rigorously evaluated how the enhanced reasoning processes of these MLLMs impact model performance and reliability in clinical tasks. This paper evaluates the active "thinking mode" capabilities of two leading MLLMs, Seed1.5-VL and Gemini-2.5-Flash, for medical applications. We assessed their performance on four visual medical tasks using VQA-RAD and ROCOv2 datasets. Our findings reveal that the improvement from activating the thinking mode remains marginal compared to the standard non-thinking mode for the majority of the tasks. Their performance on complex medical tasks such as open-ended VQA and medical image interpretation remains suboptimal, highlighting the need for domain-specific medical data and more advanced methods for medical knowledge integration.

Under strictly controlled pre-training settings, we observe a Crossover: when unique data is limited, diffusion language models (DLMs) consistently surpass autoregressive (AR) models by training for more epochs. The crossover shifts later with more or higher-quality data, earlier with larger models, and persists across dense and sparse architectures. We attribute the gains to three compounding factors: (1) any-order modeling, (2) super-dense compute from iterative bidirectional denoising, and (3) built-in Monte Carlo augmentation; input or parameter noise improves AR under data constraint but cannot close the gap. At scale, a 1.7B DLM trained with a ~1.5T-token compute budget on 10B unique Python tokens overtakes an AR coder trained with strictly matched settings. In addition, a 1B-parameter DLM achieves > 56% accuracy on HellaSwag and > 33% on MMLU using only 1B tokens, without any special tricks, just by repeating standard pre-training data. We also show that rising validation cross-entropy does not imply degraded downstream performance in this regime.

Large Language Models (LLMs) have been widely deployed across various applications, yet their potential security and ethical risks have raised increasing concerns. Existing research employs red teaming evaluations, utilizing multi-turn jailbreaks to identify potential vulnerabilities in LLMs. However, these approaches often lack exploration of successful dialogue trajectories within the attack space, and they tend to overlook the considerable overhead associated with the attack process. To address these limitations, this paper first introduces a theoretical model based on dynamically weighted graph topology, abstracting the multi-turn attack process as a path planning problem. Based on this framework, we propose ABC, an enhanced Artificial Bee Colony algorithm for multi-turn jailbreaks, featuring a collaborative search mechanism with employed, onlooker, and scout bees. This algorithm significantly improves the efficiency of optimal attack path search while substantially reducing the average number of queries required. Empirical evaluations on three open-source and two proprietary language models demonstrate the effectiveness of our approach, achieving attack success rates above 90\% across the board, with a peak of 98\% on GPT-3.5-Turbo, and outperforming existing baselines. Furthermore, it achieves comparable success with only 26 queries on average, significantly reducing red teaming overhead and highlighting its superior efficiency.

Retrieval Augmented Generation (RAG) is emerging as a powerful technique to enhance the capabilities of Generative AI models by reducing hallucination. Thus, the increasing prominence of RAG alongside Large Language Models (LLMs) has sparked interest in comparing the performance of different LLMs in question-answering (QA) in diverse domains. This study compares the performance of four open-source LLMs, Mistral-7b-instruct, LLaMa2-7b-chat, Falcon-7b-instruct and Orca-mini-v3-7b, and OpenAI's trending GPT-3.5 over QA tasks within the computer science literature leveraging RAG support. Evaluation metrics employed in the study include accuracy and precision for binary questions and ranking by a human expert, ranking by Google's AI model Gemini, alongside cosine similarity for long-answer questions. GPT-3.5, when paired with RAG, effectively answers binary and long-answer questions, reaffirming its status as an advanced LLM. Regarding open-source LLMs, Mistral AI's Mistral-7b-instruct paired with RAG surpasses the rest in answering both binary and long-answer questions. However, among the open-source LLMs, Orca-mini-v3-7b reports the shortest average latency in generating responses, whereas LLaMa2-7b-chat by Meta reports the highest average latency. This research underscores the fact that open-source LLMs, too, can go hand in hand with proprietary models like GPT-3.5 with better infrastructure.

Open-weight models provide researchers and developers with accessible foundations for diverse downstream applications. We tested the safety and security postures of eight open-weight large language models (LLMs) to identify vulnerabilities that may impact subsequent fine-tuning and deployment. Using automated adversarial testing, we measured each model's resilience against single-turn and multi-turn prompt injection and jailbreak attacks. Our findings reveal pervasive vulnerabilities across all tested models, with multi-turn attacks achieving success rates between 25.86\% and 92.78\% -- representing a $2\times$ to $10\times$ increase over single-turn baselines. These results underscore a systemic inability of current open-weight models to maintain safety guardrails across extended interactions. We assess that alignment strategies and lab priorities significantly influence resilience: capability-focused models such as Llama 3.3 and Qwen 3 demonstrate higher multi-turn susceptibility, whereas safety-oriented designs such as Google Gemma 3 exhibit more balanced performance. The analysis concludes that open-weight models, while crucial for innovation, pose tangible operational and ethical risks when deployed without layered security controls. These findings are intended to inform practitioners and developers of the potential risks and the value of professional AI security solutions to mitigate exposure. Addressing multi-turn vulnerabilities is essential to ensure the safe, reliable, and responsible deployment of open-weight LLMs in enterprise and public domains. We recommend adopting a security-first design philosophy and layered protections to ensure resilient deployments of open-weight models.

Tokenizers play a crucial role in determining the performance, training efficiency, and the inference cost of Large Language Models (LLMs). Designing effective tokenizers for multilingual LLMs is particularly challenging due to diverse scripts and rich morphological variation. While subword methods such as Byte Pair Encoding (BPE) are widely adopted, their effectiveness in multilingual settings remains underexplored. We present IndicSuperTokenizer, a tokenizer for Indic multilingual LLMs, that combines both subword and multi-word tokeniza-tion, along with language-specific pre-tokenization, leading to more linguistically aligned tokens and achieving a new state-of-the-art in fertility score. Evaluated across English, 22 Indian languages and code data, our tokenizer improves the average fertility score by 39.5% over LLaMA4 and by 18% over Sutra (the current best). Large Language Models (LLMs) (Touvron et al., 2023; Grattafiori et al., 2024; Abdin et al., 2025; Guo et al., 2025; Y ang et al., 2025; Team et al., 2025) rely on the crucial step of tokenization, the process of converting raw text into discrete units called tokens. A key metric for evaluating tokeniz-ers is the "fertility score" (or token-to-word ratio) (Ali et al., 2024) where, a lower fertility score is desirable due to more efficient (and hence cheaper) LLM training and inference. Among the many proposed approaches, subword tokenization schemes such as BPE (Sennrich et al., 2016a), Unigram (Kudo, 2018), WordPiece (Song et al., 2021), and their byte-level extensions have become the de facto choice. However, tokenization remains an understudied topic within the LLM literature (Dagan et al., 2024; Mielke et al., 2021), especially in multilingual settings (Petrov et al., 2023), where, skewed fertility scores across languages, often lead to concerns around fairness, high inference latency, cost and context size. Our analysis suggests that tokenizers of popular multilingual tokenizers, largely designed for English, could produce fertility scores as high as 10.5 (LLaMA-4 tokenizer for Oriya; Table 22) for Indic languages, far worse than the near-ideal scores achieved for English.

Psychological constructs within individuals are widely believed to be interconnected. We investigated whether and how Large Language Models (LLMs) can model the correlational structure of human psychological traits from minimal quantitative inputs. We prompted various LLMs with Big Five Personality Scale responses from 816 human individuals to role-play their responses on nine other psychological scales. LLMs demonstrated remarkable accuracy in capturing human psychological structure, with the inter-scale correlation patterns from LLM-generated responses strongly aligning with those from human data $(R^2 > 0.89)$. This zero-shot performance substantially exceeded predictions based on semantic similarity and approached the accuracy of machine learning algorithms trained directly on the dataset. Analysis of reasoning traces revealed that LLMs use a systematic two-stage process: First, they transform raw Big Five responses into natural language personality summaries through information selection and compression, analogous to generating sufficient statistics. Second, they generate target scale responses based on reasoning from these summaries. For information selection, LLMs identify the same key personality factors as trained algorithms, though they fail to differentiate item importance within factors. The resulting compressed summaries are not merely redundant representations but capture synergistic information--adding them to original scores enhances prediction alignment, suggesting they encode emergent, second-order patterns of trait interplay. Our findings demonstrate that LLMs can precisely predict individual participants' psychological traits from minimal data through a process of abstraction and reasoning, offering both a powerful tool for psychological simulation and valuable insights into their emergent reasoning capabilities.