Pretrained vision-language models (VLMs) such as CLIP excel in general multimodal comprehension but often struggle to capture nuanced, context-dependent visual cues. This makes it difficult to distinguish between similar-looking concepts with potentially different cultural meanings. Such deficiencies are mainly due to a limited amount of high-quality cultural data, contextual information, and the lack of negative examples that highlight subtle differences. To mitigate this, we design a data curation pipeline leveraging open-sourced VLMs and text-to-image models to construct CulTwin, a synthetic cultural dataset. This dataset consists of paired concept-caption-image triplets, where concepts visually resemble each other but are culturally different. Then, we fine-tune CLIP on CulTwin to develop CultureCLIP, which aligns cultural concepts with contextually enhanced captions and synthetic images through tailored contrastive learning. Experiments on culture-specific benchmarks show that CultureCLIP outperforms the base CLIP, achieving up to a notable 5.49% improvement in fine-grained concept recognition on certain tasks while preserving CLIP's original generalization ability, validating the effectiveness of our data synthesis and VLM backbone training paradigm in capturing subtle cultural distinctions.

We present Q-chunking, a simple yet effective recipe for improving reinforcement learning (RL) algorithms for long-horizon, sparse-reward tasks. Our recipe is designed for the offline-to-online RL setting, where the goal is to leverage an offline prior dataset to maximize the sample-efficiency of online learning. Effective exploration and sample-efficient learning remain central challenges in this setting, as it is not obvious how the offline data should be utilized to acquire a good exploratory policy. Our key insight is that action chunking, a technique popularized in imitation learning where sequences of future actions are predicted rather than a single action at each timestep, can be applied to temporal difference (TD)-based RL methods to mitigate the exploration challenge. Q-chunking adopts action chunking by directly running RL in a 'chunked' action space, enabling the agent to (1) leverage temporally consistent behaviors from offline data for more effective online exploration and (2) use unbiased $n$-step backups for more stable and efficient TD learning. Our experimental results demonstrate that Q-chunking exhibits strong offline performance and online sample efficiency, outperforming prior best offline-to-online methods on a range of long-horizon, sparse-reward manipulation tasks.

It is important to identify the discriminative features for high dimensional clustering. However, due to the lack of cluster labels, the regularization methods developed for supervised feature selection can not be directly applied. To learn the pseudo labels and select the discriminative features simultaneously, we propose a new unsupervised feature selection method, named GlObal and Local information combined Feature Selection (GOLFS), for high dimensional clustering problems. The GOLFS algorithm combines both local geometric structure via manifold learning and global correlation structure of samples via regularized self-representation to select the discriminative features. The combination improves the accuracy of both feature selection and clustering by exploiting more comprehensive information. In addition, an iterative algorithm is proposed to solve the optimization problem and the convergency is proved. Simulations and two real data applications demonstrate the excellent finite-sample performance of GOLFS on both feature selection and clustering.

Large Language Models have shown impressive capabilities in coding tasks like code generation and code completion, as they have been trained on a large amount of code data. Also, since one of the core pretraining objectives is Next Token Prediction, these models tends to learn surface-level syntactic patterns in code. However, this does not guarantee code comprehension ability i.e. the ability to capture the semantics of the code. In our opinion, this is the reason why these models often underperform on tasks that require deeper semantic understanding, such as code debugging and code optimization. To address this, we propose fine-tuning these models specifically for code comprehension tasks using large-scale datasets, enabling them to develop a more robust understanding of code semantics. We evaluate three code models of varying sizes on a suite of code comprehension tasks designed to assess semantic understanding beyond surface-level syntactic pattern matching. In particular, we analyze performance on the Subjectivity Grading Task and observe that model performance improves after fine-tuning on relevant downstream tasks. The most significant improvement is seen in the QWQ-32B model, where accuracy increases from 70% to 83.47%. A similar or explainable trend is observed across other models, clearly indicating an enhancement in code comprehension ability. Among the models studied, the DPO-fine-tuned Codestral-22B achieves the highest micro-accuracy of 87.66% on the Subjectivity Grading Task.

Federated Learning (FL) emerged as a solution for collaborative medical image classification while preserving data privacy. However, label noise, which arises from inter-institutional data variability, can cause training instability and degrade model performance. Existing FL methods struggle with noise heterogeneity and the imbalance in medical data. Motivated by these challenges, we propose FedGSCA, a novel framework for enhancing robustness in noisy medical FL. FedGSCA introduces a Global Sample Selector that aggregates noise knowledge from all clients, effectively addressing noise heterogeneity and improving global model stability. Furthermore, we develop a Client Adaptive Adjustment (CAA) mechanism that combines adaptive threshold pseudo-label generation and Robust Credal Labeling Loss. CAA dynamically adjusts to class distributions, ensuring the inclusion of minority samples and carefully managing noisy labels by considering multiple plausible labels. This dual approach mitigates the impact of noisy data and prevents overfitting during local training, which improves the generalizability of the model. We evaluate FedGSCA on one real-world colon slides dataset and two synthetic medical datasets under various noise conditions, including symmetric, asymmetric, extreme, and heterogeneous types. The results show that FedGSCA outperforms the state-of-the-art methods, excelling in extreme and heterogeneous noise scenarios. Moreover, FedGSCA demonstrates significant advantages in improving model stability and handling complex noise, making it well-suited for real-world medical federated learning scenarios.

Human users increasingly rely on natural language interactions with large language models (LLMs) in order to receive help on a large variety of tasks and problems. However, the trustworthiness and perceived legitimacy of LLMs is undermined by the fact that their output is frequently stated in very confident terms, even when its accuracy is questionable. Therefore, there is a need to signal the confidence of the language model to a user in order to reap the benefits of human-machine collaboration and mitigate potential harms. Verbalized uncertainty is the expression of confidence with linguistic means, an approach that integrates perfectly into language-based interfaces. Nevertheless, most recent research in natural language processing (NLP) overlooks the nuances surrounding human uncertainty communication and the data biases that influence machine uncertainty communication. We argue for anthropomimetic uncertainty, meaning that intuitive and trustworthy uncertainty communication requires a degree of linguistic authenticity and personalization to the user, which could be achieved by emulating human communication. We present a thorough overview over the research in human uncertainty communication, survey ongoing research, and perform additional analyses to demonstrate so-far overlooked biases in verbalized uncertainty. We conclude by pointing out unique factors in human-machine communication of uncertainty and deconstruct anthropomimetic uncertainty into future research directions for NLP.

--This study addresses the challenge of balancing energy efficiency with performance in AI/ML models, focusing on DeepRX, a deep learning receiver based on a fully con-volutional ResNet architecture. We evaluate the energy consumption of DeepRX, considering factors including FLOPs/Watt and FLOPs/clock, and find consistency between estimated and actual energy usage, influenced by memory access patterns. The research extends to comparing energy dynamics during training and inference phases. A key contribution is the application of knowledge distillation (KD) to train a compact DeepRX student model that emulates the performance of the teacher model but with reduced energy consumption. Performance is measured by comparing the Bit Error Rate (BER) performance versus Signal-to-Interference & Noise Ratio (SINR) values of the distilled model and a model trained from scratch. The distilled models demonstrate a lower error floor across SINR levels, highlighting the effectiveness of KD in achieving energy-efficient AI solutions. In an era marked by rapid technological advancements, the telecommunications industry is leading a major transformation by increasingly using Artificial Intelligence (AI) and Machine Learning (ML).

Vision-Language Navigation in Continuous Environments (VLNCE), where an agent follows instructions and moves freely to reach a destination, is a key research problem in embodied AI. However, most navigation policies are sensitive to viewpoint changes, i.e., variations in camera height and viewing angle that alter the agent's observation. In this paper, we introduce a generalized scenario, V2-VLNCE (VLNCE with Varied Viewpoints), and propose VIL (View Invariant Learning), a view-invariant post-training strategy that enhances the robustness of existing navigation policies to changes in camera viewpoint. VIL employs a contrastive learning framework to learn sparse and view-invariant features. Additionally, we introduce a teacher-student framework for the Waypoint Predictor Module, a core component of most VLNCE baselines, where a view-dependent teacher model distills knowledge into a view-invariant student model. We employ an end-to-end training paradigm to jointly optimize these components, thus eliminating the cost for individual module training. Empirical results show that our method outperforms state-of-the-art approaches on V2-VLNCE by 8-15% measured on Success Rate for two standard benchmark datasets R2R-CE and RxR-CE. Furthermore, we evaluate VIL under the standard VLNCE setting and find that, despite being trained for varied viewpoints, it often still improves performance. On the more challenging RxR-CE dataset, our method also achieved state-of-the-art performance across all metrics when compared to other map-free methods. This suggests that adding VIL does not diminish the standard viewpoint performance and can serve as a plug-and-play post-training method.

Faculty of Computing and Information Technology & Center of Research Excellence in AI and Data Science King Abdulaziz University Jeddah, Saudi Arabia Abstract --Multimodal large language models (MLLMs) have shown success in vision-language tasks, but their ability to reason over complex educational materials remains largely untested. This work presents the first evaluation of state-of-the-art MLLMs, including LLaV A-1.5 and LLaMA 3.2-Vision, on the textbook question answering (TQA) task using the CK12-QA dataset. We introduce a multimodal retrieval-augmented generation (RAG) pipeline to simulate real-world learning by providing relevant lesson paragraphs and diagrams as context. Our zero-shot experiments reveal a critical trade-off; while retrieved context improves LLaV A's performance on text-based questions, it significantly degrades the accuracy of the more powerful LLaMA 3.2-Vision on diagram-based tasks, dropping its validation accuracy from 74.07% to 25.93%. Furthermore, fine-tuning highlights architectural differences; LLaMA 3.2-Vision's performance substantially improves to 71.16% on the test set, demonstrating its capacity to learn multimodal integration, whereas LLaV A's performance declines, indicating challenges with generalization. Our results underscore the challenges MLLMs face in modality prioritization and context integration, providing a benchmark and pointing to key directions for developing more robust AI-driven educational tools. Personal use of this material is permitted. This work has been accepted to the 2nd International Generative AI and Computational Language Modelling Conference (GACLM 2025) for publication in the proceedings. Answering curriculum-related questions in multimodal educational materials is a central challenge in AI for education, requiring systems to reason across complex multimodal contexts such as lengthy lessons, diagrams, and videos.

Academic misconduct detection in biomedical research remains challenging due to algorithmic narrowness in existing methods and fragmented analytical pipelines. We present BMDetect, a multimodal deep learning framework that integrates journal metadata (SJR, institutional data), semantic embeddings (PubMedBERT), and GPT-4o-mined textual attributes (methodological statistics, data anomalies) for holistic manuscript evaluation. Key innovations include: (1) multimodal fusion of domain-specific features to reduce detection bias; (2) quantitative evaluation of feature importance, identifying journal authority metrics (e.g., SJR-index) and textual anomalies (e.g., statistical outliers) as dominant predictors; and (3) the BioMCD dataset, a large-scale benchmark with 13,160 retracted articles and 53,411 controls. BMDetect achieves 74.33% AUC, outperforming single-modality baselines by 8.6%, and demonstrates transferability across biomedical subfields. This work advances scalable, interpretable tools for safeguarding research integrity.