Reasoning lies at the heart of intelligence, shaping the ability to make decisions, draw conclusions, and generalize across domains. In artificial intelligence, as systems increasingly operate in open, uncertain, and multimodal environments, reasoning becomes essential for enabling robust and adaptive behavior. Large Multimodal Reasoning Models (LMRMs) have emerged as a promising paradigm, integrating modalities such as text, images, audio, and video to support complex reasoning capabilities and aiming to achieve comprehensive perception, precise understanding, and deep reasoning. As research advances, multimodal reasoning has rapidly evolved from modular, perception-driven pipelines to unified, language-centric frameworks that offer more coherent cross-modal understanding. While instruction tuning and reinforcement learning have improved model reasoning, significant challenges remain in omni-modal generalization, reasoning depth, and agentic behavior. To address these issues, we present a comprehensive and structured survey of multimodal reasoning research, organized around a four-stage developmental roadmap that reflects the field's shifting design philosophies and emerging capabilities. First, we review early efforts based on task-specific modules, where reasoning was implicitly embedded across stages of representation, alignment, and fusion. Next, we examine recent approaches that unify reasoning into multimodal LLMs, with advances such as Multimodal Chain-of-Thought (MCoT) and multimodal reinforcement learning enabling richer and more structured reasoning chains. Finally, drawing on empirical insights from challenging benchmarks and experimental cases of OpenAI O3 and O4-mini, we discuss the conceptual direction of native large multimodal reasoning models (N-LMRMs), which aim to support scalable, agentic, and adaptive reasoning and planning in complex, real-world environments.

We use algorithmic methods from online learning to explore some important objects at the intersection of model theory and combinatorics, and find natural ways that algorithmic methods can detect and explain (and improve our understanding of) stable structure in the sense of model theory. The main theorem deals with existence of $ε$-excellent sets (which are key to the Stable Regularity Lemma, a theorem characterizing the appearance of irregular pairs in Szemerédi's celebrated Regularity Lemma). We prove that $ε$-excellent sets exist for any $ε< \frac{1}{2}$ in $k$-edge stable graphs in the sense of model theory (equivalently, Littlestone classes); earlier proofs had given this only for $ε< 1/{2^{2^k}}$ or so. We give two proofs: the first uses regret bounds from online learning, the second uses Boolean closure properties of Littlestone classes and sampling. We also give a version of the dynamic Sauer-Shelah-Perles lemma appropriate to this setting, related to definability of types. We conclude by characterizing stable/Littlestone classes as those supporting a certain abstract notion of majority: the proof shows that the two distinct, natural notions of majority, arising from measure and from dimension, densely often coincide.

Recurrent Neural Networks (RNNs) are commonly used for real-time processing, streaming data, and cases where the amount of training samples is limited. Backpropagation Through Time (BPTT) is the predominant algorithm for training RNNs; however, it is frequently criticized for being prone to exploding and vanishing gradients and being biologically implausible. In this paper, we present and evaluate a target propagation-based method for RNNs, which uses local updates and seeks to reduce the said instabilities. Having stable RNN models increases their practical use in a wide range of fields such as natural language processing, time-series forecasting, anomaly detection, control systems, and robotics. The proposed solution uses local representation alignment (LRA). We thoroughly analyze the performance of this method, experiment with normalization and different local error functions, and invalidate certain assumptions about the behavior of this type of learning. Namely, we demonstrate that despite the decomposition of the network into sub-graphs, the model still suffers from vanishing gradients. We also show that gradient clipping as proposed in LRA has little to no effect on network performance. This results in an LRA RNN model that is very difficult to train due to vanishing gradients. We address this by introducing gradient regularization in the direction of the update and demonstrate that this modification promotes gradient flow and meaningfully impacts convergence. We compare and discuss the performance of the algorithm, and we show that the regularized LRA RNN considerably outperforms the unregularized version on three landmark tasks: temporal order, 3-bit temporal order, and random permutation.

The task of describing video content in natural language is commonly referred to as video captioning. Unlike conventional video captions, which are typically brief and widely available, long-form paragraph descriptions in natural language are scarce. This limitation of current datasets is due to the expensive human manual annotation required and to the highly challenging task of explaining the language formation process from the perspective of the underlying story, as a complex system of interconnected events in space and time. Through a thorough analysis of recently published methods and available datasets, we identify a general lack of published resources dedicated to the problem of describing videos in complex language, beyond the level of descriptions in the form of enumerations of simple captions. Furthermore, while state-of-the-art methods produce impressive results on the task of generating shorter captions from videos by direct end-to-end learning between the videos and text, the problem of explaining the relationship between vision and language is still beyond our reach. In this work, we propose a shared representation between vision and language, based on graphs of events in space and time, which can be obtained in an explainable and analytical way, to integrate and connect multiple vision tasks to produce the final natural language description. Moreover, we also demonstrate how our automated and explainable video description generation process can function as a fully automatic teacher to effectively train direct, end-to-end neural student pathways, within a self-supervised neuro-analytical system. We validate that our explainable neuro-analytical approach generates coherent, rich and relevant textual descriptions on videos collected from multiple varied datasets, using both standard evaluation metrics, human annotations and consensus from ensembles of state-of-the-art VLMs.

--In this work, we propose a simple but effective channel pruning framework called Progressive Channel Pruning (PCP) to accelerate Convolutional Neural Networks (CNNs). In contrast to the existing channel pruning methods that prune channels only once per layer in a layer-by-layer fashion, our new progressive framework iteratively prunes a small number of channels from several selected layers, which consists of a three-step attempting-selecting-pruning pipeline in each iteration. In the attempting step, we attempt to prune a pre-defined number of channels from one layer by using any existing channel pruning methods and estimate the accuracy drop for this layer based on the labelled samples in the validation set. In the selecting step, based on the estimated accuracy drops for all layers, we propose a greedy strategy to automatically select a set of layers that will lead to less overall accuracy drop after pruning these layers. In the pruning step, we prune a small number of channels from these selected layers. We further extend our PCP framework to prune channels for the deep transfer learning methods like Domain Adversarial Neural Network (DANN), in which we effectively reduce the data distribution mismatch in the channel pruning process by using both labelled samples from the source domain and pseudo-labelled samples from the target domain. Our comprehensive experiments on two benchmark datasets demonstrate that our PCP framework outperforms the existing channel pruning approaches under both supervised learning and transfer learning settings. HILE deep learning technologies have been successfully used for many computer vision tasks, it is still a challenging task to deploy deep neural networks on mobile devices due to tight computation resources and limited battery power. Several model compression approaches (see Section II for more details) have been recently developed to deploy deep models on resource-constrained devices, among which channel pruning technologies are attracting increasing attention as these technologies are often efficient on both CPUs and GPUs without requiring special implementation. In this work, we propose a new iterative channel pruning framework called Progressive Channel Pruning (PCP) for model compression under both supervised and transfer learning settings. Jinyang Guo, Weichen Zhang, Wanli Ouyang and Dong Xu are with the School of Electrical and Information Engineering, University of Sydney, Sydney, NSW, 2008 Australia.

Human guidance has emerged as a powerful tool for enhancing reinforcement learning (RL). However, conventional forms of guidance such as demonstrations or binary scalar feedback can be challenging to collect or have low information content, motivating the exploration of other forms of human input. Among these, relative feedback (i.e., feedback on how to improve an action, such as "more to the left") offers a good balance between usability and information richness. Previous research has shown that relative feedback can be used to enhance policy search methods. However, these efforts have been limited to specific policy classes and use feedback inefficiently. In this work, we introduce a novel method to learn from relative feedback and combine it with off-policy reinforcement learning. Through evaluations on two sparse-reward tasks, we demonstrate our method can be used to improve the sample efficiency of reinforcement learning by guiding its exploration process. Additionally, we show it can adapt a policy to changes in the environment or the user's preferences. Finally, we demonstrate real-world applicability by employing our approach to learn a navigation policy in a sparse reward setting.

Multimodal embedding models have been crucial in enabling various downstream tasks such as semantic similarity, information retrieval, and clustering over different modalities. However, existing multimodal embeddings like VLM2Vec, E5-V, GME are predominantly focused on natural images, with limited support for other visual forms such as videos and visual documents. This restricts their applicability in real-world scenarios, including AI agents, multi-modal search and recommendation, and retrieval-augmented generation (RAG). To close this gap, we propose VLM2Vec-V2, a unified framework for learning embeddings across diverse visual forms. First, we introduce MMEB-V2, a comprehensive benchmark that extends MMEB with five new task types: visual document retrieval, video retrieval, temporal grounding, video classification and video question answering - spanning text, image, video, and visual document inputs. Next, we train VLM2Vec-V2, a general-purpose embedding model that supports text, image, video, and visual document inputs. Extensive experiments show that VLM2Vec-V2 achieves strong performance not only on the newly introduced video and document retrieval tasks, but also improves over prior baselines on the original image benchmarks. Through extensive evaluation, our study offers insights into the generalizability of various multimodal embedding models and highlights effective strategies for unified embedding learning, laying the groundwork for more scalable and adaptable representation learning in both research and real-world settings.

We introduce Nile-Chat-4B, 3x4B-A6B, and 12B, a collection of LLMs for Egyptian dialect, uniquely designed to understand and generate texts written in both Arabic and Latin scripts. Specifically, with Nile-Chat-3x4B-A6B, we introduce a novel language adaptation approach by leveraging the Branch-Train-MiX strategy to merge script-specialized experts, into a single MoE model. Our Nile-Chat models significantly outperform leading multilingual and Arabic LLMs, such as LLaMa, Jais, and ALLaM, on our newly introduced Egyptian evaluation benchmarks, which span both understanding and generative tasks. Notably, our 12B model yields a 14.4% performance gain over Qwen2.5-14B-Instruct on Latin-script benchmarks. All our resources are publicly available. We believe this work presents a comprehensive methodology for adapting LLMs to dual-script languages, addressing an often overlooked aspect in modern LLM development.

Large language models (LLMs) are rapidly being integrated into psychological research as research tools, evaluation targets, human simulators, and cognitive models. However, recent evidence reveals severe measurement unreliability: Personality assessments collapse under factor analysis, moral preferences reverse with punctuation changes, and theory-of-mind accuracy varies widely with trivial rephrasing. These "measurement phantoms"--statistical artifacts masquerading as psychological phenomena--threaten the validity of a growing body of research. Guided by the dual-validity framework that integrates psychometrics with causal inference, we present a six-stage workflow that scales validity requirements to research ambition--using LLMs to code text requires basic reliability and accuracy, while claims about psychological properties demand comprehensive construct validation. Researchers must (1) explicitly define their research goal and corresponding validity requirements, (2) develop and validate computational instruments through psychometric testing, (3) design experiments that control for computational confounds, (4) execute protocols with transparency, (5) analyze data using methods appropriate for non-independent observations, and (6) report findings within demonstrated boundaries and use results to refine theory. We illustrate the workflow through an example of model evaluation--"LLM selfhood"--showing how systematic validation can distinguish genuine computational phenomena from measurement artifacts. By establishing validated computational instruments and transparent practices, this workflow provides a path toward building a robust empirical foundation for AI psychology research.

Effective data curation is essential for optimizing neural network training. In this paper, we present the Guided Spectrally Tuned Data Selection (GSTDS) algorithm, which dynamically adjusts the subset of data points used for training using an off-the-shelf pre-trained reference model. Based on a pre-scheduled filtering ratio, GSTDS effectively reduces the number of data points processed per batch. The proposed method ensures an efficient selection of the most informative data points for training while avoiding redundant or less beneficial computations. Preserving data points in each batch is performed based on spectral analysis. A Fiedler vector-based scoring mechanism removes the filtered portion of the batch, lightening the resource requirements of the learning. The proposed data selection approach not only streamlines the training process but also promotes improved generalization and accuracy. Extensive experiments on standard image classification benchmarks, including CIFAR-10, Oxford-IIIT Pet, and Oxford-Flowers, demonstrate that GSTDS outperforms standard training scenarios and JEST, a recent state-of-the-art data curation method, on several key factors. It is shown that GSTDS achieves notable reductions in computational requirements, up to four times, without compromising performance. GSTDS exhibits a considerable growth in terms of accuracy under the limited computational resource usage, in contrast to other methodologies. These promising results underscore the potential of spectral-based data selection as a scalable solution for resource-efficient deep learning and motivate further exploration into adaptive data curation strategies. You can find the code at https://github.com/rezasharifi82/GSTDS.