--Federated fine-tuning has emerged as a promising approach for adapting foundation models (FMs) to diverse downstream tasks in edge environments. In Internet of V ehicles (IoV) systems, enabling efficient and low-latency multi-task adaptation is particularly challenging due to client mobility, heterogeneous resources, and intermittent connectivity. This paper proposes a hierarchical federated fine-tuning framework that coordinates roadside units (RSUs) and vehicles to support resource-aware and mobility-resilient learning across dynamic IoV scenarios. Leveraging Low-Rank Adaptation (LoRA), we introduce a decentralized, energy-aware rank adaptation mechanism formulated as a constrained multi-armed bandit problem. A novel UCB-DUAL algorithm is developed to enable adaptive exploration under per-task energy budgets, achieving provable sublinear regret. T o evaluate our method, we construct a large-scale IoV simulator based on real-world trajectories, capturing dynamic participation, RSU handoffs, and communication variability. Extensive experiments show that our approach achieves the best accuracy-efficiency trade-off among all baselines, reducing latency by over 24% and improving average accuracy by more than 2.5%. With the deepening development of smart cities, the internet of vehicles (IoV) has attracted much attention [1]. By facilitating coordination among vehicles, roadside units (RSUs), and cloud platforms, IoV supports a wide range of intelligent services, such as traffic flow prediction, environmental monitoring, and autonomous driving [2]-[4].

Emotional support conversations are crucial for promoting emotional well-being, yet current models often lack deep empathetic reasoning grounded in psychological principles. To address this, we propose controllable empathetic reasoning, which combines natural language reasoning with structured psychological steps. We construct a fine-grained dataset annotated with reasoning correctness and response preferences to enable this capability. To further enhance training, we employ reinforcement learning with a unified process-outcome reward model that delivers precise feedback. To mitigate response repetitiveness from entropy collapse, we introduce personality-based dialogue rewriting and a redundancy-aware reward reweighting strategy. Our approach significantly improves model's emotional support ability, advancing the development of empathetic, human-like support systems.

Aspect-based sentiment analysis (ABSA) is a fine-grained sentiment analysis task that focuses on understanding opinions at the aspect level, including sentiment towards specific aspect terms, categories, and opinions. While ABSA research has seen significant progress, much of the focus has been on monolingual settings. Cross-lingual ABSA, which aims to transfer knowledge from resource-rich languages (such as English) to low-resource languages, remains an under-explored area, with no systematic review of the field. This paper aims to fill that gap by providing a comprehensive survey of cross-lingual ABSA. We summarize key ABSA tasks, including aspect term extraction, aspect sentiment classification, and compound tasks involving multiple sentiment elements. Additionally, we review the datasets, modelling paradigms, and cross-lingual transfer methods used to solve these tasks. We also examine how existing work in monolingual and multilingual ABSA, as well as ABSA with LLMs, contributes to the development of cross-lingual ABSA. Finally, we highlight the main challenges and suggest directions for future research to advance cross-lingual ABSA systems.

Cross-lingual aspect-based sentiment analysis (ABSA) involves detailed sentiment analysis in a target language by transferring knowledge from a source language with available annotated data. Most existing methods depend heavily on often unreliable translation tools to bridge the language gap. In this paper, we propose a new approach that leverages a large language model (LLM) to generate high-quality pseudo-labelled data in the target language without the need for translation tools. First, the framework trains an ABSA model to obtain predictions for unlabelled target language data. Next, LLM is prompted to generate natural sentences that better represent these noisy predictions than the original text. The ABSA model is then further fine-tuned on the resulting pseudo-labelled dataset. We demonstrate the effectiveness of this method across six languages and five backbone models, surpassing previous state-of-the-art translation-based approaches. The proposed framework also supports generative models, and we show that fine-tuned LLMs outperform smaller multilingual models.

Despite the significant advancements in Large Language Models (LLMs), catastrophic forgetting remains a substantial challenge, where models lose previously acquired knowledge upon learning new information. Continual learning (CL) strategies have emerged as a potential solution to this problem, with replay-based techniques demonstrating superior performance in preserving learned knowledge. In this context, we introduce Gauss-Tin, a novel approach that integrates the replay strategy with a Gaussian mixture model to enhance the quality of sample selection during training, supplemented by instructional guidance to facilitate the generation of past learning. This method aims to improve LLMs' retention capabilities by strategically reinforcing important past learnings while accommodating new information. Our experimental results indicate a promising 6\% improvement in retention metrics over traditional methods, suggesting that Gauss-Tin is an effective strategy for mitigating catastrophic forgetting in LLMs. This study underscores the potential of hybrid models in enhancing the robustness and adaptability of LLMs in dynamic learning environments.

Retrieval-augmented generation (RAG) systems are often bottlenecked by their reranking modules, which typically score passages independently and select a fixed Top-K size. This approach struggles with complex multi-hop queries that require synthesizing evidence across multiple documents, creating a trade-off where small K values omit crucial information and large K values introduce noise. To address this, we introduce the Dynamic Passage Selector (DPS), a novel reranking framework that treats passage selection as a supervised learning problem. Unlike traditional point-wise or list-wise methods, DPS is fine-tuned to capture inter-passage dependencies and dynamically select the most relevant set of passages for generation. As a seamless plug-and-play module, DPS requires no modifications to the standard RAG pipeline. Comprehensive evaluations on five benchmarks show that DPS consistently outperforms state-of-the-art rerankers and fine-tuning methods. Notably, on the challenging MuSiQue dataset, DPS improves the F1-score by 30.06% and 15.4% over strong baselines like Qwen3-reranker and RankingGPT, respectively. Our results demonstrate that by enabling adaptive evidence selection, DPS substantially enhances reasoning capabilities in complex RAG scenarios.

LLMs are known to store vast amounts of knowledge in their parametric memory. However, learning and recalling facts from this memory is known to be unreliable, depending largely on the prevalence of particular facts in the training data and other factors which are poorly understood. Practitioners are lacking tools which will allow them to ensure that the models learn a given body of knowledge reliably and consistently. To this end, we propose Active Reading: a framework where we train models to study a given set of material with self-generated learning strategies. First, we demonstrate models trained with Active Reading on expert domains absorb significantly more knowledge than vanilla finetuning and other data augmentations. We train expert 8B models that achieve 66% on a Wikipedia-grounded subset of SimpleQA (+313% relative over vanilla finetuning) and 26% on FinanceBench (+160% relative over vanilla finetuning) by applying Active Reading to the source documents for each benchmark. Finally, we show that Active Reading can be utilized at pre-training scale to build more factual models. As a demonstration of this, we release Meta WikiExpert-8B, a Wikipedia-expert model trained on 1 trillion generated tokens, which outcompetes models with hundreds of billions of parameters on factual QA.

Continual learning (CL) for Foundation Models (FMs) is an essential yet underexplored challenge, especially in Federated Continual Learning (FCL), where each client learns from a private, evolving task stream under strict data and communication constraints. Despite their powerful generalization abilities, FMs often exhibit suboptimal performance on local downstream tasks, as they are unable to utilize private local data. Furthermore, enabling FMs to learn new tasks without forgetting prior knowledge is inherently a challenging problem, primarily due to their immense parameter count and high model complexity. In contrast, small models can be trained locally under resource-constrained conditions and benefit from more mature CL techniques. To bridge the gap between small models and FMs, we propose the first collaborative framework in FCL, where lightweight local models act as a dynamic bridge, continually adapting to new tasks while enhancing the utility of the large model. Two novel components are also included: Small Model Continual Fine-tuning is for preventing small models from temporal forgetting; One-by-One Distillation performs personalized fusion of heterogeneous local knowledge on the server. Experimental results demonstrate its superior performance, even when clients utilize heterogeneous small models.

Video Large Language Models (Video-LLMs) excel at general video understanding but struggle with long-form videos due to context window limits. Consequently, recent approaches focus on keyframe retrieval, condensing lengthy videos into a small set of informative frames. Despite their practicality, these methods simplify the problem to static text image matching, overlooking spatio temporal relationships crucial for capturing scene transitions and contextual continuity, and may yield redundant keyframes with limited information, diluting salient cues essential for accurate video question answering. To address these limitations, we introduce Video-EM, a training free framework inspired by the principles of human episodic memory, designed to facilitate robust and contextually grounded reasoning. Rather than treating keyframes as isolated visual entities, Video-EM explicitly models them as temporally ordered episodic events, capturing both spatial relationships and temporal dynamics necessary for accurately reconstructing the underlying narrative. Furthermore, the framework leverages chain of thought (CoT) thinking with LLMs to iteratively identify a minimal yet highly informative subset of episodic memories, enabling efficient and accurate question answering by Video-LLMs. Extensive evaluations on the Video-MME, EgoSchema, HourVideo, and LVBench benchmarks confirm the superiority of Video-EM, which achieves highly competitive results with performance gains of 4-9 percent over respective baselines while utilizing fewer frames.

Ensuring robust safety alignment while preserving utility is critical for the reliable deployment of Large Language Models (LLMs). However, current techniques fundamentally suffer from intertwined deficiencies: insufficient robustness against malicious attacks, frequent refusal of benign queries, degradation in generated text quality and general task performance--the former two reflecting deficits in robust safety and the latter constituting utility impairment . We trace these limitations to the coarse-grained layer-wise interventions in existing methods. To resolve this, we propose NeuronT une, a fine-grained framework that dynamically modulates sparse neurons to achieve simultaneous safety-utility optimization. Our approach first identifies safety-critical and utility-preserving neurons across all layers via attribution, then employs meta-learning to adaptively amplify safety-neuron activations and suppress utility-neuron activations. Crucially, NeuronTune enables tunable adjustment of intervention scope via neuron-count thresholds, supporting flexible adaptation to security-critical or utility-priority scenarios. Extensive experimental results demonstrate that our method significantly outperforms existing state-of-the-art technologies, achieving superior model safety while maintaining excellent utility.