Does "Wuthering Heights" Herald the Revival of the Film Romance? Emerald Fennell's new movie may be mediocre, but its popularity demonstrates the strength of a genre that Hollywood has all but abandoned. The important thing about adaptations isn't what's taken out but what's put in. Emerald Fennell's "Wuthering Heights"--or, as she'd have it, " 'Wuthering Heights,' " complete with scare quotes--is the season's second Frankenstein movie, because Fennell takes bits and pieces from Emily Brontë's novel and, adding much of her own imagining, reassembles them into a misbegotten thing that wants only to be loved. And paying audiences seem to love it, even if many critics don't.

Kleber Mendonça Filho wants his films to reclaim lost history. For Kleber Mendonça Filho, filmmaking is an act of both provocation and preservation. Mendonça was born in 1968, in the early years of a ruthless military dictatorship--a time when cinema, like much else, was harshly constrained. His mother, Joselice Jucá, was a historian who studied Brazil's abolitionist movement, and she taught him that filling gaps in the cultural memory was a way to expose concealed truths. His relationship with film is inextricably linked with his home town, Recife--a port city where attractive beaches and high-rise developments coexist with sprawling favelas and rampant crime. In his youth, Mendonça was fascinated by the city's grand cinema palaces. He carried a Super 8 camera to the tops of marquees and shot dizzying images; he spent hours in projection booths, learning the mechanics of how films reached the screen. Over time, Mendonça watched those theatres fall into decline, an experience that he likened to being aboard a ship as it wrecked. But even as Recife lost its allure, he made the city a fixture of his films--a way of vindicating its place in history. His first narrative feature, "Neighboring Sounds," takes place on a street where he lived as a child, a setting that he spent years documenting. Later, he made "Pictures of Ghosts," a documentary about Recife told largely through its cinemas.

June Squibb sparkles opposite Cynthia Nixon in a futuristic drama, and Michelle Williams loses her way in Eugene O'Neill's Pulitzer Prize winner. Appropriately enough, Jordan Harrison's déjà-vu-inducing "Marjorie Prime" has been here before. The Off Broadway theatre Playwrights Horizons produced the poignant sci-fi play about hyperrealistic re-creations of the dead--so-called Primes, which are used as a supportive technology for the bereaved--in Anne Kauffman's spirited, delicately comic production, back in 2015. Lois Smith, then eighty-five years old, played Marjorie, a woman struggling with dementia. It's the early twenty-sixties, and so Marjorie is attended by a holographic Prime of her husband, Walter, who tells her stories from her own life.

Retrieval-Augmented Generation (RAG) is a well-established and rapidly evolving field within AI that enhances the outputs of large language models by integrating relevant information retrieved from external knowledge sources. While industry adoption of RAG is now beginning, there is a significant lack of research on its practical application in industrial contexts. To address this gap, we conducted a semistructured interview study with 13 industry practitioners to explore the current state of RAG adoption in real-world settings. Our study investigates how companies apply RAG in practice, providing (1) an overview of industry use cases, (2) a consolidated list of system requirements, (3) key challenges and lessons learned from practical experiences, and (4) an analysis of current industry evaluation methods. Our main findings show that current RAG applications are mostly limited to domain-specific QA tasks, with systems still in prototype stages; industry requirements focus primarily on data protection, security, and quality, while issues such as ethics, bias, and scalability receive less attention; data preprocessing remains a key challenge, and system evaluation is predominantly conducted by humans rather than automated methods.

In this paper, we introduce TEDxTN, the first publicly available Tunisian Arabic to English speech translation dataset. This work is in line with the ongoing effort to mitigate the data scarcity obstacle for a number of Arabic dialects. We collected, segmented, transcribed and translated 108 TEDx talks following our internally developed annotations guidelines. The collected talks represent 25 hours of speech with code-switching that cover speakers with various accents from over 11 different regions of Tunisia. We make the annotation guidelines and corpus publicly available. This will enable the extension of TEDxTN to new talks as they become available. We also report results for strong baseline systems of Speech Recognition and Speech Translation using multiple pre-trained and fine-tuned end-to-end models. This corpus is the first open source and publicly available speech translation corpus of Code-Switching Tunisian dialect. We believe that this is a valuable resource that can motivate and facilitate further research on the natural language processing of Tunisian Dialect.

COOT leads to performance improvements over the state-of-the-art methods.

We present ADI-20, an extension of the previously published ADI-17 Arabic Dialect Identification (ADI) dataset. ADI-20 covers all Arabic-speaking countries' dialects. It comprises 3,556 hours from 19 Arabic dialects in addition to Modern Standard Arabic (MSA). We used this dataset to train and evaluate various state-of-the-art ADI systems. We explored fine-tuning pre-trained ECAPA-TDNN-based models, as well as Whisper encoder blocks coupled with an attention pooling layer and a classification dense layer. We investigated the effect of (i) training data size and (ii) the model's number of parameters on identification performance. Our results show a small decrease in F1 score while using only 30% of the original training data. We open-source our collected data and trained models to enable the reproduction of our work, as well as support further research in ADI.

This paper describes Elyadata \& LIA's joint submission to the NADI multi-dialectal Arabic Speech Processing 2025. We participated in the Spoken Arabic Dialect Identification (ADI) and multi-dialectal Arabic ASR subtasks. Our submission ranked first for the ADI subtask and second for the multi-dialectal Arabic ASR subtask among all participants. Our ADI system is a fine-tuned Whisper-large-v3 encoder with data augmentation. This system obtained the highest ADI accuracy score of \textbf{79.83\%} on the official test set. For multi-dialectal Arabic ASR, we fine-tuned SeamlessM4T-v2 Large (Egyptian variant) separately for each of the eight considered dialects. Overall, we obtained an average WER and CER of \textbf{38.54\%} and \textbf{14.53\%}, respectively, on the test set. Our results demonstrate the effectiveness of large pre-trained speech models with targeted fine-tuning for Arabic speech processing.

Safety verification of dynamical systems via barrier certificates is essential for ensuring correctness in autonomous applications. Synthesizing these certificates involves discovering mathematical functions with current methods suffering from poor scalability, dependence on carefully designed templates, and exhaustive or incremental function-space searches. They also demand substantial manual expertise--selecting templates, solvers, and hyperparameters, and designing sampling strategies--requiring both theoretical and practical knowledge traditionally shared through linguistic reasoning rather than formalized methods. This motivates a key question: can such expert reasoning be captured and operationalized by language models? We address this by introducing an LLM-based agentic framework for barrier certificate synthesis. The framework uses natural language reasoning to propose, refine, and validate candidate certificates, integrating LLM-driven template discovery with SMT-based verification, and supporting barrier-controller co-synthesis to ensure consistency between safety certificates and controllers. To evaluate this capability, we introduce BarrierBench, a benchmark of 100 dynamical systems spanning linear, nonlinear, discrete-time, and continuous-time settings. Our experiments assess not only the effectiveness of LLM-guided barrier synthesis but also the utility of retrieval-augmented generation and agentic coordination strategies in improving its reliability and performance. Across these tasks, the framework achieves more than 90% success in generating valid certificates. By releasing BarrierBench and the accompanying toolchain, we aim to establish a community testbed for advancing the integration of language-based reasoning with formal verification in dynamical systems. The benchmark is publicly available at https://hycodev.com/dataset/barrierbench

Conversational recommender systems (CRSs) aim to proactively capture user preferences through natural language dialogue and recommend high-quality items. To achieve this, CRS gathers user preferences via a dialog module and builds user profiles through a recommendation module to generate appropriate recommendations. However, existing CRS faces challenges in capturing the deep semantics of user preferences and dialogue context. In particular, the efficient integration of external knowledge graph (KG) information into dialogue generation and recommendation remains a pressing issue. Traditional approaches typically combine KG information directly with dialogue content, which often struggles with complex semantic relationships, resulting in recommendations that may not align with user expectations. To address these challenges, we introduce STEP, a conversational recommender centered on pre-trained language models that combines curriculum-guided context-knowledge fusion with lightweight task-specific prompt tuning. At its heart, an F-Former progressively aligns the dialogue context with knowledge-graph entities through a three-stage curriculum, thus resolving fine-grained semantic mismatches. The fused representation is then injected into the frozen language model via two minimal yet adaptive prefix prompts: a conversation prefix that steers response generation toward user intent and a recommendation prefix that biases item ranking toward knowledge-consistent candidates. This dual-prompt scheme allows the model to share cross-task semantics while respecting the distinct objectives of dialogue and recommendation. Experimental results show that STEP outperforms mainstream methods in the precision of recommendation and dialogue quality in two public datasets.