Large language models (LLMs) possess strong multilingual capabilities, and combining Reinforcement Learning from Human Feedback (RLHF) with translation tasks has shown great potential. However, we observe that this paradigm performs unexpectedly poorly when applied to colloquial subtitle translation tasks. In this work, we investigate this issue and find that the offline reward model (RM) gradually diverges from the online LLM due to distributional shift, ultimately leading to undesirable training outcomes. To address this, we propose RIVAL, an adversarial training framework that formulates the process as a min-max game between the RM and the LLM. RIVAL iteratively updates the both models, with the RM trained to distinguish strong from weak translations (qualitative preference reward), and the LLM trained to enhance its translation for closing this gap. To stabilize training and improve generalizability, we also incorporate quantitative preference reward (e.g., BLEU) into the RM, enabling reference-free quality modeling aligned with human evaluation. Through extensive experiments, we demonstrate that the proposed adversarial training framework significantly improves upon translation baselines.

Retrieval-Augmented Generation (RAG) struggles with domain-specific enterprise datasets, often isolated behind firewalls and rich in complex, specialized terminology unseen by LLMs during pre-training. Semantic variability across domains like medicine, networking, or law hampers RAG's context precision, while fine-tuning solutions are costly, slow, and lack generalization as new data emerges. Achieving zero-shot precision with retrievers without fine-tuning still remains a key challenge. We introduce 'MetaGen Blended RAG', a novel enterprise search approach that enhances semantic retrievers through a metadata generation pipeline and hybrid query indexes using dense and sparse vectors. By leveraging key concepts, topics, and acronyms, our method creates metadata-enriched semantic indexes and boosted hybrid queries, delivering robust, scalable performance without fine-tuning. On the biomedical PubMedQA dataset, MetaGen Blended RAG achieves 82% retrieval accuracy and 77% RAG accuracy, surpassing all prior zero-shot RAG benchmarks and even rivaling fine-tuned models on that dataset, while also excelling on datasets like SQuAD and NQ. This approach redefines enterprise search using a new approach to building semantic retrievers with unmatched generalization across specialized domains.

R1-style Reinforcement Learning (RL) significantly enhances Large Language Models' reasoning capabilities, yet the mechanism behind rule-based RL remains unclear. We found that small-scale SFT has substantial influence on RL but shows poor efficiency. To explain our observations, we propose an analytical framework and compare the efficiency of SFT and RL by measuring \textbf{sample effect}. Our hypothetical analysis shows the potential to improve SFT efficiency. Guided by our analysis, we propose \textbf{Re-distillation}, a technique that aims to boost the effectiveness of small-scale distillation by sampling from the RL-trained policy. Re-distillation shows consistent surprising efficiency on three datasets and both Qwen\&Llama models: Re-distilled models matched RL performance with far fewer samples and less computation. As a result, on K\&K dataset, our re-distilled Qwen-2.5-1.5B model surpasses DeepSeek-V3-0324 with only 1K SFT samples. We demonstrate that re-distillation can be used to efficiently balance multiple goals in RL. Our work explains several interesting phenomena in R1-style RL, shedding light on the mechanisms behind its empirical success. Code is available at: https://github.com/on1262/deep-reasoning.

Modern automotive infotainment systems necessitate intelligent and adaptive solutions to manage frequent User Interface (UI) updates and diverse design variations. This work introduces a vision-language framework to facilitate the understanding of and interaction with automotive UIs, enabling seamless adaptation across different UI designs. To support research in this field, AutomotiveUI-Bench-4K, an open-source dataset comprising 998 images with 4,208 annotations, is also released. Additionally, a data pipeline for generating training data is presented. A Molmo-7B-based model is fine-tuned using Low-Rank Adaptation (LoRa), incorporating generated reasoning along with visual grounding and evaluation capabilities. The fine-tuned Evaluative Large Action Model (ELAM) achieves strong performance on AutomotiveUI-Bench-4K (model and dataset are available on Hugging Face). The approach demonstrates strong cross-domain generalization, including a +5.6% improvement on ScreenSpot over the baseline model. An average accuracy of 80.8% is achieved on ScreenSpot, closely matching or surpassing specialized models for desktop, mobile, and web, despite being trained primarily on the automotive domain. This research investigates how data collection and subsequent fine-tuning can lead to AI-driven advancements in automotive UI understanding and interaction. The applied method is cost-efficient, and fine-tuned models can be deployed on consumer-grade GPUs.

Large language models (LLMs) are increasingly being adopted in educational settings. These applications expand beyond English, though current LLMs remain primarily English-centric. In this work, we ascertain if their use in education settings in non-English languages is warranted. We evaluated the performance of popular LLMs on four educational tasks: identifying student misconceptions, providing targeted feedback, interactive tutoring, and grading translations in eight languages (Mandarin, Hindi, Arabic, German, Farsi, Telugu, Ukrainian, Czech) in addition to English. We find that the performance on these tasks somewhat corresponds to the amount of language represented in training data, with lower-resource languages having poorer task performance. Although the models perform reasonably well in most languages, the frequent performance drop from English is significant. Thus, we recommend that practitioners first verify that the LLM works well in the target language for their educational task before deployment.

Large Language Models (LLMs) have shown promise in clinical decision support, yet their application to triage remains underexplored. We systematically investigate the capabilities of LLMs in emergency department triage through two key dimensions: (1) robustness to distribution shifts and missing data, and (2) counterfactual analysis of intersectional biases across sex and race. We assess multiple LLM-based approaches, ranging from continued pre-training to in-context learning, as well as machine learning approaches. Our results indicate that LLMs exhibit superior robustness, and we investigate the key factors contributing to the promising LLM-based approaches. Furthermore, in this setting, we identify gaps in LLM preferences that emerge in particular intersections of sex and race. LLMs generally exhibit sex-based differences, but they are most pronounced in certain racial groups. These findings suggest that LLMs encode demographic preferences that may emerge in specific clinical contexts or particular combinations of characteristics.

Clinical case reports and discharge summaries may be the most complete and accurate summarization of patient encounters, yet they are finalized, i.e., timestamped after the encounter. Complementary data structured streams become available sooner but suffer from incompleteness. To train models and algorithms on more complete and temporally fine-grained data, we construct a pipeline to phenotype, extract, and annotate time-localized findings within case reports using large language models. We apply our pipeline to generate an open-access textual time series corpus for Sepsis-3 comprising 2,139 case reports from the Pubmed-Open Access (PMOA) Subset. To validate our system, we apply it on PMOA and timeline annotations from I2B2/MIMIC-IV and compare the results to physician-expert annotations. We show high recovery rates of clinical findings (event match rates: O1-preview--0.755, Llama 3.3 70B Instruct--0.753) and strong temporal ordering (concordance: O1-preview--0.932, Llama 3.3 70B Instruct--0.932). Our work characterizes the ability of LLMs to time-localize clinical findings in text, illustrating the limitations of LLM use for temporal reconstruction and providing several potential avenues of improvement via multimodal integration.

Recent zero-shot text-to-speech (TTS) systems face a common dilemma: autoregressive (AR) models suffer from slow generation and lack duration controllability, while non-autoregressive (NAR) models lack temporal modeling and typically require complex designs. In this paper, we introduce a novel pseudo-autoregressive (PAR) codec language modeling approach that unifies AR and NAR modeling. Combining explicit temporal modeling from AR with parallel generation from NAR, PAR generates dynamic-length spans at fixed time steps. Building on PAR, we propose PALLE, a two-stage TTS system that leverages PAR for initial generation followed by NAR refinement. In the first stage, PAR progressively generates speech tokens along the time dimension, with each step predicting all positions in parallel but only retaining the left-most span. In the second stage, low-confidence tokens are iteratively refined in parallel, leveraging the global contextual information. Experiments demonstrate that PALLE, trained on LibriTTS, outperforms state-of-the-art systems trained on large-scale data, including F5-TTS, E2-TTS, and MaskGCT, on the LibriSpeech test-clean set in terms of speech quality, speaker similarity, and intelligibility, while achieving up to ten times faster inference speed. Audio samples are available at https://microsoft.com/research/project/vall-e-x/palle.

Reasoning is a fundamental cognitive process that enables logical inference, problem-solving, and decision-making. With the rapid advancement of large language models (LLMs), reasoning has emerged as a key capability that distinguishes advanced AI systems from conventional models that empower chatbots. In this survey, we categorize existing methods along two orthogonal dimensions: (1) Regimes, which define the stage at which reasoning is achieved (either at inference time or through dedicated training); and (2) Architectures, which determine the components involved in the reasoning process, distinguishing between standalone LLMs and agentic compound systems that incorporate external tools, and multi-agent collaborations. Within each dimension, we analyze two key perspectives: (1) Input level, which focuses on techniques that construct high-quality prompts that the LLM condition on; and (2) Output level, which methods that refine multiple sampled candidates to enhance reasoning quality. This categorization provides a systematic understanding of the evolving landscape of LLM reasoning, highlighting emerging trends such as the shift from inference-scaling to learning-to-reason (e.g., DeepSeek-R1), and the transition to agentic workflows (e.g., OpenAI Deep Research, Manus Agent). Additionally, we cover a broad spectrum of learning algorithms, from supervised fine-tuning to reinforcement learning such as PPO and GRPO, and the training of reasoners and verifiers. We also examine key designs of agentic workflows, from established patterns like generator-evaluator and LLM debate to recent innovations. Finally, we identify emerging trends, such as domain-specific reasoning systems, and open challenges, such as evaluation and data quality. This survey aims to provide AI researchers and practitioners with a comprehensive foundation for advancing reasoning in LLMs, paving the way for more sophisticated and reliable AI systems. 1

In recent years, accurately and quickly deploying medical large language models (LLMs) has become a trend. Among these, retrieval-augmented generation (RAG) has garnered attention due to rapid deployment and privacy protection. However, the challenge hinder the practical deployment of RAG for medical diagnosis: the semantic gap between colloquial patient descriptions and the professional terminology within medical knowledge bases. We try to address the challenge from the data perspective and the method perspective. First, to address the semantic gap in existing knowledge bases, we construct DiagnosGraph, a generalist knowledge graph covering both modern medicine and Traditional Chinese Medicine. It contains 876 common diseases with the graph of 7,997 nodes and 37,201 triples. To bridge the gap between colloquial patient narratives and academic medical knowledge, DiagnosGraph also introduces $1,908$ medical record by formalizing the patient chief complaint and proposing a medical diagnosis. Second, we introduce the Multi-Round Diagnostic RAG (MRD-RAG) framework. It utilizes a multi-round dialogue to refine diagnostic possibilities, emulating the clinical reasoning of a physician. Experiments conducted on four medical benchmarks, with evaluations by human physicians, demonstrate that MRD-RAG enhances the diagnostic performance of LLMs, highlighting its potential to make automated diagnosis more accurate and human-aligned.