Audio and music generation have emerged as crucial tasks in many applications, yet existing approaches face significant limitations: they operate in isolation without unified capabilities across modalities, suffer from scarce high-quality, multi-modal training data, and struggle to effectively integrate diverse inputs. In this work, we propose AudioX, a unified Diffusion Transformer model for Anything-to-Audio and Music Generation. Unlike previous domain-specific models, AudioX can generate both general audio and music with high quality, while offering flexible natural language control and seamless processing of various modalities including text, video, image, music, and audio. Its key innovation is a multi-modal masked training strategy that masks inputs across modalities and forces the model to learn from masked inputs, yielding robust and unified cross-modal representations. To address data scarcity, we curate two comprehensive datasets: vggsound-caps with 190K audio captions based on the VGGSound dataset, and V2M-caps with 6 million music captions derived from the V2M dataset. Extensive experiments demonstrate that AudioX not only matches or outperforms state-of-the-art specialized models, but also offers remarkable versatility in handling diverse input modalities and generation tasks within a unified architecture. The code and datasets will be available at https://zeyuet.github.io/AudioX/

Discourse understanding is essential for many NLP tasks, yet most existing work remains constrained by framework-dependent discourse representations. This work investigates whether large language models (LLMs) capture discourse knowledge that generalizes across languages and frameworks. We address this question along two dimensions: (1) developing a unified discourse relation label set to facilitate cross-lingual and cross-framework discourse analysis, and (2) probing LLMs to assess whether they encode generalizable discourse abstractions. Using multilingual discourse relation classification as a testbed, we examine a comprehensive set of 23 LLMs of varying sizes and multilingual capabilities. Our results show that LLMs, especially those with multilingual training corpora, can generalize discourse information across languages and frameworks. Further layer-wise analyses reveal that language generalization at the discourse level is most salient in the intermediate layers. Lastly, our error analysis provides an account of challenging relation classes.

Policies generated by Reinforcement Learning (RL) algorithms can be difficult to describe to users, as they result from the interplay between complex reward structures and neural network-based representations. This combination often leads to unpredictable behaviors, making policies challenging to analyze and posing significant obstacles to fostering human trust in real-world applications. Global policy summarization methods aim to describe agent behavior through a demonstration of actions in a subset of world-states. However, users can only watch a limited number of demonstrations, restricting their understanding of policies. Moreover, those methods overly rely on user interpretation, as they do not synthesize observations into coherent patterns. In this work, we present SySLLM (Synthesized Summary using LLMs), a novel method that employs synthesis summarization, utilizing large language models' (LLMs) extensive world knowledge and ability to capture patterns, to generate textual summaries of policies. Specifically, an expert evaluation demonstrates that the proposed approach generates summaries that capture the main insights generated by experts while not resulting in significant hallucinations. Additionally, a user study shows that SySLLM summaries are preferred over demonstration-based policy summaries and match or surpass their performance in objective agent identification tasks.

Traditional benchmarks struggle to evaluate increasingly sophisticated language models in multilingual and culturally diverse contexts. To address this gap, we introduce MMLU-ProX, a comprehensive multilingual benchmark covering 13 typologically diverse languages with approximately 11,829 questions per language. Building on the challenging reasoning-focused design of MMLU-Pro, our framework employs a semi-automatic translation process: translations generated by state-of-the-art large language models (LLMs) are rigorously evaluated by expert annotators to ensure conceptual accuracy, terminological consistency, and cultural relevance. We comprehensively evaluate 25 state-of-the-art LLMs using 5-shot chain-of-thought (CoT) and zero-shot prompting strategies, analyzing their performance across linguistic and cultural boundaries. Our experiments reveal consistent performance degradation from high-resource languages to lower-resource ones, with the best models achieving over 70% accuracy on English but dropping to around 40% for languages like Swahili, highlighting persistent gaps in multilingual capabilities despite recent advances. MMLU-ProX is an ongoing project; we are expanding our benchmark by incorporating additional languages and evaluating more language models to provide a more comprehensive assessment of multilingual capabilities.

Large Language Models (LLMs) are revolutionizing medical diagnostics by enhancing both disease classification and clinical decision-making. In this study, we evaluate the performance of two LLM- based diagnostic tools, DeepSeek R1 and O3 Mini, using a structured dataset of symptoms and diagnoses. We assessed their predictive accuracy at both the disease and category levels, as well as the reliability of their confidence scores. DeepSeek R1 achieved a disease-level accuracy of 76% and an overall accuracy of 82%, outperforming O3 Mini, which attained 72% and 75% respectively. Notably, DeepSeek R1 demonstrated exceptional performance in Mental Health, Neurological Disorders, and Oncology, where it reached 100% accuracy, while O3 Mini excelled in Autoimmune Disease classification with 100% accuracy. Both models, however, struggled with Respiratory Disease classification, recording accuracies of only 40% for DeepSeek R1 and 20% for O3 Mini. Additionally, the analysis of confidence scores revealed that DeepSeek R1 provided high-confidence predictions in 92% of cases, compared to 68% for O3 Mini. Ethical considerations regarding bias, model interpretability, and data privacy are also discussed to ensure the responsible integration of LLMs into clinical practice. Overall, our findings offer valuable insights into the strengths and limitations of LLM-based diagnostic systems and provide a roadmap for future enhancements in AI-driven healthcare.

Recent advances in large vision-language models (LVLMs) have shown promise for embodied task planning, yet they struggle with fundamental challenges like dependency constraints and efficiency. Existing approaches either solely optimize action selection or leverage world models during inference, overlooking the benefits of learning to model the world as a way to enhance planning capabilities. We propose Dual Preference Optimization (D$^2$PO), a new learning framework that jointly optimizes state prediction and action selection through preference learning, enabling LVLMs to understand environment dynamics for better planning. To automatically collect trajectories and stepwise preference data without human annotation, we introduce a tree search mechanism for extensive exploration via trial-and-error. Extensive experiments on VoTa-Bench demonstrate that our D$^2$PO-based method significantly outperforms existing methods and GPT-4o when applied to Qwen2-VL (7B), LLaVA-1.6 (7B), and LLaMA-3.2 (11B), achieving superior task success rates with more efficient execution paths.

Crystal Structure Prediction (CSP), which aims to generate stable crystal structures from compositions, represents a critical pathway for discovering novel materials. While structure prediction tasks in other domains, such as proteins, have seen remarkable progress, CSP remains a relatively underexplored area due to the more complex geometries inherent in crystal structures. In this paper, we propose Siamese foundation models specifically designed to address CSP. Our pretrain-finetune framework, named DAO, comprises two complementary foundation models: DAO-G for structure generation and DAO-P for energy prediction. Experiments on CSP benchmarks (MP-20 and MPTS-52) demonstrate that our DAO-G significantly surpasses state-of-the-art (SOTA) methods across all metrics. Extensive ablation studies further confirm that DAO-G excels in generating diverse polymorphic structures, and the dataset relaxation and energy guidance provided by DAO-P are essential for enhancing DAO-G's performance. When applied to three real-world superconductors ($\text{CsV}_3\text{Sb}_5$, $ \text{Zr}_{16}\text{Rh}_8\text{O}_4$ and $\text{Zr}_{16}\text{Pd}_8\text{O}_4$) that are known to be challenging to analyze, our foundation models achieve accurate critical temperature predictions and structure generations. For instance, on $\text{CsV}_3\text{Sb}_5$, DAO-G generates a structure close to the experimental one with an RMSE of 0.0085; DAO-P predicts the $T_c$ value with high accuracy (2.26 K vs. the ground-truth value of 2.30 K). In contrast, conventional DFT calculators like Quantum Espresso only successfully derive the structure of the first superconductor within an acceptable time, while the RMSE is nearly 8 times larger, and the computation speed is more than 1000 times slower. These compelling results collectively highlight the potential of our approach for advancing materials science research and development.

While utilizing syntactic tools such as parts-of-speech (POS) tagging has helped us understand sentence structures and their distribution across diverse corpora, it is quite complex and poses a challenge in natural language processing (NLP). This study focuses on understanding sentence structure balance - usages of nouns, verbs, determiners, etc - harmoniously without relying on such tools. It proposes a novel statistical method that uses American Standard Code for Information Interchange (ASCII) codes to represent text of 11 text corpora from various sources and their lexical category alignment after using their compressed versions through PCA, and analyzes the results through histograms and normality tests such as Shapiro-Wilk and Anderson-Darling Tests. By focusing on ASCII codes, this approach simplifies text processing, although not replacing any syntactic tools but complementing them by offering it as a resource-efficient tool for assessing text balance. The story generated by Grok shows near normality indicating balanced sentence structures in LLM outputs, whereas 4 out of the remaining 10 pass the normality tests. Further research could explore potential applications in text quality evaluation and style analysis with syntactic integration for more broader tasks.

The rapid advancement of large language models (LLMs) has significantly improved their performance in code generation tasks. However, existing code benchmarks remain static, consisting of fixed datasets with predefined problems. This makes them vulnerable to memorization during training, where LLMs recall specific test cases instead of generalizing to new problems, leading to data contamination and unreliable evaluation results. To address these issues, we introduce DynaCode, a dynamic, complexity-aware benchmark that overcomes the limitations of static datasets. DynaCode evaluates LLMs systematically using a complexity-aware metric, incorporating both code complexity and call-graph structures. DynaCode achieves large-scale diversity, generating up to 189 million unique nested code problems across four distinct levels of code complexity, referred to as units, and 16 types of call graphs. Results on 12 latest LLMs show an average performance drop of 16.8% to 45.7% compared to MBPP+, a static code generation benchmark, with performance progressively decreasing as complexity increases. This demonstrates DynaCode's ability to effectively differentiate LLMs. Additionally, by leveraging call graphs, we gain insights into LLM behavior, particularly their preference for handling subfunction interactions within nested code.

We study the capabilities of Large Language Models (LLM) on binary relations, a ubiquitous concept in math employed in most reasoning, math and logic benchmarks. This work focuses on equality, inequality, and inclusion, along with the properties they satisfy, such as ir/reflexivity, a/symmetry, transitivity, and logical complexity (e.g., number of reasoning ``hops''). We propose an alternative to in-context learning that trains only the representations of newly introduced tokens, namely out-of-context representation learning. This method mitigates linguistic biases already present in a model and, differently from in-context learning, does not rely on external information or illustrations. We argue out-of-context representation learning as a better alternative to in-context learning and fine-tuning to evaluate the capabilities of LLMs on logic tasks that are the building blocks of more complex reasoning benchmarks.