Recent advances in large language models (LLMs) have created new opportunities for symbolic music generation. However, existing formats such as MIDI, ABC, and MusicXML are either overly complex or structurally inconsistent, limiting their suitability for token-based learning architectures. To address these challenges, we propose HNote, a novel hexadecimal-based notation system extended from YNote, which encodes both pitch and duration within a fixed 32-unit measure framework. This design ensures alignment, reduces ambiguity, and is directly compatible with LLM architectures. We converted 12,300 Jiangnan-style songs generated from traditional folk pieces from YNote into HNote, and fine-tuned LLaMA-3.1(8B) using parameter-efficient LoRA. Experimental results show that HNote achieves a syntactic correctness rate of 82.5%, and BLEU and ROUGE evaluations demonstrate strong symbolic and structural similarity, producing stylistically coherent compositions. This study establishes HNote as an effective framework for integrating LLMs with cultural music modeling.

Large language models (LLMs) have rapidly scaled in size, bringing severe memory and computational challenges that hinder their deployment. Singular Value Decomposition (SVD)-based compression has emerged as an appealing post-training compression technique for LLMs, yet most existing methods apply a uniform compression ratio across all layers, implicitly assuming homogeneous information included in various layers. This overlooks the substantial intra-layer heterogeneity observed in LLMs, where middle layers tend to encode richer information while early and late layers are more redundant. In this work, we revisit the existing SVD-based compression method and propose D-Rank, a framework with layer-wise balanced Dynamic Rank allocation for LLMs compression. We first introduce effective rank as a principled metric to measure the information density of weight matrices, and then allocate ranks via a Lagrange multiplier-based optimization scheme to adaptively assign more capacity to groups with higher information density under a fixed compression ratio. Moreover, we rebalance the allocated ranks across attention layers to account for their varying importance and extend D-Rank to latest LLMs with grouped-query attention. Extensive experiments on various LLMs with different scales across multiple compression ratios demonstrate that D-Rank consistently outperforms SVD-LLM, ASVD, and Basis Sharing, achieving more than 15 lower perplexity with LLaMA-3-8B model on C4 datasets at 20% compression ratio and up to 5% higher zero-shot reasoning accuracy with LLaMA-7B model at 40% compression ratio while achieving even higher throughput.

Reward Models (RMs) are key components for evaluating and guiding language model outputs. However, traditional scalar RMs often struggle with incorporating contextual and background information during inference, leading to incomplete evaluations. Generative RMs (GRMs) attempt to address these limitations by generating intermediate reasoning steps. Yet, their uncontrolled black-box nature and inefficiency due to sequential decoding hinder their industrial deployment. Industrial scenarios, such as search and recommendation systems, often involve single-domain tasks requiring evaluation along specific dimensions. In such contexts, diagnosing "bad cases" necessitates structured feedback to identify and optimize dimension-specific issues. In this paper, we propose the Structural Reward Model (SRM), a modular and interpretable framework integrating side-branch models as auxiliary feature generators. By introducing fine-grained dimensions, SRMs enable interpretable and efficient evaluation, facilitating targeted diagnostics and optimization. This structured approach ensures adaptability and scalability for industrial applications. Through comprehensive experiments, we demonstrate that SRMs outperform scalar RMs and GRMs in robustness and alignment with human preferences. The modular design further supports efficient optimization for practical scenarios, allowing SRM to provide a practical reward modeling solution for industry.

Political beliefs vary significantly across different countries, reflecting distinct historical, cultural, and institutional contexts. These ideologies, ranging from liberal democracies to rigid autocracies, influence human societies, as well as the digital systems that are constructed within those societies. The advent of generative artificial intelligence, particularly Large Language Models (LLMs), introduces new agents in the political space-agents trained on massive corpora that replicate and proliferate socio-political assumptions. This paper analyses whether LLMs display propensities consistent with democratic or autocratic world-views. We validate this insight through experimental tests in which we experiment with the leading LLMs developed across disparate political contexts, using several existing psychometric and political orientation measures. The analysis is based on both numerical scoring and qualitative analysis of the models' responses. Findings indicate high model-to-model variability and a strong association with the political culture of the country in which the model was developed. These findings highlight the need for more detailed examination of the socio-political dimensions embedded within AI systems.

Recent advances in large language models (LLMs) highlight the importance of training data structure and quality in shaping reasoning behavior. However, most existing approaches focus on transforming data formats while neglecting the internal reasoning complexity of training samples, leaving the reasoning potential of data under-explored and underutilized. In this work, we posit that LLM logical reasoning performance is jointly constrained by the potential of the training data and the cognitive capacity of the model. To make this relationship measurable, we introduce Data Reasoning Intensity (DRI), a novel metric that quantifies the latent logical reasoning complexity of samples by decomposing and aggregating their logical structures. This allows us to analyze how well current LLMs utilize logical reasoning signals and identify performance gaps relative to data potential. Based on this insight, we introduce a re-cognizing optimization strategy that systematically enhances the logical reasoning intensity of training data. Rather than increasing data volume, our method re-optimizes existing samples to better align with the LLM's logical reasoning boundary. Extensive experiments show that our approach significantly improves performance and generalization over data-centric strategies. We further validate our method under a reinforcement learning framework. Our results indicate that prioritizing reasoning complexity in data rather than sheer scale or superficial form is essential to realizing LLMs' full cognitive potential.

Large Reasoning Models (LRMs) have shown impressive performance on complex reasoning tasks such as mathematics, yet they also display misbehaviors that expose their limitations. In particular, when faced with hard questions, LRMs often engage in unproductive reasoning until context limit, producing wrong answers while wasting substantial computation. This phenomenon reflects a fundamental issue: current answering paradigms overlook the relationship between questions and LRMs' capability boundaries. In this paper, we investigate whether LRMs possess self-awareness of capability boundaries. We begin by an observation that LRMs may know what they cannot solve through expressed reasoning confidence. For black-box models, we find that reasoning expressions reveal boundary signals, with accelerated growing confidence trajectory for solvable problems but convergent uncertainty trajectory for unsolvable ones. For white-box models, we show that hidden states of the last input token encode boundary information, with solvable and unsolvable problems linearly separable even before reasoning begins. Building on these findings, we propose two simple yet effective optimization strategies: reasoning expression monitoring and hidden states monitoring. Experiments demonstrate that these boundary-aware strategies enable LRMs to avoid unproductive reasoning without sacrificing accuracy, significantly improving reliability and efficiency by cutting token usage up to 62.7 - 93.6%. Large Reasoning Models (LRMs) have demonstrated remarkable capabilities on complex reasoning tasks such as mathematics (Guo et al., 2025; Jaech et al., 2024; Ahn et al., 2024). However, they also exhibit a range of misbehaviors that reveal the limitations of their capabilities (Kalai et al., 2025; Y ao et al., 2025b; Sun et al., 2025; Zhang et al., 2024).

Current video understanding models rely on fixed frame sampling strategies, processing predetermined visual inputs regardless of the specific reasoning requirements of each question. This static approach limits their ability to adaptively gather visual evidence, leading to suboptimal performance on tasks that require either broad temporal coverage or fine-grained spatial detail. In this paper, we introduce FrameMind, an end-to-end framework trained with reinforcement learning that enables models to dynamically request visual information during reasoning through Frame-Interleaved Chain-of-Thought (FiCOT). Unlike traditional approaches, FrameMind operates in multiple turns where the model alternates between textual reasoning and active visual perception, using tools to extract targeted frames or video clips based on identified knowledge gaps. To train effective dynamic sampling policies, we propose Dynamic Resolution Frame Sampling (DRFS), which exposes models to diverse temporal-spatial trade-offs during learning, and DRFS-GRPO, a group-relative policy optimization algorithm that learns from outcome-based rewards without requiring frame-level annotations. Extensive experiments on challenging benchmarks like MLVU and VideoMME demonstrate that our method significantly outperforms existing models, advancing the state of the art in flexible and efficient video understanding.

OpenAI's GPT-OSS family provides open-weight language models with explicit chain-of-thought (CoT) reasoning and a Harmony prompt format. We summarize an extensive security evaluation of GPT-OSS-20B that probes the model's behavior under different adversarial conditions. Using the Jailbreak Oracle (JO) [1], a systematic LLM evaluation tool, the study uncovers several failure modes including quant fever, reasoning blackholes, Schrodinger's compliance, reasoning procedure mirage, and chain-oriented prompting. Experiments demonstrate how these behaviors can be exploited on the GPT-OSS-20B model, leading to severe consequences.

Large Language Models (LLMs) are widely used for code generation, but they face critical security risks when applied to practical production due to package hallucinations, in which LLMs recommend non-existent packages. These hallucinations can be exploited in software supply chain attacks, where malicious attackers exploit them to register harmful packages. It is critical to test LLMs for package hallucinations to mitigate package hallucinations and defend against potential attacks. Although researchers have proposed testing frameworks for fact-conflicting hallucinations in natural language generation, there is a lack of research on package hallucinations. To fill this gap, we propose HFUZZER, a novel phrase-based fuzzing framework to test LLMs for package hallucinations. HFUZZER adopts fuzzing technology and guides the model to infer a wider range of reasonable information based on phrases, thereby generating enough and diverse coding tasks. Furthermore, HFUZZER extracts phrases from package information or coding tasks to ensure the relevance of phrases and code, thereby improving the relevance of generated tasks and code. We evaluate HFUZZER on multiple LLMs and find that it triggers package hallucinations across all selected models. Compared to the mutational fuzzing framework, HFUZZER identifies 2.60x more unique hallucinated packages and generates more diverse tasks. Additionally, when testing the model GPT-4o, HFUZZER finds 46 unique hallucinated packages. Further analysis reveals that for GPT-4o, LLMs exhibit package hallucinations not only during code generation but also when assisting with environment configuration.

Large Reasoning Models (LRMs) have achieved impressive performance on challenging tasks, yet their deep reasoning often incurs substantial computational costs. To achieve efficient reasoning, existing reinforcement learning methods still struggle to construct short reasoning path during the rollout stage, limiting effective learning. Inspired by Evidence Accumulation Models, we find that LRMs have accumulated sufficient information early in reasoning, making further reasoning steps redundant. Based on this insight, we propose Just-Enough Thinking (JET), which trains models to proactively terminate unnecessary reasoning. JET performs trajectory truncation during rollout to expose the model to short, distributionally consistent reasoning paths. Besides, it uses a quality-controlled length reward to better encourage concise reasoning while maintaining correctness. Extensive experiments demonstrate that JET significantly improves reasoning efficiency without sacrificing accuracy. Especially, DeepSeek-Distill-Qwen-1.5B achieves a 4.6% accuracy gain while reducing output length by 46.3% on the Olympiad benchmark. Our code is available in the GitHub.