Search arXiv⌕ Search

arXiv subjects

Qing Cui

Publications and source records attributed to Qing Cui.

At least 37 records · Page 2Linked to original sources
arXiv2026

UniGeM: Unifying Data Mixing and Selection via Geometric Exploration and Mining

The scaling of Large Language Models (LLMs) is increasingly limited by data quality. Most methods handle data mixing and sample selection separately, which can break the structure in code corpora. We introduce \textbf{UniGeM}, a framework that unifies mixing and selection by treating data curation as a \textit{manifold approximation} problem without training proxy models or relying on external reference datasets. UniGeM operates hierarchically: \textbf{Macro-Exploration} learns mixing weights with stability-based clustering; \textbf{Micro-Mining} filters high-quality instances by their geometric distribution to ensure logical consistency. Validated by training 8B and 16B MoE models on 100B tokens, UniGeM achieves \textbf{2.0$\times$ data efficiency} over a random baseline and further improves overall performance compared to SOTA methods in reasoning-heavy evaluations and multilingual generalization.

cs.LG↗
arXiv2026

Mix Data or Merge Models? Balancing the Helpfulness, Honesty, and Harmlessness of Large Language Model via Model Merging

Achieving balanced alignment of large language models (LLMs) in terms of Helpfulness, Honesty, and Harmlessness (3H optimization) constitutes a cornerstone of responsible AI. Existing methods like data mixture strategies face limitations, including heavy reliance on expert knowledge and conflicting optimization signals. While model merging offers parameter-level conflict-resolution strategies through integrating specialized models' parameters, its potential for 3H optimization remains underexplored. This paper systematically compares the effectiveness of model merging and data mixture methods in constructing 3H-aligned LLMs for the first time, revealing previously overlooked collaborative and conflict relationships among the 3H dimensions and discussing the advantages and drawbacks of data mixture (\textit{data-level}) and model merging (\textit{parameter-level}) methods in mitigating the conflict for balanced 3H optimization. Specially, we propose a novel \textbf{R}eweighting \textbf{E}nhanced task \textbf{S}ingular \textbf{M}erging method, \textbf{RESM}, through outlier weighting and sparsity-aware rank selection strategies to address the challenges of preference noise accumulation and layer sparsity adaptation inherent in 3H-aligned LLM merging. Extensive evaluations can verify the effectiveness and robustness of RESM compared to previous data mixture (2\%-5\% gain) and model merging (1\%-3\% gain) methods in achieving balanced LLM alignment. We release our models through \href{https://huggingface.co/Jinluan}{3H\_Merging} for further investigations.

cs.CL↗
arXiv2026

Improving Autoformalization Using Direct Dependency Retrieval

The convergence of deep learning and formal mathematics has spurred research in formal verification. Statement autoformalization, a crucial first step in this process, aims to translate informal descriptions into machine-verifiable representations but remains a significant challenge. The core difficulty lies in the fact that existing methods often suffer from a lack of contextual awareness, leading to hallucination of formal definitions and theorems. Furthermore, current retrieval-augmented approaches exhibit poor precision and recall for formal library dependency retrieval, and lack the scalability to effectively leverage ever-growing public datasets. To bridge this gap, we propose a novel retrieval-augmented framework based on DDR (\textit{Direct Dependency Retrieval}) for statement autoformalization. Our DDR method directly generates candidate library dependencies from natural language mathematical descriptions and subsequently verifies their existence within the formal library via an efficient suffix array check. Leveraging this efficient search mechanism, we constructed a dependency retrieval dataset of over 500,000 samples and fine-tuned a high-precision DDR model. Experimental results demonstrate that our DDR model significantly outperforms SOTA methods in both retrieval precision and recall. Consequently, an autoformalizer equipped with DDR shows consistent performance advantages in both single-attempt accuracy and multi-attempt stability compared to models using traditional selection-based RAG methods.

cs.AI↗
arXiv2025

Every Activation Boosted: Scaling General Reasoner to 1 Trillion Open Language Foundation

We introduce Ling 2.0, a series reasoning-oriented language foundation built upon the principle that every activation boosts reasoning capability. Designed to scale from tens of billions to one trillion parameters under a unified Mixture-of-Experts (MoE) paradigm, Ling 2.0 emphasizes high sparsity, cross-scale consistency, and efficiency guided by empirical scaling laws. The series includes three non-thinking (instruct) models - Ling-mini-2.0, Ling-flash-2.0, and Ling-1T - ranging from 16B to 1T total parameters and achieving up to 7-fold active-compute efficiency compared with dense counterparts. Ling 2.0 integrates coordinated innovations across model architecture, pre-training, post-training, and infrastructure: a high-sparsity MoE with MTP for efficient reasoning, reasoning-oriented data and mid-training CoT activation, reinforcement-based fine-tuning (DFT, Evo-CoT), and full-scale FP8 training with fine-grained heterogeneous pipelines. At the trillion scale, Ling-1T establishes a new Pareto frontier of reasoning accuracy versus computational efficiency, demonstrating that sparse activation, when properly aligned with reasoning objectives, enables scalable and efficient intelligence. Collectively, Ling 2.0 provides a coherent, open, and efficient foundation for advancing future reasoning and thinking models, including the Ring series built upon the same base.

cs.CL↗
arXiv2025

Some results on minimum saturated graphs

Let $G$ be a graph and $\mathcal{F}$ be a family of graphs. We say a graph $G$ is $\mathcal{F}$-saturated if $G$ does not contain any member in $\mathcal{F}$ and for any $e\in E(\overline{G})$, $G+e$ creates a copy of some member in $ \mathcal{F}$. The saturation number of $\mathcal{F}$ is the minimum number of edges of an $\mathcal{F}$-saturated graphs with $n$ vertices, denoted by $\sat(n,\mathcal{F})$. If $\mathcal{F}=\{F\}$, then we write it as $\sat(n,F)$ for short. In this paper, we determine the exact value of $\sat(n,\{K_3,P_k\})$, and as its application, we obtain two bounds of $\sat(n,K_3\cup P_k)$ for $k\ge 10$ and sufficiently large $n$. Furthermore, $\sat(n,K_1\lor F)$ is determined, where $F$ is a linear forest without isolated vertices.

math.CO↗
arXiv2025

The Debate on RLVR Reasoning Capability Boundary: Shrinkage, Expansion, or Both? A Two-Stage Dynamic View

The ongoing debate on whether reinforcement learning with verifiable rewards (RLVR) expands or shrinks the reasoning capabilities of large language models (LLMs) remains unresolved. Some studies contend that RLVR mainly improves sampling efficiency but at the expense of diversity and exploratory capacity, resulting in capability boundary shrinkage. In contrast, others demonstrate that prolonged training can lead to the emergence of novel reasoning strategies, suggesting capability boundary expansion. To reconcile these contradictory findings, we theoretically and empirically show that both perspectives are partially valid-each aligning with a separate phase in an inherent two-stage probability mass dynamic: (1) Exploitation stage: initially, the model primarily samples explored high-reward and low-reward tokens, while rarely selecting the potentially optimal token. Positive advantage estimates increase the probability of high-reward tokens and decrease those of low-reward tokens, yet the optimal token's probability remains largely unchanged during this stage. (2) Exploration stage: as training advances, the growth rate of previously acquired high-reward tokens slows as their probabilities approach saturation. When a potentially optimal token-now receiving positive advantage estimates-is occasionally sampled, its probability increases, while those of the originally high-reward tokens decrease. This dynamic suggests that over-exploitation during the exploitation stage may lead to capability boundary shrinkage, whereas prolonged training into the exploration stage can promote an expansion of the reasoning capability boundary. Building upon our insights, we revisit the potential of only using relative negative gradients for prolonging training, providing a theoretical and empirical foundation for the development of more advanced reasoning capabilities.

cs.LG↗
arXiv2025

MASS: Mathematical Data Selection via Skill Graphs for Pretraining Large Language Models

High-quality data plays a critical role in the pretraining and fine-tuning of large language models (LLMs), even determining their performance ceiling to some degree. Consequently, numerous data selection methods have been proposed to identify subsets of data that can effectively and efficiently enhance model performance. However, most of these methods focus on general data selection and tend to overlook the specific nuances of domain-related data. In this paper, we introduce MASS, a \textbf{MA}thematical data \textbf{S}election framework using the \textbf{S}kill graph for pretraining LLMs in the mathematical reasoning domain. By taking into account the unique characteristics of mathematics and reasoning, we construct a skill graph that captures the mathematical skills and their interrelations from a reference dataset. This skill graph guides us in assigning quality scores to the target dataset, enabling us to select the top-ranked subset which is further used to pretrain LLMs. Experimental results demonstrate the efficiency and effectiveness of MASS across different model sizes (1B and 7B) and pretraining datasets (web data and synthetic data). Specifically, in terms of efficiency, models trained on subsets selected by MASS can achieve similar performance to models trained on the original datasets, with a significant reduction in the number of trained tokens - ranging from 50\% to 70\% fewer tokens. In terms of effectiveness, when trained on the same amount of tokens, models trained on the data selected by MASS outperform those trained on the original datasets by 3.3\% to 5.9\%. These results underscore the potential of MASS to improve both the efficiency and effectiveness of pretraining LLMs.

cs.CL↗
arXiv2025

Ring-lite: Scalable Reasoning via C3PO-Stabilized Reinforcement Learning for LLMs

We present Ring-lite, a Mixture-of-Experts (MoE)-based large language model optimized via reinforcement learning (RL) to achieve efficient and robust reasoning capabilities. Built upon the publicly available Ling-lite model, a 16.8 billion parameter model with 2.75 billion activated parameters, our approach matches the performance of state-of-the-art (SOTA) small-scale reasoning models on challenging benchmarks (e.g., AIME, LiveCodeBench, GPQA-Diamond) while activating only one-third of the parameters required by comparable models. To accomplish this, we introduce a joint training pipeline integrating distillation with RL, revealing undocumented challenges in MoE RL training. First, we identify optimization instability during RL training, and we propose Constrained Contextual Computation Policy Optimization(C3PO), a novel approach that enhances training stability and improves computational throughput via algorithm-system co-design methodology. Second, we empirically demonstrate that selecting distillation checkpoints based on entropy loss for RL training, rather than validation metrics, yields superior performance-efficiency trade-offs in subsequent RL training. Finally, we develop a two-stage training paradigm to harmonize multi-domain data integration, addressing domain conflicts that arise in training with mixed dataset. We will release the model, dataset, and code.

cs.CL↗
arXiv2025

SHARP: Synthesizing High-quality Aligned Reasoning Problems for Large Reasoning Models Reinforcement Learning

Training large reasoning models (LRMs) with reinforcement learning in STEM domains is hindered by the scarcity of high-quality, diverse, and verifiable problem sets. Existing synthesis methods, such as Chain-of-Thought prompting, often generate oversimplified or uncheckable data, limiting model advancement on complex tasks. To address these challenges, we introduce SHARP, a unified approach to Synthesizing High-quality Aligned Reasoning Problems for LRMs reinforcement learning with verifiable rewards (RLVR). SHARP encompasses a strategic set of self-alignment principles -- targeting graduate and Olympiad-level difficulty, rigorous logical consistency, and unambiguous, verifiable answers -- and a structured three-phase framework (Alignment, Instantiation, Inference) that ensures thematic diversity and fine-grained control over problem generation. We implement SHARP by leveraging a state-of-the-art LRM to infer and verify challenging STEM questions, then employ a reinforcement learning loop to refine the model's reasoning through verifiable reward signals. Experiments on benchmarks such as GPQA demonstrate that SHARP-augmented training substantially outperforms existing methods, markedly improving complex reasoning accuracy and pushing LRM performance closer to expert-level proficiency. Our contributions include the SHARP strategy, framework design, end-to-end implementation, and experimental evaluation of its effectiveness in elevating LRM reasoning capabilities.

cs.AI↗
arXiv2025

Every Sample Matters: Leveraging Mixture-of-Experts and High-Quality Data for Efficient and Accurate Code LLM

Recent advancements in code large language models (LLMs) have demonstrated remarkable capabilities in code generation and understanding. It is still challenging to build a code LLM with comprehensive performance yet ultimate efficiency. Many attempts have been released in the open source community to break the trade-off between performance and efficiency, such as the Qwen Coder series and the DeepSeek Coder series. This paper introduces yet another attempt in this area, namely Ling-Coder-Lite. We leverage the efficient Mixture-of-Experts (MoE) architecture along with a set of high-quality data curation methods (especially those based on program analytics) to build an efficient yet powerful code LLM. Ling-Coder-Lite exhibits on-par performance on 12 representative coding benchmarks compared to state-of-the-art models of similar size, such as Qwen2.5-Coder-7B and DeepSeek-Coder-V2-Lite, while offering competitive latency and throughput. In practice, we achieve a 50\% reduction in deployment resources compared to the similar-sized dense model without performance loss. To facilitate further research and development in this area, we open-source our models as well as a substantial portion of high-quality data for the annealing and post-training stages. The models and data can be accessed at~\url{https://huggingface.co/inclusionAI/Ling-Coder-lite}.

cs.LG↗
arXiv2025

The saturation number of W 4

For a fixed graph $H$, a graph $G$ is called $H$-saturated if $G$ does not contain $H$ as a (not necessarily induced) subgraph, but $G+e$ contains a copy of $H$ for any $e\in E(\overline{G})$. The saturation number of $H$, denoted by ${\rm sat}(n,H)$, is the minimum number of edges in an $n$-vertex $H$-saturated graph. A wheel $W_n$ is a graph obtained from a cycle of length $n$ by adding a new vertex and joining it to every vertex of the cycle. A well-known result of Erdős, Hajnal and Moon shows that ${\rm sat}(n,W_3)=2n-3$ for all $n\geq 4$ and $K_2\vee \overline{K_{n-2}}$ is the unique extremal graph, where $\vee$ denotes the graph join operation. In this paper, we study the saturation number of $W_4$. We prove that ${\rm sat}(n,W_4)=\lfloor\frac{5n-10}{2}\rfloor$ for all $n\geq 6$ and give a complete characterization of the extremal graphs.

math.CO↗
arXiv2025

Every FLOP Counts: Scaling a 300B Mixture-of-Experts LING LLM without Premium GPUs

In this technical report, we tackle the challenges of training large-scale Mixture of Experts (MoE) models, focusing on overcoming cost inefficiency and resource limitations prevalent in such systems. To address these issues, we present two differently sized MoE large language models (LLMs), namely Ling-Lite and Ling-Plus (referred to as "Bailing" in Chinese, spelled Bǎilíng in Pinyin). Ling-Lite contains 16.8 billion parameters with 2.75 billion activated parameters, while Ling-Plus boasts 290 billion parameters with 28.8 billion activated parameters. Both models exhibit comparable performance to leading industry benchmarks. This report offers actionable insights to improve the efficiency and accessibility of AI development in resource-constrained settings, promoting more scalable and sustainable technologies. Specifically, to reduce training costs for large-scale MoE models, we propose innovative methods for (1) optimization of model architecture and training processes, (2) refinement of training anomaly handling, and (3) enhancement of model evaluation efficiency. Additionally, leveraging high-quality data generated from knowledge graphs, our models demonstrate superior capabilities in tool use compared to other models. Ultimately, our experimental findings demonstrate that a 300B MoE LLM can be effectively trained on lower-performance devices while achieving comparable performance to models of a similar scale, including dense and MoE models. Compared to high-performance devices, utilizing a lower-specification hardware system during the pre-training phase demonstrates significant cost savings, reducing computing costs by approximately 20%. The models can be accessed at https://huggingface.co/inclusionAI.

cs.LG↗
arXiv2025

Complete minimal hypersurfaces in $\mathbb H^5$ with constant scalar curvature and zero Gauss-Kronecker curvature

We show that any complete minimal hypersurface in the five-dimensional hyperbolic space $\mathbb H^5$, endowed with constant scalar curvature and vanishing Gauss-Kronecker curvature, must be totally geodesic. Cheng-Peng [3] recently conjecture that any complete minimal hypersurface with constant scalar curvature in $\mathbb H^4$ is totally geodesic. Our result partially confirms this conjecture in five dimensional setting.

math.DG↗
arXiv2025

A Unified Invariant Learning Framework for Graph Classification

Invariant learning demonstrates substantial potential for enhancing the generalization of graph neural networks (GNNs) with out-of-distribution (OOD) data. It aims to recognize stable features in graph data for classification, based on the premise that these features causally determine the target label, and their influence is invariant to changes in distribution. Along this line, most studies have attempted to pinpoint these stable features by emphasizing explicit substructures in the graph, such as masked or attentive subgraphs, and primarily enforcing the invariance principle in the semantic space, i.e., graph representations. However, we argue that focusing only on the semantic space may not accurately identify these stable features. To address this, we introduce the Unified Invariant Learning (UIL) framework for graph classification. It provides a unified perspective on invariant graph learning, emphasizing both structural and semantic invariance principles to identify more robust stable features. In the graph space, UIL adheres to the structural invariance principle by reducing the distance between graphons over a set of stable features across different environments. Simultaneously, to confirm semantic invariance, UIL underscores that the acquired graph representations should demonstrate exemplary performance across diverse environments. We present both theoretical and empirical evidence to confirm our method's ability to recognize superior stable features. Moreover, through a series of comprehensive experiments complemented by in-depth analyses, we demonstrate that UIL considerably enhances OOD generalization, surpassing the performance of leading baseline methods. Our codes are available at https://github.com/yongduosui/UIL.

cs.LG↗
arXiv2024

Combining Incomplete Observational and Randomized Data for Heterogeneous Treatment Effects

Data from observational studies (OSs) is widely available and readily obtainable yet frequently contains confounding biases. On the other hand, data derived from randomized controlled trials (RCTs) helps to reduce these biases; however, it is expensive to gather, resulting in a tiny size of randomized data. For this reason, effectively fusing observational data and randomized data to better estimate heterogeneous treatment effects (HTEs) has gained increasing attention. However, existing methods for integrating observational data with randomized data must require \textit{complete} observational data, meaning that both treated subjects and untreated subjects must be included in OSs. This prerequisite confines the applicability of such methods to very specific situations, given that including all subjects, whether treated or untreated, in observational studies is not consistently achievable. In our paper, we propose a resilient approach to \textbf{C}ombine \textbf{I}ncomplete \textbf{O}bservational data and randomized data for HTE estimation, which we abbreviate as \textbf{CIO}. The CIO is capable of estimating HTEs efficiently regardless of the completeness of the observational data, be it full or partial. Concretely, a confounding bias function is first derived using the pseudo-experimental group from OSs, in conjunction with the pseudo-control group from RCTs, via an effect estimation procedure. This function is subsequently utilized as a corrective residual to rectify the observed outcomes of observational data during the HTE estimation by combining the available observational data and the all randomized data. To validate our approach, we have conducted experiments on a synthetic dataset and two semi-synthetic datasets.

stat.ME↗
arXiv2024

LLM-Guided Multi-View Hypergraph Learning for Human-Centric Explainable Recommendation

As personalized recommendation systems become vital in the age of information overload, traditional methods relying solely on historical user interactions often fail to fully capture the multifaceted nature of human interests. To enable more human-centric modeling of user preferences, this work proposes a novel explainable recommendation framework, i.e., LLMHG, synergizing the reasoning capabilities of large language models (LLMs) and the structural advantages of hypergraph neural networks. By effectively profiling and interpreting the nuances of individual user interests, our framework pioneers enhancements to recommendation systems with increased explainability. We validate that explicitly accounting for the intricacies of human preferences allows our human-centric and explainable LLMHG approach to consistently outperform conventional models across diverse real-world datasets. The proposed plug-and-play enhancement framework delivers immediate gains in recommendation performance while offering a pathway to apply advanced LLMs for better capturing the complexity of human interests across machine learning applications.

cs.IR↗
arXiv2024

A new characterization for Clifford hypersurfaces

For a closed minimal immersed hypersurface $M$ in $\mathbb S^{n+1}$ with second fundamental form $A$, and each integer $k\ge 2$, define a constant $σ_k=\dfrac{\int_M (|A|^2)^k}{|M|}$. We show that $σ_k \ge 2^k$ provided $n=2$ and $M$ is not totally geodesic. When $n=4$ and $M$ has two distinct principal curvatures, we show $σ_2 \ge 16$. When $n\ge 3$ and $M$ has two distinct principal curvatures, for each integer $k\ge 2$, there exists a positive constant $δ_k(n)<n$, if $|A|^2\ge δ_k(n)$, we have $σ_k\ge n^k$. All the equality holds iff $M$ is isometric to a Clifford hypersurface.

math.DG↗