arXiv subjects

Zonglin Yang

Publications and source records attributed to Zonglin Yang.

36 records · Page 2Linked to original sources

arXiv2025

MiroMind-M1: An Open-Source Advancement in Mathematical Reasoning via Context-Aware Multi-Stage Policy Optimization

Large language models have recently evolved from fluent text generation to advanced reasoning across diverse domains, giving rise to reasoning language models. Among these domains, mathematical reasoning serves as a representative benchmark as it requires precise multi-step logic and abstract reasoning, which can be generalized to other tasks. While closed-source RLMs such as GPT-o3 demonstrate impressive reasoning capabilities, their proprietary nature limits transparency and reproducibility. Although many open-source projects aim to close this gap, most of them lack sufficient openness by omitting critical resources such as datasets and detailed training configurations, which hinders reproducibility. To contribute toward greater transparency in RLM development, we introduce the MiroMind-M1 series, a set of fully open-source RLMs built on the Qwen-2.5 backbone that match or exceed the performance of existing open-source RLMs. Specifically, our models are trained in two stages: SFT on a carefully curated corpus of 719K math-reasoning problems with verified CoT trajectories, followed by RLVR on 62K challenging and verifiable problems. To enhance the robustness and efficiency of the RLVR process, we introduce Context-Aware Multi-Stage Policy Optimization, an algorithm that integrates length-progressive training with an adaptive repetition penalty to encourage context-aware RL training. Our model achieves state-of-the-art or competitive performance and superior token efficiency among Qwen-2.5-based open-source 7B and 32B models on the AIME24, AIME25, and MATH benchmarks. To facilitate reproducibility, we release the complete stack: models (MiroMind-M1-SFT-7B, MiroMind-M1-RL-7B, MiroMind-M1-RL-32B); datasets (MiroMind-M1-SFT-719K, MiroMind-M1-RL-62K); and all training and evaluation configurations. We hope these resources will support further research and foster community advancement.

cs.CL↗

arXiv2025

Optimization of Low-Latency Spiking Neural Networks Utilizing Historical Dynamics of Refractory Periods

The refractory period controls neuron spike firing rate, crucial for network stability and noise resistance. With advancements in spiking neural network (SNN) training methods, low-latency SNN applications have expanded. In low-latency SNNs, shorter simulation steps render traditional refractory mechanisms, which rely on empirical distributions or spike firing rates, less effective. However, omitting the refractory period amplifies the risk of neuron over-activation and reduces the system's robustness to noise. To address this challenge, we propose a historical dynamic refractory period (HDRP) model that leverages membrane potential derivative with historical refractory periods to estimate an initial refractory period and dynamically adjust its duration. Additionally, we propose a threshold-dependent refractory kernel to mitigate excessive neuron state accumulation. Our approach retains the binary characteristics of SNNs while enhancing both noise resistance and overall performance. Experimental results show that HDRP-SNN significantly reduces redundant spikes compared to traditional SNNs, and achieves state-of-the-art (SOTA) accuracy both on static datasets and neuromorphic datasets. Moreover, HDRP-SNN outperforms artificial neural networks (ANNs) and traditional SNNs in noise resistance, highlighting the crucial role of the HDRP mechanism in enhancing the performance of low-latency SNNs.

cs.NE↗

arXiv2025

Accelerating RLHF Training with Reward Variance Increase

Reinforcement learning from human feedback (RLHF) is an essential technique for ensuring that large language models (LLMs) are aligned with human values and preferences during the post-training phase. As an effective RLHF approach, group relative policy optimization (GRPO) has demonstrated success in many LLM-based applications. However, efficient GRPO-based RLHF training remains a challenge. Recent studies reveal that a higher reward variance of the initial policy model leads to faster RLHF training. Inspired by this finding, we propose a practical reward adjustment model to accelerate RLHF training by provably increasing the reward variance and preserving the relative preferences and reward expectation. Our reward adjustment method inherently poses a nonconvex optimization problem, which is NP-hard to solve in general. To overcome the computational challenges, we design a novel $O(n \log n)$ algorithm to find a global solution of the nonconvex reward adjustment model by explicitly characterizing the extreme points of the feasible set. As an important application, we naturally integrate this reward adjustment model into the GRPO algorithm, leading to a more efficient GRPO with reward variance increase (GRPOVI) algorithm for RLHF training. As an interesting byproduct, we provide an indirect explanation for the empirical effectiveness of GRPO with rule-based reward for RLHF training, as demonstrated in DeepSeek-R1. Experiment results demonstrate that the GRPOVI algorithm can significantly improve the RLHF training efficiency compared to the original GRPO algorithm.

cs.LG↗

arXiv2025

Harnessing Large Language Models for Scientific Novelty Detection

In an era of exponential scientific growth, identifying novel research ideas is crucial and challenging in academia. Despite potential, the lack of an appropriate benchmark dataset hinders the research of novelty detection. More importantly, simply adopting existing NLP technologies, e.g., retrieving and then cross-checking, is not a one-size-fits-all solution due to the gap between textual similarity and idea conception. In this paper, we propose to harness large language models (LLMs) for scientific novelty detection (ND), associated with two new datasets in marketing and NLP domains. To construct the considerate datasets for ND, we propose to extract closure sets of papers based on their relationship, and then summarize their main ideas based on LLMs. To capture idea conception, we propose to train a lightweight retriever by distilling the idea-level knowledge from LLMs to align ideas with similar conception, enabling efficient and accurate idea retrieval for LLM novelty detection. Experiments show our method consistently outperforms others on the proposed benchmark datasets for idea retrieval and ND tasks. Codes and data are available at https://anonymous.4open.science/r/NoveltyDetection-10FB/.

cs.CL↗

arXiv2025

Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoning

Vision-language models (VLMs) have shown remarkable advancements in multimodal reasoning tasks. However, they still often generate inaccurate or irrelevant responses due to issues like hallucinated image understandings or unrefined reasoning paths. To address these challenges, we introduce Critic-V, a novel framework inspired by the Actor-Critic paradigm to boost the reasoning capability of VLMs. This framework decouples the reasoning process and critic process by integrating two independent components: the Reasoner, which generates reasoning paths based on visual and textual inputs, and the Critic, which provides constructive critique to refine these paths. In this approach, the Reasoner generates reasoning responses according to text prompts, which can evolve iteratively as a policy based on feedback from the Critic. This interaction process was theoretically driven by a reinforcement learning framework where the Critic offers natural language critiques instead of scalar rewards, enabling more nuanced feedback to boost the Reasoner's capability on complex reasoning tasks. The Critic model is trained using Direct Preference Optimization (DPO), leveraging a preference dataset of critiques ranked by Rule-based Reward~(RBR) to enhance its critic capabilities. Evaluation results show that the Critic-V framework significantly outperforms existing methods, including GPT-4V, on 5 out of 8 benchmarks, especially regarding reasoning accuracy and efficiency. Combining a dynamic text-based policy for the Reasoner and constructive feedback from the preference-optimized Critic enables a more reliable and context-sensitive multimodal reasoning process. Our approach provides a promising solution to enhance the reliability of VLMs, improving their performance in real-world reasoning-heavy multimodal applications such as autonomous driving and embodied intelligence.

cs.CV↗

arXiv2025

LLM4SR: A Survey on Large Language Models for Scientific Research

In recent years, the rapid advancement of Large Language Models (LLMs) has transformed the landscape of scientific research, offering unprecedented support across various stages of the research cycle. This paper presents the first systematic survey dedicated to exploring how LLMs are revolutionizing the scientific research process. We analyze the unique roles LLMs play across four critical stages of research: hypothesis discovery, experiment planning and implementation, scientific writing, and peer reviewing. Our review comprehensively showcases the task-specific methodologies and evaluation benchmarks. By identifying current challenges and proposing future research directions, this survey not only highlights the transformative potential of LLMs, but also aims to inspire and guide researchers and practitioners in leveraging LLMs to advance scientific inquiry. Resources are available at the following repository: https://github.com/du-nlp-lab/LLM4SR

cs.CL↗

arXiv2024

Large Language Models for Automated Open-domain Scientific Hypotheses Discovery

Hypothetical induction is recognized as the main reasoning type when scientists make observations about the world and try to propose hypotheses to explain those observations. Past research on hypothetical induction is under a constrained setting: (1) the observation annotations in the dataset are carefully manually handpicked sentences (resulting in a close-domain setting); and (2) the ground truth hypotheses are mostly commonsense knowledge, making the task less challenging. In this work, we tackle these problems by proposing the first dataset for social science academic hypotheses discovery, with the final goal to create systems that automatically generate valid, novel, and helpful scientific hypotheses, given only a pile of raw web corpus. Unlike previous settings, the new dataset requires (1) using open-domain data (raw web corpus) as observations; and (2) proposing hypotheses even new to humanity. A multi-module framework is developed for the task, including three different feedback mechanisms to boost performance, which exhibits superior performance in terms of both GPT-4 based and expert-based evaluation. To the best of our knowledge, this is the first work showing that LLMs are able to generate novel (''not existing in literature'') and valid (''reflecting reality'') scientific hypotheses.

cs.CL↗

arXiv2024

Enhancing ASIC Technology Mapping via Parallel Supergate Computing

With the development of large-scale integrated circuits, electronic design automation~(EDA) tools are increasingly emphasizing efficiency, with parallel algorithms becoming a trend. The optimization of delay reduction is a crucial factor for ASIC technology mapping, and supergate technology proves to be an effective method for achieving this in EDA tools flow. However, we have observed that increasing the number of generated supergates can reduce delay, but this comes at the cost of an exponential increase in computation time. In this paper, we propose a parallel supergate computing method that addresses the tradeoff between time-consuming and delay optimization. The proposed method utilizes the input-constrained supergate pattern to parallelly generate the supergate candidates, and then filter the valid supergates as the results. Experiment results show the efficiency of the proposed method, for example, it can attain the improvement of 4x speedup in computation time and 10.1 in delay reduction with 32 threads.

cs.DC↗

arXiv2024

Parallel AIG Refactoring via Conflict Breaking

Algorithm parallelization to leverage multi-core platforms for improving the efficiency of Electronic Design Automation~(EDA) tools plays a significant role in enhancing the scalability of Integrated Circuit (IC) designs. Logic optimization is a key process in the EDA design flow to reduce the area and depth of the circuit graph by finding logically equivalent graphs for substitution, which is typically time-consuming. To address these challenges, in this paper, we first analyze two types of conflicts that need to be handled in the parallelization framework of refactoring And-Inverter Graph~(AIG). We then present a fine-grained parallel AIG refactoring method, which strikes a balance between the degree of parallelism and the conflicts encountered during the refactoring operations. Experiment results show that our parallel refactor is 28x averagely faster than the sequential algorithm on large benchmark tests with 64 physical CPU cores, and has comparable optimization quality.

cs.DC↗

arXiv2024

Logical Reasoning over Natural Language as Knowledge Representation: A Survey

Logical reasoning is central to human cognition and intelligence. It includes deductive, inductive, and abductive reasoning. Past research of logical reasoning within AI uses formal language as knowledge representation and symbolic reasoners. However, reasoning with formal language has proved challenging (e.g., brittleness and knowledge-acquisition bottleneck). This paper provides a comprehensive overview on a new paradigm of logical reasoning, which uses natural language as knowledge representation and pretrained language models as reasoners, including philosophical definition and categorization of logical reasoning, advantages of the new paradigm, benchmarks and methods, challenges of the new paradigm, possible future directions, and relation to related NLP fields. This new paradigm is promising since it not only alleviates many challenges of formal representation but also has advantages over end-to-end neural methods. This survey focus on transformer-based LLMs explicitly working on deductive, inductive, and abductive reasoning over English representation.

cs.CL↗

arXiv2024

Language Models as Inductive Reasoners

Inductive reasoning is a core component of human intelligence. In the past research of inductive reasoning within computer science, formal language is used as representations of knowledge (facts and rules, more specifically). However, formal language can cause systematic problems for inductive reasoning such as disability of handling raw input such as natural language, sensitiveness to mislabeled data, and incapacity to handle ambiguous input. To this end, we propose a new paradigm (task) for inductive reasoning, which is to induce natural language rules from natural language facts, and create a dataset termed DEER containing 1.2k rule-fact pairs for the task, where rules and facts are written in natural language. New automatic metrics are also proposed and analysed for the evaluation of this task. With DEER, we investigate a modern approach for inductive reasoning where we use natural language as representation for knowledge instead of formal language and use pretrained language models as ''reasoners''. Moreover, we provide the first and comprehensive analysis of how well pretrained language models can induce natural language rules from natural language facts. We also propose a new framework drawing insights from philosophy literature for this task, which we show in the experiment section that surpasses baselines in both automatic and human evaluations. We discuss about our future perspectives for inductive reasoning in Section 7. Dataset and code are available at https://github.com/ZonglinY/Inductive_Reasoning.

cs.CL↗

arXiv2023

Adaptive Reconvergence-driven AIG Rewriting via Strategy Learning

Rewriting is a common procedure in logic synthesis aimed at improving the performance, power, and area (PPA) of circuits. The traditional reconvergence-driven And-Inverter Graph (AIG) rewriting method focuses solely on optimizing the reconvergence cone through Boolean algebra minimization. However, there exist opportunities to incorporate other node-rewriting algorithms that are better suited for specific cones. In this paper, we propose an adaptive reconvergence-driven AIG rewriting algorithm that combines two key techniques: multi-strategy-based AIG rewriting and strategy learning-based algorithm selection. The multi-strategy-based rewriting method expands upon the traditional approach by incorporating support for multi-node-rewriting algorithms, thus expanding the optimization space. Additionally, the strategy learning-based algorithm selection method determines the most suitable node-rewriting algorithm for a given cone. Experimental results demonstrate that our proposed method yields a significant average improvement of 5.567\% in size and 5.327\% in depth.

cs.AI↗

arXiv2023

MEC: An Open-source Fine-grained Mapping Equivalence Checking Tool for FPGA

Technology mapping is an essential step in EDA flow. However, the function of the circuit may be changed after technology mapping, and equivalence checking (EC) based verification is highly necessary. The traditional EC method has significant time and resource constraints, making it only feasible to carry out at a coarse-grained level. To make it efficient for technology mapping, we propose a fine-grained method called MEC, which leverages a combination of two approaches to significantly reduce the time cost of verification. The local block verification approach performs fast verification and the global graph cover approach guarantees correctness. The proposed method is rigorously tested and compared to three EC tools, and the results show that MEC technique offers a substantial improvement in speed. MEC not only offers a faster and more efficient way of performing EC on technology mapping but also opens up new opportunities for more fine-grained verification in the future.

cs.AR↗

arXiv2023

A Survey on Semantic Processing Techniques

Semantic processing is a fundamental research domain in computational linguistics. In the era of powerful pre-trained language models and large language models, the advancement of research in this domain appears to be decelerating. However, the study of semantics is multi-dimensional in linguistics. The research depth and breadth of computational semantic processing can be largely improved with new technologies. In this survey, we analyzed five semantic processing tasks, e.g., word sense disambiguation, anaphora resolution, named entity recognition, concept extraction, and subjectivity detection. We study relevant theoretical research in these fields, advanced methods, and downstream applications. We connect the surveyed tasks with downstream applications because this may inspire future scholars to fuse these low-level semantic processing tasks with high-level natural language processing tasks. The review of theoretical research may also inspire new tasks and technologies in the semantic processing domain. Finally, we compare the different semantic processing techniques and summarize their technical trends, application trends, and future directions.

cs.CL↗

arXiv2023

Finding the Pillars of Strength for Multi-Head Attention

Recent studies have revealed some issues of Multi-Head Attention (MHA), e.g., redundancy and over-parameterization. Specifically, the heads of MHA were originally designed to attend to information from different representation subspaces, whereas prior studies found that some attention heads likely learn similar features and can be pruned without harming performance. Inspired by the minimum-redundancy feature selection, we assume that focusing on the most representative and distinctive features with minimum resources can mitigate the above issues and lead to more effective and efficient MHAs. In particular, we propose Grouped Head Attention, trained with a self-supervised group constraint that group attention heads, where each group focuses on an essential but distinctive feature subset. We additionally propose a Voting-to-Stay procedure to remove redundant heads, thus achieving a transformer with lighter weights. Moreover, our method achieves significant performance gains on three well-established tasks while considerably compressing parameters.

cs.LG↗

arXiv2023

iEDA: An Open-Source Intelligent Physical Implementation Toolkit and Library

Open-source EDA shows promising potential in unleashing EDA innovation and lowering the cost of chip design. This paper presents an open-source EDA project, iEDA, aiming for building a basic infrastructure for EDA technology evolution and closing the industrial-academic gap in the EDA area. iEDA now covers the whole flow of physical design (including Floorplan, Placement, CTS, Routing, Timing Optimization etc.), and part of the analysis tools (Static Timing Analysis and Power Analysis). To demonstrate the effectiveness of iEDA, we implement and tape out three chips of different scales (from 700k to 1.5M gates) on different process nodes (110nm and 28nm) with iEDA. iEDA is publicly available from the project home page http://ieda.oscc.cc.

cs.AR↗

arXiv2020

Improving Event Duration Prediction via Time-aware Pre-training

End-to-end models in NLP rarely encode external world knowledge about length of time. We introduce two effective models for duration prediction, which incorporate external knowledge by reading temporal-related news sentences (time-aware pre-training). Specifically, one model predicts the range/unit where the duration value falls in (R-pred); and the other predicts the exact duration value E-pred. Our best model -- E-pred, substantially outperforms previous work, and captures duration information more accurately than R-pred. We also demonstrate our models are capable of duration prediction in the unsupervised setting, outperforming the baselines.

cs.CL↗

arXiv2019

Reducing the dilution: An analysis of the information sensitiveness of capsule network with a practical improvement method

Capsule network has shown various advantages over convolutional neural network (CNN). It keeps more precise spatial information than CNN and uses equivariance instead of invariance during inference and highly potential to be a new effective tool for visual tasks. However, the current capsule networks have incompatible performance with CNN when facing datasets with background and complex target objects and are lacking in universal and efficient regularization method. We analyze a main reason of the incompatible performance as the conflict between information sensitiveness of capsule network and unreasonably higher activation value distribution of capsules in primary capsule layer. Correspondingly, we propose a practical improvement method by restraining the activation value of capsules in primary capsule layer to suppress non-informative capsules and highlight discriminative capsules. In the experiments, the method has achieved better performances on various mainstream datasets. In addition, the proposed improvement methods can be seen as a suitable, simple and efficient regularization method that can be generally used in capsule network.

cs.LG↗