Kexin Yang

An Yang, Baosong Yang, Binyuan Hui et al.

This report introduces the Qwen2 series, the latest addition to our large language models and large multimodal models. We release a comprehensive suite of foundational and instruction-tuned language models, encompassing a parameter range from 0.5 to 72 billion, featuring dense models and a Mixture-of-Experts model. Qwen2 surpasses most prior open-weight models, including its predecessor Qwen1.5, and exhibits competitive performance relative to proprietary models across diverse benchmarks on language understanding, generation, multilingual proficiency, coding, mathematics, and reasoning. The flagship model, Qwen2-72B, showcases remarkable performance: 84.2 on MMLU, 37.9 on GPQA, 64.6 on HumanEval, 89.5 on GSM8K, and 82.4 on BBH as a base language model. The instruction-tuned variant, Qwen2-72B-Instruct, attains 9.1 on MT-Bench, 48.1 on Arena-Hard, and 35.7 on LiveCodeBench. Moreover, Qwen2 demonstrates robust multilingual capabilities, proficient in approximately 30 languages, spanning English, Chinese, Spanish, French, German, Arabic, Russian, Korean, Japanese, Thai, Vietnamese, and more, underscoring its versatility and global reach. To foster community innovation and accessibility, we have made the Qwen2 model weights openly available on Hugging Face and ModelScope, and the supplementary materials including example code on GitHub. These platforms also include resources for quantization, fine-tuning, and deployment, facilitating a wide range of applications and research endeavors.

Mingfeng Xue, Dayiheng Liu, Kexin Yang et al. · tsinghua

The emergence of large language models (LLMs) has revolutionized natural language processing tasks. However, existing instruction-tuning datasets suffer from occupational bias: the majority of data relates to only a few occupations, which hampers the instruction-tuned LLMs to generate helpful responses to professional queries from practitioners in specific fields. To mitigate this issue and promote occupation-inclusive LLMs, we create an instruction-tuning dataset named \emph{OccuQuest}, which contains 110,000+ prompt-completion pairs and 30,000+ dialogues covering over 1,000 occupations in 26 occupational categories. We systematically request ChatGPT, organizing queries hierarchically based on Occupation, Responsibility, Topic, and Question, to ensure a comprehensive coverage of occupational specialty inquiries. By comparing with three commonly used datasets (Dolly, ShareGPT, and WizardLM), we observe that OccuQuest exhibits a more balanced distribution across occupations. Furthermore, we assemble three test sets for comprehensive evaluation, an occu-test set covering 25 occupational categories, an estate set focusing on real estate, and an occu-quora set containing real-world questions from Quora. We then fine-tune LLaMA on OccuQuest to obtain OccuLLaMA, which significantly outperforms state-of-the-art LLaMA variants (Vicuna, Tulu, and WizardLM) on professional questions in GPT-4 and human evaluations. Notably, on the occu-quora set, OccuLLaMA reaches a high win rate of 86.4\% against WizardLM.

Yuzhen Shi, Huanghai Liu, Yiran Hu et al.

As large language models (LLMs) are increasingly applied to legal domain-specific tasks, evaluating their ability to perform legal work in real-world settings has become essential. However, existing legal benchmarks rely on simplified and highly standardized tasks, failing to capture the ambiguity, complexity, and reasoning demands of real legal practice. Moreover, prior evaluations often adopt coarse, single-dimensional metrics and do not explicitly assess fine-grained legal reasoning. To address these limitations, we introduce PLawBench, a Practical Law Benchmark designed to evaluate LLMs in realistic legal practice scenarios. Grounded in real-world legal workflows, PLawBench models the core processes of legal practitioners through three task categories: public legal consultation, practical case analysis, and legal document generation. These tasks assess a model's ability to identify legal issues and key facts, perform structured legal reasoning, and generate legally coherent documents. PLawBench comprises 850 questions across 13 practical legal scenarios, with each question accompanied by expert-designed evaluation rubrics, resulting in approximately 12,500 rubric items for fine-grained assessment. Using an LLM-based evaluator aligned with human expert judgments, we evaluate 10 state-of-the-art LLMs. Experimental results show that none achieves strong performance on PLawBench, revealing substantial limitations in the fine-grained legal reasoning capabilities of current LLMs and highlighting important directions for future evaluation and development of legal LLMs. Data is available at: https://github.com/skylenage/PLawbench.

Kexin Yang, Dayiheng Liu, Wenqiang Lei et al.

Attribute-based Controlled Text Generation (CTG) refers to generating sentences that satisfy desirable attributes (e.g., emotions and topics). Existing works often utilize fine-tuning or resort to extra attribute classifiers, yet suffer from storage and inference time increases. To address these concerns, we explore attribute-based CTG in a prompt-based manner. In short, the proposed Tailor represents each attribute as a pre-trained continuous vector (i.e., single-attribute prompt) and guides the generation of a fixed PLM switch to a pre-specified attribute. We experimentally find that these prompts can be simply concatenated as a whole to multi-attribute CTG without any re-training, yet raises problems of fluency decrease and position sensitivity. To this end, Tailor provides a multi-attribute prompt mask and a re-indexing position-ids sequence to bridge the gap between the training (one prompt for each task) and testing stage (concatenating more than one prompt). To further enhance such single-attribute prompt combinations, Tailor also introduces a trainable prompt connector, which can be concatenated with any two single-attribute prompts to multi-attribute text generation. Experiments on 11 attribute-specific generation tasks demonstrate strong performances of Tailor on both single-attribute and multi-attribute CTG, with 0.08\% training parameters of a GPT-2.

Ce Chi, Xing Wang, Zhendong Wang et al.

In this work, we present JT-DA-8B (JiuTian Data Analyst 8B), a specialized large language model designed for complex table reasoning tasks across diverse real-world scenarios. To address the lack of high-quality supervision in tabular reasoning scenarios, we construct a comprehensive and diverse training corpus with 34 well-defined table reasoning tasks, by aggregating 29 public table QA datasets and 3 million tables. An automatic pipeline is proposed to generate realistic multi-step analytical tasks involving reasoning patterns. The model is trained upon open-source JT-Coder-8B model, an 8B-parameter decoder-only foundation model trained from scratch. In the training stage, we leverage LLM-based scoring and workflow-aligned filtering to distill high-quality, table-centric data. Both supervised fine-tuning (SFT) and Reinforcement learning (RL) are adopted to optimize our model. Afterwards, a four-stage table reasoning workflow is proposed, including table preprocessing, table sensing, tool-integrated reasoning, and prompt engineering, to improve model interpretability and execution accuracy. Experimental results show that JT-DA-8B achieves strong performance in various table reasoning tasks, demonstrating the effectiveness of data-centric generation and workflow-driven optimization.

Shoujin Huang, Guanxiong Luo, Yunlin Zhao et al.

Simultaneous multislice (SMS) imaging is a powerful technique for accelerating magnetic resonance imaging (MRI) acquisitions. However, SMS reconstruction remains challenging due to complex signal interactions between and within the excited slices. In this study, we introduce ROGER, a robust SMS MRI reconstruction method based on deep generative priors. Utilizing denoising diffusion probabilistic models (DDPM), ROGER begins with Gaussian noise and gradually recovers individual slices through reverse diffusion iterations while enforcing data consistency from measured k-space data within the readout concatenation framework. The posterior sampling procedure is designed such that the DDPM training can be performed on single-slice images without requiring modifications for SMS tasks. Additionally, our method incorporates a low-frequency enhancement (LFE) module to address the practical issue that SMS-accelerated fast spin echo (FSE) and echo planar imaging (EPI) sequences cannot easily embed fully-sampled autocalibration signals. Extensive experiments on both retrospectively and prospectively accelerated datasets demonstrate that ROGER consistently outperforms existing methods, enhancing both anatomical and functional imaging with strong out-of-distribution generalization. The source code and sample data for ROGER are available at https://github.com/Solor-pikachu/ROGER.

Xing Wang, Kexin Yang, Zhendong Wang et al.

Cellular traffic prediction is an indispensable part for intelligent telecommunication networks. Nevertheless, due to the frequent user mobility and complex network scheduling mechanisms, cellular traffic often inherits complicated spatial-temporal patterns, making the prediction incredibly challenging. Although recent advanced algorithms such as graph-based prediction approaches have been proposed, they frequently model spatial dependencies based on static or dynamic graphs and neglect the coexisting multiple spatial correlations induced by traffic generation. Meanwhile, some works lack the consideration of the diverse cellular traffic patterns, result in suboptimal prediction results. In this paper, we propose a novel deep learning network architecture, Adaptive Hybrid Spatial-Temporal Graph Neural Network (AHSTGNN), to tackle the cellular traffic prediction problem. First, we apply adaptive hybrid graph learning to learn the compound spatial correlations among cell towers. Second, we implement a Temporal Convolution Module with multi-periodic temporal data input to capture the nonlinear temporal dependencies. In addition, we introduce an extra Spatial-Temporal Adaptive Module to conquer the heterogeneity lying in cell towers. Our experiments on two real-world cellular traffic datasets show AHSTGNN outperforms the state-of-the-art by a significant margin, illustrating the superior scalability of our method for spatial-temporal cellular traffic prediction.

An Yang, Bowen Yu, Chengyuan Li et al.

We introduce Qwen2.5-1M, a series of models that extend the context length to 1 million tokens. Compared to the previous 128K version, the Qwen2.5-1M series have significantly enhanced long-context capabilities through long-context pre-training and post-training. Key techniques such as long data synthesis, progressive pre-training, and multi-stage supervised fine-tuning are employed to effectively enhance long-context performance while reducing training costs. To promote the use of long-context models among a broader user base, we present and open-source our inference framework. This framework includes a length extrapolation method that can expand the model context lengths by at least four times, or even more, without additional training. To reduce inference costs, we implement a sparse attention method along with chunked prefill optimization for deployment scenarios and a sparsity refinement method to improve precision. Additionally, we detail our optimizations in the inference engine, including kernel optimization, pipeline parallelism, and scheduling optimization, which significantly enhance overall inference performance. By leveraging our inference framework, the Qwen2.5-1M models achieve a remarkable 3x to 7x prefill speedup in scenarios with 1 million tokens of context. This framework provides an efficient and powerful solution for developing applications that require long-context processing using open-source models. The Qwen2.5-1M series currently includes the open-source models Qwen2.5-7B-Instruct-1M and Qwen2.5-14B-Instruct-1M, as well as the API-accessed model Qwen2.5-Turbo. Evaluations show that Qwen2.5-1M models have been greatly improved in long-context tasks without compromising performance in short-context scenarios. Specifically, the Qwen2.5-14B-Instruct-1M model significantly outperforms GPT-4o-mini in long-context tasks and supports contexts eight times longer.

Xing Wang, Zhendong Wang, Kexin Yang et al.

Long-term time series forecasting plays an important role in various real-world scenarios. Recent deep learning methods for long-term series forecasting tend to capture the intricate patterns of time series by decomposition-based or sampling-based methods. However, most of the extracted patterns may include unpredictable noise and lack good interpretability. Moreover, the multivariate series forecasting methods usually ignore the individual characteristics of each variate, which may affecting the prediction accuracy. To capture the intrinsic patterns of time series, we propose a novel deep learning network architecture, named Multi-resolution Periodic Pattern Network (MPPN), for long-term series forecasting. We first construct context-aware multi-resolution semantic units of time series and employ multi-periodic pattern mining to capture the key patterns of time series. Then, we propose a channel adaptive module to capture the perceptions of multivariate towards different patterns. In addition, we present an entropy-based method for evaluating the predictability of time series and providing an upper bound on the prediction accuracy before forecasting. Our experimental evaluation on nine real-world benchmarks demonstrated that MPPN significantly outperforms the state-of-the-art Transformer-based, decomposition-based and sampling-based methods for long-term series forecasting.

Kexin Yang, Dayiheng Liu, Wenqiang Lei et al.

Product description generation is a challenging and under-explored task. Most such work takes a set of product attributes as inputs then generates a description from scratch in a single pass. However, this widespread paradigm might be limited when facing the dynamic wishes of users on constraining the description, such as deleting or adding the content of a user-specified attribute based on the previous version. To address this challenge, we explore a new draft-command-edit manner in description generation, leading to the proposed new task-controllable text editing in E-commerce. More specifically, we allow systems to receive a command (deleting or adding) from the user and then generate a description by flexibly modifying the content based on the previous version. It is easier and more practical to meet the new needs by modifying previous versions than generating from scratch. Furthermore, we design a data augmentation method to remedy the low resource challenge in this task, which contains a model-based and a rule-based strategy to imitate the edit by humans. To accompany this new task, we present a human-written draft-command-edit dataset called E-cEdits and a new metric "Attribute Edit". Our experimental results show that using the new data augmentation method outperforms baselines to a greater extent in both automatic and human evaluations.

Shaobo Wang, Xuan Ouyang, Tianyi Xu et al.

As high-quality public text approaches exhaustion, a phenomenon known as the Data Wall, pre-training is shifting from more tokens to better tokens. However, existing methods either rely on heuristic static filters that ignore training dynamics, or use dynamic yet optimizer-agnostic criteria based on raw gradients. We propose OPUS (Optimizer-induced Projected Utility Selection), a dynamic data selection framework that defines utility in the optimizer-induced update space. OPUS scores candidates by projecting their effective updates, shaped by modern optimizers, onto a target direction derived from a stable, in-distribution proxy. To ensure scalability, we employ Ghost technique with CountSketch for computational efficiency, and Boltzmann sampling for data diversity, incurring only 4.7\% additional compute overhead. OPUS achieves remarkable results across diverse corpora, quality tiers, optimizers, and model scales. In pre-training of GPT-2 Large/XL on FineWeb and FineWeb-Edu with 30B tokens, OPUS outperforms industrial-level baselines and even full 200B-token training. Moreover, when combined with industrial-level static filters, OPUS further improves pre-training efficiency, even with lower-quality data. Furthermore, in continued pre-training of Qwen3-8B-Base on SciencePedia, OPUS achieves superior performance using only 0.5B tokens compared to full training with 3B tokens, demonstrating significant data efficiency gains in specialized domains.

An Yang, Anfeng Li, Baosong Yang et al. · tsinghua

In this work, we present Qwen3, the latest version of the Qwen model family. Qwen3 comprises a series of large language models (LLMs) designed to advance performance, efficiency, and multilingual capabilities. The Qwen3 series includes models of both dense and Mixture-of-Expert (MoE) architectures, with parameter scales ranging from 0.6 to 235 billion. A key innovation in Qwen3 is the integration of thinking mode (for complex, multi-step reasoning) and non-thinking mode (for rapid, context-driven responses) into a unified framework. This eliminates the need to switch between different models--such as chat-optimized models (e.g., GPT-4o) and dedicated reasoning models (e.g., QwQ-32B)--and enables dynamic mode switching based on user queries or chat templates. Meanwhile, Qwen3 introduces a thinking budget mechanism, allowing users to allocate computational resources adaptively during inference, thereby balancing latency and performance based on task complexity. Moreover, by leveraging the knowledge from the flagship models, we significantly reduce the computational resources required to build smaller-scale models, while ensuring their highly competitive performance. Empirical evaluations demonstrate that Qwen3 achieves state-of-the-art results across diverse benchmarks, including tasks in code generation, mathematical reasoning, agent tasks, etc., competitive against larger MoE models and proprietary models. Compared to its predecessor Qwen2.5, Qwen3 expands multilingual support from 29 to 119 languages and dialects, enhancing global accessibility through improved cross-lingual understanding and generation capabilities. To facilitate reproducibility and community-driven research and development, all Qwen3 models are publicly accessible under Apache 2.0.

Qwen, An Yang, Baosong Yang et al.

In this report, we introduce Qwen2.5, a comprehensive series of large language models (LLMs) designed to meet diverse needs. Compared to previous iterations, Qwen 2.5 has been significantly improved during both the pre-training and post-training stages. In terms of pre-training, we have scaled the high-quality pre-training datasets from the previous 7 trillion tokens to 18 trillion tokens. This provides a strong foundation for common sense, expert knowledge, and reasoning capabilities. In terms of post-training, we implement intricate supervised finetuning with over 1 million samples, as well as multistage reinforcement learning. Post-training techniques enhance human preference, and notably improve long text generation, structural data analysis, and instruction following. To handle diverse and varied use cases effectively, we present Qwen2.5 LLM series in rich sizes. Open-weight offerings include base and instruction-tuned models, with quantized versions available. In addition, for hosted solutions, the proprietary models currently include two mixture-of-experts (MoE) variants: Qwen2.5-Turbo and Qwen2.5-Plus, both available from Alibaba Cloud Model Studio. Qwen2.5 has demonstrated top-tier performance on a wide range of benchmarks evaluating language understanding, reasoning, mathematics, coding, human preference alignment, etc. Specifically, the open-weight flagship Qwen2.5-72B-Instruct outperforms a number of open and proprietary models and demonstrates competitive performance to the state-of-the-art open-weight model, Llama-3-405B-Instruct, which is around 5 times larger. Qwen2.5-Turbo and Qwen2.5-Plus offer superior cost-effectiveness while performing competitively against GPT-4o-mini and GPT-4o respectively. Additionally, as the foundation, Qwen2.5 models have been instrumental in training specialized models such as Qwen2.5-Math, Qwen2.5-Coder, QwQ, and multimodal models.

Yufa Zhou, Shaobo Wang, Xingyu Dong et al.

Directly training Large Language Models (LLMs) for Multi-Agent Systems (MAS) remains challenging due to intricate reward modeling, dynamic agent interactions, and demanding generalization requirements. This paper explores whether post-training techniques, specifically Supervised Fine-Tuning (SFT) and Reinforcement Learning with Verifiable Rewards (RLVR), can effectively $\textit{generalize}$ to multi-agent scenarios. We use economic reasoning as a testbed, leveraging its strong foundations in mathematics and game theory, its demand for structured analytical reasoning, and its relevance to real-world applications such as market design, resource allocation, and policy analysis. We introduce $\textbf{Recon}$ ($\textbf{R}$easoning like an $\textbf{ECON}$omist), a 7B-parameter open-source LLM post-trained on a hand-curated dataset of 2,100 high-quality economic reasoning problems. Comprehensive evaluation on economic reasoning benchmarks and multi-agent games reveals clear improvements in structured reasoning and economic rationality. These results underscore the promise of domain-aligned post-training for enhancing reasoning and agent alignment, shedding light on the roles of SFT and RL in shaping model behavior. Code is available at https://github.com/MasterZhou1/Recon .

Xiaoyuan Li, Yubo Ma, Kexin Yang et al.

The performance of Large Language Models (LLMs) on downstream tasks is fundamentally constrained by the capabilities acquired during pre-training. However, traditional benchmarks like MMLU often fail to reflect a base model's plasticity in complex open-ended scenarios, leading to inefficient model selection. We address this by introducing a new task of predicting post-training potential - forecasting a base model's performance before post-training. We propose RuDE (Rubric-based Discriminative Evaluation), a unified framework that bypasses the generation gap of base models by leveraging response discrimination. Guided by our systematic 4C Taxonomy, RuDE constructs controlled contrastive pairs across diverse domains by fine-grained rubric violations. Extensive experiments demonstrate a correlation greater than 90% with post-training performance. Crucially, validation via Reinforcement Learning (RL) confirms that RuDE effectively identifies high-potential smaller models that outperform larger counterparts, offering a compute-efficient mechanism for foundation model development.

Ce Li, Xiaofan Liu, Zhiyan Song et al.

The majority of data in businesses and industries is stored in tables, databases, and data warehouses. Reasoning with table-structured data poses significant challenges for large language models (LLMs) due to its hidden semantics, inherent complexity, and structured nature. One of these challenges is lacking an effective evaluation benchmark fairly reflecting the performances of LLMs on broad table reasoning abilities. In this paper, we fill in this gap, presenting a comprehensive table reasoning evolution benchmark, TReB, which measures both shallow table understanding abilities and deep table reasoning abilities, a total of 26 sub-tasks. We construct a high quality dataset through an iterative data processing procedure. We create an evaluation framework to robustly measure table reasoning capabilities with three distinct inference modes, TCoT, PoT and ICoT. Further, we benchmark over 20 state-of-the-art LLMs using this frame work and prove its effectiveness. Experimental results reveal that existing LLMs still have significant room for improvement in addressing the complex and real world Table related tasks. Both the dataset and evaluation framework are publicly available, with the dataset hosted on huggingface.co/datasets/JT-LM/JIUTIAN-TReB and the framework on github.com/JT-LM/jiutian-treb.

Conrad Borchers, Lijin Zhang, Kexin Yang et al.

Adaptive learning systems can produce substantial learning gains, yet many students engage for too brief or too superficial a period to benefit. A central obstacle is measuring effort. Effort during multi-step problem solving is rarely directly observed, and common log-based proxies, such as time on task, cannot distinguish between a student working carefully and a student encountering a harder problem. We examine step-to-step response time as a scalable effort signal by modeling trait-like differences in students' typical response timing during tutoring (while adjusting for skill difficulty). Using step-level logs from eight classroom deployments of algebra tutoring systems (2020 to 2023) across six U.S. schools (794 students), we estimate student- and knowledge-component-level propensities using hierarchical models and relate them to learning efficiency, defined as performance improvement per completed solution step. Response-time propensities show moderate to strong stability within students, supporting their use as an individual differences measure beyond correctness. At the same time, their relationship to learning is not uniform but conditional on the learner and context. Slower propensities predict greater learning efficiency for higher-proficiency students, consistent with constructive processing, whereas for lower-proficiency students, slower propensities are weakly related or even negative, consistent with unproductive struggle or idling. These associations are strongest early in practice sequences and attenuate later in the class period, highlighting an actionable window for detecting emerging disengagement and low persistence. Overall, response-time propensities provide a practical way to incorporate temporal process data into learner models and to target adaptive supports when effort is most diagnostic.

Xiang Zheng, Han Li, Wenjie Luo et al.

Large language models (LLMs) are increasingly applied to health management, showing promise across disease prevention, clinical decision-making, and long-term care. However, existing medical benchmarks remain largely static and task-isolated, failing to capture the openness, longitudinal structure, and safety-critical complexity of real-world clinical workflows. We introduce ClinConsensus, a Chinese medical benchmark curated, validated, and quality-controlled by clinical experts. ClinConsensus comprises 2500 open-ended cases spanning the full continuum of care--from prevention and intervention to long-term follow-up--covering 36 medical specialties, 12 common clinical task types, and progressively increasing levels of complexity. To enable reliable evaluation of such complex scenarios, we adopt a rubric-based grading protocol and propose the Clinically Applicable Consistency Score (CACS@k). We further introduce a dual-judge evaluation framework, combining a high-capability LLM-as-judge with a distilled, locally deployable judge model trained via supervised fine-tuning, enabling scalable and reproducible evaluation aligned with physician judgment. Using ClinConsensus, we conduct a comprehensive assessment of several leading LLMs and reveal substantial heterogeneity across task themes, care stages, and medical specialties. While top-performing models achieve comparable overall scores, they differ markedly in reasoning, evidence use, and longitudinal follow-up capabilities, and clinically actionable treatment planning remains a key bottleneck. We release ClinConsensus as an extensible benchmark to support the development and evaluation of medical LLMs that are robust, clinically grounded, and ready for real-world deployment.

Ru Peng, Kexin Yang, Yawen Zeng et al.

The performance emergence of large language models (LLMs) driven by data scaling laws makes the selection of pre-training data increasingly important. However, existing methods rely on limited heuristics and human intuition, lacking comprehensive and clear guidelines. To address this, we are inspired by ``reverse thinking'' -- prompting LLMs to self-identify which criteria benefit its performance. As its pre-training capabilities are related to perplexity (PPL), we derive 14 quality criteria from the causes of text perplexity anomalies and introduce 15 common application domains to support domain mixing. In this paper, we train a Data Manager (DataMan) to learn quality ratings and domain recognition from pointwise rating, and use it to annotate a 447B token pre-training corpus with 14 quality ratings and domain type. Our experiments validate our approach, using DataMan to select 30B tokens to train a 1.3B-parameter language model, demonstrating significant improvements in in-context learning (ICL), perplexity, and instruction-following ability over the state-of-the-art baseline. The best-performing model, based on the Overall Score l=5 surpasses a model trained with 50% more data using uniform sampling. We continue pre-training with high-rated, domain-specific data annotated by DataMan to enhance domain-specific ICL performance and thus verify DataMan's domain mixing ability. Our findings emphasize the importance of quality ranking, the complementary nature of quality criteria, and their low correlation with perplexity, analyzing misalignment between PPL and ICL performance. We also thoroughly analyzed our pre-training dataset, examining its composition, the distribution of quality ratings, and the original document sources.

Ce Chi, Xing Wang, Kexin Yang et al.

Transformer has become one of the most popular architectures for multivariate time series (MTS) forecasting. Recent Transformer-based MTS models generally prefer channel-independent structures with the observation that channel independence can alleviate noise and distribution drift issues, leading to more robustness. Nevertheless, it is essential to note that channel dependency remains an inherent characteristic of MTS, carrying valuable information. Designing a model that incorporates merits of both channel-independent and channel-mixing structures is a key to further improvement of MTS forecasting, which poses a challenging conundrum. To address the problem, an injection method for global information into channel-independent Transformer, InjectTST, is proposed in this paper. Instead of designing a channel-mixing model directly, we retain the channel-independent backbone and gradually inject global information into individual channels in a selective way. A channel identifier, a global mixing module and a self-contextual attention module are devised in InjectTST. The channel identifier can help Transformer distinguish channels for better representation. The global mixing module produces cross-channel global information. Through the self-contextual attention module, the independent channels can selectively concentrate on useful global information without robustness degradation, and channel mixing is achieved implicitly. Experiments indicate that InjectTST can achieve stable improvement compared with state-of-the-art models.

Shaobo Wang, Cong Wang, Wenjie Fu et al.

As the demand for comprehensive evaluations of diverse model capabilities steadily increases, benchmark suites have correspondingly grown significantly in scale. Despite notable advances in redundancy reduction and subset-level performance prediction, a systematic framework that effectively integrates these methods to ensure both prediction accuracy and ranking consistency is still largely elusive. In this paper, we first perform a sample-level analysis of benchmark redundancy and identify several highly similar samples that can be eliminated. Besides, we frame benchmark compression as an optimization problem with the aim of score reconstruction. Building on these, we then propose EssenceBench, a coarse-to-fine framework utilizing an iterative Genetic Algorithm (GA), which takes the advantages of fitness-based subset search and attribution-based sample search. Compared to previous methods, our approach yields superior compression results with lower reconstruction error and markedly higher efficiency. In particular, on the HellaSwag benchmark (10K samples), our method preserves the ranking of all models shifting within 5% using 25x fewer samples, and achieves 95% ranking preservation shifting within 5% using only 200x fewer samples.

M-A-P Team, Xinrun Du, Yifan Yao et al.

Large language models (LLMs) have demonstrated remarkable proficiency in mainstream academic disciplines such as mathematics, physics, and computer science. However, human knowledge encompasses over 200 specialized disciplines, far exceeding the scope of existing benchmarks. The capabilities of LLMs in many of these specialized fields-particularly in light industry, agriculture, and service-oriented disciplines-remain inadequately evaluated. To address this gap, we present SuperGPQA, a comprehensive benchmark that evaluates graduate-level knowledge and reasoning capabilities across 285 disciplines. Our benchmark employs a novel Human-LLM collaborative filtering mechanism to eliminate trivial or ambiguous questions through iterative refinement based on both LLM responses and expert feedback. Our experimental results reveal significant room for improvement in the performance of current state-of-the-art LLMs across diverse knowledge domains (e.g., the reasoning-focused model DeepSeek-R1 achieved the highest accuracy of 61.82% on SuperGPQA), highlighting the considerable gap between current model capabilities and artificial general intelligence. Additionally, we present comprehensive insights from our management of a large-scale annotation process, involving over 80 expert annotators and an interactive Human-LLM collaborative system, offering valuable methodological guidance for future research initiatives of comparable scope.

Zekun Wang, Ge Zhang, Kexin Yang et al.

Interactive Natural Language Processing (iNLP) has emerged as a novel paradigm within the field of NLP, aimed at addressing limitations in existing frameworks while aligning with the ultimate goals of artificial intelligence. This paradigm considers language models as agents capable of observing, acting, and receiving feedback iteratively from external entities. Specifically, language models in this context can: (1) interact with humans for better understanding and addressing user needs, personalizing responses, aligning with human values, and improving the overall user experience; (2) interact with knowledge bases for enriching language representations with factual knowledge, enhancing the contextual relevance of responses, and dynamically leveraging external information to generate more accurate and informed responses; (3) interact with models and tools for effectively decomposing and addressing complex tasks, leveraging specialized expertise for specific subtasks, and fostering the simulation of social behaviors; and (4) interact with environments for learning grounded representations of language, and effectively tackling embodied tasks such as reasoning, planning, and decision-making in response to environmental observations. This paper offers a comprehensive survey of iNLP, starting by proposing a unified definition and framework of the concept. We then provide a systematic classification of iNLP, dissecting its various components, including interactive objects, interaction interfaces, and interaction methods. We proceed to delve into the evaluation methodologies used in the field, explore its diverse applications, scrutinize its ethical and safety issues, and discuss prospective research directions. This survey serves as an entry point for researchers who are interested in this rapidly evolving area and offers a broad view of the current landscape and future trajectory of iNLP.

Luyao Yuan, Zipeng Fu, Linqi Zhou et al.

Currently, in the study of multiagent systems, the intentions of agents are usually ignored. Nonetheless, as pointed out by Theory of Mind (ToM), people regularly reason about other's mental states, including beliefs, goals, and intentions, to obtain performance advantage in competition, cooperation or coalition. However, due to its intrinsic recursion and intractable modeling of distribution over belief, integrating ToM in multiagent planning and decision making is still a challenge. In this paper, we incorporate ToM in multiagent partially observable Markov decision process (POMDP) and propose an adaptive training algorithm to develop effective collaboration between agents with ToM. We evaluate our algorithms with two games, where our algorithm surpasses all previous decentralized execution algorithms without modeling ToM.

Kexin Yang, Xiaofei Zhou, Iulian Radu

Recently, the HCI community has seen an increased interest in applying Virtual Reality (VR), AugmentedReality (AR) and Mixed Reality (MR) into educational settings. Despite many literature reviews, there stilllacks a clear framework that reveals the different design dimensions in educational Extended Reality (XR)systems. Addressing this gap, we synthesize a broad range of educational XR to propose the XR-Ed framework,which reveals design space in six dimensions (Physical Accessibility, Scenario, Social Interactivity, Agency,Virtuality Degree, Assessment). Within each dimension, we contextualize the framework using existing designcases. Based on the XR-Ed Design framework, we incorporated instructional design approaches to proposeXR-Ins, an instruction-oriented, step-by-step guideline in educational XR instruction design. Jointly, they aimto support practitioners by revealing implicit design choices, offering design inspirations as well as guide themto design instructional activities for XR technologies in a more instruction-oriented and learner-centered way.

Huishuang Tian, Kexin Yang, Dayiheng Liu et al.

Ancient Chinese is the essence of Chinese culture. There are several natural language processing tasks of ancient Chinese domain, such as ancient-modern Chinese translation, poem generation, and couplet generation. Previous studies usually use the supervised models which deeply rely on parallel data. However, it is difficult to obtain large-scale parallel data of ancient Chinese. In order to make full use of the more easily available monolingual ancient Chinese corpora, we release AnchiBERT, a pre-trained language model based on the architecture of BERT, which is trained on large-scale ancient Chinese corpora. We evaluate AnchiBERT on both language understanding and generation tasks, including poem classification, ancient-modern Chinese translation, poem generation, and couplet generation. The experimental results show that AnchiBERT outperforms BERT as well as the non-pretrained models and achieves state-of-the-art results in all cases.

Dayiheng Liu, Jiancheng Lv, Kexin Yang et al.

Ancient Chinese brings the wisdom and spirit culture of the Chinese nation. Automatic translation from ancient Chinese to modern Chinese helps to inherit and carry forward the quintessence of the ancients. However, the lack of large-scale parallel corpus limits the study of machine translation in Ancient-Modern Chinese. In this paper, we propose an Ancient-Modern Chinese clause alignment approach based on the characteristics of these two languages. This method combines both lexical-based information and statistical-based information, which achieves 94.2 F1-score on our manual annotation Test set. We use this method to create a new large-scale Ancient-Modern Chinese parallel corpus which contains 1.24M bilingual pairs. To our best knowledge, this is the first large high-quality Ancient-Modern Chinese dataset. Furthermore, we analyzed and compared the performance of the SMT and various NMT models on this dataset and provided a strong baseline for this task.