Yunke Zhang

Bo Yu, Hechang Chen, Yunke Zhang et al.

Artificial intelligence-enabled histopathological data analysis has become a valuable assistant to the pathologist. However, existing models lack representation and inference abilities compared with those of pathologists, especially in cancer subtype diagnosis, which is unconvincing in clinical practice. For instance, pathologists typically observe the lesions of a slide from global to local, and then can give a diagnosis based on their knowledge and experience. In this paper, we propose a Data and Knowledge Co-driving (D&K) model to replicate the process of cancer subtype classification on a histopathological slide like a pathologist. Specifically, in the data-driven module, the bagging mechanism in ensemble learning is leveraged to integrate the histological features from various bags extracted by the embedding representation unit. Furthermore, a knowledge-driven module is established based on the Gestalt principle in psychology to build the three-dimensional (3D) expert knowledge space and map histological features into this space for metric. Then, the diagnosis can be made according to the Euclidean distance between them. Extensive experimental results on both public and in-house datasets demonstrate that the D&K model has a high performance and credible results compared with the state-of-the-art methods for diagnosing histopathological subtypes. Code: https://github.com/Dennis-YB/Data-and-Knowledge-Co-driving-for-Cancer-Subtypes-Classification

Yanxin Xi, Yu Liu, Tong Li et al.

Cities play an important role in achieving sustainable development goals (SDGs) to promote economic growth and meet social needs. Especially satellite imagery is a potential data source for studying sustainable urban development. However, a comprehensive dataset in the United States (U.S.) covering multiple cities, multiple years, multiple scales, and multiple indicators for SDG monitoring is lacking. To support the research on SDGs in U.S. cities, we develop a satellite imagery dataset using deep learning models for five SDGs containing 25 sustainable development indicators. The proposed dataset covers the 100 most populated U.S. cities and corresponding Census Block Groups from 2014 to 2023. Specifically, we collect satellite imagery and identify objects with state-of-the-art object detection and semantic segmentation models to observe cities' bird's-eye view. We further gather population, nighttime light, survey, and built environment data to depict SDGs regarding poverty, health, education, inequality, and living environment. We anticipate the dataset to help urban policymakers and researchers to advance SDGs-related studies, especially applying satellite imagery to monitor long-term and multi-scale SDGs in cities.

Fengli Xu, Qianyue Hao, Zefang Zong et al.

Language has long been conceived as an essential tool for human reasoning. The breakthrough of Large Language Models (LLMs) has sparked significant research interest in leveraging these models to tackle complex reasoning tasks. Researchers have moved beyond simple autoregressive token generation by introducing the concept of "thought" -- a sequence of tokens representing intermediate steps in the reasoning process. This innovative paradigm enables LLMs' to mimic complex human reasoning processes, such as tree search and reflective thinking. Recently, an emerging trend of learning to reason has applied reinforcement learning (RL) to train LLMs to master reasoning processes. This approach enables the automatic generation of high-quality reasoning trajectories through trial-and-error search algorithms, significantly expanding LLMs' reasoning capacity by providing substantially more training data. Furthermore, recent studies demonstrate that encouraging LLMs to "think" with more tokens during test-time inference can further significantly boost reasoning accuracy. Therefore, the train-time and test-time scaling combined to show a new research frontier -- a path toward Large Reasoning Model. The introduction of OpenAI's o1 series marks a significant milestone in this research direction. In this survey, we present a comprehensive review of recent progress in LLM reasoning. We begin by introducing the foundational background of LLMs and then explore the key technical components driving the development of large reasoning models, with a focus on automated data construction, learning-to-reason techniques, and test-time scaling. We also analyze popular open-source projects at building large reasoning models, and conclude with open challenges and future research directions.

Jingtao Ding, Yunke Zhang, Yu Shang et al.

The concept of world models has garnered significant attention due to advancements in multimodal large language models such as GPT-4 and video generation models such as Sora, which are central to the pursuit of artificial general intelligence. This survey offers a comprehensive review of the literature on world models. Generally, world models are regarded as tools for either understanding the present state of the world or predicting its future dynamics. This review presents a systematic categorization of world models, emphasizing two primary functions: (1) constructing internal representations to understand the mechanisms of the world, and (2) predicting future states to simulate and guide decision-making. Initially, we examine the current progress in these two categories. We then explore the application of world models in key domains, including generative games, autonomous driving, robotics, and social simulacra, with a focus on how each domain utilizes these aspects. Finally, we outline key challenges and provide insights into potential future research directions. We summarize the representative papers along with their code repositories in https://github.com/tsinghua-fib-lab/World-Model.

Dingwei Zhu, Zhiheng Xi, Shihan Dou et al.

Training reinforcement learning (RL) systems in real-world environments remains challenging due to noisy supervision and poor out-of-domain (OOD) generalization, especially in LLM post-training. Recent distributional RL methods improve robustness by modeling values with multiple quantile points, but they still learn each quantile independently as a scalar. This results in rough-grained value representations that lack fine-grained conditioning on state information, struggling under complex and OOD conditions. We propose DFPO (Distributional Value Flow Policy Optimization with Conditional Risk and Consistency Control), a robust distributional RL framework that models values as continuous flows across time steps. By scaling value modeling through learning of a value flow field instead of isolated quantile predictions, DFPO captures richer state information for more accurate advantage estimation. To stabilize training under noisy feedback, DFPO further integrates conditional risk control and consistency constraints along value flow trajectories. Experiments on dialogue, math reasoning, and scientific tasks show that DFPO outperforms PPO, FlowRL, and other robust baselines under noisy supervision, achieving improved training stability and generalization.

Dingwei Zhu, Zhiheng Xi, Shihan Dou et al.

Reinforcement learning (RL) has shown strong performance in LLM post-training, but real-world deployment often involves noisy or incomplete supervision. In such settings, complex and unreliable supervision signals can destabilize training and harm generalization. While existing approaches such as worst-case optimization (e.g., RFQI, CQL) and mean-based methods (e.g., PPO, GRPO) can improve stability, they often overlook generalization and may produce overly conservative policies, leading to uneven performance across diverse real scenarios. To this end, we introduce DVPO (Distributional Value Modeling with Risk-aware Policy Optimization), a new RL framework that combines conditional risk theory with distributional value modeling to better balance robustness and generalization. DVPO learns token-level value distributions to provide fine-grained supervision, and applies an asymmetric risk regularization to shape the distribution tails: it contracts the lower tail to dampen noisy negative deviations, while expanding the upper tail to preserve exploratory diversity. Across extensive experiments and analysis in multi-turn dialogue, math reasoning, and scientific QA, DVPO consistently outperforms PPO, GRPO, and robust Bellman-based PPO under noisy supervision, showing its potential for LLM post-training in the real-world.

Xuhui Ren, Shaokang Dong, Chen Yang et al.

The evolution of Large Language Models (LLMs) from passive text processors to autonomous agents has established planning as a core component of modern intelligence. However, achieving generalized planning remains elusive, not only by the scarcity of high-quality interaction data but also by inherent conflicts across heterogeneous planning tasks. These challenges result in models that excel at isolated tasks yet struggle to generalize, while existing multi-task training attempts suffer from gradient interference. In this paper, we present \textbf{MagicAgent}, a series of foundation models specifically designed for generalized agent planning. We introduce a lightweight and scalable synthetic data framework that generates high-quality trajectories across diverse planning tasks, including hierarchical task decomposition, tool-augmented planning, multi-constraint scheduling, procedural logic orchestration, and long-horizon tool execution. To mitigate training conflicts, we propose a two-stage training paradigm comprising supervised fine-tuning followed by multi-objective reinforcement learning over both static datasets and dynamic environments. Empirical results demonstrate that MagicAgent-32B and MagicAgent-30B-A3B deliver superior performance, achieving accuracies of $75.1\%$ on Worfbench, $55.9\%$ on NaturalPlan, $57.5\%$ on $τ^2$-Bench, $86.9\%$ on BFCL-v3, and $81.2\%$ on ACEBench, as well as strong results on our in-house MagicEval benchmarks. These results substantially outperform existing sub-100B models and even surpass leading closed-source models.

Liujian Tang, Shaokang Dong, Yijia Huang et al.

This paper presents MagicGUI, a foundational mobile GUI agent designed to address critical challenges in perception, grounding, and reasoning within real-world mobile GUI environments. The framework is underpinned by following six key components: (1) a comprehensive and accurate dataset, constructed via the scalable GUI Data Pipeline, which aggregates the largest and most diverse GUI-centric multimodal data to date from open-source repositories, automated crawling, and targeted manual annotation; (2) enhanced perception and grounding capabilities, facilitating fine-grained multimodal alignment for UI element referencing, grounding, and screen comprehension; (3) a comprehensive and unified action space, encompassing both fundamental UI operations and complex interactive intents to support human-agent interactions; (4) planning-oriented reasoning mechanisms that enable the model to decompose complex user instructions into sequential actions with explicit intermediate meta-paln reasoning; (5) an iterative two-stage training procedure, combining large-scale continue pre-training on 7.8M samples with reinforcement fine-tuning utilizing a spatially enhanced composite reward and dual filtering strategy; and (6) competitive performance on both the proprietary Magic-RICH benchmark and over a dozen public benchmarks, achieving superior performance across GUI perception and agent tasks, while demonstrating robust generalization and real-world deployment potential in practical mobile GUI scenarios, as detailed in Figure 1.

Qiannian Zhao, Chen Yang, Jinhao Jing et al.

Large reasoning models (LRMs) have emerged as a powerful paradigm for solving complex real-world tasks. In practice, these models are predominantly trained via Reinforcement Learning with Verifiable Rewards (RLVR), yet most existing outcome-only RLVR pipelines rely almost exclusively on a binary correctness signal and largely ignore the model's intrinsic uncertainty. We term this discrepancy the uncertainty-reward mismatch, under which high- and low-uncertainty solutions are treated equivalently, preventing the policy from "Know What You Know" and impeding the shift from optimizing for correct answers to optimizing effective reasoning paths. This limitation is especially critical in reasoning-centric tasks such as mathematics and question answering, where performance hinges on the quality of the model's internal reasoning process rather than mere memorization of final answers. To address this, we propose EGPO, a metacognitive entropy calibration framework that explicitly integrates intrinsic uncertainty into RLVR for enhancing LRMs. EGPO estimates per-sample uncertainty using a zero-overhead entropy proxy derived from token-level likelihoods and aligns it with extrinsic correctness through an asymmetric calibration mechanism that preserves correct reasoning while selectively regulating overconfident failures, thereby enabling stable and uncertainty-aware policy optimization. Moreover, EGPO recovers informative learning signals from otherwise degenerate group-based rollouts without modifying the verifier or reward definition. Extensive experiments across multiple benchmarks demonstrate that the proposed EGPO leads to substantial and consistent improvements in reasoning performance, establishing a principled path for advancing LRMs through metacognitive entropy calibration.

Jiazheng Zhang, Ziche Fu, Junrui Shen et al.

Policy entropy has emerged as a fundamental measure for understanding and controlling exploration in reinforcement learning with verifiable rewards (RLVR) for LLMs. However, existing entropy-aware methods mainly regulate entropy through global objectives, while the token-level mechanism by which sampled policy updates reshape policy entropy remains underexplored. In this work, we develop a theoretical framework of entropy mechanics in RLVR. Our analysis yields a first-order approximation of the entropy change, giving rise to entropy polarity, a signed token-level quantity that predicts how much a sampled update expands or contracts entropy. This analysis further reveals a structural asymmetry: reinforcing frequent high-probability tokens triggers contraction tendencies, whereas expansive tendencies typically require lower-probability samples or stronger distributional correction. Empirically, we show that entropy polarity reliably predicts entropy changes, and that positive and negative polarity branches play complementary roles in preserving exploration while strengthening exploitation. Building on these insights, we propose Polarity-Aware Policy Optimization (PAPO), which preserves both polarity branches and implements entropy control through advantage reweighting. With the empirical entropy trajectory as an online phase signal, PAPO adaptively reallocates optimization pressure between entropy-expanding and entropy-contracting updates. Experiments on mathematical reasoning and agentic benchmarks show that PAPO consistently outperforms competitive baselines, while delivering superior training efficiency and substantial reward improvements.

Yuming Yang, Wantong Zhao, Caishuang Huang et al.

Open Named Entity Recognition (NER), which involves identifying arbitrary types of entities from arbitrary domains, remains challenging for Large Language Models (LLMs). Recent studies suggest that fine-tuning LLMs on extensive NER data can boost their performance. However, training directly on existing datasets neglects their inconsistent entity definitions and redundant data, limiting LLMs to dataset-specific learning and hindering out-of-domain adaptation. To address this, we present B2NERD, a compact dataset designed to guide LLMs' generalization in Open NER under a universal entity taxonomy. B2NERD is refined from 54 existing English and Chinese datasets using a two-step process. First, we detect inconsistent entity definitions across datasets and clarify them by distinguishable label names to construct a universal taxonomy of 400+ entity types. Second, we address redundancy using a data pruning strategy that selects fewer samples with greater category and semantic diversity. Comprehensive evaluation shows that B2NERD significantly enhances LLMs' Open NER capabilities. Our B2NER models, trained on B2NERD, outperform GPT-4 by 6.8-12.0 F1 points and surpass previous methods in 3 out-of-domain benchmarks across 15 datasets and 6 languages. The data, models, and code are publicly available at https://github.com/UmeanNever/B2NER.

Tao Feng, Yunke Zhang, Xiaochen Fan et al.

To uncover the city's fundamental functioning mechanisms, it is important to acquire a deep understanding of complicated relationships among citizens, location, and mobility behaviors. Previous research studies have applied direct correlation analysis to investigate such relationships. Nevertheless, due to the ubiquitous confounding effects, empirical correlation analysis may not accurately reflect underlying causal relationships among basic urban elements. In this paper, we propose a novel urban causal computing framework to comprehensively explore causalities and confounding effects among a variety of factors across different types of urban elements. In particular, we design a reinforcement learning algorithm to discover the potential causal graph, which depicts the causal relations between urban factors. The causal graph further serves as the guidance for estimating causal effects between pair-wise urban factors by propensity score matching. After removing the confounding effects from correlations, we leverage significance levels of causal effects in downstream urban mobility prediction tasks. Experimental studies on open-source urban datasets show that the discovered causal graph demonstrates a hierarchical structure, where citizens affect locations, and they both cause changes in urban mobility behaviors. Experimental results in urban mobility prediction tasks further show that the proposed method can effectively reduce confounding effects and enhance performance of urban computing tasks.

Yunke Zhang, Chi Wang, Miaomiao Cui et al.

This paper proposes a novel deep learning-based video object matting method that can achieve temporally coherent matting results. Its key component is an attention-based temporal aggregation module that maximizes image matting networks' strength for video matting networks. This module computes temporal correlations for pixels adjacent to each other along the time axis in feature space, which is robust against motion noises. We also design a novel loss term to train the attention weights, which drastically boosts the video matting performance. Besides, we show how to effectively solve the trimap generation problem by fine-tuning a state-of-the-art video object segmentation network with a sparse set of user-annotated keyframes. To facilitate video matting and trimap generation networks' training, we construct a large-scale video matting dataset with 80 training and 28 validation foreground video clips with ground-truth alpha mattes. Experimental results show that our method can generate high-quality alpha mattes for various videos featuring appearance change, occlusion, and fast motion. Our code and dataset can be found at: https://github.com/yunkezhang/TCVOM

Jingtao Ding, Chang Liu, Yu Zheng et al. · tsinghua

Complex networks pervade various real-world systems, from the natural environment to human societies. The essence of these networks is in their ability to transition and evolve from microscopic disorder-where network topology and node dynamics intertwine-to a macroscopic order characterized by certain collective behaviors. Over the past two decades, complex network science has significantly enhanced our understanding of the statistical mechanics, structures, and dynamics underlying real-world networks. Despite these advancements, there remain considerable challenges in exploring more realistic systems and enhancing practical applications. The emergence of artificial intelligence (AI) technologies, coupled with the abundance of diverse real-world network data, has heralded a new era in complex network science research. This survey aims to systematically address the potential advantages of AI in overcoming the lingering challenges of complex network research. It endeavors to summarize the pivotal research problems and provide an exhaustive review of the corresponding methodologies and applications. Through this comprehensive survey-the first of its kind on AI for complex networks-we expect to provide valuable insights that will drive further research and advancement in this interdisciplinary field.

Jie Feng, Jinwei Zeng, Qingyue Long et al. · tsinghua

Over the past year, the development of large language models (LLMs) has brought spatial intelligence into focus, with much attention on vision-based embodied intelligence. However, spatial intelligence spans a broader range of disciplines and scales, from navigation and urban planning to remote sensing and earth science. What are the differences and connections between spatial intelligence across these fields? In this paper, we first review human spatial cognition and its implications for spatial intelligence in LLMs. We then examine spatial memory, knowledge representations, and abstract reasoning in LLMs, highlighting their roles and connections. Finally, we analyze spatial intelligence across scales -- from embodied to urban and global levels -- following a framework that progresses from spatial memory and understanding to spatial reasoning and intelligence. Through this survey, we aim to provide insights into interdisciplinary spatial intelligence research and inspire future studies.

Chenglu Pan, Xiaogang Xu, Ganggui Ding et al.

Restoring low-resolution text images presents a significant challenge, as it requires maintaining both the fidelity and stylistic realism of the text in restored images. Existing text image restoration methods often fall short in hard situations, as the traditional super-resolution models cannot guarantee clarity, while diffusion-based methods fail to maintain fidelity. In this paper, we introduce a novel framework aimed at improving the generalization ability of diffusion models for text image super-resolution (SR), especially promoting fidelity. First, we propose a progressive data sampling strategy that incorporates diverse image types at different stages of training, stabilizing the convergence and improving the generalization. For the network architecture, we leverage a pre-trained SR prior to provide robust spatial reasoning capabilities, enhancing the model's ability to preserve textual information. Additionally, we employ a cross-attention mechanism to better integrate textual priors. To further reduce errors in textual priors, we utilize confidence scores to dynamically adjust the importance of textual features during training. Extensive experiments on real-world datasets demonstrate that our approach not only produces text images with more realistic visual appearances but also improves the accuracy of text structure.

Dingwei Zhu, Shihan Dou, Zhiheng Xi et al.

Reinforcement Learning from Human Feedback (RLHF) often suffers from noisy or imperfect reward supervision in real-world settings, which undermines policy stability and generalization. Such noise may cause models to lose attention on key words during advantage estimation. While prior work focuses on reward denoising or filtering poor data, it often overlooks the critical role of the value model in policy optimization. In this work, we show that a strong value model is essential for mitigating noise by absorbing unstable signals and enabling more reliable advantage estimation. We propose VRPO, a value-centric framework for robust PPO training under noisy supervision. VRPO combines two core designs: (1) an auxiliary loss guided by entropy and perplexity from a frozen language model, and (2) a variational information bottleneck. These mechanisms enhance the value model's ability to filter out noise and capture key words from the context during advantage estimation, transforming it from a passive predictor into an active regulator of noise. Experiments on math reasoning, science QA, and multi-turn dialogue, under both rule-based and model-based noisy rewards, show that VRPO consistently outperforms PPO and GRPO baselines. Our findings underscore the often-overlooked importance of the value model in RLHF and offer a principled and practical approach to robust policy optimization in noisy real-world environments.

En Xu, Huandong Wang, Yunke Zhang et al.

Urban systems are typical examples of complex systems, where the integration of physics-based modeling with artificial intelligence (AI) presents a promising paradigm for enhancing predictive accuracy, interpretability, and decision-making. In this context, AI excels at capturing complex, nonlinear relationships, while physics-based models ensure consistency with real-world laws and provide interpretable insights. We provide a comprehensive review of physics-informed AI methods in urban applications. The proposed taxonomy categorizes existing approaches into three paradigms - Physics-Integrated AI, Physics-AI Hybrid Ensemble, and AI-Integrated Physics - and further details seven representative methods. This classification clarifies the varying degrees and directions of physics-AI integration, guiding the selection and development of appropriate methods based on application needs and data availability. We systematically examine their applications across eight key urban domains: energy, environment, economy, transportation, information, public services, emergency management, and the urban system as a whole. Our analysis highlights how these methodologies leverage physical laws and data-driven models to address urban challenges, enhancing system reliability, efficiency, and adaptability. By synthesizing existing methodologies and their urban applications, we identify critical gaps and outline future research directions, paving the way toward next-generation intelligent urban system modeling.

Tao Feng, Yunke Zhang, Huandong Wang et al.

Accurate origin-destination (OD) flow prediction is of great importance to developing cities, as it can contribute to optimize urban structures and layouts. However, with the common issues of missing regional features and lacking OD flow data, it is quite daunting to predict OD flow in developing cities. To address this challenge, we propose a novel Causality-Enhanced OD Flow Prediction (CE-OFP), a unified framework that aims to transfer urban knowledge between cities and achieve accuracy improvements in OD flow predictions across data-scarce cities. In specific, we propose a novel reinforcement learning model to discover universal causalities among urban features in data-rich cities and build corresponding causal graphs. Then, we further build Causality-Enhanced Variational Auto-Encoder (CE-VAE) to incorporate causal graphs for effective feature reconstruction in data-scarce cities. Finally, with the reconstructed features, we devise a knowledge distillation method with a graph attention network to migrate the OD prediction model from data-rich cities to data-scare cities. Extensive experiments on two pairs of real-world datasets validate that the proposed CE-OFP remarkably outperforms state-of-the-art baselines, which can reduce the RMSE of OD flow prediction for data-scarce cities by up to 11%.

Tong Xia, Jiankun Zhang, Ruiwen You et al.

Urban research aims to understand how cities operate and evolve as complex adaptive systems. With the rapid growth of urban data and analytical methodologies, the central challenge of the field has shifted from data availability to the integration of heterogeneous data into coherent, verifiable urban knowledge through multidisciplinary approaches. Recent advances in AI, particularly the emergence of large language models (LLMs), have enabled the development of AI scientists capable of autonomous reasoning, hypothesis generation, and data-driven experimentation, demonstrating substantial potential for autonomous urban research. However, most general-purpose AI systems remain misaligned with the domain-specific knowledge, methodological conventions, and inferential standards required in urban studies. Here, we introduce the AI Urban Scientist, a knowledge-driven multi-agent framework designed to support autonomous urban research. Grounded in hypotheses, peer-review feedback, datasets, and research methodologies distilled from large-scale prior studies, the system constructs structured domain knowledge that guides LLM-based agents to automatically generate hypotheses, identify and integrate multi-source urban datasets, conduct empirical analyses and simulations, and iteratively refine analytical methods. Through this process, the framework synthesizes new insights in urban science and accelerates the urban research lifecycle.

Yifei Cao, Changhao Jiang, Jiabao Zhuang et al.

Assessing the perceptual quality of synthetic speech is crucial for guiding the development and refinement of speech generation models. However, it has traditionally relied on human subjective ratings such as the Mean Opinion Score (MOS), which depend on manual annotations and often suffer from inconsistent rating standards and poor reproducibility. To address these limitations, we introduce MOS-RMBench, a unified benchmark that reformulates diverse MOS datasets into a preference-comparison setting, enabling rigorous evaluation across different datasets. Building on MOS-RMBench, we systematically construct and evaluate three paradigms for reward modeling: scalar reward models, semi-scalar reward models, and generative reward models (GRMs). Our experiments reveal three key findings: (1) scalar models achieve the strongest overall performance, consistently exceeding 74% accuracy; (2) most models perform considerably worse on synthetic speech than on human speech; and (3) all models struggle on pairs with very small MOS differences. To improve performance on these challenging pairs, we propose a MOS-aware GRM that incorporates an MOS-difference-based reward function, enabling the model to adaptively scale rewards according to the difficulty of each sample pair. Experimental results show that the MOS-aware GRM significantly improves fine-grained quality discrimination and narrows the gap with scalar models on the most challenging cases. We hope this work will establish both a benchmark and a methodological framework to foster more rigorous and scalable research in automatic speech quality assessment.

Daiye Miao, Yufang Liu, Jie Wang et al.

LoRA has become one of the most widely used parameter-efficient fine-tuning methods due to its simplicity and effectiveness. However, numerous studies have shown that LoRA often introduces substantial parameter redundancy, which not only increases the number of trainable parameters but also hinders the effectiveness of fine-tuning. Since identifying redundant parameters in LoRA is inherently difficult, how to eliminate them efficiently and accurately remains a challenging problem. In this paper, we propose TASO, a redundancy reduction method that leverages importance information from the pretrained model's weights to mitigate LoRA redundancy. Specifically, we estimate parameter importance on downstream tasks and identify task-specific core regions based on the distribution of importance scores. The location information of these core regions is then used to determine the sparse structure of LoRA modules, enabling redundancy removal before fine-tuning. Our approach significantly reduces the number of trainable parameters required for task adaptation, while providing a novel task-aligned perspective for LoRA redundancy reduction. Experimental results demonstrate that, with a parameter budget comparable to LoRA with rank $r = 1$, TASO consistently outperforms standard LoRA across multiple tasks, achieving strong fine-tuning performance while effectively eliminating redundant parameters.

Xiaoran Fan, Zhichao Sun, Yangfan Gao et al.

Speech-language models (SLMs) offer a promising path toward unifying speech and text understanding and generation. However, challenges remain in achieving effective cross-modal alignment and high-quality speech generation. In this work, we systematically investigate the role of speech tokenizer designs in LLM-centric SLMs, augmented by speech heads and speaker modeling. We compare coupled, semi-decoupled, and fully decoupled speech tokenizers under a fair SLM framework and find that decoupled tokenization significantly improves alignment and synthesis quality. To address the information density mismatch between speech and text, we introduce multi-token prediction (MTP) into SLMs, enabling each hidden state to decode multiple speech tokens. This leads to up to 12$\times$ faster decoding and a substantial drop in word error rate (from 6.07 to 3.01). Furthermore, we propose a speaker-aware generation paradigm and introduce RoleTriviaQA, a large-scale role-playing knowledge QA benchmark with diverse speaker identities. Experiments demonstrate that our methods enhance both knowledge understanding and speaker consistency.

Tao Feng, Yunke Zhang, Huandong Wang et al.

User consumption behavior data, which records individuals' online spending history at various types of stores, has been widely used in various applications, such as store recommendation, site selection, and sale forecasting. However, its high worth is limited due to deficiencies in data comprehensiveness and changes of application scenarios. Thus, generating high-quality sequential consumption data by simulating complex user consumption behaviors is of great importance to real-world applications. Two branches of existing sequence generation methods are both limited in quality. Model-based methods with simplified assumptions fail to model the complex decision process of user consumption, while data-driven methods that emulate real-world data are prone to noises, unobserved behaviors, and dynamic decision space. In this work, we propose to enhance the fidelity and trustworthiness of the data-driven Generative Adversarial Imitation Learning (GAIL) method by blending it with the Exploration and Preferential Return EPR model . The core idea of our EPR-GAIL framework is to model user consumption behaviors as a complex EPR decision process, which consists of purchase, exploration, and preference decisions. Specifically, we design the hierarchical policy function in the generator as a realization of the EPR decision process and employ the probability distributions of the EPR model to guide the reward function in the discriminator. Extensive experiments on two real-world datasets of user consumption behaviors on an online platform demonstrate that the EPR-GAIL framework outperforms the best state-of-the-art baseline by over 19\% in terms of data fidelity. Furthermore, the generated consumption behavior data can improve the performance of sale prediction and location recommendation by up to 35.29% and 11.19%, respectively, validating its advantage for practical applications.

Chi Wang, Yunke Zhang, Miaomiao Cui et al.

This paper proposes a novel active boundary loss for semantic segmentation. It can progressively encourage the alignment between predicted boundaries and ground-truth boundaries during end-to-end training, which is not explicitly enforced in commonly used cross-entropy loss. Based on the predicted boundaries detected from the segmentation results using current network parameters, we formulate the boundary alignment problem as a differentiable direction vector prediction problem to guide the movement of predicted boundaries in each iteration. Our loss is model-agnostic and can be plugged in to the training of segmentation networks to improve the boundary details. Experimental results show that training with the active boundary loss can effectively improve the boundary F-score and mean Intersection-over-Union on challenging image and video object segmentation datasets.