Xinyue Yang

Xiao Liu, Tianjie Zhang, Yu Gu et al. · cmu, microsoft-research

Large Multimodal Models (LMMs) have ushered in a new era in artificial intelligence, merging capabilities in both language and vision to form highly capable Visual Foundation Agents. These agents are postulated to excel across a myriad of tasks, potentially approaching general artificial intelligence. However, existing benchmarks fail to sufficiently challenge or showcase the full potential of LMMs in complex, real-world environments. To address this gap, we introduce VisualAgentBench (VAB), a comprehensive and pioneering benchmark specifically designed to train and evaluate LMMs as visual foundation agents across diverse scenarios, including Embodied, Graphical User Interface, and Visual Design, with tasks formulated to probe the depth of LMMs' understanding and interaction capabilities. Through rigorous testing across nine proprietary LMM APIs and eight open models, we demonstrate the considerable yet still developing agent capabilities of these models. Additionally, VAB constructs a trajectory training set constructed through hybrid methods including Program-based Solvers, LMM Agent Bootstrapping, and Human Demonstrations, promoting substantial performance improvements in LMMs through behavior cloning. Our work not only aims to benchmark existing models but also provides a solid foundation for future development into visual foundation agents. Code, train \& test data, and part of fine-tuned open LMMs are available at \url{https://github.com/THUDM/VisualAgentBench}.

Yu Zhang, Xinyue Yang, Dongming Wang et al.

Ultra-reliable low-latency communication (uRLLC) is a pivotal enabler for B5G/6G networks, yet it faces severe challenges from rare but critical extreme events, which are characterized by heavy tails in the delay distribution. While the cell-free radio access network (CF-RAN) architecture offers essential spatial diversity to combat these uncertainties, conventional user-centric clustering designs typically focus on average metrics, thereby inadequately addressing such tail behaviors. We propose a novel, tail-risk-aware, user-centric clustering framework operating within the finite blocklength (FBL) regime. Our approach employs extreme value theory (EVT), specifically the peaks-over-threshold (POT) model, to accurately quantify the probability of queue latency violations. This framework is applied to formulate an energy efficiency (EE) maximization problem under strict tail latency constraints. The problem is solved via an efficient online algorithm that integrates Lyapunov optimization with successive convex approximation (SCA). Simulation results demonstrate that the proposed scheme, through its dynamic adaptation of cluster formation to mitigate tail risks, achieves a superior reliability-efficiency trade-off and leads to a significant suppression of extreme latency events.

Tianxin Xie, Wentao Lei, Guanjie Huang et al.

Text-to-audio-video (T2AV) generation underpins a wide range of applications demanding realistic audio-visual content, including virtual reality, world modeling, gaming, and filmmaking. However, existing T2AV models remain incapable of generating physically plausible sounds, primarily due to their limited understanding of physical principles. To situate current research progress, we present PhyAVBench, a challenging audio physics-sensitivity benchmark designed to systematically evaluate the audio physics grounding capabilities of existing T2AV models. PhyAVBench comprises 1,000 groups of paired text prompts with controlled physical variables that implicitly induce sound variations, enabling a fine-grained assessment of models' sensitivity to changes in underlying acoustic conditions. We term this evaluation paradigm the Audio-Physics Sensitivity Test (APST). Unlike prior benchmarks that primarily focus on audio-video synchronization, PhyAVBench explicitly evaluates models' understanding of the physical mechanisms underlying sound generation, covering 6 major audio physics dimensions, 4 daily scenarios (music, sound effects, speech, and their mix), and 50 fine-grained test points, ranging from fundamental aspects such as sound diffraction to more complex phenomena, e.g., Helmholtz resonance. Each test point consists of multiple groups of paired prompts, where each prompt is grounded by at least 20 newly recorded or collected real-world videos, thereby minimizing the risk of data leakage during model pre-training. Both prompts and videos are iteratively refined through rigorous human-involved error correction and quality control to ensure high quality. We argue that only models with a genuine grasp of audio-related physical principles can generate physically consistent audio-visual content. We hope PhyAVBench will stimulate future progress in this critical yet largely unexplored domain.

Team GLM, Aohan Zeng, Bin Xu et al.

We introduce ChatGLM, an evolving family of large language models that we have been developing over time. This report primarily focuses on the GLM-4 language series, which includes GLM-4, GLM-4-Air, and GLM-4-9B. They represent our most capable models that are trained with all the insights and lessons gained from the preceding three generations of ChatGLM. To date, the GLM-4 models are pre-trained on ten trillions of tokens mostly in Chinese and English, along with a small set of corpus from 24 languages, and aligned primarily for Chinese and English usage. The high-quality alignment is achieved via a multi-stage post-training process, which involves supervised fine-tuning and learning from human feedback. Evaluations show that GLM-4 1) closely rivals or outperforms GPT-4 in terms of general metrics such as MMLU, GSM8K, MATH, BBH, GPQA, and HumanEval, 2) gets close to GPT-4-Turbo in instruction following as measured by IFEval, 3) matches GPT-4 Turbo (128K) and Claude 3 for long context tasks, and 4) outperforms GPT-4 in Chinese alignments as measured by AlignBench. The GLM-4 All Tools model is further aligned to understand user intent and autonomously decide when and which tool(s) touse -- including web browser, Python interpreter, text-to-image model, and user-defined functions -- to effectively complete complex tasks. In practical applications, it matches and even surpasses GPT-4 All Tools in tasks like accessing online information via web browsing and solving math problems using Python interpreter. Over the course, we have open-sourced a series of models, including ChatGLM-6B (three generations), GLM-4-9B (128K, 1M), GLM-4V-9B, WebGLM, and CodeGeeX, attracting over 10 million downloads on Hugging face in the year 2023 alone. The open models can be accessed through https://github.com/THUDM and https://huggingface.co/THUDM.

Zehan Qi, Xiao Liu, Iat Long Iong et al. · tsinghua

Large language models (LLMs) have shown remarkable potential as autonomous agents, particularly in web-based tasks. However, existing LLM web agents heavily rely on expensive proprietary LLM APIs, while open LLMs lack the necessary decision-making capabilities. This paper introduces WebRL, a self-evolving online curriculum reinforcement learning framework designed to train high-performance web agents using open LLMs. WebRL addresses three key challenges in building LLM web agents, including the scarcity of training tasks, sparse feedback signals, and policy distribution drift in online learning. Specifically, WebRL incorporates 1) a self-evolving curriculum that generates new tasks from unsuccessful attempts, 2) a robust outcome-supervised reward model (ORM), and 3) adaptive reinforcement learning strategies to ensure consistent improvements. We apply WebRL to transform open Llama-3.1 and GLM-4 models into proficient web agents. On WebArena-Lite, WebRL improves the success rate of Llama-3.1-8B from 4.8% to 42.4%, and from 6.1% to 43% for GLM-4-9B. These open models significantly surpass the performance of GPT-4-Turbo (17.6%) and GPT-4o (13.9%) and outperform previous state-of-the-art web agents trained on open LLMs (AutoWebGLM, 18.2%). Our findings demonstrate WebRL's effectiveness in bridging the gap between open and proprietary LLM-based web agents, paving the way for more accessible and powerful autonomous web interaction systems.

Xiao Liu, Bo Qin, Dongzhu Liang et al. · tsinghua

We present AutoGLM, a new series in the ChatGLM family, designed to serve as foundation agents for autonomous control of digital devices through Graphical User Interfaces (GUIs). While foundation models excel at acquiring human knowledge, they often struggle with decision-making in dynamic real-world environments, limiting their progress toward artificial general intelligence. This limitation underscores the importance of developing foundation agents capable of learning through autonomous environmental interactions by reinforcing existing models. Focusing on Web Browser and Phone as representative GUI scenarios, we have developed AutoGLM as a practical foundation agent system for real-world GUI interactions. Our approach integrates a comprehensive suite of techniques and infrastructures to create deployable agent systems suitable for user delivery. Through this development, we have derived two key insights: First, the design of an appropriate "intermediate interface" for GUI control is crucial, enabling the separation of planning and grounding behaviors, which require distinct optimization for flexibility and accuracy respectively. Second, we have developed a novel progressive training framework that enables self-evolving online curriculum reinforcement learning for AutoGLM. Our evaluations demonstrate AutoGLM's effectiveness across multiple domains. For web browsing, AutoGLM achieves a 55.2% success rate on VAB-WebArena-Lite (improving to 59.1% with a second attempt) and 96.2% on OpenTable evaluation tasks. In Android device control, AutoGLM attains a 36.2% success rate on AndroidLab (VAB-Mobile) and 89.7% on common tasks in popular Chinese APPs.

Xinyue Yang, Chen Zheng, Yaoyang Hou et al.

Configuration tuning is critical for database performance. Although recent advancements in database tuning have shown promising results in throughput and latency improvement, challenges remain. First, the vast knob space makes direct optimization unstable and slow to converge. Second, reinforcement learning pipelines often lack effective warm-start guidance and require long offline training. Third, transferability is limited: when hardware or workloads change, existing models typically require substantial retraining to recover performance. To address these limitations, we propose L2T-Tune, a new LLM-guided hybrid database tuning framework that features a three-stage pipeline: Stage one performs a warm start that simultaneously generates uniform samples across the knob space and logs them into a shared pool; Stage two leverages a large language model to mine and prioritize tuning hints from manuals and community documents for rapid convergence. Stage three uses the warm-start sample pool to reduce the dimensionality of knobs and state features, then fine-tunes the configuration with the Twin Delayed Deep Deterministic Policy Gradient algorithm. We conduct experiments on L2T-Tune and the state-of-the-art models. Compared with the best-performing alternative, our approach improves performance by an average of 37.1% across all workloads, and by up to 73% on TPC-C. Compared with models trained with reinforcement learning, it achieves rapid convergence in the offline tuning stage on a single server. Moreover, during the online tuning stage, it only takes 30 steps to achieve best results.

Meiliang Liu, Yunfang Xu, Zijin Li et al.

We propose the Granger causality inference Kolmogorov-Arnold Networks (KANGCI), a novel architecture that extends the recently proposed Kolmogorov-Arnold Networks (KAN) to the domain of causal inference. By extracting base weights from KAN layers and incorporating the sparsity-inducing penalty and ridge regularization, KANGCI effectively infers the Granger causality from time series. Additionally, we propose an algorithm based on time-reversed Granger causality that automatically selects causal relationships with better inference performance from the original or time-reversed time series or integrates the results to mitigate spurious connectivities. Comprehensive experiments conducted on Lorenz-96, Gene regulatory networks, fMRI BOLD signals, VAR, and real-world EEG datasets demonstrate that the proposed model achieves competitive performance to state-of-the-art methods in inferring Granger causality from nonlinear, high-dimensional, and limited-sample time series.

Meiliang Liu, Huiwen Dong, Xiaoxiao Yang et al.

With the advancement of deep learning technologies, various neural network-based Granger causality models have been proposed. Although these models have demonstrated notable improvements, several limitations remain. Most existing approaches adopt the component-wise architecture, necessitating the construction of a separate model for each time series, which results in substantial computational costs. In addition, imposing the sparsity-inducing penalty on the first-layer weights of the neural network to extract causal relationships weakens the model's ability to capture complex interactions. To address these limitations, we propose Gradient Regularization-based Neural Granger Causality (GRNGC), which requires only one time series prediction model and applies $L_{1}$ regularization to the gradient between model's input and output to infer Granger causality. Moreover, GRNGC is not tied to a specific time series forecasting model and can be implemented with diverse architectures such as KAN, MLP, and LSTM, offering enhanced flexibility. Numerical simulations on DREAM, Lorenz-96, fMRI BOLD, and CausalTime show that GRNGC outperforms existing baselines and significantly reduces computational overhead. Meanwhile, experiments on real-world DNA, Yeast, HeLa, and bladder urothelial carcinoma datasets further validate the model's effectiveness in reconstructing gene regulatory networks.

Han Zhang, Fengji Ma, Jiamin Su et al.

Prediction for ADMET (Absorption, Distribution, Metabolism, Excretion, and Toxicity) plays a crucial role in drug discovery and development, accelerating the screening and optimization of new drugs. Existing methods primarily rely on single-task learning (STL), which often fails to fully exploit the complementarities between tasks. Besides, it requires more computational resources while training and inference of each task independently. To address these issues, we propose a new unified Quantum-enhanced and task-Weighted Multi-Task Learning (QW-MTL) framework, specifically designed for ADMET classification tasks. Built upon the Chemprop-RDKit backbone, QW-MTL adopts quantum chemical descriptors to enrich molecular representations with additional information about the electronic structure and interactions. Meanwhile, it introduces a novel exponential task weighting scheme that combines dataset-scale priors with learnable parameters to achieve dynamic loss balancing across tasks. To the best of our knowledge, this is the first work to systematically conduct joint multi-task training across all 13 Therapeutics Data Commons (TDC) classification benchmarks, using leaderboard-style data splits to ensure a standardized and realistic evaluation setting. Extensive experimental results show that QW-MTL significantly outperforms single-task baselines on 12 out of 13 tasks, achieving high predictive performance with minimal model complexity and fast inference, demonstrating the effectiveness and efficiency of multi-task molecular learning enhanced by quantum-informed features and adaptive task weighting.

Xiaoxiao Yang, Meiliang Liu, Yunfang Xu et al.

Alzheimer's disease (AD) is a progressive neurodegenerative disorder that severely impairs cognitive function and quality of life. Timely intervention in AD relies heavily on early and precise diagnosis, which remains challenging due to the complex and subtle structural changes in the brain. Most existing deep learning methods focus only on a single plane of structural magnetic resonance imaging (sMRI) and struggle to accurately capture the complex and nonlinear relationships among pathological regions of the brain, thus limiting their ability to precisely identify atrophic features. To overcome these limitations, we propose an innovative framework, MPF-KANSC, which integrates multi-plane fusion (MPF) for combining features from the coronal, sagittal, and axial planes, and a Kolmogorov-Arnold Network-guided spatial-channel attention mechanism (KANSC) to more effectively learn and represent sMRI atrophy features. Specifically, the proposed model enables parallel feature extraction from multiple anatomical planes, thus capturing more comprehensive structural information. The KANSC attention mechanism further leverages a more flexible and accurate nonlinear function approximation technique, facilitating precise identification and localization of disease-related abnormalities. Experiments on the ADNI dataset confirm that the proposed MPF-KANSC achieves superior performance in AD diagnosis. Moreover, our findings provide new evidence of right-lateralized asymmetry in subcortical structural changes during AD progression, highlighting the model's promising interpretability.

Xinyue Yang, Meiliang Liu, Yunfang Xu et al.

Alzheimer's disease (AD) is a progressive neurodegenerative disorder that predominantly affects the elderly population and currently has no cure. Magnetic Resonance Imaging (MRI), as a non-invasive imaging technique, is essential for the early diagnosis of AD. MRI inherently contains both spatial and frequency information, as raw signals are acquired in the frequency domain and reconstructed into spatial images via the Fourier transform. However, most existing AD diagnostic models extract features from a single domain, limiting their capacity to fully capture the complex neuroimaging characteristics of the disease. While some studies have combined spatial and frequency information, they are mostly confined to 2D MRI, leaving the potential of dual-domain analysis in 3D MRI unexplored. To overcome this limitation, we propose Spatio-Frequency Network (SFNet), the first end-to-end deep learning framework that simultaneously leverages spatial and frequency domain information to enhance 3D MRI-based AD diagnosis. SFNet integrates an enhanced dense convolutional network to extract local spatial features and a global frequency module to capture global frequency-domain representations. Additionally, a novel multi-scale attention module is proposed to further refine spatial feature extraction. Experiments on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset demonstrate that SFNet outperforms existing baselines and reduces computational overhead in classifying cognitively normal (CN) and AD, achieving an accuracy of 95.1%.