VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents

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}.

Personalized Federated Continual Learning via Multi-granularity Prompt

Personalized Federated Continual Learning (PFCL) is a new practical scenario that poses greater challenges in sharing and personalizing knowledge. PFCL not only relies on knowledge fusion for server aggregation at the global spatial-temporal perspective but also needs model improvement for each client according to the local requirements. Existing methods, whether in Personalized Federated Learning (PFL) or Federated Continual Learning (FCL), have overlooked the multi-granularity representation of knowledge, which can be utilized to overcome Spatial-Temporal Catastrophic Forgetting (STCF) and adopt generalized knowledge to itself by coarse-to-fine human cognitive mechanisms. Moreover, it allows more effectively to personalized shared knowledge, thus serving its own purpose. To this end, we propose a novel concept called multi-granularity prompt, i.e., coarse-grained global prompt acquired through the common model learning process, and fine-grained local prompt used to personalize the generalized representation. The former focuses on efficiently transferring shared global knowledge without spatial forgetting, and the latter emphasizes specific learning of personalized local knowledge to overcome temporal forgetting. In addition, we design a selective prompt fusion mechanism for aggregating knowledge of global prompts distilled from different clients. By the exclusive fusion of coarse-grained knowledge, we achieve the transmission and refinement of common knowledge among clients, further enhancing the performance of personalization. Extensive experiments demonstrate the effectiveness of the proposed method in addressing STCF as well as improving personalized performance. Our code now is available at https://github.com/SkyOfBeginning/FedMGP.

ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools

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.

Effectively Compress KV Heads for LLM

The advent of pre-trained large language models (LLMs) has revolutionized various natural language processing tasks. These models predominantly employ an auto-regressive decoding mechanism that utilizes Key-Value (KV) caches to eliminate redundant calculations for previous tokens. Nevertheless, as context lengths and batch sizes increase, the linear expansion in memory footprint of KV caches becomes a key bottleneck of LLM deployment, which decreases generation speeds significantly. To mitigate this issue, previous techniques like multi-query attention (MQA) and grouped-query attention (GQA) have been developed, in order to reduce KV heads to accelerate inference with comparable accuracy to multi-head attention (MHA). Despite their effectiveness, existing strategies for compressing MHA often overlook the intrinsic properties of the KV caches. In this work, we explore the low-rank characteristics of the KV caches and propose a novel approach for compressing KV heads. In particular, we carefully optimize the MHA-to-GQA transformation to minimize compression error, and to remain compatible with rotary position embeddings (RoPE), we also introduce specialized strategies for key caches with RoPE. We demonstrate that our method can compress half or even three-quarters of KV heads while maintaining performance comparable to the original LLMs, which presents a promising direction for more efficient LLM deployment in resource-constrained environments.

CodeR: Issue Resolving with Multi-Agent and Task Graphs

GitHub issue resolving recently has attracted significant attention from academia and industry. SWE-bench is proposed to measure the performance in resolving issues. In this paper, we propose CodeR, which adopts a multi-agent framework and pre-defined task graphs to Repair & Resolve reported bugs and add new features within code Repository. On SWE-bench lite, CodeR is able to solve 28.00% of issues, in the case of submitting only once for each issue. We examine the performance impact of each design of CodeR and offer insights to advance this research direction.

Unified Low-rank Compression Framework for Click-through Rate Prediction

Deep Click-Through Rate (CTR) prediction models play an important role in modern industrial recommendation scenarios. However, high memory overhead and computational costs limit their deployment in resource-constrained environments. Low-rank approximation is an effective method for computer vision and natural language processing models, but its application in compressing CTR prediction models has been less explored. Due to the limited memory and computing resources, compression of CTR prediction models often confronts three fundamental challenges, i.e., (1). How to reduce the model sizes to adapt to edge devices? (2). How to speed up CTR prediction model inference? (3). How to retain the capabilities of original models after compression? Previous low-rank compression research mostly uses tensor decomposition, which can achieve a high parameter compression ratio, but brings in AUC degradation and additional computing overhead. To address these challenges, we propose a unified low-rank decomposition framework for compressing CTR prediction models. We find that even with the most classic matrix decomposition SVD method, our framework can achieve better performance than the original model. To further improve the effectiveness of our framework, we locally compress the output features instead of compressing the model weights. Our unified low-rank compression framework can be applied to embedding tables and MLP layers in various CTR prediction models. Extensive experiments on two academic datasets and one real industrial benchmark demonstrate that, with 3-5x model size reduction, our compressed models can achieve both faster inference and higher AUC than the uncompressed original models. Our code is at https://github.com/yuhao318/Atomic_Feature_Mimicking.

Evaluation of Retrieval-Augmented Generation: A Survey

Retrieval-Augmented Generation (RAG) has emerged as a pivotal innovation in natural language processing, enhancing generative models by incorporating external information retrieval. Evaluating RAG systems, however, poses distinct challenges due to their hybrid structure and reliance on dynamic knowledge sources. We consequently enhanced an extensive survey and proposed an analysis framework for benchmarks of RAG systems, RAGR (Retrieval, Generation, Additional Requirement), designed to systematically analyze RAG benchmarks by focusing on measurable outputs and established truths. Specifically, we scrutinize and contrast multiple quantifiable metrics of the Retrieval and Generation component, such as relevance, accuracy, and faithfulness, of the internal links within the current RAG evaluation methods, covering the possible output and ground truth pairs. We also analyze the integration of additional requirements of different works, discuss the limitations of current benchmarks, and propose potential directions for further research to address these shortcomings and advance the field of RAG evaluation. In conclusion, this paper collates the challenges associated with RAG evaluation. It presents a thorough analysis and examination of existing methodologies for RAG benchmark design based on the proposed RGAR framework.

Rethinking Efficient and Effective Point-based Networks for Event Camera Classification and Regression: EventMamba

Event cameras, drawing inspiration from biological systems, efficiently detect changes in ambient light with low latency and high dynamic range while consuming minimal power. The most current approach to processing event data often involves converting it into frame-based representations, which is well-established in traditional vision. However, this approach neglects the sparsity of event data, loses fine-grained temporal information during the transformation process, and increases the computational burden, making it ineffective for characterizing event camera properties. In contrast, Point Cloud is a popular representation for 3D processing and is better suited to match the sparse and asynchronous nature of the event camera. Nevertheless, despite the theoretical compatibility of point-based methods with event cameras, the results show a performance gap that is not yet satisfactory compared to frame-based methods. In order to bridge the performance gap, we propose EventMamba, an efficient and effective Point Cloud framework that achieves competitive results even compared to the state-of-the-art (SOTA) frame-based method in both classification and regression tasks. This notable accomplishment is facilitated by our rethinking of the distinction between Event Cloud and Point Cloud, emphasizing effective temporal information extraction through optimized network structures. Specifically, EventMamba leverages temporal aggregation and State Space Model (SSM) based Mamba boasting enhanced temporal information extraction capabilities. Through a hierarchical structure, EventMamba is adept at abstracting local and global spatial features and implicit and explicit temporal features. By adhering to the lightweight design principle, EventMamba delivers impressive results with minimal computational resource utilization, demonstrating its efficiency and effectiveness.

FedProK: Trustworthy Federated Class-Incremental Learning via Prototypical Feature Knowledge Transfer

Federated Class-Incremental Learning (FCIL) focuses on continually transferring the previous knowledge to learn new classes in dynamic Federated Learning (FL). However, existing methods do not consider the trustworthiness of FCIL, i.e., improving continual utility, privacy, and efficiency simultaneously, which is greatly influenced by catastrophic forgetting and data heterogeneity among clients. To address this issue, we propose FedProK (Federated Prototypical Feature Knowledge Transfer), leveraging prototypical feature as a novel representation of knowledge to perform spatial-temporal knowledge transfer. Specifically, FedProK consists of two components: (1) feature translation procedure on the client side by temporal knowledge transfer from the learned classes and (2) prototypical knowledge fusion on the server side by spatial knowledge transfer among clients. Extensive experiments conducted in both synchronous and asynchronous settings demonstrate that our FedProK outperforms the other state-of-the-art methods in three perspectives of trustworthiness, validating its effectiveness in selectively transferring spatial-temporal knowledge.

AutoWebGLM: Bootstrap And Reinforce A Large Language Model-based Web Navigating Agent

Large language models (LLMs) have fueled many intelligent agent tasks, such as web navigation -- but most existing agents perform far from satisfying in real-world webpages due to three factors: (1) the versatility of actions on webpages, (2) HTML text exceeding model processing capacity, and (3) the complexity of decision-making due to the open-domain nature of web. In light of the challenge, we develop AutoWebGLM, a GPT-4-outperforming automated web navigation agent built upon ChatGLM3-6B. Inspired by human browsing patterns, we design an HTML simplification algorithm to represent webpages, preserving vital information succinctly. We employ a hybrid human-AI method to build web browsing data for curriculum training. Then, we bootstrap the model by reinforcement learning and rejection sampling to further facilitate webpage comprehension, browser operations, and efficient task decomposition by itself. For testing, we establish a bilingual benchmark -- AutoWebBench -- for real-world web browsing tasks. We evaluate AutoWebGLM across diverse web navigation benchmarks, revealing its improvements but also underlying challenges to tackle real environments. Related code, model, and data will be released at \url{https://github.com/THUDM/AutoWebGLM}.