Zhiqiang Xie

Ying Sheng, Lianmin Zheng, Binhang Yuan et al.

The high computational and memory requirements of large language model (LLM) inference make it feasible only with multiple high-end accelerators. Motivated by the emerging demand for latency-insensitive tasks with batched processing, this paper initiates the study of high-throughput LLM inference using limited resources, such as a single commodity GPU. We present FlexGen, a high-throughput generation engine for running LLMs with limited GPU memory. FlexGen can be flexibly configured under various hardware resource constraints by aggregating memory and computation from the GPU, CPU, and disk. By solving a linear programming problem, it searches for efficient patterns to store and access tensors. FlexGen further compresses the weights and the attention cache to 4 bits with negligible accuracy loss. These techniques enable FlexGen to have a larger space of batch size choices and thus significantly increase maximum throughput. As a result, when running OPT-175B on a single 16GB GPU, FlexGen achieves significantly higher throughput compared to state-of-the-art offloading systems, reaching a generation throughput of 1 token/s for the first time with an effective batch size of 144. On the HELM benchmark, FlexGen can benchmark a 30B model with a 16GB GPU on 7 representative sub-scenarios in 21 hours. The code is available at https://github.com/FMInference/FlexGen

Yao Mu, Tianxing Chen, Shijia Peng et al.

In the rapidly advancing field of robotics, dual-arm coordination and complex object manipulation are essential capabilities for developing advanced autonomous systems. However, the scarcity of diverse, high-quality demonstration data and real-world-aligned evaluation benchmarks severely limits such development. To address this, we introduce RoboTwin, a generative digital twin framework that uses 3D generative foundation models and large language models to produce diverse expert datasets and provide a real-world-aligned evaluation platform for dual-arm robotic tasks. Specifically, RoboTwin creates varied digital twins of objects from single 2D images, generating realistic and interactive scenarios. It also introduces a spatial relation-aware code generation framework that combines object annotations with large language models to break down tasks, determine spatial constraints, and generate precise robotic movement code. Our framework offers a comprehensive benchmark with both simulated and real-world data, enabling standardized evaluation and better alignment between simulated training and real-world performance. We validated our approach using the open-source COBOT Magic Robot platform. Policies pre-trained on RoboTwin-generated data and fine-tuned with limited real-world samples improve the success rate of over 70% for single-arm tasks and over 40% for dual-arm tasks compared to models trained solely on real-world data. This significant improvement demonstrates RoboTwin's potential to enhance the development and evaluation of dual-arm robotic manipulation systems. Project Page: https://robotwin-benchmark.github.io/early-version/.

Tianqi Xu, Linyao Chen, Dai-Jie Wu et al.

The development of autonomous agents increasingly relies on Multimodal Language Models (MLMs) to perform tasks described in natural language with GUI environments, such as websites, desktop computers, or mobile phones. Existing benchmarks for MLM agents in interactive environments are limited by their focus on a single environment, lack of detailed and generalized evaluation methods, and the complexities of constructing tasks and evaluators. To overcome these limitations, we introduce Crab, the first agent benchmark framework designed to support cross-environment tasks, incorporating a graph-based fine-grained evaluation method and an efficient mechanism for task and evaluator construction. Our framework supports multiple devices and can be easily extended to any environment with a Python interface. Leveraging Crab, we developed a cross-platform Crab Benchmark-v0 comprising 120 tasks in computer desktop and mobile phone environments. We evaluated four advanced MLMs using different single and multi-agent system configurations on this benchmark. The experimental results demonstrate that the single agent with GPT-4o achieves the best completion ratio of 38.01%. All framework code, agent code, and task datasets are publicly available at https://github.com/camel-ai/crab.

Shihan Wu, Xuecheng Liu, Shaoxuan Xie et al.

Despite the critical role of bimanual manipulation in endowing robots with human-like dexterity, large-scale and diverse datasets remain scarce due to the significant hardware heterogeneity across bimanual robotic platforms. To bridge this gap, we introduce RoboCOIN, a large-scale multi-embodiment bimanual manipulation dataset comprising over 180,000 demonstrations collected from 15 distinct robotic platforms. Spanning 16 diverse environments-including residential, commercial, and industrial settings-the dataset features 421 bimanual tasks systematically categorized by 39 bimanual collaboration actions and 432 objects. A key innovation of our work is the hierarchical capability pyramid, which provides granular annotations ranging from trajectory-level concepts to segment-level subtasks and frame-level kinematics. Furthermore, we present CoRobot, an efficient data processing pipeline powered by the Robot Trajectory Markup Language (RTML), designed to facilitate quality assessment, automated annotation, and unified multi-embodiment and data management. Extensive experiments demonstrate the effectiveness of RoboCOIN in enhancing the performance of various bimanual manipulation models across a wide spectrum of robotic embodiments. The entire dataset and codebase are fully open-sourced, providing a valuable resource for advancing research in bimanual and multi-embodiment manipulation.

Lianmin Zheng, Liangsheng Yin, Zhiqiang Xie et al.

Large language models (LLMs) are increasingly used for complex tasks that require multiple generation calls, advanced prompting techniques, control flow, and structured inputs/outputs. However, efficient systems are lacking for programming and executing these applications. We introduce SGLang, a system for efficient execution of complex language model programs. SGLang consists of a frontend language and a runtime. The frontend simplifies programming with primitives for generation and parallelism control. The runtime accelerates execution with novel optimizations like RadixAttention for KV cache reuse and compressed finite state machines for faster structured output decoding. Experiments show that SGLang achieves up to 6.4x higher throughput compared to state-of-the-art inference systems on various large language and multi-modal models on tasks including agent control, logical reasoning, few-shot learning benchmarks, JSON decoding, retrieval-augmented generation pipelines, and multi-turn chat. The code is publicly available at https://github.com/sgl-project/sglang

Yao Mu, Tianxing Chen, Zanxin Chen et al.

In the rapidly advancing field of robotics, dual-arm coordination and complex object manipulation are essential capabilities for developing advanced autonomous systems. However, the scarcity of diverse, high-quality demonstration data and real-world-aligned evaluation benchmarks severely limits such development. To address this, we introduce RoboTwin, a generative digital twin framework that uses 3D generative foundation models and large language models to produce diverse expert datasets and provide a real-world-aligned evaluation platform for dual-arm robotic tasks. Specifically, RoboTwin creates varied digital twins of objects from single 2D images, generating realistic and interactive scenarios. It also introduces a spatial relation-aware code generation framework that combines object annotations with large language models to break down tasks, determine spatial constraints, and generate precise robotic movement code. Our framework offers a comprehensive benchmark with both simulated and real-world data, enabling standardized evaluation and better alignment between simulated training and real-world performance. We validated our approach using the open-source COBOT Magic Robot platform. Policies pre-trained on RoboTwin-generated data and fine-tuned with limited real-world samples demonstrate significant potential for enhancing dual-arm robotic manipulation systems by improving success rates by over 70% for single-arm tasks and over 40% for dual-arm tasks compared to models trained solely on real-world data.

Zhiqiang Xie, Yujia Zheng, Lizi Ottens et al.

Runtime failure and performance degradation is commonplace in modern cloud systems. For cloud providers, automatically determining the root cause of incidents is paramount to ensuring high reliability and availability as prompt fault localization can enable faster diagnosis and triage for timely resolution. A compelling solution explored in recent work is causal reasoning using causal graphs to capture relationships between varied cloud system performance metrics. To be effective, however, systems developers must correctly define the causal graph of their system, which is a time-consuming, brittle, and challenging task that increases in difficulty for large and dynamic systems and requires domain expertise. Alternatively, automated data-driven approaches have limited efficacy for cloud systems due to the inherent rarity of incidents. In this work, we present Atlas, a novel approach to automatically synthesizing causal graphs for cloud systems. Atlas leverages large language models (LLMs) to generate causal graphs using system documentation, telemetry, and deployment feedback. Atlas is complementary to data-driven causal discovery techniques, and we further enhance Atlas with a data-driven validation step. We evaluate Atlas across a range of fault localization scenarios and demonstrate that Atlas is capable of generating causal graphs in a scalable and generalizable manner, with performance that far surpasses that of data-driven algorithms and is commensurate to the ground-truth baseline.

Shan Yu, Jiarong Xing, Yifan Qiao et al.

Serving large language models (LLMs) is expensive, especially for providers hosting many models, making cost reduction essential. The unique workload patterns of serving multiple LLMs (i.e., multi-LLM serving) create new opportunities and challenges for this task. The long-tail popularity of models and their long idle periods present opportunities to improve utilization through GPU sharing. However, existing GPU sharing systems lack the ability to adjust their resource allocation and sharing policies at runtime, making them ineffective at meeting latency service-level objectives (SLOs) under rapidly fluctuating workloads. This paper presents Prism, a multi-LLM serving system that unleashes the full potential of GPU sharing to achieve both cost efficiency and SLO attainment. At its core, Prism tackles a key limitation of existing systems$\unicode{x2014}$the lack of $\textit{cross-model memory coordination}$, which is essential for flexibly sharing GPU memory across models under dynamic workloads. Prism achieves this with two key designs. First, it supports on-demand memory allocation by dynamically mapping physical to virtual memory pages, allowing flexible memory redistribution among models that space- and time-share a GPU. Second, it improves memory efficiency through a two-level scheduling policy that dynamically adjusts sharing strategies based on models' runtime demands. Evaluations on real-world traces show that Prism achieves more than $2\times$ cost savings and $3.3\times$ SLO attainment compared to state-of-the-art systems.

Zhiqiang Xie, Hao Kang, Ying Sheng et al.

With more advanced natural language understanding and reasoning capabilities, large language model (LLM)-powered agents are increasingly developed in simulated environments to perform complex tasks, interact with other agents, and exhibit emergent behaviors relevant to social science and gaming. However, current multi-agent simulations frequently suffer from inefficiencies due to the limited parallelism caused by false dependencies, resulting in performance bottlenecks. In this paper, we introduce AI Metropolis, a simulation engine that improves the efficiency of LLM agent simulations by incorporating out-of-order execution scheduling. By dynamically tracking real dependencies between agents, AI Metropolis minimizes false dependencies, enhancing parallelism and enabling efficient hardware utilization. Our evaluations demonstrate that AI Metropolis achieves speedups from 1.3x to 4.15x over standard parallel simulation with global synchronization, approaching optimal performance as the number of agents increases.

Yijing Lin, Zhipeng Gao, Hongyang Du et al.

Federated unlearning is a promising paradigm for protecting the data ownership of distributed clients. It allows central servers to remove historical data effects within the machine learning model as well as address the "right to be forgotten" issue in federated learning. However, existing works require central servers to retain the historical model parameters from distributed clients, such that allows the central server to utilize these parameters for further training even, after the clients exit the training process. To address this issue, this paper proposes a new blockchain-enabled trustworthy federated unlearning framework. We first design a proof of federated unlearning protocol, which utilizes the Chameleon hash function to verify data removal and eliminate the data contributions stored in other clients' models. Then, an adaptive contribution-based retraining mechanism is developed to reduce the computational overhead and significantly improve the training efficiency. Extensive experiments demonstrate that the proposed framework can achieve a better data removal effect than the state-of-the-art frameworks, marking a significant stride towards trustworthy federated unlearning.

Tianxing Chen, Kaixuan Wang, Zhaohui Yang et al.

Embodied Artificial Intelligence (Embodied AI) is an emerging frontier in robotics, driven by the need for autonomous systems that can perceive, reason, and act in complex physical environments. While single-arm systems have shown strong task performance, collaborative dual-arm systems are essential for handling more intricate tasks involving rigid, deformable, and tactile-sensitive objects. To advance this goal, we launched the RoboTwin Dual-Arm Collaboration Challenge at the 2nd MEIS Workshop, CVPR 2025. Built on the RoboTwin Simulation platform (1.0 and 2.0) and the AgileX COBOT-Magic Robot platform, the competition consisted of three stages: Simulation Round 1, Simulation Round 2, and a final Real-World Round. Participants totally tackled 17 dual-arm manipulation tasks, covering rigid, deformable, and tactile-based scenarios. The challenge attracted 64 global teams and over 400 participants, producing top-performing solutions like SEM and AnchorDP3 and generating valuable insights into generalizable bimanual policy learning. This report outlines the competition setup, task design, evaluation methodology, key findings and future direction, aiming to support future research on robust and generalizable bimanual manipulation policies. The Challenge Webpage is available at https://robotwin-benchmark.github.io/cvpr-2025-challenge/.

Vishnu Sarukkai, Zhiqiang Xie, Kayvon Fatahalian

Improving Large Language Model (LLM) agents for sequential decision-making tasks typically requires extensive task-specific knowledge engineering--custom prompts, curated examples, and specialized observation/action spaces. We investigate a different approach where agents automatically improve by learning from their own successful experiences without human intervention. Our method constructs and refines a database of self-generated trajectories that serve as in-context examples for future tasks. Even naive accumulation of successful trajectories yields substantial performance gains across three diverse benchmarks: ALFWorld (73% to 89%), Wordcraft (55% to 64%), and InterCode-SQL (75% to 79%). These improvements exceed those achieved by upgrading from gpt-4o-mini to gpt-4o and match the performance of allowing multiple attempts per task. We further enhance this approach with two innovations: database-level curation using population-based training to propagate high-performing example collections, and exemplar-level curation that selectively retains trajectories based on their empirical utility as in-context examples. With these enhancements, our method achieves 93% success on ALFWorld--surpassing approaches that use more powerful LLMs and hand-crafted components. Our trajectory bootstrapping technique demonstrates that agents can autonomously improve through experience, offering a scalable alternative to labor-intensive knowledge engineering.

Chenyu Wang, Zishen Wan, Hao Kang et al.

With the rapid development of language models, the number of small language models (SLMs) has grown significantly. Although they do not achieve state-of-the-art accuracy, they are more efficient and often excel at specific tasks. This raises a natural question: can multiple SLMs be orchestrated into a system where each contributes effectively, achieving higher accuracy than any individual model? Existing orchestration methods have primarily targeted frontier models (e.g., GPT-4) and perform suboptimally when applied to SLMs. To address this gap, we propose a three-stage approach for orchestrating SLMs. First, we introduce SLM-MUX, a multi-model architecture that effectively coordinates multiple SLMs. Building on this, we develop two optimization strategies: (i) a model selection search that identifies the most complementary SLMs from a given pool, and (ii) test-time scaling tailored to SLM-MUX. Our approach delivers strong results: Compared to existing orchestration methods, our approach achieves up to 13.4% improvement on MATH, 8.8% on GPQA, and 7.0% on GSM8K. With just two SLMS, SLM-MUX outperforms Qwen 2.5 72B on GPQA and GSM8K, and matches its performance on MATH. We further provide theoretical analyses to substantiate the advantages of our method. In summary, we demonstrate that SLMs can be effectively orchestrated into more accurate and efficient systems through the proposed approach.

Xiangshu Gong, Zhiqiang Xie, Xiaowei Jin et al.

Many problems are governed by differential equations (DEs). Artificial intelligence (AI) is a new path for solving DEs. However, data is very scarce and existing AI solvers struggle with approximation of high frequency components (AHFC). We propose an AI paradigm for solving diverse DEs, including DE-ruled first-principles data generation methodology and scale-dilation operator (SDO) AI solver. Using either prior knowledge or random fields, we generate solutions and then substitute them into the DEs to derive the sources and initial/boundary conditions through balancing DEs, thus producing arbitrarily vast amount of, first-principles-consistent training datasets at extremely low computational cost. We introduce a reversible SDO that leverages the Fourier transform of the multiscale solutions to fix AHFC, and design a spatiotemporally coupled, attention-based Transformer AI solver of DEs with SDO. An upper bound on the Hessian condition number of the loss function is proven to be proportional to the squared 2-norm of the solution gradient, revealing that SDO yields a smoother loss landscape, consequently fixing AHFC with efficient training. Extensive tests on diverse DEs demonstrate that our AI paradigm achieves consistently superior accuracy over state-of-the-art methods. This work makes AI solver of DEs to be truly usable in broad nature and engineering fields.

Yang Wang, Chen Zhang, Zhiqiang Xie et al.

Leveraging sparsity in deep neural network (DNN) models is promising for accelerating model inference. Yet existing GPUs can only leverage the sparsity from weights but not activations, which are dynamic, unpredictable, and hence challenging to exploit. In this work, we propose a novel architecture to efficiently harness the dual-side sparsity (i.e., weight and activation sparsity). We take a systematic approach to understand the (dis)advantages of previous sparsity-related architectures and propose a novel, unexplored paradigm that combines outer-product computation primitive and bitmap-based encoding format. We demonstrate the feasibility of our design with minimal changes to the existing production-scale inner-product-based Tensor Core. We propose a set of novel ISA extensions and co-design the matrix-matrix multiplication and convolution algorithms, which are the two dominant computation patterns in today's DNN models, to exploit our new dual-side sparse Tensor Core. Our evaluation shows that our design can fully unleash the dual-side DNN sparsity and improve the performance by up to one order of magnitude with \hl{small} hardware overhead.

Liming Deng, Jie Wang, Hangming Liang et al.

Owing to its unique literal and aesthetical characteristics, automatic generation of Chinese poetry is still challenging in Artificial Intelligence, which can hardly be straightforwardly realized by end-to-end methods. In this paper, we propose a novel iterative polishing framework for highly qualified Chinese poetry generation. In the first stage, an encoder-decoder structure is utilized to generate a poem draft. Afterwards, our proposed Quality-Aware Masked Language Model (QAMLM) is employed to polish the draft towards higher quality in terms of linguistics and literalness. Based on a multi-task learning scheme, QA-MLM is able to determine whether polishing is needed based on the poem draft. Furthermore, QAMLM is able to localize improper characters of the poem draft and substitute with newly predicted ones accordingly. Benefited from the masked language model structure, QAMLM incorporates global context information into the polishing process, which can obtain more appropriate polishing results than the unidirectional sequential decoding. Moreover, the iterative polishing process will be terminated automatically when QA-MLM regards the processed poem as a qualified one. Both human and automatic evaluation have been conducted, and the results demonstrate that our approach is effective to improve the performance of encoder-decoder structure.