arXiv subjects

Mingcong Han

Publications and source records attributed to Mingcong Han.

6 recordsLinked to original sources

arXiv2026

Seed3D 2.0: Advancing High-Fidelity Simulation-Ready 3D Content Generation

We present Seed3D 2.0, an advanced 3D content generation system built on Seed3D 1.0, with substantial improvements across generation fidelity, simulation-ready capabilities, and application coverage. For geometry, a coarse-to-fine two-stage pipeline decouples global structure learning from high-frequency detail recovery, while a locality-aware VAE achieves higher spatial compression and more efficient decoding. For texture and material generation, we replace the cascaded pipeline of Seed3D 1.0 with a unified PBR model that directly generates multi-view albedo and metallic-roughness maps, enhanced by Mixture-of-Experts scaling and VLM-based semantic conditioning for improved material precision and visual fidelity. Beyond single-object generation, Seed3D 2.0 introduces a simulation-ready model suite comprising scene layout planning, part-aware decomposition, and training-free articulation generation, enabling coherent scene construction and part-level physical interaction across physics and graphics engines. A large-scale human preference study against five recent commercial models shows that Seed3D 2.0 achieves consistent win rates of 69.0% to 89.9% in textured 3D asset generation. Seed3D 2.0 is available on https://exp.volcengine.com/ark/vision?_vtm_=0.0.c70961.d701978.0&mode=vision&modelId=doubao-seed3d-2-0-260328&tab=Gen3D

cs.GR↗

arXiv2026

TensorHub: Scalable and Elastic Weight Transfer for LLM RL Training

Modern LLM reinforcement learning (RL) workloads require a highly efficient weight transfer system to scale training across heterogeneous computational resources. However, existing weight transfer approaches either fail to provide flexibility for dynamically scaling clusters or incur fundamental data movement overhead, resulting in poor performance. We introduce Reference-Oriented Storage (ROS), a new storage abstraction for RL weight transfer that exploits the highly replicated model weights in place. ROS presents the illusion that certain versions of the model weights are stored and can be fetched on demand. Underneath, ROS does not physically store any copies of the weights; instead, it tracks the workers that hold these weights on GPUs for inference. Upon request, ROS directly uses them to serve reads. We build TensorHub, a production-quality system that extends the ROS idea with topology-optimized transfer, strong consistency, and fault tolerance. Evaluation shows that TensorHub fully saturates RDMA bandwidth and adapts to three distinct rollout workloads with minimal engineering effort. Specifically, TensorHub reduces total GPU stall time by up to 6.7x for standalone rollouts, accelerates weight update for elastic rollout by 4.8x, and cuts cross-datacenter rollout stall time by 19x. TensorHub has been deployed in production to support cutting-edge RL training.

cs.DC↗

arXiv2025

Fast LLM Post-training via Decoupled and Fastest-of-N Speculation

Rollout dominates the training time in large language model (LLM) post-training, where the trained model is used to generate tokens given a batch of prompts. This work, SpecActor, achieves fast rollout with speculative decoding that deploys a fast draft path to accelerate the unparallelizable generation, while the correctness is guaranteed by fast parallel verification of the outputs with the original model. SpecActor addresses two foundational challenges that hinder speculation efficiency: (1) a Decoupled speculation method that overcomes the computation inefficiency issue when executing speculative decoding with relative large per-worker batch size -- a common configuration in training but unfriendly to speculation, and (2) a Fastest-of-N speculation method that selects and combines different draft methods according to the rollout progress to approximate the optimal draft method even when the best one is unknown a priori. Extensive evaluations on production traces show that SpecActor accelerates mean rollout speed by 2.0--2.4x, with up to 2.7x speedup, over common post-training baselines. The results are consistent across both dense and MoE models and across different RL algorithms. Notably, SpecActor is 1.1--2.6x faster compared to vanilla speculative rollout in different traces. The accelerated rollout achieves 1.4--2.3x faster end-to-end training time.

cs.DC↗

arXiv2025

Holistic Heterogeneous Scheduling for Autonomous Applications using Fine-grained, Multi-XPU Abstraction

Modern autonomous applications are increasingly utilizing multiple heterogeneous processors (XPUs) to accelerate different stages of algorithm modules. However, existing runtime systems for these applications, such as ROS, can only perform module-level task management, lacking awareness of the fine-grained usage of multiple XPUs. This paper presents XAUTO, a runtime system designed to cooperatively manage XPUs for latency-sensitive autonomous applications. The key idea is a fine-grained, multi-XPU programming abstraction -- XNODE, which aligns with the stage-level task granularity and can accommodate multiple XPU implementations. XAUTO holistically assigns XPUs to XNODEs and schedules their execution to minimize end-to-end latency. Experimental results show that XAUTO can reduce the end-to-end latency of a perception pipeline for autonomous driving by 1.61x compared to a state-of-the-art module-level scheduling system (ROS2).

cs.OS↗

arXiv2024

Microsecond-scale Dynamic Validation of Idempotency for GPU Kernels

We discovered that a GPU kernel can have both idempotent and non-idempotent instances depending on the input. These kernels, called conditionally-idempotent, are prevalent in real-world GPU applications (490 out of 547 from six applications). Consequently, prior work that classifies GPU kernels as either idempotent or non-idempotent can severely compromise the correctness or efficiency of idempotence-based systems. This paper presents PICKER, the first system for instance-level idempotency validation. PICKER dynamically validates the idempotency of GPU kernel instances before their execution, by utilizing their launch arguments. Several optimizations are proposed to significantly reduce validation latency to microsecond-scale. Evaluations using representative GPU applications (547 kernels and 18,217 instances in total) show that PICKER can identify idempotent instances with no false positives and a false-negative rate of 18.54%, and can complete the validation within 5 us for all instances. Furthermore, by integrating PICKER, a fault-tolerant system can reduce the checkpoint cost to less than 4% and a scheduling system can reduce the preemption latency by 84.2%.

cs.OS↗

arXiv2024

PhoenixOS: Concurrent OS-level GPU Checkpoint and Restore with Validated Speculation

PHOENIXOS (PHOS) is the first OS service that can concurrently checkpoint and restore (C/R) GPU processes--a fundamental capability for critical tasks such as fault tolerance, process migration, and fast startup. While concurrent C/R is well-established on CPUs, it poses unique challenges on GPUs due to their lack of essential features for efficiently tracing concurrent memory reads and writes, such as specific hardware capabilities (e.g., dirty bits) and OS-mediated data paths (e.g., copy-on-write). To ensure correct concurrent C/R, PHOS proactively detects GPU memory reads and writes through a two-step process: first, it speculates about GPU memory accesses based on the arguments used when launching GPU kernels; then, it validates these accesses efficiently at runtime using binary instrumentation. With this validated speculation, PHOS retrofits CPU-based concurrent C/R for GPUs through software-based approaches, including soft copy-on-write, soft recopy, and soft on-demand restore. PHOS further proposes several GPU-aware techniques for efficient GPU C/R, including coordinated checkpoint data transfer and execution context pool. For downstream tasks that use C/R for tolerating failures, migrating processes between machines, and accelerating cold starts in serverless computing, PHOS achieves orders of magnitude higher performance than state-of-the-art OS-level GPU C/R systems like NVIDIA cuda-checkpoint.

cs.DC↗