arXiv subjects

Xiaojian Liu

Publications and source records attributed to Xiaojian Liu.

5 recordsLinked to original sources

arXiv2026

SCOPE-RL: Optimizing Reasoning Paths Before and After Success

Reinforcement learning with verifiable rewards (RLVR) optimizes LLMs using sparse verifiable final-answer rewards. This sparse anchor reliably verifies whether a trajectory succeeds but provides no direct feedback on the reasoning path that produced it. Before success, prerequisite progress on hard problems receives no reward signal; after success, outcome rewards cannot distinguish well-organized correct trajectories from redundant or locally flawed ones. We introduce SCOPE-RL (Scaffolded Chain Optimization with Process Efficiency), a two-stage framework that densifies this anchor while retaining the GRPO update: Adaptive Scaffolded RL adds prefix-decomposed verifiable rewards on answer-hidden sub-question chains before success, and Quality-Aware Process RL applies correctness-gated process-shape rewards to refine correct trajectories after success. An expert-validated Step-Quality Evaluation Protocol evaluates useful-step density, error localization, and token efficiency beyond final-answer accuracy. On Qwen3-8B-Instruct trained on DAPO-Math and Big-Math, SCOPE-RL improves average accuracy by up to 11.2 pp and reduces reasoning tokens by up to 27.1% over outcome-only GRPO; the gains hold under GSPO and on Qwen3-0.6B-Instruct, indicating that reward-signal densification is complementary to policy-update-level RLVR advances. Code and data are available at https://github.com/tokencraft-lab/SCOPE-RL.

cs.LG↗

arXiv2026

STAMP: Provenance-Guided Credit Assignment for Deep Search Agents

Reinforcement learning for deep-search agents has largely focused on trajectory-level scoring -- outcome correctness, citation-aware rewards, and evidence coverage. Yet the actions that expose supporting documents receive no targeted credit, a gap we call the reward-credit mismatch. We propose STAMP, in which a reference-based verifier judges whether each cited document supports an entity or relation in a training-time evidence graph, and first-exposure attribution traces each supported citation back to the action that first surfaced it. This step credit is injected through sign-preserving advantage modulation, which redistributes advantage across steps without changing the trajectory-level reward or the relative ranking of trajectories within each group. On BrowseComp, BrowseComp-ZH, and xbench-DS, STAMP improves the GRPO baseline by +2.0/+5.5/+3.0 points under matched SFT initialization, training data, and search tools, and composes with both outcome-only and citation-rubric base rewards. Component ablations confirm that the provenance-based credit signal and the sign-preserving advantage modulation each contribute to the gains.

cs.AI↗

arXiv2026

Ming-Flash-Omni: A Sparse, Unified Architecture for Multimodal Perception and Generation

We propose Ming-Flash-Omni, an upgraded version of Ming-Omni, built upon a sparser Mixture-of-Experts (MoE) variant of Ling-Flash-2.0 with 100 billion total parameters, of which only 6.1 billion are active per token. This architecture enables highly efficient scaling (dramatically improving computational efficiency while significantly expanding model capacity) and empowers stronger unified multimodal intelligence across vision, speech, and language, representing a key step toward Artificial General Intelligence (AGI). Compared to its predecessor, the upgraded version exhibits substantial improvements across multimodal understanding and generation. Notably, it achieves strong performance on vision-language understanding benchmarks, with overall scores on par with Gemini 2.5 Pro, and enables seamless switching among multimodal tasks in multi-turn interactions. In speech, it achieves strong performance in contextual and dialect-aware ASR while enabling joint, continuous-generation of speech, sound, and music. In vision, it introduces generative semantic segmentation that achieves competitive standalone performance and enhances spatial control and editing consistency, alongside marked improvements in identity preservation, and high-fidelity in-image text rendering. Together, these capabilities demonstrate that a single unified model can serve as a practical foundation for general-purpose multimodal intelligence.

cs.CV↗

arXiv2025

A Multidisciplinary Design and Optimization (MDO) Agent Driven by Large Language Models

To accelerate mechanical design and enhance design quality and innovation, we present a Multidisciplinary Design and Optimization (MDO) Agent driven by Large Language Models (LLMs). The agent semi-automates the end-to-end workflow by orchestrating three core capabilities: (i) natural-language-driven parametric modeling, (ii) retrieval-augmented generation (RAG) for knowledge-grounded conceptualization, and (iii) intelligent orchestration of engineering software for performance verification and optimization. Working in tandem, these capabilities interpret high-level, unstructured intent, translate it into structured design representations, automatically construct parametric 3D CAD models, generate reliable concept variants using external knowledge bases, and conduct evaluation with iterative optimization via tool calls such as finite-element analysis (FEA). Validation on three representative cases - a gas-turbine blade, a machine-tool column, and a fractal heat sink - shows that the agent completes the pipeline from natural-language intent to verified and optimized designs with reduced manual scripting and setup effort, while promoting innovative design exploration. This work points to a practical path toward human-AI collaborative mechanical engineering and lays a foundation for more dependable, vertically customized MDO systems.

cs.HC↗

arXiv2022

Dark Spot Detection from SAR Images Based on Superpixel Deeper Graph Convolutional Network

Synthetic Aperture Radar (SAR) is the main instrument utilized for the detection of oil slicks on the ocean surface. In SAR images, some areas affected by ocean phenomena, such as rain cells, upwellings, and internal waves, or discharge from oil spills appear as dark spots on images. Dark spot detection is the first step in the detection of oil spills, which then become oil slick candidates. The accuracy of dark spot segmentation ultimately affects the accuracy of oil slick identification. Although some advanced deep learning methods that use pixels as processing units perform well in remote sensing image semantic segmentation, detecting some dark spots with weak boundaries from noisy SAR images remains a huge challenge. We propose a dark spot detection method based on superpixels deeper graph convolutional networks (SGDCN) in this paper, which takes the superpixels as the processing units and extracts features for each superpixel. The features calculated from superpixel regions are more robust than those from fixed pixel neighborhoods. To reduce the difficulty of learning tasks, we discard irrelevant features and obtain an optimal subset of features. After superpixel segmentation, the images are transformed into graphs with superpixels as nodes, which are fed into the deeper graph convolutional neural network for node classification. This graph neural network uses a differentiable aggregation function to aggregate the features of nodes and neighbors to form more advanced features. It is the first time using it for dark spot detection. To validate our method, we mark all dark spots on six SAR images covering the Baltic Sea and construct a dark spots detection dataset, which has been made publicly available (https://drive.google.com/drive/folders/12UavrntkDSPrItISQ8iGefXn2gIZHxJ6?usp=sharing). The experimental results demonstrate that our proposed SGDCN is robust and effective.

cs.CV↗