Jinqi Jiang

Yipeng Yang, Yiqiao Tang, Hao Zhang et al.

Conventional multirotors suffer from a rapid collapse of attainable wrench space (AWS) under abrupt total rotor failures, rendering full 6-DOF recovery physically impossible. This paper addresses passive fault-tolerant flight of a biaxial-tilt overactuated hexacopter (BTO) under abrupt total rotor failures that are a priori unknown to the controller. The control design and analysis focus on representative abrupt rotor-failure cases for which the post-failure system remains fully actuated, while no explicit fault detection, isolation, or fault-mode switching is assumed. First, we extend the inscribed-sphere metric of the AWS by incorporating the transient-wrench-jump term, enabling quantitative feasibility assessment under up to three simultaneous rotor failures and benchmarking against uniaxial-tilt and coplanar hexacopters. Second, we develop two computationally efficient passive schemes without relying on fault detection or online optimization. One scheme operates at the controller layer by combining a high-order fully actuated (HOFA) controller with a linear extended state observer (LESO) for lumped-disturbance rejection. The other scheme operates at the allocator layer by using model-reference adaptive control allocation with momentum-based wrench estimation to compensate for control-allocation biases. Simulations and flight experiments validate stable hovering and 6-DOF trajectory tracking under single and multiple rotor failures. Further systematic comparisons confirm that the BTO provides larger recovery margins than uniaxial-tilt and coplanar designs. Additional onboard-sensor-only experiments, including indoor tracking under wind disturbance, outdoor tracking under extreme conditions, narrow-frame traversal, and contact-based aerial writing, further validate the robustness of the proposed framework in complex operational environments.

Zihan Luo, Xiran Song, Hong Huang et al.

Improving the general capabilities of large language models (LLMs) is an active research topic. As a common data structure in many real-world domains, understanding graph data is a crucial part of advancing general intelligence. To this end, we propose a dynamic benchmark named GraphInstruct in this paper, which comprehensively includes 21 classical graph reasoning tasks, providing diverse graph generation pipelines and detailed intermediate reasoning steps for each sample. Based on GraphInstruct, we develop GraphSolver via efficient instruction-tuning, which demonstrates prominent graph understanding capability compared to other open-sourced LLMs. To further endow LLMs with multi-step graph reasoning capability, we propose a label-mask training strategy and build GraphSolver+, which leverages masked supervision on intermediate reasoning tokens to emphasize crucial node-identification signals. As one of the pioneering efforts to enhance the graph understanding and reasoning abilities of LLMs, extensive experiments have demonstrated the superiority of GraphSolver and GraphSolver+ over other LLMs. We sincerely hope GraphInstruct will facilitate further research on applying LLMs to graph-structured data. Our code and data are released publicly at: https://github.com/CGCL-codes/GraphInstruct.

Zhaoyang Wang, Jinqi Jiang, Huichi Zhou et al.

Recent Large Language Models (LLMs) have demonstrated satisfying general instruction following ability. However, small LLMs with about 7B parameters still struggle fine-grained format following (e.g., JSON format), which seriously hinder the advancements of their applications. Most existing methods focus on benchmarking general instruction following while overlook how to improve the specific format following ability for small LLMs. Besides, these methods often rely on evaluations based on advanced LLMs (e.g., GPT-4), which can introduce the intrinsic bias of LLMs and be costly due to the API calls. In this paper, we first curate a fully verifiable format following dataset VFF. In contrast to existing works often adopting external LLMs for instruction-following validations, every sample of VFF can be easily validated with a Python function. Further, we propose to leverage this verifiable feature to synthesize massive data for progressively training small LLMs, in order to improve their format following abilities. Experimental results highlight the prevalent limitations in the format following capabilities of 7B level open-source LLMs and demonstrate the effectiveness of our method in enhancing this essential ability.

Zhaoyang Wang, Jinqi Jiang, Tian Qiu et al.

Recent large reasoning models such as DeepSeek-R1 exhibit strong complex problems solving abilities by generating long chain-of-thought (CoT) reasoning steps. It is challenging to directly train small language models (SLMs) to emerge long CoT. Thus, distillation becomes a practical method to enable SLMs for such reasoning ability. However, the long CoT often contains a lot of redundant contents (e.g., overthinking steps) which may make SLMs hard to learn considering their relatively poor capacity and generalization. To address this issue, we propose a simple-yet-effective method to prune unnecessary steps in long CoT, and then employ an on-policy method for the SLM itself to curate valid and useful long CoT training data. In this way, SLMs can effectively learn efficient long CoT reasoning and preserve competitive performance at the same time. Experimental results across a series of mathematical reasoning benchmarks demonstrate the effectiveness of the proposed method in distilling long CoT reasoning ability into SLMs which maintains the competitive performance but significantly reduces generating redundant reasoning steps.

Senkang Hu, Xudong Han, Jinqi Jiang et al.

Adapting billion-parameter language models to a downstream task is still costly, even with parameter-efficient fine-tuning (PEFT). We re-cast task adaptation as output-distribution alignment: the objective is to steer the output distribution toward the task distribution directly during decoding rather than indirectly through weight updates. Building on this view, we introduce Steering Vector Decoding (SVDecode), a lightweight, PEFT-compatible, and theoretically grounded method. We start with a short warm-start fine-tune and extract a task-aware steering vector from the Kullback-Leibler (KL) divergence gradient between the output distribution of the warm-started and pre-trained models. This steering vector is then used to guide the decoding process to steer the model's output distribution towards the task distribution. We theoretically prove that SVDecode is first-order equivalent to the gradient step of full fine-tuning and derive a globally optimal solution for the strength of the steering vector. Across three tasks and nine benchmarks, SVDecode paired with four standard PEFT methods improves multiple-choice accuracy by up to 5 percentage points and open-ended truthfulness by 2 percentage points, with similar gains (1-2 percentage points) on commonsense datasets without adding trainable parameters beyond the PEFT adapter. SVDecode thus offers a lightweight, theoretically grounded path to stronger task adaptation for large language models.

Guiyong Zheng, Jinqi Jiang, Chen Feng et al.

Surface prediction and completion have been widely studied in various applications. Recently, research in surface completion has evolved from small objects to complex large-scale scenes. As a result, researchers have begun increasing the volume of data and leveraging a greater variety of data modalities including rendered RGB images, descriptive texts, depth images, etc, to enhance algorithm performance. However, existing datasets suffer from a deficiency in the amounts of scene-level models along with the corresponding multi-modal information. Therefore, a method to scale the datasets and generate multi-modal information in them efficiently is essential. To bridge this research gap, we propose MASSTAR: a Multi-modal lArge-scale Scene dataset with a verSatile Toolchain for surfAce pRediction and completion. We develop a versatile and efficient toolchain for processing the raw 3D data from the environments. It screens out a set of fine-grained scene models and generates the corresponding multi-modal data. Utilizing the toolchain, we then generate an example dataset composed of over a thousand scene-level models with partial real-world data added. We compare MASSTAR with the existing datasets, which validates its superiority: the ability to efficiently extract high-quality models from complex scenarios to expand the dataset. Additionally, several representative surface completion algorithms are benchmarked on MASSTAR, which reveals that existing algorithms can hardly deal with scene-level completion. We will release the source code of our toolchain and the dataset. For more details, please see our project page at https://sysu-star.github.io/MASSTAR.