Dong Wei

Ziting Wang, Shize Zhang, Haitao Yuan et al.

The growing demand for data-driven decision-making has created an urgent need for data agents that can reason over heterogeneous data (databases, documents, web content, images, videos, and audio) to answer complex analytical queries. However, evaluating such agents remains challenging: existing benchmarks often focus on isolated agent capabilities or limited data modalities, lacking comprehensive coverage of heterogeneous data and rigorous evaluation across diverse data agent architectures. To address these challenges, we present FDABench, a benchmark for evaluating data agents' reasoning ability over heterogeneous data in analytical scenarios. Our contributions are threefold: (1) A comprehensive benchmark of 2,007 tasks spanning six data modalities with a unified, multi-granularity evaluation framework. (2) We design PUDDING, an agentic dataset construction framework that leverages LLM generation with iterative expert validation for reliable and scalable benchmark construction. (3) Extensive experiments across diverse data agent architectures, including general analytical agents, semantic operator frameworks, and RAG-based methods, revealing key insights and guidelines for future data agent development. Our data and source code are released at https://github.com/fdabench/FDAbench.

Linbin Huang, Huanhai Xin, Wei Dong et al.

Small-signal instability of grid-connected power converters may arise when the converters use a phase-locked loop (PLL) to synchronize with a weak grid. Commonly, this stability problem (referred as PLL-synchronization stability in this paper) was studied by employing a single-converter system connected to an infinite bus, which however, omits the impacts of power grid structure and the interactions among multiple converters. Motivated by this, we investigate how the grid structure affects PLL-synchronization stability of multi-converter systems. By using Kron reduction to eliminate the interior nodes, an equivalent reduced network is obtained which contains only the converter nodes. We explicitly show how the Kron-reduced multi-converter system can be decoupled into its modes. This modal representation allows us to demonstrate that the smallest eigenvalue of the grounded Laplacian matrix of the Kron-reduced network dominates the stability margin. We also carry out a sensitivity analysis of this smallest eigenvalue to explore how a perturbation in the original network affects the stability margin. On this basis, we provide guidelines on how to improve the PLL-synchronization stability of multi-converter systems by PLL-retuning, proper placement of converters or enhancing some weak connection in the network. Finally, we validate our findings with simulation results based on a 39-bus test system.

Eric Hanchen Jiang, Weixuan Ou, Run Liu et al.

Safety alignment of large language models (LLMs) faces a key challenge: current alignment techniques often only focus on improving safety against harmful prompts, causing LLMs to become over-cautious and refuse to respond to benign prompts. Therefore, a key objective of safe alignment is to enhance safety while simultaneously reducing false refusals. In this paper, we introduce Energy-Driven Steering (EDS), a novel, fine-tuning free framework designed to resolve this challenge through dynamic, inference-time intervention. We trained a lightweight, external Energy-Based Model (EBM) to assign high energy to undesirable (false refusal or jailbreak) states and low energy to desirable (helpful response or safe reject) ones. During inference, EBM maps the LLM's internal activations to an "energy landscape". We use the gradient of the energy function to dynamically steer the LLM's hidden states to low energy regions, correcting the model to generate a desirable response in real-time without modifying its weights. This method decouples behavioral control from the model's core knowledge, offering a flexible solution with minimal computational overhead. Extensive experiments across a wide range of models show our method successfully achieves this objective: it substantially lowers false refusal rates. For example, raising compliance on the ORB-H benchmark from 57.3% to 82.6% while maintaining the baseline safety performance. Our work presents an effective paradigm for building LLMs that achieve both low false refusal rates and high safety.

Dong Wei, Xiaoning Sun, Huaijiang Sun et al.

The emergence of text-driven motion synthesis technique provides animators with great potential to create efficiently. However, in most cases, textual expressions only contain general and qualitative motion descriptions, while lack fine depiction and sufficient intensity, leading to the synthesized motions that either (a) semantically compliant but uncontrollable over specific pose details, or (b) even deviates from the provided descriptions, bringing animators with undesired cases. In this paper, we propose DiffKFC, a conditional diffusion model for text-driven motion synthesis with KeyFrames Collaborated, enabling realistic generation with collaborative and efficient dual-level control: coarse guidance at semantic level, with only few keyframes for direct and fine-grained depiction down to body posture level. Unlike existing inference-editing diffusion models that incorporate conditions without training, our conditional diffusion model is explicitly trained and can fully exploit correlations among texts, keyframes and the diffused target frames. To preserve the control capability of discrete and sparse keyframes, we customize dilated mask attention modules where only partial valid tokens participate in local-to-global attention, indicated by the dilated keyframe mask. Additionally, we develop a simple yet effective smoothness prior, which steers the generated frames towards seamless keyframe transitions at inference. Extensive experiments show that our model not only achieves state-of-the-art performance in terms of semantic fidelity, but more importantly, is able to satisfy animator requirements through fine-grained guidance without tedious labor.

Gang Chen, Peng Peng, Peihan Zhang et al.

Obstacle avoidance of quadrotors in dynamic environments is still a very open problem. Current works commonly leverage traditional static maps to represent static obstacles and the detection and tracking of moving objects (DATMO) method to model dynamic obstacles separately. The detection module requires pre-training, and the dynamic obstacles can only be modeled with certain shapes, such as cylinders or ellipsoids. This work utilizes the dual-structure particle-based (DSP) dynamic occupancy map to represent the arbitrary-shaped static obstacles and dynamic obstacles simultaneously, and proposes an efficient risk-aware sampling-based local trajectory planner to realize safe flights in this map. The trajectory is planned by sampling motion primitives generated in the state space. Each motion primitive is divided into two phases: a short-term phase with a strict risk limitation and a relatively long-term phase designed to avoid high-risk regions. The risk is evaluated with the predicted particle-form future occupancy status, considering the time dimension. With an approach to split from and merge to an arbitrary global trajectory, the planner can also be used in the tasks with preplanned global trajectories. Comparison experiments show that the obstacle avoidance system composed of the DSP map and our planner performs the best in dynamic environments. In real-world tests, our quadrotor reaches a speed of 6 m/s with the motion capture system and 2.5 m/s with everything running on a low-price single-board computer.

Wei Dong, Kwonyoung Ryu, Michael Kaess et al.

Spinning LiDAR data are prevalent for 3D vision tasks. Since LiDAR data is presented in the form of point clouds, expensive 3D operations are usually required. This paper revisits spinning LiDAR scan formation and presents a cylindrical range image representation with a ray-wise projection/unprojection model. It is built upon raw scans and supports lossless conversion from 2D to 3D, allowing fast 2D operations, including 2D index-based neighbor search and downsampling. We then propose, to the best of our knowledge, the first multi-scale registration and dense signed distance function (SDF) reconstruction system for LiDAR range images. We further collect a dataset of indoor and outdoor LiDAR scenes in the posed range image format. A comprehensive evaluation of registration and reconstruction is conducted on the proposed dataset and the KITTI dataset. Experiments demonstrate that our approach outperforms surface reconstruction baselines and achieves similar performance to state-of-the-art LiDAR registration methods, including a modern learning-based registration approach. Thanks to the simplicity, our registration runs at 100Hz and SDF reconstruction in real time. The dataset and a modularized C++/Python toolbox will be released.

Peihan Zhang, Gang Chen, Yuzhu Li et al.

The vision-based relative localization can provide effective feedback for the cooperation of aerial swarm and has been widely investigated in previous works. However, the limited field of view (FOV) inherently restricts its performance. To cope with this issue, this letter proposes a novel distributed active vision-based relative localization framework and apply it to formation control in aerial swarms. Inspired by bird flocks in nature, we devise graph-based attention planning (GAP) to improve the observation quality of the active vision in the swarm. Then active detection results are fused with onboard measurements from Ultra-WideBand (UWB) and visual-inertial odometry (VIO) to obtain real-time relative positions, which further improve the formation control performance of the swarm. Simulations and experiments demonstrate that the proposed active vision system outperforms the fixed vision system in terms of estimation and formation accuracy.