Liang Ding

Yangguang Li, Zi-Xin Zou, Zexiang Liu et al.

Recent advancements in diffusion techniques have propelled image and video generation to unprecedented levels of quality, significantly accelerating the deployment and application of generative AI. However, 3D shape generation technology has so far lagged behind, constrained by limitations in 3D data scale, complexity of 3D data processing, and insufficient exploration of advanced techniques in the 3D domain. Current approaches to 3D shape generation face substantial challenges in terms of output quality, generalization capability, and alignment with input conditions. We present TripoSG, a new streamlined shape diffusion paradigm capable of generating high-fidelity 3D meshes with precise correspondence to input images. Specifically, we propose: 1) A large-scale rectified flow transformer for 3D shape generation, achieving state-of-the-art fidelity through training on extensive, high-quality data. 2) A hybrid supervised training strategy combining SDF, normal, and eikonal losses for 3D VAE, achieving high-quality 3D reconstruction performance. 3) A data processing pipeline to generate 2 million high-quality 3D samples, highlighting the crucial rules for data quality and quantity in training 3D generative models. Through comprehensive experiments, we have validated the effectiveness of each component in our new framework. The seamless integration of these parts has enabled TripoSG to achieve state-of-the-art performance in 3D shape generation. The resulting 3D shapes exhibit enhanced detail due to high-resolution capabilities and demonstrate exceptional fidelity to input images. Moreover, TripoSG demonstrates improved versatility in generating 3D models from diverse image styles and contents, showcasing strong generalization capabilities. To foster progress and innovation in the field of 3D generation, we will make our model publicly available.

Xiabin Zhou, Wenbin Wang, Minyan Zeng et al.

Efficient KV cache management in LLMs is crucial for long-context tasks like RAG and summarization. Existing KV cache compression methods enforce a fixed pattern, neglecting task-specific characteristics and reducing the retention of essential information. However, we observe distinct activation patterns across layers in various tasks, highlighting the need for adaptive strategies tailored to each task's unique demands. Based on this insight, we propose DynamicKV, a method that dynamically optimizes token retention by adjusting the number of tokens retained at each layer to adapt to the specific task. DynamicKV establishes global and per-layer maximum KV cache budgets, temporarily retaining the maximum budget for the current layer, and periodically updating the KV cache sizes of all preceding layers during inference. Our method retains only 1.7% of the KV cache size while achieving ~85% of the Full KV cache performance on LongBench. Notably, even under extreme compression (0.9%), DynamicKV surpasses state-of-the-art (SOTA) methods by 11% in the Needle-in-a-Haystack test using Mistral-7B-Instruct-v0.2. The code will be released.

Yuchen Wu, Liang Ding, Li Shen et al.

Knowledge editing allows for efficient adaptation of large language models (LLMs) to new information or corrections without requiring full retraining. However, prior methods typically focus on either single-language editing or basic multilingual editing, failing to achieve true cross-linguistic knowledge synchronization. To address this, we present a simple and practical state-of-the-art (SOTA) recipe Cross-Lingual Knowledge Democracy Edit (X-KDE), designed to propagate knowledge from a dominant language to other languages effectively. Our X-KDE comprises two stages: (i) Cross-lingual Edition Instruction Tuning (XE-IT), which fine-tunes the model on a curated parallel dataset to modify in-scope knowledge while preserving unrelated information, and (ii) Target-language Preference Optimization (TL-PO), which applies advanced optimization techniques to ensure consistency across languages, fostering the transfer of updates. Additionally, we contribute a high-quality, cross-lingual dataset, specifically designed to enhance knowledge transfer across languages. Extensive experiments on the Bi-ZsRE and MzsRE benchmarks show that X-KDE significantly enhances cross-lingual performance, achieving an average improvement of +8.19%, while maintaining high accuracy in monolingual settings.

Ruyi Zhou, Wenhao Feng, Huaiguang Yang et al.

Non-geometric mobility hazards such as rover slippage and sinkage posing great challenges to costly planetary missions are closely related to the mechanical properties of terrain. In-situ proprioceptive processes for rovers to estimate terrain mechanical properties need to experience different slip as well as sinkage and are helpless to untraversed regions. This paper proposes to predict terrain mechanical properties with vision in the distance, which expands the sensing range to the whole view and can partly halt potential slippage and sinkage hazards in the planning stage. A semantic-based method is designed to predict bearing and shearing properties of terrain in two stages connected with semantic clues. The former segmentation phase segments terrain with a light-weighted network promising to be applied onboard with competitive 93% accuracy and high recall rate over 96%, while the latter inference phase predicts terrain properties in a quantitative manner based on human-like inference principles. The prediction results in several test routes are 12.5% and 10.8% in full-scale error and help to plan appropriate strategies to avoid suffering non-geometric hazards.

Liang Ding, Peng Xu, Haibo Gao et al.

Legged robots can pass through complex field environments by selecting gaits and discrete footholds carefully. Traditional methods plan gait and foothold separately and treat them as the single-step optimal process. However, such processing causes its poor passability in a sparse foothold environment. This paper novelly proposes a coordinative planning method for hexapod robots that regards the planning of gait and foothold as a sequence optimization problem with the consideration of dealing with the harshness of the environment as leg fault. The Monte Carlo tree search algorithm(MCTS) is used to optimize the entire sequence. Two methods, FastMCTS, and SlidingMCTS are proposed to solve some defeats of the standard MCTS applicating in the field of legged robot planning. The proposed planning algorithm combines the fault-tolerant gait method to improve the passability of the algorithm. Finally, compared with other planning methods, experiments on terrains with different densities of footholds and artificially-designed challenging terrain are carried out to verify our methods. All results show that the proposed method dramatically improves the hexapod robot's ability to pass through sparse footholds environment.