Yukun Shi

Chengbin Hou, Xinyu Lin, Hanhui Huang et al.

Identification of fossil species is crucial to evolutionary studies. Recent advances from deep learning have shown promising prospects in fossil image identification. However, the quantity and quality of labeled fossil images are often limited due to fossil preservation, conditioned sampling, and expensive and inconsistent label annotation by domain experts, which pose great challenges to training deep learning based image classification models. To address these challenges, we follow the idea of the wisdom of crowds and propose a multiview ensemble framework, which collects Original (O), Gray (G), and Skeleton (S) views of each fossil image reflecting its different characteristics to train multiple base models, and then makes the final decision via soft voting. Experiments on the largest fusulinid dataset with 2400 images show that the proposed OGS consistently outperforms baselines (using a single model for each view), and obtains superior or comparable performance compared to OOO (using three base models for three the same Original views). Besides, as the training data decreases, the proposed framework achieves more gains. While considering the identification consistency estimation with respect to human experts, OGS receives the highest agreement with the original labels of dataset and with the re-identifications of two human experts. The validation performance provides a quantitative estimation of consistency across different experts and genera. We conclude that the proposed framework can present state-of-the-art performance in the fusulinid fossil identification case study. This framework is designed for general fossil identification and it is expected to see applications to other fossil datasets in future work. The source code is publicly available at https://github.com/houchengbin/Fossil-Image-Identification to benefit future research in fossil image identification.

Zhentao Huang, Yukun Shi, Minglun Gong

The performance of PatchMatch-based multi-view stereo algorithms depends heavily on the source views selected for computing matching costs. Instead of modeling the visibility of different views, most existing approaches handle occlusions in an ad-hoc manner. To address this issue, we propose a novel visibility-guided pixelwise view selection scheme in this paper. It progressively refines the set of source views to be used for each pixel in the reference view based on visibility information provided by already validated solutions. In addition, the Artificial Multi-Bee Colony (AMBC) algorithm is employed to search for optimal solutions for different pixels in parallel. Inter-colony communication is performed both within the same image and among different images. Fitness rewards are added to validated and propagated solutions, effectively enforcing the smoothness of neighboring pixels and allowing better handling of textureless areas. Experimental results on the DTU dataset show our method achieves state-of-the-art performance among non-learning-based methods and retrieves more details in occluded and low-textured regions.

Tin Lai, Yukun Shi, Zicong Du et al.

The demand for psychological counselling has grown significantly in recent years, particularly with the global outbreak of COVID-19, which has heightened the need for timely and professional mental health support. Online psychological counselling has emerged as the predominant mode of providing services in response to this demand. In this study, we propose the Psy-LLM framework, an AI-based assistive tool leveraging Large Language Models (LLMs) for question-answering in psychological consultation settings to ease the demand for mental health professions. Our framework combines pre-trained LLMs with real-world professional Q\&A from psychologists and extensively crawled psychological articles. The Psy-LLM framework serves as a front-end tool for healthcare professionals, allowing them to provide immediate responses and mindfulness activities to alleviate patient stress. Additionally, it functions as a screening tool to identify urgent cases requiring further assistance. We evaluated the framework using intrinsic metrics, such as perplexity, and extrinsic evaluation metrics, with human participant assessments of response helpfulness, fluency, relevance, and logic. The results demonstrate the effectiveness of the Psy-LLM framework in generating coherent and relevant answers to psychological questions. This article discusses the potential and limitations of using large language models to enhance mental health support through AI technologies.

Gang Lin, Dongfang Li, Zhuoen Chen et al.

The proliferation of long-context large language models (LLMs) exposes a key bottleneck: the rapidly expanding key-value cache during decoding, which imposes heavy memory and latency costs. While recent approaches attempt to alleviate this by sharing a single set of crucial tokens across layers, such coarse-grained sharing undermines model performance by neglecting the functional diversity of attention heads. To address this, we propose LycheeDecode, an efficient decoding method centered on a fine-grained hybrid-head attention mechanism that employs a hardware-efficient top-k selection strategy. Specifically, the novel HardKuma-based mechanism partitions attention heads into a small subset of retrieval heads that dynamically identify crucial tokens and a majority of sparse heads that reuse them for efficient computation. Through extensive experiments on leading models like Llama3 and Qwen3 across diverse benchmarks for long-context understanding (e.g., LongBench, RULER) and complex reasoning (e.g., AIME24, OlympiadBench), we demonstrate that LycheeDecode achieves generative quality comparable to, and at times surpassing even the full-attention baseline. Crucially, this is accomplished with up to a 2.7x speedup at a 128K context length. By preserving the functional diversity of attention heads, our fine-grained strategy overcomes the performance bottlenecks of existing methods, providing a powerful and validated pathway to both efficient and high-quality long-context LLM inference.

Shijie Lian, Bin Yu, Xiaopeng Lin et al.

Vision-language-action models have advanced rapidly, but robot trajectories alone provide limited coverage for learning broad physical understanding. PhysBrain 1.0 studies a complementary route: converting large-scale human egocentric video into structured physical commonsense supervision before robot adaptation. Our data engine extracts scene elements, spatial dynamics, action execution, and depth-aware relations, then turns them into question-answer supervision for training PhysBrain VLMs. The resulting physical priors are further transferred to VLA policies through a capability-preserving and language-sensitive adaptation design. Across multimodal QA benchmarks and embodied control benchmarks, including ERQA, PhysBench, SimplerEnv-WidowX, LIBERO, and RoboCasa, PhysBrain 1.0 achieves SOTA results and shows especially strong out-of-domain performance on SimplerEnv. These results suggest that scaling physical commonsense from human interaction video can provide an effective bridge from multimodal understanding to robot action.

Yuxuan Tian, Yurun Jin, Bin Yu et al.

Robotic manipulation critically requires reasoning about future spatial-temporal interactions, yet existing VLA policies and world-model-enhanced policies do not fully model action-relevant spatial-temporal interaction structure. We propose STARRY, a world-model-enhanced action-generation policy that aligns spatial-temporal prediction with action generation. STARRY jointly denoises future spatial-temporal latents and action sequences, and introduces Geometry-Aware Selective Attention Modulation to convert predicted depth and end-effector geometry into token-aligned weights for selective action-attention modulation. On RoboTwin 2.0, STARRY achieves 93.82% / 93.30% average success under Clean and Randomized settings. Real-world experiments further improve average success from 42.5% to 70.8% over $π_{0.5}$, demonstrating the effectiveness of action-centric spatial-temporal world modeling for spatial-temporally demanding robotic action generation.

Zhentao Huang, Yukun Shi, Neil Bruce et al.

The widespread adoption of implicit neural representations, especially Neural Radiance Fields (NeRF), highlights a growing need for editing capabilities in implicit 3D models, essential for tasks like scene post-processing and 3D content creation. Despite previous efforts in NeRF editing, challenges remain due to limitations in editing flexibility and quality. The key issue is developing a neural representation that supports local edits for real-time updates. Current NeRF editing methods, offering pixel-level adjustments or detailed geometry and color modifications, are mostly limited to static scenes. This paper introduces SealD-NeRF, an extension of Seal-3D for pixel-level editing in dynamic settings, specifically targeting the D-NeRF network. It allows for consistent edits across sequences by mapping editing actions to a specific timeframe, freezing the deformation network responsible for dynamic scene representation, and using a teacher-student approach to integrate changes.