#GuoPeng
LightNews LightNews
alycearmstrong.bsky.social
Coming home.
白鹭的一家 养育下一代不易
Egret parenthood is not easy. 📸 by Ji Guopeng from China
March 17, 2025 at 5:26 PM
funecology.bsky.social
📰Published📰 Soil fauna trophic multifunctionality mediates the release of elements from decomposing typhoon generated leaf litter

https://buff.ly/3WAP9Qe

🧪🌍
Soil fauna trophic multifunctionality mediates the release of elements from decomposing typhoon generated leaf litter
Lifeng Wang, Craig R. See, Huibin Wang, Rui Cao, Guopeng Liang, Ajuan Zhang, Zhuang Wang, Qin Wang, Zhihui Wang, Benjuan Liu, Wanqin Yang This is a plain language summary of a Functional Ecology re…
buff.ly
January 28, 2025 at 10:00 AM
arxiv-cs-cv.bsky.social
Guopeng Li, Ming Qian, Gui-Song Xia
Unleashing Unlabeled Data: A Paradigm for Cross-View Geo-Localization
https://arxiv.org/abs/2403.14198
March 22, 2024 at 10:14 AM
edreview.bsky.social
Gain insights into teachers' science curriculum enactment through the lens of structural supports in this new article from Guopeng Fu & Siqi Li

🔗 doi.org/10.1080/0013...

#CurriculumEnactment #ScienceEducation #EducationResearch #ChinaEducation
Educational Review journal title appears at the top. On the left is the article title and author name(s): ‘Structural and cultural properties in teachers’ practices: enactment of the 2022 national science curriculum standards in China’ by Guopeng Fu & Siqi Li. On the right is an image of a science diagram drawn on a chalkboard.
April 2, 2026 at 8:46 AM
arxiv-cs-cr.bsky.social
Shuyu Chen, Guopeng Lin, Haoyu Niu, Lushan Song, Chengxun Hong, Weili Han
IDCloak: A Practical Secure Multi-party Dataset Join Framework for Vertical Privacy-preserving Machine Learning
https://arxiv.org/abs/2506.01072
June 3, 2025 at 7:09 AM
cdramanews.bsky.social
Upcoming cdrama #MyDestiny releases official trailer featuring #TanSongyun, #DongQing, #Wishy, #GaoZhiting, #WangJinsong, #LiuWei, #ShiYunpeng, #ZhaoZhiwei, #WangQianguo, #BianCheng, #QuZheming, #RenShuai, #GuoPeng, #DaiXiangyu, #TongLei, #HuXiaoting and more!

youtu.be/K61zrFPdz4c?...
【Official Trailer】MY DESTINY: Destiny is written, the past is left behind.🔥 | Tan Songyun | YOUKU
YouTube video by YOUKU English-Get APP now
youtu.be
February 28, 2026 at 5:09 PM
earthdotcom.bsky.social
New battery material could replace liquid lithium forever #EarthDotCom #EarthSnap #Earth
New battery material could replace liquid lithium forever
A new solid electrolyte can move lithium ions fast enough at about 86°F (30°C) to match the speed seen in common battery liquids. Scientists recently created a solid material meant to take the place of the liquid inside today’s lithium-ion batteries while still allowing fast charging. The work was led by Dr. Guopeng Han at
www.earth.com
December 28, 2025 at 10:16 PM
paper.bsky.social
[4/30] 39 Likes, 2 Comments, 1 Posts
2602.09007, cs․AI | cs․CV, 10 Feb 2026

🆕GEBench: Benchmarking Image Generation Models as GUI Environments

Haodong Li, Jingwei Wu, Quan Sun, Guopeng Li, Juanxi Tian, Huanyu Zhang, Yanlin Lai, Ruichuan An, Hongbo Peng, Yuhong Dai, Chenxi Li, Chunmei Qing, J...
Recent advancements in image generation models have enabled the prediction of future Graphical User Interface (GUI) states based on user instructions. However, existing benchmarks primarily focus on general domain visual fidelity, leaving the evaluation of state transitions and temporal coherence in GUI-specific contexts underexplored. To address this gap, we introduce GEBench, a comprehensive benchmark for evaluating dynamic interaction and temporal coherence in GUI generation. GEBench comprises 700 carefully curated samples spanning five task categories, covering both single-step interactions and multi-step trajectories across real-world and fictional scenarios, as well as grounding point localization. To support systematic evaluation, we propose GE-Score, a novel five-dimensional metric that assesses Goal Achievement, Interaction Logic, Content Consistency, UI Plausibility, and Visual Quality. Extensive evaluations on current models indicate that while they perform well on single-step transitions, they struggle significantly with maintaining temporal coherence and spatial grounding over longer interaction sequences. Our findings identify icon interpretation, text rendering, and localization precision as critical bottlenecks. This work provides a foundation for systematic assessment and suggests promising directions for future research toward building high-fidelity generative GUI environments. The code is available at: https://github.com/stepfun-ai/GEBench.
March 4, 2026 at 12:14 AM
paper.bsky.social
[20/30] 146 Likes, 3 Comments, 1 Posts
2601.06521, cs․CV | cs․CL, 10 Jan 2026

🆕BabyVision: Visual Reasoning Beyond Language

Liang Chen, Weichu Xie, Yiyan Liang, Hongfeng He, Hans Zhao, Zhibo Yang, Zhiqi Huang, Haoning Wu, Haoyu Lu, Y. charles, Yiping Bao, Yuantao Fan, Guopeng Li, Haiyang She...
While humans develop core visual skills long before acquiring language, contemporary Multimodal LLMs (MLLMs) still rely heavily on linguistic priors to compensate for their fragile visual understanding. We uncovered a crucial fact: state-of-the-art MLLMs consistently fail on basic visual tasks that humans, even 3-year-olds, can solve effortlessly. To systematically investigate this gap, we introduce BabyVision, a benchmark designed to assess core visual abilities independent of linguistic knowledge for MLLMs. BabyVision spans a wide range of tasks, with 388 items divided into 22 subclasses across four key categories. Empirical results and human evaluation reveal that leading MLLMs perform significantly below human baselines. Gemini3-Pro-Preview scores 49.7, lagging behind 6-year-old humans and falling well behind the average adult score of 94.1. These results show despite excelling in knowledge-heavy evaluations, current MLLMs still lack fundamental visual primitives. Progress in BabyVision represents a step toward human-level visual perception and reasoning capabilities. We also explore solving visual reasoning with generation models by proposing BabyVision-Gen and automatic evaluation toolkit. Our code and benchmark data are released at https://github.com/UniPat-AI/BabyVision for reproduction.
January 14, 2026 at 12:06 AM
paper.bsky.social
[29/30] 189 Likes, 5 Comments, 2 Posts
2508.10711, cs․CV, 18 Aug 2025

🆕NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale

NextStep Team, Chunrui Han, Guopeng Li, Jingwei Wu, Quan Sun, Yan Cai, Yuang Peng, Zheng Ge, Deyu Zhou, Haomiao Tang, Hongyu Zhou, Kenkun L...
Prevailing autoregressive (AR) models for text-to-image generation either rely on heavy, computationally-intensive diffusion models to process continuous image tokens, or employ vector quantization (VQ) to obtain discrete tokens with quantization loss. In this paper, we push the autoregressive paradigm forward with NextStep-1, a 14B autoregressive model paired with a 157M flow matching head, training on discrete text tokens and continuous image tokens with next-token prediction objectives. NextStep-1 achieves state-of-the-art performance for autoregressive models in text-to-image generation tasks, exhibiting strong capabilities in high-fidelity image synthesis. Furthermore, our method shows strong performance in image editing, highlighting the power and versatility of our unified approach. To facilitate open research, we will release our code and models to the community.
August 21, 2025 at 12:07 AM
paper.bsky.social
[30/30] 85 Likes, 3 Comments, 1 Posts
2504.17761, cs․CV, 28 Apr 2025

🆕Step1X-Edit: A Practical Framework for General Image Editing

Shiyu Liu, Yucheng Han, Peng Xing, Fukun Yin, Rui Wang, Wei Cheng, Jiaqi Liao, Yingming Wang, Honghao Fu, Chunrui Han, Guopeng Li, Yuang Peng, Quan Sun, Jingwei W...
In recent years, image editing models have witnessed remarkable and rapid development. The recent unveiling of cutting-edge multimodal models such as GPT-4o and Gemini2 Flash has introduced highly promising image editing capabilities. These models demonstrate an impressive aptitude for fulfilling a vast majority of user-driven editing requirements, marking a significant advancement in the field of image manipulation. However, there is still a large gap between the open-source algorithm with these closed-source models. Thus, in this paper, we aim to release a state-of-the-art image editing model, called Step1X-Edit, which can provide comparable performance against the closed-source models like GPT-4o and Gemini2 Flash. More specifically, we adopt the Multimodal LLM to process the reference image and the user's editing instruction. A latent embedding has been extracted and integrated with a diffusion image decoder to obtain the target image. To train the model, we build a data generation pipeline to produce a high-quality dataset. For evaluation, we develop the GEdit-Bench, a novel benchmark rooted in real-world user instructions. Experimental results on GEdit-Bench demonstrate that Step1X-Edit outperforms existing open-source baselines by a substantial margin and approaches the performance of leading proprietary models, thereby making significant contributions to the field of image editing.
May 2, 2025 at 12:05 AM
krxiv-cond-mat.bsky.social
Singular Weak-Field Thermodynamics of 2D Superconductors
https://arxiv.org/pdf/2609.01602
Guopeng Xu, Chunli Huang.
https://arxiv.org/abs/2609.01602
arXiv abstract link
arxiv.org
September 2, 2026 at 11:11 AM
condmatsuprcon-bot.bsky.social
Guopeng Xu, Chunli Huang: Singular Weak-Field Thermodynamics of 2D Superconductors https://arxiv.org/abs/2609.01602 https://arxiv.org/pdf/2609.01602 https://arxiv.org/html/2609.01602
September 2, 2026 at 6:53 AM
cslg-bot.bsky.social
Guopeng Li, Yiyang Duan, Yiru Jiao, Chengcheng Xu: Arrive and Survive: Scaling Safe Goal-Conditioned Policy Learning from One-Bit Failure Signals https://arxiv.org/abs/2608.26571 https://arxiv.org/pdf/2608.26571 https://arxiv.org/html/2608.26571
August 28, 2026 at 6:42 AM
arxiv-cs-cl.bsky.social
Hongqiu Ni, Han Tian, Chi Zhang, Guopeng Li, Haisheng Tan
TOPAS: Workflow-Aware Prefix-State Scheduling for Multi-Agent LLM Serving
https://arxiv.org/abs/2608.25523
August 27, 2026 at 3:30 PM
cscl-bot.bsky.social
Hongqiu Ni, Han Tian, Chi Zhang, Guopeng Li, Haisheng Tan: TOPAS: Workflow-Aware Prefix-State Scheduling for Multi-Agent LLM Serving https://arxiv.org/abs/2608.25523 https://arxiv.org/pdf/2608.25523 https://arxiv.org/html/2608.25523
August 27, 2026 at 6:40 AM
arxiv-cs-ro.bsky.social
Zhenjie Yang, Xingyu Jiao, Guopeng Zhong, Shuzhe Yang, Shi Che, Chao Wu, Chenyu Jiang, Dongjie Zhang, Yideng Zhang, Zheng Zhang, Muyun Jiang, Haisheng Su, ...
HandEdit: A Unified Benchmark for Egocentric Human-to-Robot Dexterous Hand Image Editing
https://arxiv.org/abs/2608.12122
August 14, 2026 at 3:56 AM
paper.bsky.social
[14/30] 40 Likes, 4 Comments, 1 Posts
2603.20422, cs․CV | cs․AI | cs․IR, 20 Mar 2026

🆕PEARL: Personalized Streaming Video Understanding Model

Yuanhong Zheng, Ruichuan An, Xiaopeng Lin, Yuxing Liu, Sihan Yang, Huanyu Zhang, Haodong Li, Qintong Zhang, Renrui Zhang, Guopeng Li, Yifan Zhang, Yu...
Human cognition of new concepts is inherently a streaming process: we continuously recognize new objects or identities and update our memories over time. However, current multimodal personalization methods are largely limited to static images or offline videos. This disconnects continuous visual input from instant real-world feedback, limiting their ability to provide the real-time, interactive personalized responses essential for future AI assistants. To bridge this gap, we first propose and formally define the novel task of Personalized Streaming Video Understanding (PSVU). To facilitate research in this new direction, we introduce PEARL-Bench, the first comprehensive benchmark designed specifically to evaluate this challenging setting. It evaluates a model's ability to respond to personalized concepts at exact timestamps under two modes: (1) Frame-level, focusing on a specific person or object in discrete frames, and (2) a novel Video-level, focusing on personalized actions unfolding across continuous frames. PEARL-Bench comprises 132 unique videos and 2,173 fine-grained annotations with precise timestamps. Concept diversity and annotation quality are strictly ensured through a combined pipeline of automated generation and human verification. To tackle this challenging new setting, we further propose PEARL, a plug-and-play, training-free strategy that serves as a strong baseline. Extensive evaluations across 8 offline and online models demonstrate that PEARL achieves state-of-the-art performance. Notably, it brings consistent PSVU improvements when applied to 3 distinct architectures, proving to be a highly effective and robust strategy. We hope this work advances vision-language model (VLM) personalization and inspires further research into streaming personalized AI assistants. Code is available at https://github.com/Yuanhong-Zheng/PEARL.
April 11, 2026 at 12:11 AM
natrevbiodiv.nature.com
Liang (@guopeng-liang.bsky.social) on a paper by Chen et al: go.nature.com/4b38kbj
Tree diversity increases soil carbon accumulation - Nature Reviews Biodiversity
Nature Reviews Biodiversity - Tree diversity increases soil carbon accumulation
go.nature.com
February 17, 2025 at 11:27 AM
jpecol.bsky.social
Guopeng Wu et al. explored divergent accumulation of soil amino sugars and lignin phenols during Castanopsis hystrix plantation #Restoration.

#Microbial-derivedC | #Plant-derivedC | #ForestEcosystem | #ForestSoil

doi.org/10.1093/jpe/...
January 11, 2026 at 3:06 PM
babygoldie.bsky.social
[1/3] 2026-07-07 15:19:23 - [CATL established a new company in Langfang with a registered capital of 5 million yuan] Tianyancha App shows that Times Qiji New Energy Technology (Langfang) Co., Ltd. was recently established. The legal representative is Liu Guopeng and the registered
July 7, 2026 at 7:34 AM
babygoldie.bsky.social
[1/3] 2026-07-07 15:19:23 - [CATL established a new company in Langfang with a registered capital of 5 million yuan] Tianyancha App shows that Times Qiji New Energy Technology (Langfang) Co., Ltd. was recently established. The legal representative is Liu Guopeng and the registered
July 7, 2026 at 7:33 AM
babygoldie.bsky.social
[1/3] 2026-07-07 15:19:23 - [CATL established a new company in Langfang with a registered capital of 5 million yuan] Tianyancha App shows that Times Qiji New Energy Technology (Langfang) Co., Ltd. was recently established. The legal representative is Liu Guopeng and the registered
July 7, 2026 at 7:30 AM
babygoldie.bsky.social
[1/3] 2026-07-07 15:19:23 - [CATL established a new company in Langfang with a registered capital of 5 million yuan] Tianyancha App shows that Times Qiji New Energy Technology (Langfang) Co., Ltd. was recently established. The legal representative is Liu Guopeng and the registered
July 7, 2026 at 7:24 AM