Yafeng Deng

Yafeng Deng

Auto-generated profile, based on publicly available information

Yafeng Deng

Evermind AI, INC., California, USA

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 March 2025 in Science Advances
Verified
Journal Article
Open access
JWJike Wang
Jike Wang
JFJianwen Feng
Jianwen Feng
YKYu Kang
Yu Kang
PPPeichen Pan
Peichen Pan
JGJingxuan Ge
Jingxuan Ge
THTingjun Hou
Tingjun Hou
Large language models (LLMs) have shown remarkable advancements in chemistry and biomedical research, acting as versatile foundation models for various tasks. We introduce AMP-Designer, an LLM-based approach, for swiftly designing antimicrobial peptides (AMPs) with desired properties. Within 11 days, AMP-Designer achieved the de novo design of 18 AMPs with broad-spectrum activity against Gram-negative bacteria. In vitro validation revealed a 94.4% success rate, with two candidates demonstrating exceptional antibacterial efficacy, minimal hemotoxicity, stability in human plasma, and low potential to induce resistance, as evidenced by significant bacterial load reduction in murine lung infection experiments. The entire process, from design to validation, concluded in 48 days. AMP-Designer excels in creating AMPs targeting specific strains despite limited data availability, with a top candidate displaying a minimum inhibitory concentration of 2.0 micrograms per milliliter against Propionibacterium acnes . Integrating advanced machine learning techniques, AMP-Designer demonstrates remarkable efficiency, paving the way for innovative solutions to antibiotic resistance.

31 July 2025 in Nature Communications
Verified
Journal Article
Open access
PDF file
YDYafeng Deng
Yafeng Deng
XZXinda Zhao
Xinda Zhao
HSHanyu Sun
Hanyu Sun
YCYu Chen
Yu Chen
XWXiaorui Wang
Xiaorui Wang
XWXiaojian Wang
Xiaojian Wang
Retrosynthesis planning is a crucial task in organic synthesis, and deep-learning methods have enhanced and accelerated this process. With the advancement of the emergence of large language models, the demand for data is rapidly increasing. However, available retrosynthesis data are limited to only millions. Therefore, we pioneer the utilization of the template-based algorithm to generate chemical reaction data, resulting in the production of over 10 billion reaction datapoints. A generative pretrained transformer model is subsequently developed for template-free retrosynthesis planning by pre-training on 10 billion generated data. Inspired by the strategies of large language models, we introduce reinforcement learning to capture the relationships among products, reactants, and templates more accurately. Experiments demonstrate that our model achieves state-of-the-art performance on the benchmark, with a Top-1 accuracy of 63.4%, substantially outperforming previous models.

21 August 2023 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
XMXin Ma
Xin Ma
CLChang Liu
Chang Liu
CXChunyu Xie
Chunyu Xie
LYLong Ye
Long Ye
YDYafeng Deng
Yafeng Deng
XJXiangyang Ji
Xiangyang Ji
Masked image modeling (MIM) has shown great promise for self-supervised learning (SSL) yet been criticized for learning inefficiency. We believe the insufficient utilization of training signals should be responsible. To alleviate this issue, we introduce a conceptually simple yet learning-efficient MIM training scheme, termed D isjoint M asking with J oint D istillation (DMJD). For disjoint masking (DM), we sequentially sample multiple masked views per image in a mini-batch with the disjoint regulation to raise the usage of tokens for reconstruction in each image while keeping the masking rate of each view. For joint distillation (JD), we adopt a dual branch architecture to respectively predict invisible (masked) and visible (unmasked) tokens with superior learning targets. Rooting in orthogonal perspectives for training efficiency improvement, DM and JD cooperatively accelerate the training convergence yet not sacrificing the model generalization ability. Concretely, DM can train ViT with less effective training epochs (at most $3.7\times$ less time-consuming) to report competitive performance. With JD, our DMJD clearly improves the linear probing classification accuracy, up to 3.4 $\%$ . On fine-grained downstream tasks like semantic segmentation, object detection, etc. , our DMJD also presents superior generalization compared with state-of-the-art SSL methods. The code and model can be found at https://github.com/mx-mark/DMJD .

26 October 2023
Verified
Conference Paper
Open access
CXChunyu Xie
Chunyu Xie
HCHeng Cai
Heng Cai
JLJincheng Li
Jincheng Li
FKFanjing Kong
Fanjing Kong
XWXiaoyu Wu
Xiaoyu Wu
YDYafeng Deng
Yafeng Deng
Vision-language pre-training (VLP) on large-scale datasets has shown premier performance on various downstream tasks. In contrast to plenty of available benchmarks with English corpus, large-scale pre-training datasets and downstream datasets with Chinese corpus remain largely unexplored. In this work, we build a large-scale high-quality Chinese Cross-Modal Benchmark named CCMB for the research community, which contains the currently largest public pre-training dataset Zero and five human-annotated fine-tuning datasets for downstream tasks. Zero contains 250 million images paired with 750 million text descriptions, plus two of the five fine-tuning datasets are also currently the largest ones for Chinese cross-modal downstream tasks. Along with the CCMB, we also develop a VLP framework named R2D2, applying a pre-Ranking + Ranking strategy to learn powerful vision-language representations and a two-way distillation method (i.e., target-guided Distillation and feature-guided Distillation) to further enhance the learning capability. With the Zero and the R2D2 VLP framework, we achieve state-of-the-art performance on twelve downstream datasets from five broad categories of tasks including image-text retrieval, image-text matching, image caption, text-to-image generation, and zero-shot image classification. The datasets, models, and codes are available at https://github.com/yuxie11/R2D2


8 August 2026
Verified
Conference Paper
Open access
CHChuanrui Hu
Chuanrui Hu
TLTong Li
Tong Li
XGXingze Gao
Xingze Gao
HCHongda Chen
Hongda Chen
YBYi Bai
Yi Bai
YDYafeng Deng
Yafeng Deng
Long-term conversational memory in practical LLM applications is inherently collaborative: information is produced by multiple participants, scattered across groups and channels, revised over time, and implicitly grounded in roles and social context. Yet there is currently no established benchmark that evaluates memory under interaction patterns resembling real-world deployment, as existing benchmarks largely focus on dyadic or single-topic dialogues. In this paper, we introduce EverMemBench, the first benchmark designed for long-horizon collaborative memory, built from multi-party, multi-group conversations spanning over one million tokens with dense cross-topic interleaving, temporally evolving decisions, and role-conditioned personas. EverMemBench evaluates memory systems using 2,400 QA pairs across three dimensions essential for real applications: fine-grained recall, memory awareness, and user profile understanding. Our evaluation reveals fundamental limitations of current systems: multi-hop reasoning collapses under multi-party attribution even with oracle evidence (26% accuracy), temporal reasoning fails without explicit version semantics beyond timestamps, and memory awareness is bottlenecked by retrieval, as similarity-based methods miss implicitly relevant information. EverMemBench thus represents a concrete step toward realistic evaluation of LLM memory and a cornerstone benchmark for developing next-generation LLMs that reason over time, roles, and collaborative interaction structure. Our benchmark and code are publicly available at https://github.com/EverMind-AI/EverMemBench.