5 papers
Branch-JEPA: Finite-Support Predictive Distributions for JEPA World Models
Zhi Song, Ximing Xing, Zhenchao Tang +9
Joint-embedding predictive architectures (JEPAs) learn dynamics by predicting future observations in representation space. Yet most JEPA world models return one latent successor, e…
Aligning LLMs with Biomedical Knowledge using Balanced Fine-Tuning
Zhenchao Tang, Fang Wang, Haohuai He +12
Engineering LLMs to accelerate life sciences research requires a robust alignment with biomedical knowledge. We observe that biomedical text exhibits a fundamentally different unce…
PulseBat: A field-accessible dataset for second-life battery diagnostics from realistic histories using multidimensional rapid pulse test
Shengyu Tao, Guangyuan Ma, Huixiong Yang +4
As electric vehicles (EVs) approach the end of their operational life, their batteries retain significant economic value and present promising opportunities for second-life use and…
Meta-Learn Unimodal Signals with Weak Supervision for Multimodal Sentiment Analysis
Sijie Mai, Yu Zhao, Ying Zeng +2
Multimodal sentiment analysis aims to effectively integrate information from various sources to infer sentiment, where in many cases there are no annotations for unimodal labels. T…
StableMask: Refining Causal Masking in Decoder-only Transformer
Qingyu Yin, Xuzheng He, Xiang Zhuang +4
The decoder-only Transformer architecture with causal masking and relative position encoding (RPE) has become the de facto choice in language modeling. Despite its exceptional perf…