activity
20242026
most citedReciNet: Reciprocal Space-Aware Long-Range Modeling for Crystalline Property Prediction

1 citations · 1 across the 2 of their papers we have counts for

collaborators

10 papers

cs.LG20261 cited

ReciNet: Reciprocal Space-Aware Long-Range Modeling for Crystalline Property Prediction

Jianan Nie, Peiyao Xiao, Kaiyi Ji +1

Predicting properties of crystals from their structures is a fundamental yet challenging task in materials science. Unlike molecules, crystal structures exhibit infinite periodic a…

cs.LG2026

Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs

Hao Ban, Kaiyi Ji

Large language models are often adapted using parameter-efficient techniques such as Low-Rank Adaptation (LoRA), formulated as , where is the pre-trained para…

cs.LG2026

DeepMTL2R: A Library for Deep Multi-task Learning to Rank

Chaosheng Dong, Peiyao Xiao, Yijia Wang +1

This paper presents DeepMTL2R, an open-source deep learning framework for Multi-task Learning to Rank (MTL2R), where multiple relevance criteria must be optimized simultaneously. D…

cs.RO2025

Imperative Learning: A Self-supervised Neuro-Symbolic Learning Framework for Robot Autonomy

Chen Wang, Kaiyi Ji, Junyi Geng +16

Data-driven methods such as reinforcement and imitation learning have achieved remarkable success in robot autonomy. However, their data-centric nature still hinders them from gene…

cs.LG2025

LDC-MTL: Balancing Multi-Task Learning through Scalable Loss Discrepancy Control

Peiyao Xiao, Chaosheng Dong, Shaofeng Zou +1

Multi-task learning (MTL) has been widely adopted for its ability to simultaneously learn multiple tasks. While existing gradient manipulation methods often yield more balanced sol…

cs.LG2025

SAMO: A Lightweight Sharpness-Aware Approach for Multi-Task Optimization with Joint Global-Local Perturbation

Hao Ban, Gokul Ram Subramani, Kaiyi Ji

Multi-task learning (MTL) enables a joint model to capture commonalities across multiple tasks, reducing computation costs and improving data efficiency. However, a major challenge…