Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models
Paper • 2405.14297 • Published • 3
XiaoyingTANG
XiaoyingTANG
AI & ML interests
None yet
Organizations
None yet
authored 8
papers 6 months ago
FedBR: Improving Federated Learning on Heterogeneous Data via Local Learning Bias Reduction
Paper • 2205.13462 • Published
VTG-LLM: Integrating Timestamp Knowledge into Video LLMs for Enhanced Video Temporal Grounding
Paper • 2405.13382 • Published • 1
FedRC: Tackling Diverse Distribution Shifts Challenge in Federated Learning by Robust Clustering
Paper • 2301.12379 • Published
Difficult Task Yes but Simple Task No: Unveiling the Laziness in Multimodal LLMs
Paper • 2410.11437 • Published
TRACE: Temporal Grounding Video LLM via Causal Event Modeling
Paper • 2410.05643 • Published • 9
G$^2$RPO-A: Guided Group Relative Policy Optimization with Adaptive Guidance
Paper • 2508.13023 • Published • 1
The End of Manual Decoding: Towards Truly End-to-End Language Models
Paper • 2510.26697 • Published • 119