Jie Peng

Select the Key, Then Generate the Rest: Improving Multi-Modal Learning with Limited Data Budget

Graph-of-Agents: A Graph-based Framework for Multi-Agent LLM Collaboration

GRACE-MoE: Grouping and Replication with Locality-Aware Routing for Efficient Distributed MoE Inference

$GEM$: 3D Gaussian Splatting for Efficient and Accurate Cryo-EM Reconstruction

AlphaFormer: End-to-End Symbolic Regression of Alpha Factors with Transformers

Learning Flexible Large Multimodal Models with Arbitrary Modality Combinations

(Be Cautious!) Bio-Foundation Models Are Not Yet Robust to Biological Plausible Perturbations and ML Transformations

Adaptive Sensor Selection for Power Efficient 3D Object Detection on Autonomous Driving

Symbiotic Cooperation for Web Agents: Harnessing Complementary Strengths of Large and Small LLMs

scMoE: single-cell Multi-Modal Multi-Task Learning via Sparse Mixture-of-Experts

Mozart: Modularized and Efficient MoE Training on 3.5D Wafer-Scale Chiplet Architectures

Occult: Optimizing Collaborative Communications across Experts for Accelerated Parallel MoE Training and Inference

Modalities Contribute Unequally: Enhancing Medical Multi-modal Learning through Adaptive Modality Token Re-balancing

$I$^2$MoE$: Interpretable Multimodal Interaction-aware Mixture-of-Experts

$UQ-Merge$: UNCERTAINTY GUIDED MULTIMODAL LARGE LANGUAGE MODEL MERGING

Sparse MoE as a New Retriever: Addressing Missing Modality Problem in Incomplete Multimodal Data

$LLaPA$: Harnessing Language Models for Protein Enzyme Function

Replicate and Quantize: A Plug-and-Play Strategy for Load Balancing in Sparse Mixture-of-Experts LLMs

Regularized Optimal Transport for Single-Cell Temporal Trajectory Analysis

Glider: Global and Local Instruction-Driven Expert Router

Enhancing single-cell Multi-Modal Multi-Task Learning via Sparse Mixture-of-Experts

Multimodal Graph-LLM: Leveraging Graph-Enhanced LLMs for Multimodal Healthcare Predictions