works on

From the 1 of 9 linked papers with an AI index.

activity
20242026
collaborators

9 papers

cs.LG2026

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

Zijie Liu, Jie Peng, Jinhao Duan +7

The paper proposes a training‑free method that replicates heavily used experts and quantizes less important ones to rebalance workload in sparse mixture‑of‑experts large language m…

cs.AI2026

LEC: Linear Expectation Constraints for Selection-Conditioned Risk Control in Selective Prediction and Routing Systems

Zhiyuan Wang, Aniri, Tianlong Chen +4

Foundation models often generate unreliable answers, while heuristic uncertainty estimators fail to fully distinguish correct from incorrect outputs, causing users to accept errone…

cs.CY2026

Can Multimodal LLMs See Science Instruction? Benchmarking Pedagogical Reasoning in K-12 Classroom Videos

Yixuan Shen, Peng He, Honglu Liu +6

K-12 science classrooms are rich sites of inquiry where students coordinate phenomena, evidence, and explanatory models through discourse; yet, the multimodal complexity of these i…

cs.AI2025

AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Prediction

Song Wang, Zhen Tan, Zihan Chen +3

Recent progress in large language model (LLM)-based multi-agent collaboration highlights the power of structured communication in enabling collective intelligence. However, existin…

cs.CL2025

SConU: Selective Conformal Uncertainty in Large Language Models

Zhiyuan Wang, Qingni Wang, Yue Zhang +4

As large language models are increasingly utilized in real-world applications, guarantees of task-specific metrics are essential for their reliable deployment. Previous studies hav…

cs.CL2025

COIN: Uncertainty-Guarding Selective Question Answering for Foundation Models with Provable Risk Guarantees

Zhiyuan Wang, Jinhao Duan, Qingni Wang +4

Uncertainty quantification (UQ) for foundation models is essential to identify and mitigate potential hallucinations in automatically generated text. However, heuristic UQ approach…