activity
20242026
collaborators

7 papers

cs.CL2026

Extracting and Following Paths for Robust Relational Reasoning with Large Language Models

Ge Zhang, Mohammad Ali Alomrani, Hongjian Gu +7

Large language models (LLMs) possess vast semantic knowledge but often struggle with complex reasoning tasks, particularly in relational reasoning problems such as kinship or spati…

cs.LG2025

C3PO: Optimized Large Language Model Cascades with Probabilistic Cost Constraints for Reasoning

Antonios Valkanas, Soumyasundar Pal, Pavel Rumiantsev +2

Large language models (LLMs) have achieved impressive results on complex reasoning tasks, but their high inference cost remains a major barrier to real-world deployment. A promisin…

cs.LG2025

FEval-TTC: Fair Evaluation Protocol for Test-Time Compute

Pavel Rumiantsev, Soumyasundar Pal, Yingxue Zhang +1

The performance of Large Language Models (LLMs) and the associated dollar costs of API calls can fluctuate over time, potentially invalidating conclusions drawn in prior research.…

cs.LG2025

Half Search Space is All You Need

Pavel Rumiantsev, Mark Coates

Neural Architecture Search (NAS) is a powerful tool for automating architecture design. One-Shot NAS techniques, such as DARTS, have gained substantial popularity due to their comb…

cs.LG2025

Sparse Decomposition of Graph Neural Networks

Yaochen Hu, Mai Zeng, Ge Zhang +4

Graph Neural Networks (GNN) exhibit superior performance in graph representation learning, but their inference cost can be high, due to an aggregation operation that can require a…

cs.LG2025

Variation Matters: from Mitigating to Embracing Zero-Shot NAS Ranking Function Variation

Pavel Rumiantsev, Mark Coates

Neural Architecture Search (NAS) is a powerful automatic alternative to manual design of a neural network. In the zero-shot version, a fast ranking function is used to compare arch…