activity
20242026
collaborators

6 papers

cs.AI2026

A Formal Comparison Between Chain of Thought and Latent Thought

Kevin Xu, Issei Sato

Chain of thought (CoT) elicits reasoning in large language models by explicitly generating intermediate tokens. In contrast, latent thought reasoning operates directly in the conti…

cs.NE2025

Neural Cellular Automata for ARC-AGI

Kevin Xu, Risto Miikkulainen

Cellular automata and their differentiable counterparts, Neural Cellular Automata (NCA), are highly expressive and capable of surprisingly complex behaviors. This paper explores ho…

cs.LG2025

To CoT or To Loop? A Formal Comparison Between Chain-of-Thought and Looped Transformers

Kevin Xu, Issei Sato

Chain-of-Thought (CoT) and Looped Transformers have been shown to empirically improve performance on reasoning tasks and to theoretically enhance expressivity by recursively increa…

cs.LG2025

On Expressive Power of Looped Transformers: Theoretical Analysis and Enhancement via Timestep Encoding

Kevin Xu, Issei Sato

Looped Transformers provide advantages in parameter efficiency, computational capabilities, and generalization for reasoning tasks. However, their expressive power regarding functi…

cs.AI2025

Tur[k]ingBench: A Challenge Benchmark for Web Agents

Kevin Xu, Yeganeh Kordi, Tanay Nayak +7

Can advanced multi-modal models effectively tackle complex web-based tasks? Such tasks are often found on crowdsourcing platforms, where crowdworkers engage in challenging micro-ta…

cs.CL2024

Revisiting Absence withSymptoms that *T* Show up Decades Later to Recover Empty Categories

Emily Chen, Nicholas Huang, Casey Robinson +3

This paper explores null elements in English, Chinese, and Korean Penn treebanks. Null elements contain important syntactic and semantic information, yet they have typically been t…