Qiang Liu

activity

20242026

most citedSteinDreamer: Variance Reduction for Text-to-3D Score Distillation via Stein Identity

3 citations · 4 across the 4 of their papers we have counts for

collaborators

Showing 2026Show all

1 paper · 1 filter

cs.LG2026

$\nabla$ -Reasoner: LLM Reasoning via Test-Time Gradient Descent in Latent Space

Peihao Wang, Ruisi Cai, Zhen Wang +4

Scaling inference-time compute for Large Language Models (LLMs) has unlocked unprecedented reasoning capabilities. However, existing inference-time scaling methods typically rely o…

∇-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Latent Space

$\nabla$ -Reasoner: LLM Reasoning via Test-Time Gradient Descent in Latent Space