Xi Zhao

papers

2,529

total citations

papers (10)

Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

ICLR 2025arXiv

2,226

citations

To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning

ICLR 2025arXiv

250

citations

Towards Doctor-Like Reasoning: Medical RAG Fusing Knowledge with Patient Analogy through Textual Gradients

NEURIPS 2025

citations

FALCON: An ML Framework for Fully Automated Layout-Constrained Analog Circuit Design

NEURIPS 2025arXiv

citations

ArchCAD-400K: A Large-Scale CAD drawings Dataset and New Baseline for Panoptic Symbol Spotting

NEURIPS 2025arXiv

citations

Two-Steps Diffusion Policy for Robotic Manipulation via Genetic Denoising

NEURIPS 2025arXiv

citations

Joint Design of Protein Surface and Backbone Using a Diffusion Bridge Model

NEURIPS 2025

citations

Xi Zhao

papers (10)

Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning

X-NeMo: Expressive Neural Motion Reenactment via Disentangled Latent Attention

Have the VLMs Lost Confidence? A Study of Sycophancy in VLMs

Boosting LLM Reasoning via Spontaneous Self-Correction

Towards Doctor-Like Reasoning: Medical RAG Fusing Knowledge with Patient Analogy through Textual Gradients

FALCON: An ML Framework for Fully Automated Layout-Constrained Analog Circuit Design

ArchCAD-400K: A Large-Scale CAD drawings Dataset and New Baseline for Panoptic Symbol Spotting

Two-Steps Diffusion Policy for Robotic Manipulation via Genetic Denoising

Joint Design of Protein Surface and Backbone Using a Diffusion Bridge Model

papers (10)

Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning

X-NeMo: Expressive Neural Motion Reenactment via Disentangled Latent Attention

Have the VLMs Lost Confidence? A Study of Sycophancy in VLMs

Boosting LLM Reasoning via Spontaneous Self-Correction

Towards Doctor-Like Reasoning: Medical RAG Fusing Knowledge with Patient Analogy through Textual Gradients

FALCON: An ML Framework for Fully Automated Layout-Constrained Analog Circuit Design

ArchCAD-400K: A Large-Scale CAD drawings Dataset and New Baseline for Panoptic Symbol Spotting

Two-Steps Diffusion Policy for Robotic Manipulation via Genetic Denoising

Joint Design of Protein Surface and Backbone Using a Diffusion Bridge Model