影响力指数

74.36/100

前 2%

全站排名 #1,273

发表论文19 篇

平均评分5.9

年均产出6.3 篇/年

Zhiting Hu

Assistant Professor@University of California, San Diego·美国·OpenReview

研究方向

Deep learning · deep generative modeling · text generation · machine learning · natural language processing · deep learning

6.4

Emergence of Superposition: Unveiling the Training Dynamics of Chain of Continuous Thought

ICLR 2026Poster

三作

4.5

FIRE-Bench: Evaluating Research Agents on the Rediscovery of Scientific Insights

ICLR 2026Rejected

通讯

7.3

Reasoning by Superposition: A Theoretical Perspective on Chain of Continuous Thought

NeurIPS 2025Poster

三作

7.3

Towards General Continuous Memory for Vision-Language Models

NeurIPS 2025Poster

7.3

Synthesizing Photorealistic and Dynamic Urban Environments for Multimodal Robot Navigation and Collaboration

NeurIPS 2025Poster

7.3

SimWorld: An Open-ended Simulator for Agents in Physical and Social Worlds

NeurIPS 2025Spotlight

7.1

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models

NeurIPS 2025Spotlight

6.4

Synthesizing Privacy-Preserving Text Data via Finetuning without Finetuning Billion-Scale LLMs

ICML 2025Poster

6.4

scPilot: Large Language Model Reasoning Toward Automated Single-Cell Analysis and Discovery

NeurIPS 2025Poster

6.3

Training Large Language Models to Reason in a Continuous Latent Space

COLM 2025Poster

5.8

Training Large Language Model to Reason in a Continuous Latent Space

合作者 (20)

Zhiting Hu

Emergence of Superposition: Unveiling the Training Dynamics of Chain of Continuous Thought

ArcMemo: Abstract Reasoning Composition with Lifelong LLM Memory

Auto-scaling Continuous Memory for GUI Agent

Learning Modal-mixed Chain-of-thought Reasoning with Latent Embedding

FIRE-Bench: Evaluating Research Agents on the Rediscovery of Scientific Insights

Reasoning by Superposition: A Theoretical Perspective on Chain of Continuous Thought

Towards General Continuous Memory for Vision-Language Models

Synthesizing Photorealistic and Dynamic Urban Environments for Multimodal Robot Navigation and Collaboration

SimWorld: An Open-ended Simulator for Agents in Physical and Social Worlds

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models

Synthesizing Privacy-Preserving Text Data via Finetuning *without* Finetuning Billion-Scale LLMs

scPilot: Large Language Model Reasoning Toward Automated Single-Cell Analysis and Discovery

Training Large Language Models to Reason in a Continuous Latent Space

Training Large Language Model to Reason in a Continuous Latent Space

Synthesizing Privacy-Preserving Text Data via Finetuning without Finetuning Billion-Scale LLMs