影响力指数

73.78/100

前 2.1%

全站排名 #1,331

发表论文19 篇

平均评分5.8

年均产出6.3 篇/年

Bill Yuchen Lin

Researcher@xAI·美国·OpenReview

研究方向

Large Language Model · Continual Learning · Embodied AI · Machine Learning · Natural Language Processing · Commonsense Reasoning

5.5

CrossWordBench: Evaluating the Reasoning Capabilities of LLMs and LVLMs with Controllable Puzzle Generation

COLM 2025Poster

6.3

HAICOSYSTEM: An Ecosystem for Sandboxing Safety Risks in Human-AI Interactions

ICLR 2025Rejected

5.8

Latent Action Pretraining from Videos

ICLR 2025Poster

5.7

Visual Perception in Text Strings

ICLR 2025Rejected

5.7

Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing

ICLR 2025Poster

通讯

5.5

ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning

ICML 2025Poster

一作

5.3

On Memorization of Large Language Models in Logical Reasoning

ICLR 2025Rejected

5.0

CulturalBench: a Robust, Diverse and Challenging Benchmark on Measuring (the Lack of) Cultural Knowledge of LLMs

合作者 (20)

Abhilasha Ravichander

Bill Yuchen Lin

ASCIIEval: Benchmarking Models' Visual Perception in Text Strings via ASCII Art

Temporal Sampling for Forgotten Reasoning in LLMs

WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild

CrossWordBench: Evaluating the Reasoning Capabilities of LLMs and LVLMs with Controllable Puzzle Generation

HAICOSYSTEM: An Ecosystem for Sandboxing Safety Risks in Human-AI Interactions

Latent Action Pretraining from Videos

Visual Perception in Text Strings

Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing

ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning

On Memorization of Large Language Models in Logical Reasoning

CulturalBench: a Robust, Diverse and Challenging Benchmark on Measuring (the Lack of) Cultural Knowledge of LLMs