WZ

Wang Bill Zhu

cs.CLcs.AIcs.CVcs.SEcs.HCcs.LGcs.CY

On Valency

published · living versions

W_d6hr2h9s·v1 · currentpublished

Language Impairment as a Lens onto Large Language Models

with Muxuan He, Yue Chen, Elsi Kaiser, Weizhi Du +3

1 version

Preprints & journals

11 papers in the corpus · 2024–2026

Language Impairment as a Lens onto Large Language Models2610.28992v1 · Muxuan He, Wang Bill Zhu, Yue Chen et al.2026 · 0 citationsarXivon Valency

PreciseCoder: Faithful and Generalizable Debugging Beyond Unit-Test Rewards2610.18755v1 · Yunkai Zhan, Miaosen Chai, Shangshang Wang et al.2026 · 0 citationsarXiv

EUDAIMONIA: Evaluating Undesirable Dynamics in AI2605.30654v2 · Jun Rui Huang, Wang Bill Zhu, Ziyi Liu et al.2026 · 0 citationsarXiv

Generating Complex Code Analyzers from Natural Language Questions2605.09304v1 · Amirmohammad Nazari, Sadra Sabouri, Wang Bill Zhu et al.2026 · 0 citationsarXiv

Algorithmic Primitives of Theory of Mind Benchmarks2604.17819v2 · Qiutong Tony Yi, Wang Bill Zhu, Robin Jia et al.2026 · 0 citationsarXiv

Precise Debugging Benchmark: Is Your Model Debugging or Regenerating?2604.17338v5 · Miaosen Chai, Wang Bill Zhu, Shangshang Wang et al.2026 · 0 citationsarXiv

Self-Evolving LLM Memory Extraction Across Heterogeneous Tasks2604.11610v1 · Yuqing Yang, Tengxiao Liu, Wang Bill Zhu et al.2026 · 0 citationsarXiv

Zebra-CoT: A Dataset for Interleaved Vision Language Reasoning2507.16746v2 · Ang Li, Charles Wang, Deqing Fu et al.2025 · 0 citationsarXiv

Cancer-Myth: Evaluating Large Language Models on Patient Questions with False Presuppositions2504.11373v3 · Wang Bill Zhu, Tianqi Chen, Xinyan Velocity Yu et al.2025 · 2 citationsarXiv

VisualLens: Personalization through Task-Agnostic Visual History2411.16034v2 · Wang Bill Zhu, Deqing Fu, Kai Sun et al.2024 · 0 citationsarXiv

TLDR: Token-Level Detective Reward Model for Large Vision Language Models2410.04734v2 · Deqing Fu, Tong Xiao, Rui Wang et al.2024 · 0 citationsarXiv

Career total: 31 works. 11 are in this corpus.

Profile built from the corpus for this byline.

Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.