Author

Dong Fang

Observed name: Fang, Dong

Institution: Chinese University of Hong Kong

Observed institution: Chinese University of Hong Kong

OpenAlex ID: A5122535952

Vision-Language Introspection: Mitigating Overconfident Hallucinations in MLLMs via Interpretable Bi-Causal Steering

2026 · Association for Computational Linguistics 2026, Fang, Dong, et al. · Underline Science Inc.

Conditional Equivalence of DPO and RLHF: Implicit Assumption, Failure Modes, and Provable Alignment

2026 · Yang, Zhiqin, Zhang, Yonggang, et al. · arXiv (Cornell University)

GRAVITY: Architecture-Agnostic Structured Anchoring for Long-Horizon Conversational Memory

2026 · Sun, Yushi, Cao, Bowen, et al. · arXiv (Cornell University)

From Multi-Agent to Single-Agent: When Is Skill Distillation Beneficial?

2026 · Xu, Binyan, Fang, Dong, et al. · arXiv (Cornell University)

APEX-SQL: Talking to the data via Agentic Exploration for Text-to-SQL

2026 · Cao, Bowen, Liao, Weibin, et al. · arXiv (Cornell University)

Distilling the Thought, Watermarking the Answer: A Principle Semantic Guided Watermark for Large Reasoning Models

2026 · Liu, Shuliang, Li, Xingyu, et al. · arXiv (Cornell University)

Vision-Language Introspection: Mitigating Overconfident Hallucinations in MLLMs via Interpretable Bi-Causal Steering

2026 · Liu, Shuliang, Yang, Songbo, et al. · arXiv (Cornell University)

Vision-Language Introspection: Mitigating Overconfident Hallucinations in MLLMs via Interpretable Bi-Causal Steering

2026 · Shuliang Liu, Songbo Yang, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting

Works count: 8

Citation count:

H-index:

I10-index: