Get started
Author

Chih-Ting Liao

Observed name: Liao, Chih-Ting
Institution: UNSW Sydney
Observed institution: UNSW Sydney
ORCID: 0009-0008-2223-9131
Observed ORCID: 0009-0008-2223-9131
OpenAlex ID: A5053113105
Staying VIGILant: Mitigating Visual Laziness via Counterfactual Visual Alignment in MLLMs
2026 · Xi Xiao, Chen Liu, et al. · Lecture notes in computer science · 25
PDF
SpaMEM: Benchmarking Dynamic Spatial Reasoning via Perception–Memory Integration in Embodied Environments
2026 · Chih-Ting Liao, Xi Xiao, et al. · Lecture notes in computer science · 10
PDF
Present but Not Remembered: Auditing How Frozen VLAs Encode, Deploy, and Steer Visual History
2026 · Liao, Chih-Ting, Cao, Xin · arXiv (Cornell University) · 4
PDF
Decodable Is Not Grounded: A Vision-Ablation Arbiter for VLM Spatial Reasoning
2026 · Liao, Chih-Ting, Shen, Fei, et al. · arXiv (Cornell University) · 3
PDF
Adaptive Hierarchical Representation Alliance for Multimodal Learning
2026 · Chunlei Meng, Pengbin Feng, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · 2
PDF
Do LLMs Build World Models From Text? A Multilingual Diagnostic of Spatial Reasoning
2026 · Pan, Zhikai, Liao, Chih-Ting, et al. · arXiv (Cornell University) · 1
PDF
Reversion, Retention, and Semantic Intervention: Measuring Functional Content in CLIP Fine-Tuning Deltas
2026 · Liao, Chih-Ting, Bao, Kezhen, et al. · arXiv (Cornell University)
PDF
EviViT: Evidence-Adaptive Vision Transformers for Fine-Grained Perception
2026 · Niu, Yaoxin, Chen, Zhangquan, et al. · arXiv (Cornell University)
PDF
HaPRL: Human-Anchored Process Reinforcement Learning for Visual Search Agent
2026 · Chen, Zhangquan, Niu, Yaoxin, et al. · arXiv (Cornell University)
PDF
TempFinRAG: Multimodal Temporal Retrieval-Augmented Generation for Point-in-Time Financial Question Answering
2026 · Lanju Tao, Zhengji Li, et al. · Symmetry
The Objective Decides: When a Learned Dynamics Model Uses a Conserved Quantity
2026 · Liao, Chih-Ting, Cao, Xin · arXiv (Cornell University)
PDF
Brand-as-Memory: Vision-Language Models Encode Causal, Mechanistically Localizable Credibility Priors for News Sources
2026 · Liao, Chih-Ting, Cao, Xin · arXiv (Cornell University)
PDF
Works count: 12
Citation count: 45
H-index: 3
I10-index: 2
Year
Topic
Type