ZL
Zhaohe Liao
cs.CVcs.LGcs.AIcs.CLcs.NE
On Valency
published · living versionsW_93u3d2fg·v1 · currentpublished
From Label Priors to Task Evidence: Efficient Long-Video Frame Selection via Bayesian GRPO
with Shuochen Chang, Bingjie Gao, Qingyang Liu, Qianli Ma +5
1 version
Preprints & journals
11 papers in the corpus · 2020–2026From Label Priors to Task Evidence: Efficient Long-Video Frame Selection via Bayesian GRPO2610.25418v1 · Shuochen Chang, Bingjie Gao, Qingyang Liu et al.2026 · 0 citationsarXivon Valency
Beyond Binary Preferences: Graded Preference Optimization for Limb-Motion Captioning2609.36628v1 · Yanan Wang, Tingsong Li, Kaixun Jiang et al.2026 · 0 citationsarXiv
AffineTok: Semantic Affine Consistency for Diffusion-Friendly Visual Tokenizer2608.23864v1 · Junqiu Yu, Pandeng Li, Yikai Wang et al.2026 · 0 citationsarXiv
Unlocking the Black Box of Latent Reasoning: An Interpretability-Guided Approach to Intervention2606.01243v1 · Shuochen Chang, Tong Bai, Xiaofeng Zhang et al.2026 · 1 citationACL2026 Main
Parse, Align and Aggregate: Graph-Driven Compositional Reasoning for Video Question Answering.41525566 · Li, Jiangtong, Liao, Zhaohe, Xiao, Fengshun et al.2026 · 1 citationIEEE transactions on pattern analysis and machine intelligence. 2026;48(5):5586-5603
Bottleneck Tokens for Unified Multimodal Retrieval2604.11095v1 · Siyu Sun, Jing Ren, Zhaohe Liao et al.2026 · 0 citationsarXiv
AIBench: Evaluating Visual-Logical Consistency in Academic Illustration Generation2603.28068v2 · Zhaohe Liao, Kaixun Jiang, Zhihang Liu et al.2026 · 0 citationsarXiv
ShowTable: Unlocking Creative Table Visualization with Collaborative Reflection and Refinement2512.13303v2 · Zhihang Liu, Xiaoyi Bao, Pandeng Li et al.2025 · 0 citationsarXiv
AnimateScene: Camera-controllable Animation in Any Scene2508.05982v2 · Qingyang Liu, Bingjie Gao, Weiheng Huang et al.2025 · 0 citationsarXiv
Align and Aggregate: Compositional Reasoning with Video Alignment and Answer Aggregation for Video Question-Answering2407.03008v1 · Zhaohe Liao, Jiangtong Li, Li Niu et al.2024 · 9 citationsCVPR (2024) 13395-13404
Trainable Activation Function in Image Classification2004.13271v2 · Zhaohe Liao2020 · 6 citationsarXiv
Career total: 15 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.