BG
Bingjie Gao
cs.CVcs.CLcs.AIcs.SE
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, Qingyang Liu, Qianli Ma, Yibo Miao +5
1 version
Preprints & journals
10 papers in the corpus · 2025–2026From 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
The Right Future for Action: Learning Action-Relevant Predictive States in World Action Models2609.23369v1 · Qiwen Gu, Jifan Li, Bingjie Gao et al.2026 · 0 citationsarXiv
R2M-Bench: Evaluating Revisit Memory via Relative Consistency in Interactive Video World Models2608.27328v1 · Qiwen Gu, Bingjie Gao, Rui Chen et al.2026 · 0 citationsarXiv
Why Struggle with Continuous Latents? Interpretable Discrete Latent Reasoning via Rendered Compression2606.29712v1 · Shuochen Chang, Qingyang Liu, Shaobo Wang et al.2026 · 0 citationsarXiv
In-context Region-based Drag: Drag Any Region to Any Shape2606.25907v1 · Jiacheng Sui, Tianyu Hao, Bingjie Gao et al.2026 · 0 citationsarXiv
PermaVid: Consistent Video Generation Across Edits via Disentangled Context Memory2606.16449v2 · Shuai Yang, Bingjie Gao, Ziwei Liu et al.2026 · 0 citationsarXiv
DreamX-World 1.0: A General-Purpose Interactive World Model2606.16993v1 · DreamX Team, Yancheng Bai, Rui Chen et al.2026 · 0 citationsarXiv
Breaking Dual Bottlenecks: Evolving Unified Multimodal Models into Self-Adaptive Interleaved Visual Reasoners2605.14709v2 · Qingyang Liu, Bingjie Gao, Canmiao Fu et al.2026 · 0 citationsarXiv
Uni-Classifier: Leveraging Video Diffusion Priors for Universal Guidance Classifier2603.20382v1 · Yujie Zhou, Pengyang Ling, Jiazi Bu et al.2026 · 0 citationsarXiv
Human-Agent Collaborative Paper-to-Page Crafting2510.19600v2 · Qianli Ma, Siyu Wang, Yilin Chen et al.2025 · 0 citationsarXiv
Career total: 11 works. 10 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.