Skip to content

Author

Jin-Fa Huang

We have 6 of 27 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

SCOPE: Semantic Bounded Credit Optimization for Prompt Engineering in Text-to-image Generation

Reinforcement learning (RL) enables language models to improve text-to-image (T2I) generation by rewriting prompts for a frozen image generator. Existing methods typically apply a single signal derived from the image to individual subword tokens, although objects, counts, attributes, and relations form coherent semanti...

Yu-Fei Jiao, Jin-Fa Huang, Ze-Yue Xue et al. · 0 citations
Preprint Sep 2026

VideoLoop: Looped Working Memory Against Semantic Thrashing in Long-Form Video Agents

This work provides a structural argument showing that append-only memory can incorporate newly observed target evidence, but cannot remove accumulated noise or prevent ordered context growth without a rewrite operator, and proposes VideoLoop, a multimodal agent with two coupled loops.

Jian-Ming Xu, Jin-Fa Huang, Jing-Yang Lin et al. · 0 citations

SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models

SocialOmni is introduced, an offline diagnostic benchmark that separates three turn-level decisions: identifying who is speaking, deciding when a designated participant should enter at an annotated query time, and determining how that participant should continue the dialogue.

Tian-Yu Xie, Jin-Fa Huang, Yue-Xiao Ma et al. · 12 citations · ⚡1
Preprint Aug 2026

One Ranking, Any Budget: Matryoshka Evidence-to-Context Frame Selection for Long-Video Understanding

Matryoshka Evidence-to-Context (MEC) Frame Selection is introduced, a training-free framework that builds a reusable sparse video index, discovers candidates through sparse probing and local zooming, and greedily constructs a position-adaptive ranking - early positions emphasize evidence; later positions progressively...

Wang Chen, Yu Chen, Xiang Wang et al. · 1 citation · ⚡1
Jul 2026

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation

WaveZip is proposed, a joint signal-frequency-domain framework for efficient video inference that requires no task-specific training and can be seamlessly integrated into off-the-shelf LVLMs to boost inference efficiency.

Yuhui Zeng, Wang Chen, Jin-Fa Huang et al. · 1 citation
Jul 2026

TimePLE: Rethinking Temporal Representation for Video Temporal Grounding

TimePLE is proposed, which reformulates VTG from endpoint prediction to interval-native grounding by predicting a single joint distribution over valid temporal intervals, and curate 90K-scale grounded samples and human-verify 3K-scale benchmark annotations.

Yuhui Zeng, Xin-Yu Mao, Xiaokun Liu et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.