Jingyu Liu

9

Papers

17

Total Citations

Papers (9)

Speculative Prefill: Turbocharging TTFT with Lightweight and Training-Free Token Importance Estimation

PALMBENCH: A COMPREHENSIVE BENCHMARK OF COMPRESSED LARGE LANGUAGE MODELS ON MOBILE PLATFORMS

D&M: Enriching E-commerce Videos with Sound Effects by Key Moment Detection and SFX Matching

Multi-Object Sketch Animation by Scene Decomposition and Motion Planning

Music Grounding by Short Video

Perfect Alignment May be Poisonous to Graph Contrastive Learning

TC-LLaVA: Rethinking the Transfer of LLava from Image to Video Understanding with Temporal Considerations

VTG-LLM: Integrating Timestamp Knowledge into Video LLMs for Enhanced Video Temporal Grounding

WaveNet: Tackling Non-stationary Graph Signals via Graph Spectral Wavelets