Yicheng Ji

3 papers · 2025–2026 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (11)

Venues

ACL (1) CVPR (1) EMNLP (1)

Top co-authors

Huan Li (3) Jinpeng Chen (2) Jun Zhang (2) Gang Chen (2) Cong Wang (2) Lidan Shou (2) Quan Kong (1) Yuhao Shen (1) Heming Xia (1)

Research topics

Computer Vision (3) Artificial Intelligence (2) Deep Learning (2) Core AI · Artificial Intelligence (2) Processing (2) Machine Learning (1) Application Areas (1) Architectures (1) Core AI · Computer Vision (1) Learning Types (1) Models (1) Optimization & Theory (1)

Keywords

speculative decoding (3) video understanding (2) video large language model (2) token pruning (2) decoder efficiency (1) verifier guidance (1) video token (1) visual semantic guidance (1) autoregressive generation (1) attention-guided pruning (1) efficient inference (1) autoregressive decoding (1) video token reduction (1)

Papers

ParallelVLM: Lossless Video-LLM Acceleration with Visual Alignment Aware Parallel Speculative Decoding CVPR 2026 See the Forest for the Trees: Loosely Speculative Decoding via Visual-Semantic Guidance for Efficient Inference of Video LLMs ACL 2026 SpecVLM: Enhancing Speculative Decoding of Video LLMs via Verifier-Guided Token Pruning EMNLP 2025