Skip to content
conftrace_

Jiaming Tang

3 papers · 2024–2025 · 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 🐣 Hot Topic Early Bird

Venues

ICCV (1) ICLR (1) ICML (1)

Top co-authors

Song Han (3) Junxian Guo (2) Shang Yang (2) Guangxuan Xiao (2) Baris Kasikci (1) Kan Zhu (1) Haotian Tang (1) Yilong Zhao (1) Zhijian Liu (1) Yukang Chen (1)

Research topics

Artificial Intelligence (3) Machine Learning (3) Application Areas (3) Core AI (3) Deep Learning (1) Natural Language Processing (1) Architectures (1) Optimization & Theory · Deep Learning (1) Optimization & Theory · Machine Learning (1) Resources & Methods (1)

Keywords

kv cache (2) attention mechanism (1) multimodal learning (1) efficient inference (1) neural network optimization (1) vision-language model (1) token pruning (1) inference efficiency (1) sparse attention (1) inference latency (1) self attention (1) large language model (1) prefill decoding (1) criticality (1) query-aware (1) model compression (1) topk (1)

Papers

DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads ICLR 2025 SparseVILA: Decoupling Visual Sparsity for Efficient VLM Inference ICCV 2025 QUEST: Query-Aware Sparsity for Efficient Long-Context LLM Inference ICML 2024