5 papers
GTR: Gated Token Recurrence for Efficient Dense Prediction
Zhe Feng, Longfei Liu, Wei Liu +7
Self-attention-based vision backbones perform well on dense prediction, but the quadratic computational cost of global softmax attention limits their efficiency as image resolution…
Rethinking Normalization Placement for LLMs: Post-Norm under Curriculum Depth Growing
Sheng Ren, Yadong Wang, Naiqiang Tan +7
Pre-norm is the standard normalization placement in modern Transformers because it facilitates joint optimization of full-depth models. We ask whether this preference persists when…
SKEL-CF: Coarse-to-Fine Biomechanical Skeleton and Surface Mesh Recovery
Da Li, Jiping Jin, Xuanlong Yu +6
Parametric 3D human models such as SMPL have driven significant advances in human pose and shape estimation, yet their simplified kinematics limit biomechanical realism. The recent…
InstCache: A Predictive Cache for LLM Serving
Longwei Zou, Yan Liu, Jiamu Kang +3
The revolutionary capabilities of Large Language Models (LLMs) are attracting rapidly growing popularity and leading to soaring user requests to inference serving systems. Caching…
CQIL: Inference Latency Optimization with Concurrent Computation of Quasi-Independent Layers
Longwei Zou, Qingyang Wang, Han Zhao +3
The fast-growing large scale language models are delivering unprecedented performance on almost all natural language processing tasks. However, the effectiveness of large language…