4 citations · 7 across the 15 of their papers we have counts for
8 papers · 1 filter
ReTrace: Rejected-Trajectory Conditioning for Speculative Decoding
Luxi Lin, Zhanpeng Zeng, Shuang Peng +2
Speculative decoding accelerates autoregressive language model inference by having a lightweight draft model propose multiple candidate tokens, which are then verified in parallel…
SelfLift: Accelerating Few-Step Diffusion via Self-Recovering Resolution Transition
Tingyan Wen, Chenqian Yan, Xurui Peng +4
Few-step diffusion models substantially compress temporal computation, making the spatial cost of each model evaluation an increasingly dominant source of inference latency. Progre…
Accelerating Unified Multimodal Models with Core-Expansion Routing and Unified Computation Scheduling
Wengyi Zhan, Chenqian Yan, Songwei Liu +2
Unified multimodal models jointly support understanding and generation, but incur substantial redundant computation across tokens, layers, and generation timesteps. Through token-i…
HyperDFlash: Hyper-Connection-Aligned Block Speculative Decoding with Gated Residual Reduction
Luxi Lin, Shuang Peng, Rui Ma +7
We present HyperDFlash, a block-parallel speculative decoding framework tailored to DeepSeek-V4's Hyper-Connections (HC). Despite the strong performance of DeepSeek-V4's native Mul…
Motion-Aware Caching for Efficient Autoregressive Video Generation
Jing Xu, Yuexiao Ma, Xuzhe Zheng +7
Autoregressive video generation paradigms offer theoretical promise for long video synthesis, yet their practical deployment is hindered by the computational burden of sequential i…
DreamLite: A Lightweight On-Device Unified Model for Image Generation and Editing
Kailai Feng, Yuxiang Wei, Bo Chen +5
Diffusion models have made significant progress in both text-to-image (T2I) generation and text-guided image editing. However, these models are typically built with billions of par…
AngelSlim: A more accessible, comprehensive, and efficient toolkit for large model compression
Rui Cen, QiangQiang Hu, Hong Huang +10
This technical report introduces AngelSlim, a comprehensive and versatile toolkit for large model compression developed by the Tencent Hunyuan team. By consolidating cutting-edge a…
S2O: Early Stopping for Sparse Attention via Online Permutation
Yu Zhang, Songwei Liu, Chenqian Yan +4
Attention scales quadratically with sequence length, fundamentally limiting long-context inference. Existing block-granularity sparsification can reduce latency, but coarse blocks…