1 citations · 1 across the 10 of their papers we have counts for
10 papers
HACK++: Towards More Effective Head-Aware Key-Value Compression for Efficient Visual Autoregressive Modeling
Ziran Qin, Yuchen Jiang, Mingbao Lin +4
Visual Autoregressive (VAR) models adopt a next-scale prediction paradigm, offering high-quality generation with substantially fewer decoding steps. However, existing VAR models su…
Reversible Diffusion Decoding for Diffusion Language Models
Xinyun Wang, Min Zhang, Sen Cui +4
Diffusion language models enable parallel token generation through block-wise decoding, but their irreversible commitments can lead to stagnation, where the reverse diffusion proce…
Autoregressive Image Generation Needs Only a Few Lines of Cached Tokens
Ziran Qin, Youru Lv, Mingbao Lin +4
Autoregressive (AR) visual generation has emerged as a powerful paradigm for image and multimodal synthesis, owing to its scalability and generality. However, existing AR image gen…
Progressive Supernet Training for Efficient Visual Autoregressive Modeling
Xiaoyue Chen, Yuling Shi, Kaiyuan Li +5
Visual Auto-Regressive (VAR) models significantly reduce inference steps through the "next-scale" prediction paradigm. However, progressive multi-scale generation incurs substantia…
Computing-In-Memory Aware Model Adaption For Edge Devices
Ming-Han Lin, Tian-Sheuan Chang
Computing-in-Memory (CIM) macros have gained popularity for deep learning acceleration due to their highly parallel computation and low power consumption. However, limited macro si…
Beyond Benchmarks: Understanding Mixture-of-Experts Models through Internal Mechanisms
Jiahao Ying, Mingbao Lin, Qianru Sun +1
Mixture-of-Experts (MoE) architectures have emerged as a promising direction, offering efficiency and scalability by activating only a subset of parameters during inference. Howeve…
ERTACache: Error Rectification and Timesteps Adjustment for Efficient Diffusion
Xurui Peng, Chenqian Yan, Hong Liu +6
Diffusion models suffer from substantial computational overhead due to their inherently iterative inference process. While feature caching offers a promising acceleration strategy…
SynergyAmodal: Deocclude Anything with Text Control
Xinyang Li, Chengjie Yi, Jiawei Lai +4
Image deocclusion (or amodal completion) aims to recover the invisible regions (\ie, shape and appearance) of occluded instances in images. Despite recent advances, the scarcity of…
Head-Aware KV Cache Compression for Efficient Visual Autoregressive Modeling
Ziran Qin, Youru Lv, Mingbao Lin +4
Visual Autoregressive (VAR) models adopt a next-scale prediction paradigm, offering high-quality content generation with substantially fewer decoding steps. However, existing VAR m…
CAKE: Cascading and Adaptive KV Cache Eviction with Layer Preferences
Ziran Qin, Yuchen Cao, Mingbao Lin +5
Large language models (LLMs) excel at processing long sequences, boosting demand for key-value (KV) caching. While recent efforts to evict KV cache have alleviated the inference bu…