7 papers · 1 filter
VASC: Value-Aware Sparse Attention with Cross-Layer Memory for Efficient 3D Reconstruction
Junyi Wu, Fanqing Kong, Leyang Chen +2
Feed-forward 3D vision models such as VGGT have achieved remarkable progress, unifying camera estimation and dense scene reconstruction in a single pass. However, their quadratic g…
CAST: Reconstruction-Coupled Acceleration of Interactive World Models
Leyang Chen, Junyi Wu, Fanqing Kong +2
Interactive world models must respond quickly to controls while preserving scene consistency. Existing acceleration methods can miss heterogeneous control responses and spatial tra…
ET-Prune: Evidence-Aware Dynamic Budgeting for Visual Token Pruning in Text-Rich MLLMs
Zizhong Ding, Junxian Li, Kai Liu +4
Visual token pruning reduces the inference cost of multimodal large language models, but a fixed token ratio is poorly matched to text-rich inputs. In OCR-centric tasks, decisive e…
Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers
Maohua Li, Qirui Li, Yanke Zhou +10
Modern text-to-image diffusion transformers (DiTs) generate images through joint attention, in which text and image tokens interact directly within a single sequence. In large-scal…
Rethinking Cross-Layer Information Routing in Diffusion Transformers
Chao Xu, Maohua Li, Qirui Li +9
Diffusion Transformers (DiTs) have become a de facto backbone of modern visual generation, and nearly every major axis of their design -- tokenization, attention, conditioning, obj…
AdaTSQ: Pushing the Pareto Frontier of Diffusion Transformers via Temporal-Sensitivity Quantization
Shaoqiu Zhang, Zizhong Ding, Kaicheng Yang +6
Diffusion Transformers (DiTs) have emerged as the state-of-the-art backbone for high-fidelity image and video generation. However, their massive computational cost and memory footp…
CLQ: Cross-Layer Guided Orthogonal-based Quantization for Diffusion Transformers
Kai Liu, Shaoqiu Zhang, Linghe Kong +1
Visual generation quality has been greatly promoted with the rapid advances in diffusion transformers (DiTs), which is attributed to the scaling of model size and complexity. Howev…