arXiv:2609.37001v1 Announce Type: cross Abstract: Diffusion Transformers (DiTs) enable high-quality video generation but suffer from substantial inference latency, primarily attributable to the compu...
EFQ-Softmax is a low‑bit probability‑generation technique that replaces the traditional exp‑then‑quantize path in Transformer attention. It maps shifted attention scores directly to block‑scaled E2M1 operands using an exponent‑only scale and a single affine rule, allowing the same low‑bit representation to be used for both numerator and denominator updates. Experiments on Qwen3‑8B, Qwen3‑VL‑8B‑Instruct, and WAN2.2‑TI2V‑5B show that EFQ‑Softmax maintains or improves model quality while reducing vector‑stage latency by about 40% on the A5 vector unit.
Low-bit attention accelerates Transformer inference by moving the $QK^\top$ and $PV$ matrix multiplications to FP8 or FP4 matrix engines. However, the softmax path often evaluates shifted-score expone...
arXiv:2605. 01910v2 Announce Type: replace-cross Abstract: Autoregressive decoding becomes bandwidth-limited at long contexts, as generating each token requires reading all $n_k$ key and value vectors from KV cache.
iCATS introduces a training‑free sparse attention mechanism for Diffusion Transformers that accelerates video generation by reducing computations. It improves importance estimation by clustering query‑key dot‑product interactions and reformulates the objective as a quadratic form for low‑cost computation. The method also adapts sparsity dynamically across denoising timesteps using an SNR‑guided schedule and employs a tail‑merging strategy to enhance GPU kernel utilization, achieving significant speedups while maintaining high PSNR scores.
arXiv:2610.35706v1 Announce Type: cross Abstract: Attention over tens of thousands of visual tokens dominates the inference of video diffusion transformers (DiTs). Existing methods reduce this cost t...
arXiv:2609.38166v1 Announce Type: cross Abstract: Recent LLMs increasingly adopt hybrid designs that replace standard attention with linear attention, such as Gated DeltaNet (GDN) and Kimi Delta Atte...
arXiv:2611.05917v1 Announce Type: new Abstract: Sparse attention accelerates few-step video diffusion transformers by computing a few key blocks exactly and compensating for the rest. However, existi...
arXiv:2608.06912v2 Announce Type: replace Abstract: Selecting the top-$k$ elements is a fundamental operation for inducing sparsity in large-scale models and optimization problems, enabling robust ex...
arXiv:2609.23153v1 Announce Type: new Abstract: Video diffusion transformers are expensive because attention dominates long spatiotemporal token sequences. We identify the \emph{high-sparsity trap}:...
arXiv:2607. 03012v1 Announce Type: cross Abstract: Video Diffusion Transformers (VDiTs) have demonstrated significant capabilities in high-fidelity video generation.
The paper introduces Gated Token Recurrence (GTR), a softmax‑free recurrent vision backbone that replaces global softmax attention with gated linear attention, alternating scan directions, and enhanced SwiGLU blocks. GTR is distilled from a DINOv3 teacher using only final‑layer patch‑token alignment, and achieves strong performance on COCO object detection (58.9 box AP) with very low latency (1.908 ms on an RTX 4090). The backbone also transfers to multiple dense prediction tasks and runs efficiently on edge hardware via a specialized CUDA operator and TensorRT deployment.