HASTE delivers up to 1.93x speedup on Wan2.1 video DiTs via head-wise adaptive sparse attention using temporal mask reuse and error-guided per-head calibration while preserving video quality.
Sageattention: Accurate 8-bit attention for plug-and-play inference acceleration
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 8roles
background 2polarities
background 2representative citing papers
A survey that groups efficient video diffusion methods into four paradigms—step distillation, efficient attention, model compression, and cache/trajectory optimization—and outlines open challenges for practical use.
π₀.₇ is a steerable generalist robotic model that uses rich multimodal prompts including language, subgoal images, and performance metadata to achieve out-of-the-box generalization across tasks and robot bodies.
ScaleSearch optimizes block floating point scales via fine-grained search to cut quantization error by 27% for NVFP4, improving PTQ by up to 15 points on MATH500 for Qwen3-8B and attention PPL by 0.77 on Llama 3.1 70B.
Salca is a new ASIC accelerator that achieves 3.82× speedup and 74.19× energy efficiency over A100 for long-context attention via dual-compression dynamic sparse attention and pipelined hardware.
Focused Forcing is a training-free per-frame KV selection method that combines attention scores with diversity metrics and head-importance estimation to accelerate autoregressive video diffusion up to 1.48x while improving quality.
Wan releases open 1.3B and 14B video diffusion models claiming superior performance over open-source and commercial baselines across multiple tasks with consumer-grade efficiency.
RoME reformulates RoPE as matrix operations to eliminate dimension-specific vector overhead and enable fused execution on modern hardware while remaining mathematically equivalent.
citing papers explorer
-
HASTE: Training-Free Video Diffusion Acceleration via Head-Wise Adaptive Sparse Attention
HASTE delivers up to 1.93x speedup on Wan2.1 video DiTs via head-wise adaptive sparse attention using temporal mask reuse and error-guided per-head calibration while preserving video quality.
-
Efficient Video Diffusion Models: Advancements and Challenges
A survey that groups efficient video diffusion methods into four paradigms—step distillation, efficient attention, model compression, and cache/trajectory optimization—and outlines open challenges for practical use.
-
${\pi}_{0.7}$: a Steerable Generalist Robotic Foundation Model with Emergent Capabilities
π₀.₇ is a steerable generalist robotic model that uses rich multimodal prompts including language, subgoal images, and performance metadata to achieve out-of-the-box generalization across tasks and robot bodies.
-
Search Your Block Floating Point Scales!
ScaleSearch optimizes block floating point scales via fine-grained search to cut quantization error by 27% for NVFP4, improving PTQ by up to 15 points on MATH500 for Qwen3-8B and attention PPL by 0.77 on Llama 3.1 70B.
-
Salca: A Sparsity-Aware Hardware Accelerator for Efficient Long-Context Attention Decoding
Salca is a new ASIC accelerator that achieves 3.82× speedup and 74.19× energy efficiency over A100 for long-context attention via dual-compression dynamic sparse attention and pipelined hardware.
-
Focused Forcing: Content-Aware Per-Frame KV Selection for Efficient Autoregressive Video Diffusion
Focused Forcing is a training-free per-frame KV selection method that combines attention scores with diversity metrics and head-importance estimation to accelerate autoregressive video diffusion up to 1.48x while improving quality.
-
Wan: Open and Advanced Large-Scale Video Generative Models
Wan releases open 1.3B and 14B video diffusion models claiming superior performance over open-source and commercial baselines across multiple tasks with consumer-grade efficiency.
-
Efficient Matrix Implementation for Rotary Position Embedding
RoME reformulates RoPE as matrix operations to eliminate dimension-specific vector overhead and enable fused execution on modern hardware while remaining mathematically equivalent.