SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation | Paper Citation Record

Observation 1b1e1ac5-9340-47c9-9240-c51e842ff138 · outbound

This paper cites Cosmos 3: Omnimodal World Models for Physical AI.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation Cosmos 3: Omnimodal World Models for Physical AI

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:04.165440Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbcb147a-5dfb-477b-ace1-7a7c0e394126 · outbound

This paper cites Simple Linear Attention Language Models Balance the Recall-Throughput Tradeoff.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation Simple Linear Attention Language Models Balance the Recall-Throughput Tradeoff

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:04.210677Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19d8d957-ddf4-4adb-a4e4-6a5fc2817c4b · outbound

This paper cites Bernini: Latent Semantic Planning for Video Diffusion.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation Bernini: Latent Semantic Planning for Video Diffusion

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:04.295403Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73899bf4-96e4-450c-b1a2-0d5e30f248c9 · outbound

This paper cites UniPercept: Towards Unified Perceptual-Level Image Understanding across Aesthetics, Quality, Structure, and Texture.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation UniPercept: Towards Unified Perceptual-Level Image Understanding across Aesthetics, Quality, Structure, and Texture

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:04.408160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2c70687-a060-4975-9f38-cccde0324b59 · outbound

This paper cites Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:04.542402Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 082ea584-5be5-4446-9ef3-89016abe5e69 · outbound

This paper cites SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:04.684694Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b61acad-4356-4f24-abae-18cbd0c4f276 · outbound

This paper cites Breaking the Low-Rank Dilemma of Linear Attention.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation Breaking the Low-Rank Dilemma of Linear Attention

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:04.828094Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef5954d5-8d0e-4d5c-8c8d-8cea12cb2f78 · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation Gemma 2: Improving Open Language Models at a Practical Size

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:04.934288Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a052d4ae-dd25-40af-9300-421992159c62 · outbound

This paper cites Attention Surgery: An Efficient Recipe to Linearize Your Video Diffusion Transformer.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation Attention Surgery: An Efficient Recipe to Linearize Your Video Diffusion Transformer

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:05.084210Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83e788a5-4197-45ad-b62f-15d98788b0d2 · outbound

This paper cites Mamba: Linear-Time Sequence Modeling with Selective State Spaces.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation Mamba: Linear-Time Sequence Modeling with Selective State Spaces

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:05.188820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9872eb2-77b7-401c-99be-2203668466c1 · outbound

This paper cites LTX-Video: Realtime Video Latent Diffusion.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation LTX-Video: Realtime Video Latent Diffusion

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:05.305026Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9996f1d9-74bc-4cfa-bf1f-f29249bb040f · outbound

This paper cites VBench: Comprehensive Benchmark Suite for Video Generative Models.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation VBench: Comprehensive Benchmark Suite for Video Generative Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:05.421147Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f800d22a-e588-4f25-ba32-62d101f1e751 · outbound

This paper cites Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:05.517153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3fed15d-513b-4eb8-acb4-9120230e8599 · outbound

This paper cites Kimi Linear: An Expressive, Efficient Attention Architecture.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation Kimi Linear: An Expressive, Efficient Attention Architecture

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:05.662964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ef96763-d99f-4034-94c4-9aaf620025be · outbound

This paper cites Kimi K3: Open Frontier Intelligence.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation Kimi K3: Open Frontier Intelligence

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:05.821367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 022e5892-adbc-4a92-9637-75959bf95652 · outbound

This paper cites Attention Residuals.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation Attention Residuals

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:05.956746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9ca3f93-369e-4c1e-8150-804e07b3b727 · outbound

This paper cites HunyuanVideo: A Systematic Framework For Large Video Generative Models.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation HunyuanVideo: A Systematic Framework For Large Video Generative Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:06.066938Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a203054-2a57-4b2d-bf8e-d8f943ac781b · outbound

This paper cites PISA: Piecewise Sparse Attention Is Wiser for Efficient Diffusion Transformers.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation PISA: Piecewise Sparse Attention Is Wiser for Efficient Diffusion Transformers

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:06.173473Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e72ad94b-33b6-4ffe-8d0f-ea30a0ce162e · outbound

This paper cites VideoMamba: State Space Model for Efficient Video Understanding.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation VideoMamba: State Space Model for Efficient Video Understanding

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:06.301385Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ada065ee-a314-427c-a7e2-ad15f2412de9 · outbound

This paper cites Radial Attention: 𝑂(𝑛log𝑛) Sparse Attention with Energy Decay for Long Video Generation.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation Radial Attention: 𝑂(𝑛log𝑛) Sparse Attention with Energy Decay for Long Video Generation

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:06.452147Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d840381f-f287-40b2-94af-15806ed26d88 · outbound

This paper cites Sol Video Inference Engine: Agent-Native Full-Stack Acceleration Framework for Efficient Video Generation.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation Sol Video Inference Engine: Agent-Native Full-Stack Acceleration Framework for Efficient Video Generation

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:06.585681Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b267aca-3c10-4a8a-b317-02f155a496f4 · outbound

This paper cites Toward A Prac- tical Perceptual Video Quality Metric.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation Toward A Prac- tical Perceptual Video Quality Metric

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:06.696742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5fd60a1-ef5c-4b34-ae1e-d24eddf3b9d8 · outbound

This paper cites an unresolved cited work.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation Unresolved cited work

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:06.815351Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51d1d801-8c1e-49db-a11c-4c54f1947083 · outbound

This paper cites HPSv3++: Scaling Reward Models Across the Full Spectrum of Diffusion Model Capabilities.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation HPSv3++: Scaling Reward Models Across the Full Spectrum of Diffusion Model Capabilities

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:06.929517Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e02b234-06f3-4820-8891-4dc30a4d5f13 · outbound

This paper cites VMamba: Visual State Space Model.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation VMamba: Visual State Space Model

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:07.057918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 887082f7-fe31-4548-837c-3e0827a0d247 · outbound

This paper cites Beyond the Golden Data: Resolving the Motion-Vision Quality Dilemma via Timestep Selective Training.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation Beyond the Golden Data: Resolving the Motion-Vision Quality Dilemma via Timestep Selective Training

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:07.203444Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2119e194-4fbd-4a60-b3f8-fc2cb5f98de2 · outbound

This paper cites Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:07.343135Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66c7c2a2-659e-4565-89fe-d6d83a225b28 · outbound

This paper cites Scalable Diffusion Models with Transformers.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation Scalable Diffusion Models with Transformers

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:07.456884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cced871c-cbd8-48f4-bf59-aee4cac671e4 · outbound

This paper cites Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:07.598100Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 999d7a27-f956-4b8d-bfc8-10436d5d4cbd · outbound

This paper cites Qwen3-Next: Towards Ultimate Training & Inference Efficiency.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation Qwen3-Next: Towards Ultimate Training & Inference Efficiency

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:07.715164Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f604e2e5-8fec-46e6-b833-afdcf770b5f4 · outbound

This paper cites MAGI-1: Autoregressive Video Generation at Scale.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation MAGI-1: Autoregressive Video Generation at Scale

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:07.832039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b73745d6-0306-48bd-b60a-eaca92f8ca2e · outbound

This paper cites Seedance 2.0: Advancing Video Generation for World Complexity.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation Seedance 2.0: Advancing Video Generation for World Complexity

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:07.970233Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 640c4dcc-79f7-46cf-b6cf-7c238bbc1559 · outbound

This paper cites TransNet V2: An effective deep network architecture for fast shot transition detection.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation TransNet V2: An effective deep network architecture for fast shot transition detection

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:08.081225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b8fee61-361d-430c-90d0-733631c88fea · outbound

This paper cites RoFormer: Enhanced Transformer with Rotary Position Embedding.Neurocomputing, 568:127063, 2024.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation RoFormer: Enhanced Transformer with Rotary Position Embedding.Neurocomputing, 568:127063, 2024

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:08.266614Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd2842a6-f9b5-4354-aa62-8f3e9b4e5626 · outbound

This paper cites DiM: Diffusion Mamba for Efficient High-Resolution Image Synthesis.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation DiM: Diffusion Mamba for Efficient High-Resolution Image Synthesis

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:08.398370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f250d9a7-6ee0-4c57-b19a-8015c93c36cc · outbound

This paper cites Diffusion Model Alignment Using Direct Preference Optimization.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation Diffusion Model Alignment Using Direct Preference Optimization

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:08.542920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44ca3871-0407-4b82-9035-bb26fe2bbc1d · outbound

This paper cites Wan2.2: Open and Advanced Large-Scale Video Generative Models.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation Wan2.2: Open and Advanced Large-Scale Video Generative Models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:08.630618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58cd1b90-7d58-4106-b8f4-44bbaad2dd34 · outbound

This paper cites Wan: Open and Advanced Large-Scale Video Generative Models.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation Wan: Open and Advanced Large-Scale Video Generative Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:08.710736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61bbe66a-4ef4-4dcc-be18-67897e00162d · outbound

This paper cites Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:08.848484Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9653e097-2e9c-4e36-a90a-2cbb82949270 · outbound

This paper cites Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:08.982968Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54b66d7c-87ba-4a79-af70-eb4703016be7 · outbound

This paper cites Unifying Flow, Stereo and Depth Estimation.IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(11): 13941–13958, 2023.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation Unifying Flow, Stereo and Depth Estimation.IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(11): 13941–13958, 2023

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:09.153544Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64856d84-6dcd-4441-8e23-464b8cd55285 · outbound

This paper cites ImageRe- ward: Learning and Evaluating Human Preferences for Text-to-Image Generation.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation ImageRe- ward: Learning and Evaluating Human Preferences for Text-to-Image Generation

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:09.259598Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 110fe622-34d5-4823-9dc4-28cc3066df91 · outbound

This paper cites Gated Linear Attention Transformers with Hardware-Efficient Training.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation Gated Linear Attention Transformers with Hardware-Efficient Training

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:09.367772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae2c8a2a-1f1c-45cf-a701-a40ac93977ab · outbound

This paper cites CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:09.504622Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42e049af-2592-4825-8dc4-ec39913eac64 · outbound

This paper cites Teaching Large Language Models to Regress Accurate Image Quality Scores Using Score Distribution.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation Teaching Large Language Models to Regress Accurate Image Quality Scores Using Score Distribution

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:09.627087Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53766f05-37c6-4596-bbab-07456923d508 · outbound

This paper cites Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:09.744027Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e918a28b-d180-4ba4-9e46-985de5cee056 · outbound

This paper cites Sigmoid Loss for Language Image Pre-Training.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation Sigmoid Loss for Language Image Pre-Training

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:09.905050Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c359b24-7a7b-42ff-9b5c-c1796c5181d0 · outbound

This paper cites SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:10.076055Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5537ff05-11a8-416a-bb93-5fef02adcac6 · outbound

This paper cites SANA-Streaming: Real-time Streaming Video Editing with Hybrid Diffusion Transformer.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation SANA-Streaming: Real-time Streaming Video Editing with Hybrid Diffusion Transformer

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:10.254223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f939f6d-c5fb-4c6e-92dd-4cef37750e66 · outbound

This paper cites Open-Sora 2.0: Training a Commercial-Level Video Generation Model in $200k.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation Open-Sora 2.0: Training a Commercial-Level Video Generation Model in $200k

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:10.371272Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 147a1451-2749-4bef-9a9f-1f90c6b49484 · outbound

This paper cites SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:10.471087Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c70410cd-7a54-425b-89bc-1f033054650b · outbound

This paper cites DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention

Reference 52

Resolution: malformed identifier; no resolver link, observed 2026-08-01T07:09:10.589942Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers