222 citations · 457 across the 31 of their papers we have counts for
38 papers
Physis-Lang: Self-Evolving Language as a Physical Representation for Video World Model
Liming Lu, Xianzheng Ma, Wenkun He +14
Video world models are expected to predict how the physical world evolves, yet they often produce visually plausible videos that violate basic physical principles. Existing approac…
Delta-Matching: Closing the Final Gap of Native 8-bit Training for LLMs
Haozhan Tang, Hao Kang, Han Cai +2
Reliable FP8 attention remains a barrier to fully native 8-bit large language model training. We derive how forward-backward inconsistencies produce stale delta and empirically sho…
Lightning OPD 2.0: Mitigating Style Bias in Cross-Teacher On-Policy Distillation for Large Reasoning Models
Yecheng Wu, Song Han, Han Cai
On-policy distillation (OPD) provides dense token-level supervision from a teacher, but its effectiveness can depend on teacher consistency, meaning that the model providing OPD su…
Jet-Long: Efficient Long-Context Extension with Dynamic Bifocal RoPE
Haozhan Tang, Zerui Wang, Yuxian Gu +2
Modern LLMs are increasingly deployed in long-context applications such as retrieval-augmented generation, repository-level coding, and agentic workflows whose accumulated reasonin…
ActionMap: Robot Policy Learning via Voxel Action Heatmap
Pei Yang, Hai Ci, Yanzhe Chen +3
Vision-language-action (VLA) models have advanced rapidly across backbones, training recipes, and data scale, yet the action decoder, which converts the backbone's hidden state int…
JetViT: Efficient High-Resolution Vision Transformer with Post-Training Attention Search
Dongyun Zou, Zhuoyang Zhang, Junyu Chen +8
We introduce JetViT, a novel family of hybrid-architecture Vision Transformer (ViT) models that match the accuracy of state-of-the-art full-attention vision foundation models while…
Hide to Guide: Learning via Semantic Masking
Ruitao Liu, Qinghao Hu, Alex Hu +6
Reinforcement learning with verifiable rewards (RLVR) has become a powerful paradigm for improving language models on reasoning-intensive tasks, but its effectiveness is often limi…
AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation
Yuchao Gu, Guian Fang, Yuxin Jiang +4
Few-step video generation has been significantly advanced by consistency distillation. However, the performance of consistency-distilled models often degrades as more sampling step…
Flash-KMeans: Fast and Memory-Efficient Exact K-Means
Shuo Yang, Haocheng Xi, Yilong Zhao +10
-means has historically been positioned primarily as an offline processing primitive, typically used for dataset organization or embedding preprocessing rather than as a first-c…
Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization
Haocheng Xi, Shuo Yang, Yilong Zhao +13
Despite rapid progress in autoregressive video diffusion, an emerging system algorithm bottleneck limits both deployability and generation capability: KV cache memory. In autoregre…
Jet-RL: Enabling On-Policy FP8 Reinforcement Learning with Unified Training and Rollout Precision Flow
Haocheng Xi, Charlie Ruan, Peiyuan Liao +7
Reinforcement learning (RL) is essential for enhancing the complex reasoning capabilities of large language models (LLMs). However, existing RL training pipelines are computational…
Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter
Qinghao Hu, Shang Yang, Junxian Guo +7
The emergence of Large Language Models (LLMs) with strong reasoning capabilities marks a significant milestone, unlocking new frontiers in complex problem-solving. However, trainin…
SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer
Junsong Chen, Yuyang Zhao, Jincheng Yu +17
We introduce SANA-Video, a small diffusion model that can efficiently generate videos up to 720x1280 resolution and minute-length duration. SANA-Video synthesizes high-resolution,…
DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder
Junyu Chen, Wenkun He, Yuchao Gu +12
We introduce DC-VideoGen, a post-training acceleration framework for efficient video generation. DC-VideoGen can be applied to any pre-trained video diffusion model, improving effi…
Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search
Yuxian Gu, Qinghao Hu, Shang Yang +4
We present Jet-Nemotron, a new family of hybrid-architecture language models, which matches or exceeds the accuracy of leading full-attention models while significantly improving g…
DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space
Wenkun He, Yuchao Gu, Junyu Chen +11
Existing text-to-image diffusion models excel at generating high-quality images, but face significant efficiency challenges when scaled to high resolutions, like 4K image generatio…
DC-AE 1.5: Accelerating Diffusion Model Convergence with Structured Latent Space
Junyu Chen, Dongyun Zou, Wenkun He +4
We present DC-AE 1.5, a new family of deep compression autoencoders for high-resolution diffusion models. Increasing the autoencoder's latent channel number is a highly effective a…
DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer
Yecheng Wu, Junyu Chen, Zhuoyang Zhang +7
We introduce DC-AR, a novel masked autoregressive (AR) text-to-image generation framework that delivers superior image generation quality with exceptional computational efficiency.…
Seismic resolution enhancement via deep Learning with Knowledge Distillation and Domain Adaptation
Hanpeng Cai, Haonan Zhang, Liyu Zhang +1
High-resolution processing of seismic signals is crucial for subsurface geological characterization and thin-layer reservoir identification. Traditional high-resolution algorithms…
Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation
Shuo Yang, Haocheng Xi, Yilong Zhao +10
Diffusion Transformers (DiTs) are essential for video generation but suffer from significant latency due to the quadratic complexity of attention. By computing only critical tokens…
Scaling Vision Pre-Training to 4K Resolution
Baifeng Shi, Boyi Li, Han Cai +8
High-resolution perception of visual details is crucial for daily tasks. Current vision pre-training, however, is still limited to low resolutions (e.g., 378 x 378 pixels) due to t…
SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation
Junsong Chen, Shuchen Xue, Yuyang Zhao +6
This paper presents SANA-Sprint, an efficient diffusion model for ultra-fast text-to-image (T2I) generation. SANA-Sprint is built on a pre-trained foundation model and augmented wi…
Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity
Haocheng Xi, Shuo Yang, Yilong Zhao +11
Diffusion Transformers (DiTs) dominate video generation but their high computational cost severely limits real-world applicability, usually requiring tens of minutes to generate a…
SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer
Enze Xie, Junsong Chen, Yuyang Zhao +11
This paper presents SANA-1.5, a linear Diffusion Transformer for efficient scaling in text-to-image generation. Building upon SANA-1.0, we introduce three key innovations: (1) Effi…