178 citations · 987 across the 31 of their papers we have counts for
34 papers
Adversarial Gradient Forcing for Robust Few-Step Autoregressive Video Generation
Chenxi Xia, Yixuan Xu, Shan Liu +7
Autoregressive video generation models generate videos sequentially, with each new block conditioned on previously generated blocks. By training on the model's own rollouts, Self F…
Super-Resolution in The Right Latent Space: A Frozen Vision-Foundation Substrate
Wanzhou Lei, Cuifeng Sheng, Cuifeng Shen +7
In an image latent space, the embeddings of high-resolution, natural, and sharp images form a manifold. Degradation of high-resolution images pushes their embeddings off this manif…
SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention
Qi Zhao, Qirui Li, Hanlin Tang +10
Diffusion Transformers (DiTs) incur quadratic self-attention cost over spatiotemporal tokens. Existing training-free sparse attention methods often construct sparse masks from bloc…
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…
CKV: Compressed and Composable KV Cache Reuse for Efficient LLM Inference
Chuheng Du, Junyi Chen, Hanlin Tang +7
Long-context inference is central to modern large language model (LLM) applications such as retrieval-augmented generation and multi-document reasoning. To mitigate the growing inf…
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…
Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps
Yanke Zhou, Yiduo Li, Hanlin Tang +6
Long-context inference in large language models is bottlenecked by the quadratic cost of full attention. Existing efficient alternatives often rely either on native sparse training…
RT-Lynx: Putting GEMM Sparsity in the Right Place for Diffusion Models
Xing Cong, Hanlin Tang, Kan Liu +3
Diffusion Transformers (DiT) achieve strong performance in image generation but incur substantial inference costs. While prior work has reduced this cost via quantization and disti…
Shiva-DiT: Residual-Based Differentiable Top- Selection for Efficient Diffusion Transformers
Jiaji Zhang, Hailiang Zhao, Jiaju Wu +3
Diffusion Transformers (DiTs) are costly at high resolution because self-attention scales quadratically with token sequence length. Existing pruning methods do not jointly provide…
RazorAttention: Efficient KV Cache Compression Through Retrieval Heads
Hanlin Tang, Yang Lin, Jing Lin +4
The memory and computational demands of Key-Value (KV) cache present significant challenges for deploying long-context language models. Previous approaches attempt to mitigate this…
EasyQuant: An Efficient Data-free Quantization Algorithm for LLMs
Hanlin Tang, Yifu Sun, Decheng Wu +3
Large language models (LLMs) have proven to be very superior to conventional methods in various tasks. However, their expensive computations and high memory requirements are prohib…
MKQ-BERT: Quantized BERT with 4-bits Weights and Activations
Hanlin Tang, Xipeng Zhang, Kai Liu +2
Recently, pre-trained Transformer based language models, such as BERT, have shown great superiority over the traditional methods in many Natural Language Processing (NLP) tasks. Ho…
PASTO: Strategic Parameter Optimization in Recommendation Systems -- Probabilistic is Better than Deterministic
Weicong Ding, Hanlin Tang, Jingshuo Feng +17
Real-world recommendation systems often consist of two phases. In the first phase, multiple predictive models produce the probability of different immediate user actions. In the se…
ErrorCompensatedX: error compensation for variance reduced algorithms
Hanlin Tang, Yao Li, Ji Liu +1
Communication cost is one major bottleneck for the scalability for distributed learning. One approach to reduce the communication cost is to compress the gradient during communicat…
1-bit Adam: Communication Efficient Large-Scale Training with Adam's Convergence Speed
Hanlin Tang, Shaoduo Gan, Ammar Ahmad Awan +6
Scalable training of large models (like BERT and GPT-3) requires careful optimization rooted in model design, architecture, and system capabilities. From a system standpoint, commu…
APMSqueeze: A Communication Efficient Adam-Preconditioned Momentum SGD Algorithm
Hanlin Tang, Shaoduo Gan, Samyam Rajbhandari +4
Adam is the important optimization algorithm to guarantee efficiency and accuracy for training many important tasks such as BERT and ImageNet. However, Adam is generally not compat…
Optimizing Memory Placement using Evolutionary Graph Reinforcement Learning
Shauharda Khadka, Estelle Aflalo, Mattias Marder +6
For deep neural network accelerators, memory movement is both energetically expensive and can bound computation. Therefore, optimal mapping of tensors to memory hierarchies is crit…
Shifted and Squeezed 8-bit Floating Point format for Low-Precision Training of Deep Neural Networks
Léopold Cambier, Anahita Bhiwandiwalla, Ting Gong +3
Training with larger number of parameters while keeping fast iterations is an increasingly adopted strategy and trend for developing better performing Deep Neural Network (DNN) mod…
Mimic The Raw Domain: Accelerating Action Recognition in the Compressed Domain
Barak Battash, Haim Barad, Hanlin Tang +1
Video understanding usually requires expensive computation that prohibits its deployment, yet videos contain significant spatiotemporal redundancy that can be exploited. In particu…
MLPerf Inference Benchmark
Vijay Janapa Reddi, Christine Cheng, David Kanter +44
Machine-learning (ML) hardware and software system demand is burgeoning. Driven by ML applications, the number of different ML inference systems has exploded. Over 100 organization…
Using Image Priors to Improve Scene Understanding
Brigit Schroeder, Hanlin Tang, Alexandre Alahi
Semantic segmentation algorithms that can robustly segment objects across multiple camera viewpoints are crucial for assuring navigation and safety in emerging applications such as…
Central Server Free Federated Learning over Single-sided Trust Social Networks
Chaoyang He, Conghui Tan, Hanlin Tang +2
Federated learning has become increasingly important for modern machine learning, especially for data privacy-sensitive scenarios. Existing federated learning mostly adopts the cen…
MLPerf Training Benchmark
Peter Mattson, Christine Cheng, Cody Coleman +34
Machine learning (ML) needs industry-standard performance benchmarks to support design and competitive evaluation of the many emerging software and hardware solutions for ML. But M…
Triplet-Aware Scene Graph Embeddings
Brigit Schroeder, Subarna Tripathi, Hanlin Tang
Scene graphs have become an important form of structured knowledge for tasks such as for image generation, visual relation detection, visual question answering, and image retrieval…