Publications (41)
Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers
Maohua Li, Qirui Li, Yanke Zhou +10
Using Scene Graph Context to Improve Image Generation
Subarna Tripathi, Anahita Bhiwandiwalla, Alexei Bastidas +1
Communication Compression for Decentralized Training
Hanlin Tang, Shaoduo Gan, Ce Zhang +2
RazorAttention: Efficient KV Cache Compression Through Retrieval Heads
Hanlin Tang, Yang Lin, Jing Lin +4
MLPerf Training Benchmark
Peter Mattson, Christine Cheng, Cody Coleman +34
Triplet-Aware Scene Graph Embeddings
Brigit Schroeder, Subarna Tripathi, Hanlin Tang
D: Decentralized Training over Decentralized Data
Hanlin Tang, Xiangru Lian, Ming Yan +2
Lifetime-limited Gigahertz-frequency Mechanical Oscillators with Millisecond Coherence Times
Yizhi Luo, Hilel Hagai Diamandi, Hanshi Li +9
Emergence of Separable Manifolds in Deep Language Representations
Jonathan Mamou, Hang Le, Miguel Del Rio +4
Distributed Learning over Unreliable Networks
Chen Yu, Hanlin Tang, Cedric Renggli +5
: Decentralization Meets Error-Compensated Compression
Hanlin Tang, Xiangru Lian, Shuang Qiu +4
Generalization to Novel Objects using Prior Relational Knowledge
Varun Kumar Vijay, Abhinav Ganesh, Hanlin Tang +1
Rethinking Cross-Layer Information Routing in Diffusion Transformers
Chao Xu, Maohua Li, Qirui Li +9
Mimic The Raw Domain: Accelerating Action Recognition in the Compressed Domain
Barak Battash, Haim Barad, Hanlin Tang +1
APMSqueeze: A Communication Efficient Adam-Preconditioned Momentum SGD Algorithm
Hanlin Tang, Shaoduo Gan, Samyam Rajbhandari +4
Syntactic Perturbations Reveal Representational Correlates of Hierarchical Phrase Structure in Pretrained Language Models
Matteo Alleman, Jonathan Mamou, Miguel A Del Rio +3
ErrorCompensatedX: error compensation for variance reduced algorithms
Hanlin Tang, Yao Li, Ji Liu +1
MKQ-BERT: Quantized BERT with 4-bits Weights and Activations
Hanlin Tang, Xipeng Zhang, Kai Liu +2
Shifted and Squeezed 8-bit Floating Point format for Low-Precision Training of Deep Neural Networks
Léopold Cambier, Anahita Bhiwandiwalla, Ting Gong +3
Compact Scene Graphs for Layout Composition and Patch Retrieval
Subarna Tripathi, Sharath Nittur Sridhar, Sairam Sundaresan +1
CKV: Compressed and Composable KV Cache Reuse for Efficient LLM Inference
Chuheng Du, Junyi Chen, Hanlin Tang +7
Shiva-DiT: Residual-Based Differentiable Top- Selection for Efficient Diffusion Transformers
Jiaji Zhang, Hailiang Zhao, Guoxuan Zhu +9
Using Image Priors to Improve Scene Understanding
Brigit Schroeder, Hanlin Tang, Alexandre Alahi
Isotopically enriched epitaxial CaWO thin films for Er spin-photon quantum interfaces
Hanlin Tang, Kidae Shin, Ashwin K. Boddeti +10
Decentralized Online Learning: Take Benefits from Others' Data without Sharing Your Own to Track Global Trend
Yawei Zhao, Chen Yu, Peilin Zhao +3
On the geometry of generalization and memorization in deep neural networks
Cory Stephenson, Suchismita Padhy, Abhinav Ganesh +3
MLPerf Inference Benchmark
Vijay Janapa Reddi, Christine Cheng, David Kanter +44
DoubleSqueeze: Parallel Stochastic Gradient Descent with Double-Pass Error-Compensated Compression
Hanlin Tang, Xiangru Lian, Chen Yu +2
Recurrent computations for visual pattern completion
Hanlin Tang, Martin Schrimpf, Bill Lotter +6
Optimizing Memory Placement using Evolutionary Graph Reinforcement Learning
Shauharda Khadka, Estelle Aflalo, Mattias Marder +6
Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps
Yanke Zhou, Yiduo Li, Hanlin Tang +6
Central Server Free Federated Learning over Single-sided Trust Social Networks
Chaoyang He, Conghui Tan, Hanlin Tang +2
1-bit Adam: Communication Efficient Large-Scale Training with Adam's Convergence Speed
Hanlin Tang, Shaoduo Gan, Ammar Ahmad Awan +6
ATRW: A Benchmark for Amur Tiger Re-identification in the Wild
Shuyuan Li, Jianguo Li, Hanlin Tang +2
Untangling in Invariant Speech Recognition
Cory Stephenson, Jenelle Feather, Suchismita Padhy +4
A role for recurrent processing in object completion: neurophysiological, psychophysical and computational"evidence
Hanlin Tang, Calin Buia, Joseph Madsen +2
RT-Lynx: Putting the GEMM Sparsity In a Right Way for Diffusion Models
Xing Cong, Hanlin Tang, Kan Liu +3
SpaceNet MVOI: a Multi-View Overhead Imagery Dataset
Nicholas Weir, David Lindenbaum, Alexei Bastidas +5
EasyQuant: An Efficient Data-free Quantization Algorithm for LLMs
Hanlin Tang, Yifu Sun, Decheng Wu +3
1-bit LAMB: Communication Efficient Large-Scale Large-Batch Training with LAMB's Convergence Speed
Conglong Li, Ammar Ahmad Awan, Hanlin Tang +2
PASTO: Strategic Parameter Optimization in Recommendation Systems -- Probabilistic is Better than Deterministic
Weicong Ding, Hanlin Tang, Jingshuo Feng +17