activity
20232026
most citedRethinking Benchmark and Contamination for Language Models with Rephrased Samples

7 citations · 15 across the 16 of their papers we have counts for

collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2025

vAttention: Verified Sparse Attention

Aditya Desai, Kumar Krishna Agrawal, Shuo Yang +5

State-of-the-art sparse attention methods for reducing decoding latency fall into two main categories: approximate top- (and its extension, top-) and recently introduced samp…

cs.LG2025

SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention

Jintao Zhang, Haoxu Wang, Kai Jiang +10

In Diffusion Transformer (DiT) models, particularly for video generation, attention latency is a major bottleneck due to the long sequence length and the quadratic complexity. We f…

cs.LG2025

Twilight: Adaptive Attention Sparsity with Hierarchical Top- Pruning

Chaofan Lin, Jiaming Tang, Shuo Yang +6

Leveraging attention sparsity to accelerate long-context large language models (LLMs) has been a hot research topic. However, current algorithms such as sparse attention or key-val…

cs.LG2024

HashAttention: Semantic Sparsity for Faster Inference

Aditya Desai, Shuo Yang, Alejandro Cuadron +3

Leveraging long contexts is crucial for advanced AI systems, but attention computation poses a scalability challenge. While scaled dot-product attention (SDPA) exhibits token spars…

cs.LG2024

BlendServe: Optimizing Offline Inference for Auto-regressive Large Models with Resource-aware Batching

Yilong Zhao, Shuo Yang, Kan Zhu +5

Offline batch inference, which leverages the flexibility of request batching to achieve higher throughput and lower costs, is becoming more popular for latency-insensitive applicat…

cs.LG20241 cited

Post-Training Sparse Attention with Double Sparsity

Shuo Yang, Ying Sheng, Joseph E. Gonzalez +2

The inference process for large language models is slow and memory-intensive, with one of the most critical bottlenecks being excessive Key-Value (KV) cache accesses. This paper in…