VC-Attention: Value Smoothing and Softmax Casting for Low-bit Attention
Paper • 2609.15810 • Published • 50
AI & ML interests
None defined yet.
Recent Activity
View all activity
Team members 12 private
Lmxyy
authored a
paper 10 days ago
Radioheading
submitted a
paper to Daily Papers 10 days ago
synxlin
authored 18
papers 5 months ago
Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training
Paper • 1712.01887 • Published
TorchSparse: Efficient Point Cloud Inference Engine
Paper • 2204.10319 • Published
QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving
Paper • 2405.04532 • Published
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers
Paper • 2410.10629 • Published • 13
SVDQunat: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
Paper • 2411.05007 • Published • 25
SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer
Paper • 2501.18427 • Published • 27
Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity
Paper • 2502.01776 • Published • 3
Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation
Paper • 2505.18875 • Published • 42
Radial Attention: $O(n\log n)$ Sparse Attention with Energy Decay for Long Video Generation
Paper • 2506.19852 • Published • 43
DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space
Paper • 2509.25180 • Published • 10
DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder
Paper • 2509.25182 • Published • 40
QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs
Paper • 2510.11696 • Published • 183
VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inference
Paper • 2512.01031 • Published • 28
Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter
Paper • 2511.16665 • Published
Jet-RL: Enabling On-Policy FP8 Reinforcement Learning with Unified Training and Rollout Precision Flow
Paper • 2601.14243 • Published • 26
Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization
Paper • 2602.02958 • Published • 35
Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling
Paper • 2512.02010 • Published
Flash-KMeans: Fast and Memory-Efficient Exact K-Means
Paper • 2603.09229 • Published • 85