SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness
Paper • 2609.20519 • Published • 137
AI & ML interests
Efficient algorithm, system, and hardware for machine learning.
Recent Activity
View all activity
songhanÂ
authored a
paper 11 days ago
LmxyyÂ
authored a
paper 12 days ago
RadioheadingÂ
submitted a
paper to Daily Papers 12 days ago
RadioheadingÂ
authored 3
papers 12 days ago
FourTune: Towards Fully 4-Bit Efficient Post-Training for Diffusion Models
Paper • 2607.05711 • Published
Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization
Paper • 2602.02958 • Published • 35
Radial Attention: $O(n\log n)$ Sparse Attention with Energy Decay for Long Video Generation
Paper • 2506.19852 • Published • 43
gbcfchcÂ
submitted a
paper to Daily Papers 13 days ago
gbcfchcÂ
authored 5
papers 13 days ago
Lightning Weave: Improving the Accuracy-Efficiency Frontier of Reasoning Models through Capability Composition
Paper • 2609.14708 • Published • 3
Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation
Paper • 2604.13010 • Published • 20
DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer
Paper • 2507.04947 • Published • 1
HART: Efficient Visual Generation with Hybrid Autoregressive Transformer
Paper • 2410.10812 • Published • 18
VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation
Paper • 2409.04429 • Published
songhanÂ
authored a
paper about 1 month ago
songhanÂ
authored 3
papers 2 months ago
Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification
Paper • 2607.24027 • Published • 39
SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation
Paper • 2607.21553 • Published • 40
Nemotron-Labs-Diffusion: A Tri-Mode Language Model Unifying Autoregressive, Diffusion, and Self-Speculation Decoding
Paper • 2607.05722 • Published • 12
songhanÂ
authored 4
papers 3 months ago
DC-AE 1.5: Accelerating Diffusion Model Convergence with Structured Latent Space
Paper • 2508.00413 • Published • 7
DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder
Paper • 2509.25182 • Published • 40
AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation
Paper • 2605.13724 • Published • 104
Sol Video Inference Engine: Agent-Native Full-Stack Acceleration Framework for Efficient Video Generation
Paper • 2606.23743 • Published • 1