OARS Collection On Post-Training for Cost-Efficient Heterogeneous Multi-Agent Systems • 2 items • Updated 1 day ago
OARS Collection On Post-Training for Cost-Efficient Heterogeneous Multi-Agent Systems • 2 items • Updated 1 day ago
Weaken to Strengthen: Weakening-Induced On-Policy Self-Distillation for Large Reasoning Models Paper • 2610.38681 • Published 14 days ago • 4
SoL-Refiner: Speed-of-Light One-Step Refinement for High-Resolution Video Paper • 2609.37969 • Published Sep 29 • 28
Sol-H3: Recursive Self-Improvement for MiniMax-H3 Inference Acceleration on Sol-Engine across Cloud and Edge Paper • 2609.35110 • Published Sep 28 • 1
SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness Paper • 2609.20519 • Published Sep 17 • 90
VC-Attention: Value Smoothing and Softmax Casting for Low-bit Attention Paper • 2609.15810 • Published Sep 14 • 26
VC-Attention: Value Smoothing and Softmax Casting for Low-bit Attention Paper • 2609.15810 • Published Sep 14 • 26
FourTune: Towards Fully 4-Bit Efficient Post-Training for Diffusion Models Paper • 2607.05711 • Published Jul 7
Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization Paper • 2602.02958 • Published Feb 3 • 35
Radial Attention: $O(n\log n)$ Sparse Attention with Energy Decay for Long Video Generation Paper • 2506.19852 • Published Jun 24, 2025 • 43
Lightning Weave: Improving the Accuracy-Efficiency Frontier of Reasoning Models through Capability Composition Paper • 2609.14708 • Published Sep 13 • 4
Lightning Weave: Improving the Accuracy-Efficiency Frontier of Reasoning Models through Capability Composition Paper • 2609.14708 • Published Sep 13 • 4
Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation Paper • 2604.13010 • Published Apr 14 • 21
DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Paper • 2507.04947 • Published Jul 7, 2025 • 1
HART: Efficient Visual Generation with Hybrid Autoregressive Transformer Paper • 2410.10812 • Published Oct 14, 2024 • 18
VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation Paper • 2409.04429 • Published Sep 6, 2024
Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization Paper • 2602.02958 • Published Feb 3 • 35