DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression Paper • 2609.19969 • Published 9 days ago • 181
SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness Paper • 2609.20519 • Published 9 days ago • 133
Running MiniMax H3 Ref2VA Community Comparison 🎞 10 reference tasks, 6 H3 variants, inputs and results
Running MiniMax H3 Ref2VA Community Comparison 🎞 10 reference tasks, 6 H3 variants, inputs and results
Running MiniMax H3 Reference and Generation Performance 🎞 Reference effects on MiniMax-H3 generation quality and speed
Running MiniMax H3 Reference and Generation Performance 🎞 Reference effects on MiniMax-H3 generation quality and speed
GenFirst: Generation Before Reconstruction for Stable End-to-End Latent Generative Modeling Paper • 2608.29335 • Published 28 days ago • 73
Self-Evaluation Unlocks Any-Step Text-to-Image Generation Paper • 2512.22374 • Published Dec 26, 2025 • 17
Both Semantics and Reconstruction Matter: Making Representation Encoders Ready for Text-to-Image Generation and Editing Paper • 2512.17909 • Published Dec 19, 2025 • 37
Advantage Weighted Matching: Aligning RL with Pretraining in Diffusion Models Paper • 2509.25050 • Published Sep 29, 2025 • 5
Advantage Weighted Matching: Aligning RL with Pretraining in Diffusion Models Paper • 2509.25050 • Published Sep 29, 2025 • 5 • 1
Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding Paper • 2505.22618 • Published May 28, 2025 • 47
Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding Paper • 2505.22618 • Published May 28, 2025 • 47
SA-Solver: Stochastic Adams Solver for Fast Sampling of Diffusion Models Paper • 2309.05019 • Published Sep 10, 2023 • 1