deepseek-ai/DeepSeek-V4.1-Flash-1017 Image-Text-to-Text • 763B • Updated 10 days ago • 502k • • 5.99k
Reasoning on the Manifold: Bidirectional Consistency for Self-Verification in Diffusion Language Models Paper • 2604.16565 • Published May 27 • 1
MacTok: Robust Continuous Tokenization for Image Generation Paper • 2603.29634 • Published Mar 31 • 2
AesCode: Aesthetic Code Generation with Decoupled Cross-Modal Rewards Paper • 2610.18860 • Published Oct 13 • 30
GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives Paper • 2609.39601 • Published Sep 30 • 83
AesCode: Aesthetic Code Generation with Decoupled Cross-Modal Rewards Paper • 2610.18860 • Published Oct 13 • 30
AesCode: Aesthetic Code Generation with Decoupled Cross-Modal Rewards Paper • 2610.18860 • Published Oct 13 • 30
Beyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation Paper • 2609.35347 • Published Sep 28 • 61
Reasoning on the Manifold: Bidirectional Consistency for Self-Verification in Diffusion Language Models Paper • 2604.16565 • Published May 27 • 1
GOOD: Training-Free Guided Diffusion Sampling for Out-of-Distribution Detection Paper • 2510.17131 • Published Oct 27, 2025
Deep Incomplete Multi-view Learning via Cyclic Permutation of VAEs Paper • 2502.11037 • Published Feb 28, 2025
Dark-ISP: Enhancing RAW Image Processing for Low-Light Object Detection Paper • 2509.09183 • Published Sep 11, 2025
Beyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation Paper • 2609.35347 • Published Sep 28 • 61
MacTok: Robust Continuous Tokenization for Image Generation Paper • 2603.29634 • Published Mar 31 • 2
BizGenEval: A Systematic Benchmark for Commercial Visual Content Generation Paper • 2603.25732 • Published Mar 26 • 9