APT: Feedback-Driven Agentic Post-Training for Text-to-Image Generation Paper • 2610.18097 • Published 6 days ago • 24
DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF Image-Text-to-Text • 27B • Updated 1 day ago • 1.75M • 1.88k
Source Preference in the Wild: How LLM Agents Favor Items by Source, and How to Reduce It Paper • 2610.03195 • Published 17 days ago • 47
Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL Paper • 2609.20715 • Published Sep 17 • 45
SpectralShift: Effective Context Window Extension of Gated DeltaNet via Spectral Reparameterization Paper • 2609.14320 • Published Sep 13 • 34
UniH^3: Unifying Hierarchical Homogeneity and Heterogeneity for All-in-One Medical Image Restoration Paper • 2609.11156 • Published Sep 10 • 24
Knowing When Not to Reuse: Conditional Experience Transfer in Autonomous LLM Post-Training Paper • 2608.26730 • Published Aug 27 • 154
CORE: Improving Compositional Reasoning in MLLM Embedding via Reranker Distillation Paper • 2609.04083 • Published Sep 3 • 27