Puffin-World: Scaling a Unified Multimodal Model with Native 3D World States Paper • 2609.04196 • Published 4 days ago • 66
Select, Compress, Reinvest: A Controlled Study of Visual-Token Allocation in Long-Video MLLMs Paper • 2609.03820 • Published 4 days ago • 15
Knowing When Not to Reuse: Conditional Experience Transfer in Autonomous LLM Post-Training Paper • 2608.26730 • Published 11 days ago • 149
LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes Paper • 2609.03796 • Published 4 days ago • 226
OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution Paper • 2608.00677 • Published Aug 1 • 263
JigShape: Evaluating Visual-Geometric Reasoning in VLMs through Jigsaw Puzzles Paper • 2607.27670 • Published Aug 4 • 8
Don't Scroll Back: Missing-Evidence Memory for Streaming Dialogue Summarization Paper • 2608.09043 • Published 28 days ago • 8
MameLoshnLM: Yiddish Language Model and Evaluation Benchmark Paper • 2608.05850 • Published Aug 6 • 23
Interpretable MEG Decoding of Perceived Speech: Cortical Sources and the Stimulus Features That Drive Retrieval Paper • 2608.01481 • Published Aug 2 • 71
PCSD: Persistent Consistency for Self-Distillation in Agentic Reinforcement Learning Paper • 2608.01837 • Published Aug 3 • 39
3DZip: Spatial-Aware Feature Diversity-Guided Token Compression for 3D Question Answering Paper • 2608.01185 • Published Aug 2 • 18
DavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF Image-Text-to-Text • 9B • Updated 14 days ago • 978k • 573