DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression Paper • 2609.19969 • Published 9 days ago • 181
Zing-0.5: Toward Playable Worlds with Real-Time Joint Action and Text Control Paper • 2609.17909 • Published 11 days ago • 44
Why Gated DeltaNet Survives 4-Bit Quantization: NVFP4 W4A4 for the Recurrent Half of a Hybrid 27B LLM Paper • 2609.04098 • Published 23 days ago • 84
Hierarchical Self-Improvement: A Framework for Task-Specific Evolvable Agent Harnesses Paper • 2608.08466 • Published Aug 9 • 14
nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 Text Generation • 32B • Updated Aug 24 • 426k • • 221
Decoding-Level Taboo: A Diagnostic Stress Test for LLM Robustness Paper • 2608.09900 • Published Aug 10 • 13
BDH-CQ: In-Context Learning with Recurrent Latent Reasoning Paper • 2608.09888 • Published Aug 10 • 792
GST-Bench: Can VLMs Develop Global Spatial Awareness from Video? Paper • 2608.05747 • Published Aug 6 • 47