Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory Paper β’ 2504.19413 β’ Published Apr 28 β’ 36
SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion Paper β’ 2503.11576 β’ Published Mar 14 β’ 122
TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times Paper β’ 2512.16093 β’ Published 12 days ago β’ 84
Emergent temporal abstractions in autoregressive models enable hierarchical reinforcement learning Paper β’ 2512.20605 β’ Published 6 days ago β’ 54
β Long-context post-training π§Ά β Collection Resources for post-training LLMs with long-context samples β’ 5 items β’ Updated Sep 14 β’ 6
VL-JEPA: Joint Embedding Predictive Architecture for Vision-language Paper β’ 2512.10942 β’ Published 18 days ago β’ 11
V-JEPA 2 Collection A frontier video understanding model developed by FAIR, Meta, which extends the pretraining objectives of https://ai.meta.com/blog/v-jepa-yann β’ 8 items β’ Updated Jun 13 β’ 177
view article Article AprielGuard: A Guardrail for Safety and Adversarial Robustness in Modern LLM Systems 6 days ago β’ 33
view article Article The Open Evaluation Standard: Benchmarking NVIDIA Nemotron 3 Nano with NeMo Evaluator 12 days ago β’ 35
Google Gemma Scope 2 - Neuronpedia Collection Google Gemma Scope 2: JumpReLU SAEs for Gemma 2 interpretability. 270M PT/IT, 1B PT variants. Neuronpedia integration. Mechanistic analysis. β’ 11 items β’ Updated 1 day ago β’ 1