2025-09-22

Models

• [ ]

Papers

• [2508.20722] rStar2-Agent: Agentic Reasoning Technical Report
• [2509.09372] VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model
• [2509.17765] Qwen3-Omni Technical Report
• [2509.18095] MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction
• [2509.16633] When Big Models Train Small Ones: Label-Free Model Parity Alignment for Efficient Visual Question Answering using Small VLMs
• [2509.16197] MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer

Code

• GitHub - NVlabs/GatedDeltaNet: [ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Rule
• [ ]

Articles

• All About Transformer Inference | How To Scale Your Model
• The Parallelism Mesh Zoo : ezyang’s blog

Videos

• [ ]

Other

• RLHF Book by Nathan Lambert

Tweets