Explore tools, prompts, skills, news and resources related to Meta 第9页.
Latest articles, prompts, use cases and editorial content about Meta 第9页
This paper investigates how reward models learned from human preferences can be exploited by sampling-based control methods like MPPI and best-of-N selection. Experiments on HalfCheetah, Hopper, and Meta-World tasks show...
DataHelix is a metadata-first CPU-GPU co-scheduling data plane designed to reduce pipeline bubbles in multimodal model training. It coordinates preprocessing across data-parallel ranks by treating GPU compute windows as...
Reason Machines has released Aspen, an Apache 2.0 Git server designed for repositories receiving heavy push traffic from AI agents. Aspen is a Rust binary that stores branch history in PostgreSQL or SQLite and packs in S...
The paper applies weight-space programming to a robot foundation policy: a language model reads the policy's weights and edits token-embedding rows using a CPU workspace and budgeted simulator feedback, with no grad...
Researchers manually analyzed 300 GitHub issue reports, discussions, and fixes across seven GPU kernel libraries used in LLM systems: FlashInfer, FlashAttention, Triton, CUTLASS, DeepGEMM, xFormers, and bitsandbytes. The...
This article compares routing mechanisms across 10 open Mixture-of-Experts (MoE) models, detailing expert counts, top-k values, shared experts, gating functions, and load-balancing methods. It highlights trends like grow...
Alibaba introduced Co-Design Bench, a benchmark based on real user requests that coding agents previously failed in practice. The top-performing model, GPT-6 Astra, fully solved 26.4% of tasks, despite the same models sc...
Nous Research released Arete-27B, a supervised fine-tune of Qwen3.8-27B trained on 52.8 million tokens without reinforcement learning or architectural changes. On Nous Research's self-built 803-prompt evaluation, th...