Knowledge you can apply
Daily bookmarks: relevant news, facts and discoveries.
A paper describes query and item embeddings for efficiently retrieving candidates when relevance computation is expensive. The reported approach uses relevance to selected support items or queries.
Read articlePublished on July 7, 2026, Lilian Weng’s article examines recursive self-improvement and presents designing and optimizing a model harness as a practical starting point.
Read articlePublished on July 7, 2026, the material presents Hierarchical Landmark Sparse (HiLS) Attention, a method that learns chunk selection end to end using the language-modeling loss.
Read articleA post published on July 7, 2026 describes JetSpec, which uses a single forward pass with causal conditioning to create coherent draft trees. It reports speedups of up to 9.64× on MATH-500 and 4.58× in open-ended conversations.
Read articlePublished on July 7, 2026, the notice describes a live stream about new chapters of Programming Massively Parallel Processors and an overview of the material.
Read articlePublished on July 7, 2026, the work presents a method for linking training samples to interpretable attention heads and reports effects of interventions on those circuits.
Read articlePublished on July 7, 2026, the summary presents a proposal to convert off-policy tokens into tokens treated as on-policy through rejection sampling, addressing variance in LLM alignment.
Read articleA study evaluates self-distillation with privileged information in reasoning models and reports degradation in long trajectories across five models tested on AIME.
Read articleA survey published on July 7, 2026 proposes classifying recommender systems with LLM-based agents by their level of autonomy.
Read articlePublished on July 6, 2026, this summary presents Autodata, a method that uses agents to create training and evaluation data by selecting questions that distinguish weak and strong solvers.
Read articleA post about a paper describes agents that write, search and organize notes, learning when memory is useful. According to the post, this improved an open 32B model's performance by 2x to 4x in long games.
Read articlePublished on July 6, 2026, the article presents building floating-point arithmetic from scratch as a high-difficulty project.
Read articleA 2021 book by Douglas Thain introduces compilers and language design for engineers interested in building these technologies.
Read articlePublished on July 6, 2026, the paper summary describes learned bases and a compact matrix for representing attention, reports linear cost in the number of points, and cites results in three evaluation areas.
Read articleA bookmark published on July 6, 2026 reports that NVIDIA's CUDA C++ Programming Guide was updated in June 2026 and describes it as a current reference for engineers working with CUDA C++.
Read articleIn a post published July 6, 2026, HOLA combines recurrent state with a small KV cache for exact memory. The post reports a 16.1% reduction in perplexity and robust retrieval at 32k tokens.
Read articleAn article published on July 6, 2026 examines innovations, broad impact, and ongoing work around the LLVM compiler infrastructure, offering context for engineers in the field.
Read articlePublished on July 6, 2026, the post presents PACE, which uses regression on a small set of non-agentic tasks to estimate agents’ full performance.
Read articlePublished on July 6, 2026, the paper presents ReContext, a training-free inference method that resubmits relevant evidence before generation. It reports results on eight 128K datasets and three model backbones.
Read articleA study examines language models as in-context retrievers over one-million-token corpora and reports that BlockSearch generalizes up to ten times beyond its training length.
Read articleRota Nacional
30 days, no card, with a starting quota. After that, Pix credit from R$ 10,00.