Knowledge you can apply
Daily bookmarks: relevant news, facts and discoveries.
Published on July 2, 2026, the post presents Diffusion-GR2, a block diffusion model for generative-reasoning reranking. It reports ranking accuracy close to the autoregressive model and decoding 2.4–3.5 times faster.
Read articlePublished on July 2, 2026, the video covers Q/K/V, attention scores, and encoder blocks. Its description explains how queries are compared with keys to weight value vectors.
Read articleMaterial by Vasily Volkov of UC Berkeley explores GPU architecture and performance concepts that are not covered in depth in a well-known parallel programming book.
Read articleA paper proposes self-supervised hard-negative sampling for two-tower recommendation, using LLM-derived item clusters to generate harder examples in real time.
Read articlePublished on July 2, 2026, this bookmark describes a study of attention-projection sharing variants and reports that setting K equal to V was excessive for the author's small ternary LLMs.
Read articleThe paper formalizes LLM evaluator panels under a contamination model and proposes aggregating scores with the geometric median. It reports experiments with 13 judges and corruption rates up to 50%.
Read articlePublished on July 2, 2026, the list presents ten papers in a suggested order on Transformers, scaling, few-shot learning, RLHF, LoRA, FlashAttention, chain-of-thought, and DPO.
Read articlePublished on July 2, 2026, this entry highlights a Speculators shell script for online DSpark training with Qwen3 0.6B and ShareGPT.
Read articleAn article describes a radix trie execution plan for PyTerrier that reuses shared pipeline prefixes and reports experiment time reductions of up to 26%.
Read articleA record about Frances Allen’s 1971 article cataloguing compiler optimization transformations and listing passes attributed to Graydon Hoare.
Read articleA July 2, 2026 brief on a proposal to address vocabulary gaps in learned sparse retrieval with advanced encoders.
Read articleResearchers at the University of Florida and Ohio University present Effective Model Pruning, a method that uses effective sample size to calculate how many components to retain in neural networks and language models.
Read articleOn July 1, 2026, an update was announced to Intel’s technical paper on memory protections for confidential computing.
Read articlePublished on July 1, 2026, this open book has five chapters and is available in PDF and EPUB. The author says its general debugging methodology applies broadly, despite a focus on Unix, Python, and PyTorch.
Read articleA post reports Python programs synthesized from attention maps, reaching 69–79% mean IoU on three models; replacing up to 30–40% of heads reportedly caused little decline in QA.
Read articleThe open-source benchmark compares style embeddings across 96 datasets and seven languages. The post reports that semantic embeddings perform worse on stylistic tasks and that no model dominates.
Read articleA June 30, 2026 post says that learning during inference in the ARC-AGI-3 benchmark leads agents to build and update internal models of the environment’s rules and mechanics.
Read articlePublished on June 30, 2026, the paper proposes organizing information retrieval systems with indexes, models, and inference on users’ devices, while making remote services optional.
Read articlePublished on June 30, 2026, the post says C++26 standardizes Hazard Pointers, an approach that delays deleting nodes until concurrent readers finish using them.
Read articlePublished on June 30, 2026, the CAMI paper frames the construction of multiple semantic enrichment indexes as portfolio selection with multiple objectives and a limited budget.
Read articleRota Nacional
30 days, no card, with a starting quota. After that, Pix credit from R$ 10,00.