Knowledge you can apply
Daily bookmarks: relevant news, facts and discoveries.
Published on September 17, 2026, the article describes a framework using specific weights and recurrent Transformer layers to emulate computational operations, including conditional branches and program counters.
Read articleAn architecture applies a Transformer layer recurrently to blocks of tokens, using self-attention and cross-attention to process sequences with complexity linear in their length.
Read articleA September 17, 2026 post describes an architecture that repeatedly applies the same Transformer layer instead of stacking distinct layers, and highlights sequential versus parallel computation.
Read articleXiaomi's model uses a reference voice to transcribe a selected speaker in overlapping audio; the publication reports support for English and Chinese.
Read articleIn MLPerf Inference v6.1 results, Crusoe reported 5.75 million tokens per second for gpt-oss-120b using 512 AMD Instinct MI355X GPUs.
Read articlePublished on September 16, 2026, the article presents attention as Entropic Optimal Transport and proposes replacing the implicit uniform prior with a continuous, trainable prior.
Read articleA September 16, 2026 article frames associative recall in linear attention as a spherical packing problem and presents KATA activations derived from a homogeneous self-dual cone.
Read articleIn a September 16, 2026 publication, SAS describes a selector trained inside Softmax to filter context in attention designed for hardware with limited computational resources.
Read articleSoftmax Linear Attention proposes applying softmax at the head level to restore global competition in linear attention while retaining the goal of linear complexity. The approach can be compared with standard softmax normalization.
Read articleA paper presents a dynamic, granular approach combining full and sliding-window attention in hybrid transformers, addressing the former's quadratic cost and the latter's narrower receptive field.
Read articleA post published on September 16, 2026, reports that local denoising objectives helped recurrent Looped Flows models with multi-step computation. It says they outperformed earlier looped models on six reasoning benchmarks, including 58.8% accuracy on ARC-AGI-1.
Read articleThe article presents Tucker Attention as a tensor-factorization approach that frames MHA, GQA, and MLA within a shared perspective on low-rank approximate attention.
Read articlePublished on September 15, 2026, the article examines rank collapse as context grows and analyzes rescaling attention scores.
Read articleVersion 1.0 introduces an autonomous meta-harness that evolves both GPU kernels and the harness layer; the project won the DSA category in an MLSys 2026 FlashInfer contest.
Read articleVersion v0.1.6-alpha.1 adds a Web sidebar with persistent terminals, multiple tabs, and MCP resource support. Experimental options include browser tools and computer drivers.
Read articlePublished on September 15, 2026, the post describes Octop as an open-source, self-hosted AI assistant platform supporting multiple users and agents.
Read articlePublished on September 15, 2026, the paper presents RoLA, a low-rank linear attention method with rotary position for Diffusion Transformers. It addresses quadratic scaling in dense spatiotemporal self-attention and a compatibility problem between RoPE and the global branch
Read articlePublished on September 15, 2026, the entry describes an open-source project with a web interface for training voice conversion models using 10 minutes or less of voice data.
Read articlePublished on September 15, 2026, Xiaomi-CocktailASR-1 demonstrates speaker-conditioned speech recognition on overlapping audio.
Read articleA paper compares distilled byte and token models trained at scales up to 1 trillion bytes and reports a higher performance ceiling for byte models as compute increases.
Read articleRota Nacional
30 days, no card, with a starting quota. After that, Pix credit from R$ 10,00.