Daily bookmarks: relevant news, facts and discoveries.
Articles 1219
Engineering ·
Published on July 10, 2026, the article presents an architecture for continuous learning by agents on real workloads, with step-by-step signals, task-to-training-data conversion, and automatic updates.
Engineering ·
July 10, 2026 archive entry: a post shares a Triton paged attention kernel attributed to Grok and a solution file hosted on KernelBench.
Engineering ·
An ACL 2026 article reports that using 4 bits for keys and 2 for values may work well for KV cache compression; reversing those bit widths substantially degrades accuracy.
Engineering ·
Published on July 10, 2026, the report presents Latent Exploration Decoding (LED), a method requiring no additional training that uses intermediate-layer distributions to improve sampling in reasoning models.
Engineering ·
A paper dated July 10, 2026 presents a separate memory agent that maintains structured information and decides when to offer reminders to an action agent.
Engineering ·
An article investigates whether models can balance accuracy, context size, compute cost, and latency without relying on long reasoning chains.
Engineering ·
Published on July 10, 2026, Jeff Geerling’s account presents QuadRF, a phased-array radio built with a Raspberry Pi 5 and an FPGA board. It uses signal processing and beamforming to track drones and detect Wi-Fi through walls.
Engineering ·
An article published on July 9, 2026 examines how to distribute model capacity across delegation and execution roles in hierarchical search agents. The post identifies decomposition capacity as the main performance bottleneck.
Engineering ·
Published on July 9, 2026, the project describes a two-core GPU on a US$30 FPGA, with a 16-bit ISA, assembler, J++ language, compiler, and AI inference at 81 MHz.
Engineering ·
Published July 9, 2026, the study evaluates 22 tasks across six models, changing only the orchestration layer. It reports lower costs, token use, and runtime, with equivalent task-completion quality.
Engineering ·
Published on July 9, 2026, the article discusses asynchronous RL for language-model post-training, with updates as rollouts arrive. It cites clipping adjustments in GLM 5.2 PPO and also points to VAPO.
Engineering ·
Efficient memory can improve service capacity. The design must also prevent one session's context from appearing in another session.
Engineering ·
The article presents CMDR and CMDR-Bench for retrieving relevant pages from multimodal documents when queries depend on context spanning multiple pages.
Engineering ·
A Kuleshov Group post presents research on diffusion language models, covering masked diffusion, iterative refinement, post-training, and variable-length generation.
Engineering ·
Published on July 8, 2026, the article follows a vector-sum kernel from compilation with nvcc to execution by GPU warps.
Engineering ·
A paper describes a method that dynamically selects, token by token, between supervision based on a teacher and on the model itself.
Engineering ·
A paper published on July 8, 2026 presents pooling-aware fine-tuning and k-means to reduce token vectors in ColBERT documents, claiming to preserve accuracy.
Engineering ·
An article published on July 8, 2026 presents NapMem, a framework that organizes a user's history in a linked memory pyramid with multiple granularities.
Engineering ·
Published on July 8, 2026, NapMem organizes user history into memory layers and trains an agent to choose which layer to inspect. The proposal contrasts with relying only on evidence preselected by a retriever.
Engineering ·
Published on July 8, 2026, the article examines MaxSim’s representational power and reports that it can exactly reproduce inner products between nonnegative k-sparse vectors.
Looking for something else?DocumentationContact
