Series introduces memory and process organization
Published on December 24, 2025, Byte Lab’s series introduces virtual memory, address spaces, process anatomy, registers, stacks, threads, and allocation methods.
Read articleKnowledge you can apply
Radar
Daily bookmarks: relevant news, facts and discoveries.
Research uses AI to optimize systems algorithms
The article presents ADRS, a framework in which language models generate, evaluate, and refine algorithms for systems performance problems. It reports applying three open-source frameworks to ten tasks in networking, databases, and distributed systems.
Read articleTransformer techniques in gpt-oss
Published on December 24, 2025, the post lists optimizations used with gpt-oss in Transformers: MXFP4 quantization, tensor and expert parallelism, and dynamic sliding windows.
Read articleCollection catalogs prompt injection vectors
Published on December 23, 2025, the entry points to a collection of prompt injection vectors and strategies, with examples, that may help identify techniques during security evaluations.
Read articleVirtual memory: an introduction for beginners
An introductory article published on December 23, 2025, presenting the basics of virtual memory and its usefulness for understanding memory behavior in systems software.
Read articleMultimodal RL: advantage shaping in a single rollout
A publication reports that single-rollout multimodal RL became stable with advantage shaping and an entropy bonus, a topic of interest to researchers studying policy-gradient methods.
Read articleSSR explores self-training for repository bugs
Published on December 23, 2025, the post presents Self-play SWE-RL (SSR), a method for training a language agent to inject and fix bugs in real repositories without human-labeled issues or tests.
Read articleSquinch compresses gradients in pretraining
Published on December 23, 2025, the account credits the Squinch algorithm with using one quarter of IB bandwidth while maintaining SOTA MFU in pretraining on GCP H100-TCPX.
Read articleIceberg broadens vector search evaluation
A benchmark suite with eight datasets evaluates vector similarity search beyond recall and latency, examining its impact on downstream tasks such as RAG and image classification.
Read articleOpenTinker separates RL programming and execution
OpenTinker is an open-source RL-as-a-Service platform for foundation models. Its design separates programming from execution and describes developing environments locally while using remote compute.
Read articleOverview of RL training systems and pass@k results
A December 21, 2025 publication covers on-policy rollout divergence, rollout-system design, and the effects of RL on pass@k performance.
Read articleSA-RAG applies spreading activation to knowledge graphs
Published on December 20, 2025, this item describes a retrieval approach for knowledge-graph RAG, intended to find connected evidence for multi-hop questions.
Read articleWhy token order challenges masked models
A paper recognized at ICML 2025 investigates masked models’ weaker performance on generation benchmarks and points to difficulties associated with training on arbitrary subsets of revealed tokens.
Read articleDEER proposes diffusion drafts to speed up LLMs
A publication dated December 18, 2025 describes DEER, which drafts tokens with diffusion models and verifies them with autoregressive models. It reports inference speedups of up to 5.54× with no loss of quality.
Read articleRadar: stabilizing reinforcement learning with LLMs
An article published on December 16, 2025 examines instability in reinforcement learning for large language models and highlights relevant differences and techniques.
Read articleCUDA-L2 optimizes HGEMM kernels with reinforcement learning
Published on December 15, 2025, the paper presents an approach combining language models and reinforcement learning to optimize CUDA half-precision matrix multiplication kernels. It evaluates kernels across 1,000 configurations and reports results above matmul baselines.
Read articleOlmo 3: SFT, DPO and RLVR in training
Published on December 15, 2025, the post describes an Olmo 3 training pipeline: SFT on curated reasoning traces, followed by preference tuning with DPO and RLVR using Group Relative Policy Optimization.
Read articlePasoDoble explores dual-play for LLM reasoning
Published on December 15, 2025, the paper presents dual-play: two models take specialized roles—one poses questions and the other solves them—to reduce reliance on external supervision.
Read articleRouteRAG adapts retrieval across text and graphs
The framework uses reinforcement learning to choose when to retrieve information from text and graphs during reasoning, with a reward that discourages unnecessary searches.
Read articleSWAA proposes more efficient inference with long context
A December 15, 2025 post presents training-free recipes to adapt full-attention LLMs to linear scaling and recover performance.
Read articleRota Nacional
Bring privacy into your workflow.
30 days, no card, with a starting quota. After that, Pix credit from R$ 10,00.