RAG: expand documents, not the model
Published on January 14, 2026, this summary describes a CMU researchers’ study of expanding the retrieval corpus in RAG as an alternative to scaling up the language model.
Read articleKnowledge you can apply
Radar
Daily bookmarks: relevant news, facts and discoveries.
UniversalRAG routes retrieval across modalities and granularities
Published on January 14, 2026, the summary presents UniversalRAG, a framework that routes queries to a corpus for a specific modality before retrieving information from it.
Read articleMemRL learns to assess agent memories
Published on January 13, 2026, the summary presents MemRL, an approach that learns to rank episodic memories by utility without changing language-model weights.
Read articleMicrosoft launches 14B FrogMini coding agent
A January 13, 2026 publication reports the launch of FrogMini, a 14B coding agent, and gives a score of 45.3% on SWE-Bench Verified.
Read articlePocket TTS: compact speech synthesis for laptops
A January 13, 2026 publication presents Pocket TTS, a 100-million-parameter text-to-speech model described as running on a laptop without a GPU and offering voice cloning.
Read articleDroPE: extending context without positional embeddings
Published on January 12, 2026, the summary presents DroPE, a method that removes positional embeddings after training and uses brief calibration to extend context.
Read articleInterviews map the RL environments field
In a post dated January 12, 2026, Chris Barber and JS Denain report interviews with 18 people from RL environment startups, neolabs, and frontier labs. The material offers engineers a view of how different organizations develop these environments.
Read articleLeaker: passive breach enumeration
Published on January 12, 2026, the listing describes Leaker as a tool that searches passive online sources for credential leaks associated with email addresses.
Read articleLEMAS announces speech dataset with 150,000 hours
Published on January 12, 2026, the announcement describes a multilingual audio dataset with 150,000 hours, coverage of 10 languages and word-level timestamps, along with the generative models LEMAS-TTS and LEMAS-Edit.
Read articleLoPA explores lookahead in diffusion LLM decoding
Published on January 11, 2026, the summary describes LoPA, a training-free, plug-and-play algorithm that uses lookahead to choose token-filling orders in diffusion LLMs.
Read articleSFT and reinforcement fine-tuning in continual post-training
The article compares SFT and reinforcement fine-tuning for continual adaptation of foundation models; its title claims the latter naturally mitigates forgetting.
Read articleReport examines model tuning for the Q programming language
Published on January 9, 2026, the technical report presents an open-source approach to adapting language models to Q, a programming language used in quantitative finance.
Read articleSETA announces RL resources for terminal agents
On January 9, 2026, SETA announced 400 training environments, a reinforcement-learning pipeline, and SETA-RL-Qwen3-8B weights for terminal-agent experiments.
Read articleOpenTinker proposes RL-as-a-Service infrastructure
A Radar entry dated January 8, 2026 describes OpenTinker as an open-source reinforcement learning platform for agents, separating programming from execution.
Read articleASUS and XREAL plan 240 Hz AR glasses for 2026
The announcement plans augmented-reality glasses with 1080p micro-OLED panels, a USB-C connection, and a dock with HDMI and DisplayPort.
Read articleDell announces a 52-inch 6K monitor
On January 6, 2026, Dell announced a 52-inch Thunderbolt monitor with 6K resolution and inputs for connecting multiple computers.
Read articleRecursive models use code to process long prompts
A January 6, 2026 MIT post describes recursive language models that use a Python interface to search, filter and recursively process smaller sections of long inputs. The post says they handle inputs up to about 100 times larger than usual and outperform base models and retrieval configurations.
Read articleMasters: mask-progressive distillation for VLMs
Published on January 4, 2026, the post describes the Masters framework and reports score gains on two VLMs, with the stated aim of avoiding online RL's computational cost.
Read articleJustRL tests simple RL on 1.5B models
A paper preview describes single-stage training with fixed hyperparameters and reports average accuracies of 54.9% and 64.3% on two 1.5B reasoning models.
Read articleLoRA and RLVR: comparing strategies across domains
Published on January 3, 2026, this account compares practical PEFT strategies for multi-domain RLVR. In the reported experiments, averaging specialist LoRA weights and then continuing training outperformed the tested gating method.
Read articleRota Nacional
Bring privacy into your workflow.
30 days, no card, with a starting quota. After that, Pix credit from R$ 10,00.