Auto Added by WPeMatico
Prime Intellect has released Prime Mega MoE, a training extension of DeepSeek’s fused Mega MoE kernel. DeepSeek’s kernel only ran the forward pass. Prime Intellect added a fast, overlapping backward pass. That makes the fused kernel usable for training, not just inference. In its prime-rl trainer, full training steps on Qwen3 MoE models run up
Researchers from Polymathic AI, Princeton University, USC ISI, NYU and the Flatiron Institute have released FlashMap. FlashMap speculative decoding replaces the discrete diffusion drafter with a continuous flow map. It drafts a full 16-token block in 1 forward pass. Tokens in that block stay consistent with each other. On Qwen3-8B, the research team reports up
The crack of a bat accompanied by a roar from the crowd can capture a baseball fan’s attention, even if they miss seeing the home run. Humans may be visual creatures, but we also perceive the world around us by listening to it. To improve artificial perception, MIT Professor Paris Smaragdis SM ’97, PhD ’01 seeks
UC Berkeley’s Sky Computing Lab built LEANN, an open-source vector index that stores almost no embeddings. The LEANN vector index recomputes embeddings at query time instead of saving them to disk. The repo benchmark shows a 60 million chunk Wikipedia index dropping from 201 GB to 6 GB. The research paper won the Best Research
Mirendil has released Fern, its first AI model. Mirendil Fern is a from-scratch coding model with a context window of up to 10M tokens. Mirendil explains how that equals about 23 MB of code, or roughly half a million lines. That is a codebase on the scale of Megatron-LM, held in context at once. Fern
Mirendil Launches Fern 0.1, Its First Model, With 10M-Token Context Read More »
Nace AI has released Drex for Search, which brings its Drex decision models to document search. Drex for Search is a retrieval layer that helps people and agents find evidence. Coding agents such as Claude Code, Codex, Cursor and OpenCode call it through CLI, SDKs, MCP or REST. In Nace’s evaluation, it scores 92.05% on
Hugging Face has released Carbon-X, an open DNA language model with 14.8B parameters. Carbon-X is a decoder-only model from Hugging Face Bio. It reads raw DNA in a chat and answers in English. It predicts whether mutations are benign or pathogenic, flags regulatory regions, classifies organisms and predicts next bases. The weights ship under Apache
Stanford and UC Berkeley researchers released TokenGate, a module for long-context prefill. TokenGate learned token pruning lets an existing LLM skim its input. Only the tokens that matter get full processing. The research team reports 1.4x to 11.3x faster time-to-first-token (TTFT) with no accuracy loss. Peak prefill memory drops 1.5x to 3.4x. Code and checkpoints
Microsoft Research has open-sourced Agensh, a decentralized harness for large teams of coding agents. The Agensh multi-agent harness removes the central orchestrator that most agent frameworks depend on. Every worker picks its own sub-task, shares findings and merges code into a common Git repo. On ProgramBench, the team scaled the setup from 1 agent to
Microsoft Open-Sources Agensh: A Multi-Agent Harness for 1,024 Agents Read More »
Kyutai has released CADRE, open causal diffusion representation autoencoders for interactive world models. The Kyutai CADRE video autoencoder targets one problem: action lag. Many world models borrow autoencoders from text-to-video generators. Those autoencoders pack many frames into one latent, so every action waits. Per the research paper, CADRE world models run at 20 fps on
Kyutai CADRE: Video Autoencoders That Cut World Model Lag Below 230 ms Read More »
