MiniMax released MSA (MiniMax Sparse Attention), a sparse attention method built directly on Grouped Query Attention (GQA). It targets one […]
Category: AI Paper Summary
Meet Flash-KMeans: An IO-Aware, Exact K-Means That Runs Over 200× Faster Than FAISS on GPUs
k-means has been an offline tool for decades. You run it once to preprocess data, then move on. A team […]
A New Study from Harvard and Perplexity Finds AI Agents Perform 26 Minutes of Autonomous Work per Session vs 33 Seconds for Search
A new working research from Perplexity and Harvard offers field evidence on what AI agents do to knowledge work. It […]
Meet Harness-1: A 20B Retrieval Subagent Trained With Reinforcement Learning Inside a Stateful Search Harness on gpt-oss-20b
Most search agents are trained as policies over a growing transcript. The model decides how to search. It must also […]
NVIDIA AI Releases Nemotron 3 Ultra: An Open 550B Mixture-of-Experts Hybrid Mamba-Transformer for Long-Running Agents
NVIDIA has released Nemotron 3 Ultra, the largest model in its Nemotron 3 family. It targets a specific problem: long-running […]
Meet OpenJarvis: A Local-First Framework for On-Device Personal AI Agents with Tools, Memory, and Learning
Researchers at Stanford University and Lambda Labs, have published the research paper for OpenJarvis, an open-source framework that runs inference, […]
Parallax: A Parameterized Local Linear Attention That Keeps Softmax and Adds a Learned Covariance Correction Branch
The Transformer’s attention mechanism has barely changed since 2017. Most efficiency work has tried to replace softmax attention outright. A […]
NVIDIA Introduces X-Token: Projection-Guided Cross-Tokenizer KD That Outperforms GOLD by +3.82 Average Points on Llama-3.2-1B
Knowledge distillation (KD) transfers “dark knowledge” from a large teacher model to a smaller student. The student learns from the […]
Sakana AI Proposes DiffusionBlocks: a Block-wise Training Framework That Converts Residual Networks into Independently Trainable Denoising Modules
Researchers from Sakana AI and the University of Tokyo propose DiffusionBlocks. It trains transformer-based networks one block at a time. […]
NVIDIA Releases Polar, a Token-Faithful Rollout Framework for GRPO Training Across Codex, Claude Code, and Qwen Code
Reinforcement learning for language agents is growing more complex. Agents now manage multi-turn tool use, long-running contexts, and multi-agent orchestration. […]