Noticias
MSCoRe: A Benchmark for Multi-Stage Collaborative Reasoning in LLM Agents
arXiv:2509.17628v1 Announce Type: new Abstract: Large Language Models (LLMs) have excelled in question-answering (QA) tasks...
MOSAIC: Multi-agent Orchestration for Task-Intelligent Scientific Coding
arXiv:2510.08804v1 Announce Type: new Abstract: We present MOSAIC, a multi-agent Large Language Model (LLM) framework...
MoonshotAI Released Checkpoint-Engine: A Simple Middleware to Update Model Weights in LLM Inference Engines, Effective for Reinforcement Learning
MoonshotAI has open-sourced checkpoint-engine, a lightweight middleware aimed at solving one of the key bottlenecks...
Moonshot AI’s Kimi K2 outperforms GPT-4 in key benchmarks — and it’s free
Chinese AI startup Moonshot releases open-source Kimi K2 model that outperforms OpenAI and Anthropic on...
Moonshot AI Releases Kimi K2: A Trillion-Parameter MoE Model Focused on Long Context, Code, Reasoning, and Agentic Behavior
Kimi K2, launched by Moonshot AI in July 2025, is a purpose-built, open-source Mixture-of-Experts (MoE)...
MoE Architecture Comparison: Qwen3 30B-A3B vs. GPT-OSS 20B
This article provides a technical comparison between two recently released Mixture-of-Experts (MoE) transformer models: Alibaba’s...
Model Interpretability and Rationale Extraction by Input Mask Optimization
arXiv:2508.11388v1 Announce Type: new Abstract: Concurrent to the rapid progress in the development of neural-network...
Model Context Protocol: A promising AI integration layer, but not a standard (yet)
Enterprises should experiment with MCP where it adds value, isolate dependencies and prepare for a...
MIT’s LEGO: A Compiler for AI Chips that Auto-Generates Fast, Efficient Spatial Accelerators
Table of contents Hardware Generation without Templates Input IR: Affine, Relation-Centric Semantics (Deconstruct) Front End:...
MIT Researchers Enhanced Artificial Intelligence (AI) 64x Better at Planning, Achieving 94% Accuracy
Can a 8B-parameter language model produce provably valid multi-step plans instead of plausible guesses? MIT...
MIT Researchers Develop Methods to Control Transformer Sensitivity with Provable Lipschitz Bounds and Muon
Training large-scale transformers stably has been a longstanding challenge in deep learning, particularly as models...
