← Back to Videos

LongCat-2.5: Native Multimodal Agents

Loading video

LongCat-2.5 combines 1.6T total parameters, about 48B active, native visual understanding, and agentic coding to generate an interactive 3D artifact showcase.

LongCat-2.5 Multimodal Agentic AI Visual Coding 3D Meituan LongCat

Category: llm

Author: @Meituan_LongCat

Date: 2026-11-02T14:35:23

Duration: 14.675s

Source: https://x.com/Meituan_LongCat/status/2117264311714537633

Reference: https://longcat.ai/blog/longcat-2.5/

NVIDIA Nemotron 3.5 Super VL: a 120B open vision-language model for long-running agents

NVIDIA Nemotron 3.5 Super VL: a 120B open vision-language model for long-running agents

@NVIDIAAI · 167 views · 2026-10-15

DeepSeek V4.1 Flash Builds Tetris in 5.21 Seconds

DeepSeek V4.1 Flash Builds Tetris in 5.21 Seconds

@FireworksAI_HQ · 157 views · 2026-10-21

DeepSeek V4.1 Flash hits 1,521 tokens/s on Fireworks

DeepSeek V4.1 Flash hits 1,521 tokens/s on Fireworks

@MinLiBuilds · 142 views · 2026-10-22

Google AI Edge Foresight: Free Offline AI Note-Taking on Apple Silicon

Google AI Edge Foresight: Free Offline AI Note-Taking on Apple Silicon

@AYi_AInotes · 260 views · 2026-10-11

Google AI EdgeOn-Device AI

JEV-27B-VL: Calibrated Visual Decisions for Long-Context Workflows

JEV-27B-VL: Calibrated Visual Decisions for Long-Context Workflows

@ModelScope2022 · 353 views · 2026-10-10

Vision-language modelsCalibrated Confidence

DeepGEMM-Ascend Brings DeepSeek Kernels to Huawei NPUs

DeepGEMM-Ascend Brings DeepSeek Kernels to Huawei NPUs

@EngMoElgaraihy · 458 views · 2026-10-05

DeepGEMMDeepGEMM-Ascend

As an Amazon Associate, we earn from qualifying purchases.