Termsslug: vision-language-model-vlm

Vision-Language Model (VLM)

视觉语言模型

Multimodal AI models capable of processing and understanding both image and text data simultaneously.

Curated Intelligence

40 items · Page 1/4
量子位 (微信公众号)T2·Models
40 pts
China Merchants' Lion Mountain Lab Releases 35B Embodied Reasoning Model with 3B Active Params

The Lion Mountain AI Lab under China Merchants Advanced Technology Institute has released Lion-ER-35B-A3B, an embodied-reasoning vision-language model built on a mixture-of-experts architecture with roughly 35B total parameters and only about 3B activated per token. The lab claims across-the-board gains on ten embodied-AI benchmarks, with some capabilities surpassing larger models, and attributes this to a capability-first data engine that decomposes embodied reasoning into 8 top-level domains and 39 sub-capabilities and iterates data against evaluation gaps rather than scaling raw data volume. No concrete benchmark numbers, baseline configurations, or release/access details are disclosed, so the claims remain vendor assertions.

Rohan Paul (@rohanpaul_ai)T2·Models
78 pts
DeepMind Study: Irrelevant Shapes Steer AI Code Logic

A new paper from Google DeepMind and Stanford reveals that vision-language models are susceptible to hidden steering by irrelevant geometric shapes in prompts. Experiments showed that adding a red heart image caused Claude Opus 4.7 and GPT-5.4 to shift their recursive solution choice from 0% to 100% on binary tree tasks, while Gemini's reasoning traces often failed to flag the visual influence. This highlights the critical need for rigorous isolation testing of multimodal inputs.

Rohan Paul (@rohanpaul_ai)T2·Models
78 pts
OXR Releases Open-Source Document Parser with RSI Training Loop

OXR releases a 1.3B-parameter open-source document parser that pioneers Recursive Self-Improvement (RSI) in OCR training. By using VLMs to evaluate outputs and cluster failure causes for targeted data generation, the model tops olmOCR-Bench, OmniDocBench, and DocParsingBench while achieving 3.05x the throughput of GLM-OCR on a single RTX PRO 6000.

IT之家 · 智能时代T2·Infra
68 pts
Micron Develops Edge Inference Memory for Physical AI Latency

Micron is developing Edge Inference Memory (EIM), a specialized storage chip for autonomous driving and humanoid robots that stacks low-power memory to reduce latency and boost bandwidth. Distinct from Processing-in-Memory (PIM), EIM aims to integrate with LPDDR6 by late 2028 to meet the growing demands of physical AI systems.

宝玉 (@dotey)T2·Agents
68 pts
Gemini 4 Argon Generates Japanese Temple in Blender via Single Prompt Using Multi-Agent Workflow and Visual Feedback Loop

Gemini 4 Argon, within the Antigravity framework, successfully generated a complex Japanese temple structure in Blender using a single prompt containing detailed workflow instructions. The process demonstrates a full automation loop: blueprint planning, reference image generation via Nano Banana, multi-agent collaborative modeling, and iterative refinement through visual comparison between Blender renders and references. A coordinator agent managed tasks while a critic agent validated outputs, ensuring accuracy against visual targets. The final result extended to procedurally generated animations and ambient sounds, highlighting significant advancements in LLMs' ability to understand real-world physics and execute long-horizon complex tasks.

量子位官网T2·Models
86 pts
MiniCPM-V 4.7 Open-Sourced: 35B MoE Multimodal Model Runs on iPhone with 3GB RAM and 13 Tokens/s Offline

ModelBest and OpenBMB have open-sourced MiniCPM-V 4.7, a multimodal LLM featuring a 35B-parameter MoE architecture that activates only 3B parameters per inference. The model runs offline on devices like the iPhone 17 Pro Max using just ~3GB of RAM, achieving decoding speeds exceeding 13 tokens per second after optimization. It also demonstrates strong performance in general vision, math, and video understanding benchmarks, with broad support for mobile OSes and major chip platforms.

IT之家 · 智能时代T2·Models
78 pts
Liquid AI Open-Sources d1 Decision Models: 3B Params Achieve 8ms Inference with Multimodal Support

Liquid AI has released and open-sourced the d1-3B and d1-omni-600M decision models, emphasizing ultra-low latency and multimodal capabilities. The d1-3B model achieves 8ms text inference on an RTX 4090 and leads in Decision Index v0.2.1 benchmarks among sub-10B models. The d1-omni-600M variant adds voice input support, offering a lightweight solution for real-time agent applications on edge devices.

vLLM 官方博客T1·Tools
58 pts
NVIDIA Integrates PyNvVideoCodec into vLLM: GPU Hardware Decoding Breaks Multi-GPU Video Captioning Throughput Bottlenecks

NVIDIA announced official support for GPU hardware video decoding via PyNvVideoCodec within vLLM, addressing the throughput bottleneck caused by CPU-based decoding in multi-GPU video captioning tasks. By offloading frame decoding from CPU to GPU, this integration significantly enhances end-to-end inference efficiency and scalability for Vision Language Models (VLMs) handling short-output video annotation scenarios.