vision-language-model

[ICLR 2025] - Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion

OmniAgent (ICML 2026): the first native omni-modal agent for active video perception — a 7B agent that beats Qwen2.5-VL-72B with 73% fewer frames on LVBench.

Android native AI inference library, bringing text, image, video, STT, TTS inference

The official implementation of CVPR 24' Paper "Learning Transferable Negative Prompts for Out-of-Distribution Detection"

Mark web pages for use with vision-language models

ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model

[CVPR 2024] The official implementation of paper "synthesize, diagnose, and optimize: towards fine-grained vision-language understanding"

OpenSceneSense Ollama is a Python library that harnesses AI for advanced local video analysis, offering customizable frame and audio insights for dynamic applications in media, education, and content moderation.

Reproducible, production-grade pipelines for modern multimodal vision systems. Efficient VLM adaptation · Embedding-space drift detection · Edge inference · Robustness & safety

Toy-scale unified multimodal model experiments — encoder-free understanding & generation with Mixture-of-Transformers on MLX/Apple Silicon

[CVPR 2024 Highlight] ImageNet-D

Code repository for "Post-pre-training for Modality Alignment in Vision-Language Foundation Models" (CVPR2025)

Synthetic medical VQA pipeline: 119K images annotated by frontier VLMs, cross-validated at 93% agreement, fine-tuned on 3 model families (2-3B params)

[ICLR 2025] Official code repository for "TULIP: Token-length Upgraded CLIP"

ComfyUI custom nodes for DeepSeek, Qwen, GPT, and other OpenAI-compatible LLM APIs, with tools for chat, translation, vision, and JSON workflows.

[ICLR 2026] AgilePruner: An Empirical Study of Attention and Diversity for Adaptive Visual Token Pruning in Large Vision-Language Models

a simple lightweight large language model pipeline framework.

An open-source implementaion for fine-tuning Pixtral by MistralAI.

[ICLR 2026] - Spectral Concept Selection and Cross-modal Representation Learning for Generalized Category Discovery

We introduce new approach, Token Reduction using CLIP Metric (TRIM), aimed at improving the efficiency of MLLMs without sacrificing their performance.