vision-language

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

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

Awesome List of Vision Language Prompt Papers

VL-JEPA inspired pipeline — compress images/text locally via Ollama, send compact payloads to any LLM API. Cut token costs by ~80%.

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

[NLPCC'23] ZeroGen: Zero-shot Multimodal Controllable Text Generation with Multiple Oracles PyTorch Implementation

Multimodal document QA: vision + retrieval over PDFs (LLaVA + LlamaIndex)

ArtSeek: Deep artwork understanding via multimodal in-context reasoning and late interaction retrieval

Vision-Language Models on AMD GPUs — LLaVA, MiniGPT-4, Idefics on ROCm 🚀