Hugging Face's logo
Sai Rajeswar's picture
3 1

Sai Rajeswar

rajeswarsai
·
https://sairajeswar.com/

AI & ML interests

None yet

Recent Activity

upvoted a collection about 1 month ago
WebMMU
reacted to ahmed-masry's post with 👍 7 months ago
Happy to announce AlignVLM 📏 – a novel approach to bridging vision and language latent spaces for multimodal understanding in Vision-Language Models (VLMs) 🌍📄🖼 🔗 Read the paper: https://huggingface.co/papers/2502.01341 🧐 What’s the challenge? Aligning visual features with language embeddings remains a major bottleneck in VLMs. Existing connectors such as Multi-layer perceptron (MLPs) often introduce noise that degrades performance. ❌ 🎯 Our Solution: ALIGN Connector We propose AlignVLM, a method that maps vision features into a weighted average of LLM text embeddings, ensuring they remain in a space that the LLM can effectively interpret. ✅ 🔬 How does it perform? We compared ALIGN against common connectors like MLPs, Perceiver Resampler, and Ovis trained under similar configurations. The results? ALIGN outperforms them all 🏆 on diverse document understanding tasks 📄. 📊 Meet the AlignVLM Model Family! We trained Llama 3.1 (1B, 3B, 8B) using our connector and benchmarked them against various models. The results: ✅ AlignVLM surpasses all Base VLMs trained under similar configurations. ✅ Our models also perform competitively against Instruct VLMs such as Qwen2-VL and InternVL-2.5 🚀. 🤔 What about robustness to noise? We injected Gaussian noise (μ=0, σ=3) into the vision encoder’s outputs before feeding them to the connector: ✅ ALIGN Connector: Minimal drop (↓1.67%) – proving its high robustness! ❌ MLP Connector: Severe degradation (↓25.54%) – struggling with noisy inputs. Code & model weights coming soon! Stay tuned! 🔥
upvoted a paper 7 months ago
AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Understanding
View all activity

Organizations

ServiceNow's profile picture SNOW-Multimodal's profile picture Agent Poirot's profile picture