Dominik Schnaus
@schnaus.bsky.social
PhD student @ TUM with Daniel Cremers
4/4
𝐈𝐭’𝐬 𝐚 (𝐁𝐥𝐢𝐧𝐝) 𝐌𝐚𝐭𝐜𝐡! 𝐓𝐨𝐰𝐚𝐫𝐝𝐬 𝐕𝐢𝐬𝐢𝐨𝐧–𝐋𝐚𝐧𝐠𝐮𝐚𝐠𝐞 𝐂𝐨𝐫𝐫𝐞𝐬𝐩𝐨𝐧𝐝𝐞𝐧𝐜𝐞 𝐰𝐢𝐭𝐡𝐨𝐮𝐭 𝐏𝐚𝐫𝐚𝐥𝐥𝐞𝐥 𝐃𝐚𝐭𝐚
@schnaus.bsky.social @neekans.bsky.social @dcremers.bsky.social
📝 Paper: arxiv.org/pdf/2503.241...
🌐 Project page: dominik-schnaus.github.io/itsamatch/
💻 Code: github.com/dominik-schn...
𝐈𝐭’𝐬 𝐚 (𝐁𝐥𝐢𝐧𝐝) 𝐌𝐚𝐭𝐜𝐡! 𝐓𝐨𝐰𝐚𝐫𝐝𝐬 𝐕𝐢𝐬𝐢𝐨𝐧–𝐋𝐚𝐧𝐠𝐮𝐚𝐠𝐞 𝐂𝐨𝐫𝐫𝐞𝐬𝐩𝐨𝐧𝐝𝐞𝐧𝐜𝐞 𝐰𝐢𝐭𝐡𝐨𝐮𝐭 𝐏𝐚𝐫𝐚𝐥𝐥𝐞𝐥 𝐃𝐚𝐭𝐚
@schnaus.bsky.social @neekans.bsky.social @dcremers.bsky.social
📝 Paper: arxiv.org/pdf/2503.241...
🌐 Project page: dominik-schnaus.github.io/itsamatch/
💻 Code: github.com/dominik-schn...
June 3, 2025 at 9:27 AM
4/4
𝐈𝐭’𝐬 𝐚 (𝐁𝐥𝐢𝐧𝐝) 𝐌𝐚𝐭𝐜𝐡! 𝐓𝐨𝐰𝐚𝐫𝐝𝐬 𝐕𝐢𝐬𝐢𝐨𝐧–𝐋𝐚𝐧𝐠𝐮𝐚𝐠𝐞 𝐂𝐨𝐫𝐫𝐞𝐬𝐩𝐨𝐧𝐝𝐞𝐧𝐜𝐞 𝐰𝐢𝐭𝐡𝐨𝐮𝐭 𝐏𝐚𝐫𝐚𝐥𝐥𝐞𝐥 𝐃𝐚𝐭𝐚
@schnaus.bsky.social @neekans.bsky.social @dcremers.bsky.social
📝 Paper: arxiv.org/pdf/2503.241...
🌐 Project page: dominik-schnaus.github.io/itsamatch/
💻 Code: github.com/dominik-schn...
𝐈𝐭’𝐬 𝐚 (𝐁𝐥𝐢𝐧𝐝) 𝐌𝐚𝐭𝐜𝐡! 𝐓𝐨𝐰𝐚𝐫𝐝𝐬 𝐕𝐢𝐬𝐢𝐨𝐧–𝐋𝐚𝐧𝐠𝐮𝐚𝐠𝐞 𝐂𝐨𝐫𝐫𝐞𝐬𝐩𝐨𝐧𝐝𝐞𝐧𝐜𝐞 𝐰𝐢𝐭𝐡𝐨𝐮𝐭 𝐏𝐚𝐫𝐚𝐥𝐥𝐞𝐥 𝐃𝐚𝐭𝐚
@schnaus.bsky.social @neekans.bsky.social @dcremers.bsky.social
📝 Paper: arxiv.org/pdf/2503.241...
🌐 Project page: dominik-schnaus.github.io/itsamatch/
💻 Code: github.com/dominik-schn...
3/4
✅ This enables unsupervised matching — finding vision-language correspondences without any paired data.
🤯 As a proof of concept, we build an unsupervised image classifier that assigns labels without seeing a single image-text pair.
✅ This enables unsupervised matching — finding vision-language correspondences without any paired data.
🤯 As a proof of concept, we build an unsupervised image classifier that assigns labels without seeing a single image-text pair.
June 3, 2025 at 9:27 AM
3/4
✅ This enables unsupervised matching — finding vision-language correspondences without any paired data.
🤯 As a proof of concept, we build an unsupervised image classifier that assigns labels without seeing a single image-text pair.
✅ This enables unsupervised matching — finding vision-language correspondences without any paired data.
🤯 As a proof of concept, we build an unsupervised image classifier that assigns labels without seeing a single image-text pair.
2/4
🔍 As models and datasets scale, distances in vision and language embeddings become similar (Platonic Representation Hypothesis).
💡 We cast the matching task as a Quadratic Assignment Problem (QAP) and propose a new heuristic solver.
🔍 As models and datasets scale, distances in vision and language embeddings become similar (Platonic Representation Hypothesis).
💡 We cast the matching task as a Quadratic Assignment Problem (QAP) and propose a new heuristic solver.
June 3, 2025 at 9:27 AM
2/4
🔍 As models and datasets scale, distances in vision and language embeddings become similar (Platonic Representation Hypothesis).
💡 We cast the matching task as a Quadratic Assignment Problem (QAP) and propose a new heuristic solver.
🔍 As models and datasets scale, distances in vision and language embeddings become similar (Platonic Representation Hypothesis).
💡 We cast the matching task as a Quadratic Assignment Problem (QAP) and propose a new heuristic solver.