Denis Rakitin

[Viacheslav Meshchaninov @Viacheslav91112]

🚀COSMOS is OUT! @NeurIPSconf 2025!

📈COSMOS achieves up to 2x faster text generation compared to other diffusion models, utilizing up to 8x compression in text representations for superior efficiency.

📄 Paper: https://t.co/UF4TNZpq4t
💻 Code: https://t.co/zonTgWVXNF

(1/6)

[Timofei Gritsaev @gritsaev]

1/ Can we efficiently learn the destruction process of diffusion samplers? Can we learn not just the drift, but also the variance for all transition kernels? – We answer YES in our recent paper “Adaptive Destruction Processes for Diffusion Samplers” (Oral at NeurIPS 2025 FPI Workshop).

[Kirill Struminsky @k_struminsky]

We will be presenting “Leveraging Recursive Gumbel-Max Trick for Approximate Inference in Combinatorial Spaces” during #NeurIPS2021 poster session 8! We iteratively apply the Gumbel-Max trick to obtain structured variables instead of categorical.

Poster: https://t.co/Z8PY15pndX