works on

From the 1 of 79 linked papers with an AI index.

activity
20242026
most citedAstral: training physics-informed neural networks with error majorants

1 citations · 1 across the 25 of their papers we have counts for

collaborators
Showing cs.CLShow all

12 papers · 1 filter

cs.CL2026

LLM-Guided Evolution for Medical Decision Pipelines

Ivan Sviridov, Artem Oskin, Ivan Panin +4

Adapting large language models (LLMs) to clinical workflows often requires costly fine-tuning or manual prompt and pipeline engineering. We study LLM-guided MAP-Elites evolution as…

cs.CL2026

OCC-RAG: Optimal Cognitive Core for Faithful Question Answering

Maksim Savkin, Mikhail Goncharov, Alexander Gambashidze +7

Recent progress in the development of language models has been defined by scale, with each generation absorbing more of the world's knowledge into its weights. However, many practi…

cs.CL2026

Logit-KL Flow Matching: Non-Autoregressive Text Generation via Sampling-Hybrid Inference

Egor Sevriugov, Nikita Dragunov, Anton Razzhigaev +2

Non-autoregressive (NAR) language models offer notable efficiency in text generation by circumventing the sequential bottleneck of autoregressive decoding. However, accurately mode…

cs.CL2025

Exploring the Hidden Capacity of LLMs for One-Step Text Generation

Gleb Mezentsev, Ivan Oseledets

A recent study showed that large language models (LLMs) can reconstruct surprisingly long texts - up to thousands of tokens - via autoregressive generation from just one trained in…

cs.CL2025

CLARITY: Clinical Assistant for Routing, Inference, and Triage

Vladimir Shaposhnikov, Aleksandr Nesterov, Ilia Kopanichuk +7

We present CLARITY (Clinical Assistant for Routing, Inference and Triage), an AI-driven platform designed to facilitate patient-to-specialist routing, clinical consultations, and s…

cs.CL2025

I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders

Andrey Galichin, Alexey Dontsov, Polina Druzhinina +4

Recent LLMs like DeepSeek-R1 have demonstrated state-of-the-art performance by integrating deep thinking and complex reasoning during generation. However, the internal mechanisms b…