activity
20242026
collaborators

7 papers

cs.AI2026

The Role of Feedback Alignment in Self-Distillation

Semih Kara, Oğuzhan Ersoy

Conditioning a language model on additional context, such as feedback on a previous attempt, typically improves its response. Self-distillation trains the model to retain this impr…

cs.CL2026

IR3DE: A Linear Router for Large Language Models

Eros Fanì, Oğuzhan Ersoy

Foundational Large Language Models (LLMs) demonstrate proficiency on a wide range of general tasks, and achieve remarkable results on various specialized tasks via domain-expert LL…

cs.LG2026

Hail to the Thief: Exploring Attacks and Defenses in Decentralised GRPO

Nikolay Blagoev, Oğuzhan Ersoy, Lydia Yiyu Chen

Group Relative Policy Optimization (GRPO) has demonstrated wide adoption in the post-training of Large Language Models (LLMs). In GRPO, prompts are answered by the model and prefer…

cs.DC2026

All is Not Lost: LLM Recovery without Checkpoints

Nikolay Blagoev, Oğuzhan Ersoy, Lydia Yiyu Chen

Training LLMs on decentralized nodes or on-spot instances, lowers the training cost and enables model democratization. The inevitable challenge here is the transient churns of node…

cs.CR2026

Backdoor Attacks on Decentralised Post-Training

Oğuzhan Ersoy, Nikolay Blagoev, Jona te Lintelo +3

Decentralised post-training of large language models utilises data and pipeline parallelism techniques to split the data and the model. Unfortunately, decentralised post-training c…

cs.LG2025

Verde: Verification via Refereed Delegation for Machine Learning Programs

Arasu Arun, Adam St. Arnaud, Alexey Titov +6

Machine learning programs, such as those performing inference, fine-tuning, and training of LLMs, are commonly delegated to untrusted compute providers. To provide correctness guar…