collaborators

9 papers

cs.AI2026

DRIFT: Decompose, Retrieve, Illustrate, then Formalize Theorems

Meiru Zhang, Philipp Borchert, Milan Gritta +1

Automating the formalization of mathematical statements for theorem proving remains a major challenge for Large Language Models (LLMs). LLMs struggle to identify and utilize the pr…

cs.AI2026

A Benchmark for Deep Information Synthesis

Debjit Paul, Daniel Murphy, Milan Gritta +14

Large language model (LLM)-based agents are increasingly used to solve complex tasks involving tool use, such as web browsing, code execution, and data analysis. However, current e…

cs.CL2025

SparsePO: Controlling Preference Alignment of LLMs via Sparse Token Masks

Fenia Christopoulou, Ronald Cardenas, Gerasimos Lampouras +2

Direct alignment algorithms have proven an effective step for aligning language models to human-desired behaviors. Current variants of the Direct Preference Optimization objective…

cs.CL2025

Conjecturing: An Overlooked Step in Formal Mathematical Reasoning

Jasivan Alex Sivakumar, Philipp Borchert, Ronald Cardenas +1

Autoformalisation, the task of expressing informal mathematical statements in formal language, is often viewed as a direct translation process. This, however, disregards a critical…

cs.CL2025

TopoAlign: A Framework for Aligning Code to Math via Topological Decomposition

Yupei Li, Philipp Borchert, Gerasimos Lampouras

Large Language Models (LLMs) excel at both informal and formal (e.g. Lean 4) mathematical reasoning but still struggle with autoformalisation, the task of transforming informal int…

cs.AI2025

Human-inspired Episodic Memory for Infinite Context LLMs

Zafeirios Fountas, Martin A Benfeghoul, Adnan Oomerjee +4

Large language models (LLMs) have shown remarkable capabilities, but still struggle with processing extensive contexts, limiting their ability to maintain coherence and accuracy ov…