2 citations · 3 across the 7 of their papers we have counts for
7 papers
OpenThoughts-Agent: Data Recipes for Agentic Models
Negin Raoof, Richard Zhuang, Marianna Nezhurina +47
Agentic language models dramatically expand the applications of AI yet little is publicly known about how to curate training data for broadly capable agents. Existing open efforts…
Asymmetric Prompt Weighting for Reinforcement Learning with Verifiable Rewards
Reinhard Heckel, Mahdi Soltanolkotabi, Christos Thramboulidis
Reinforcement learning with verifiable rewards has driven recent advances in LLM post-training, in particular for reasoning. Policy optimization algorithms generate a number of res…
Near Optimal Code Construction for the Adversarial Torn Paper Channel With Edit Errors
Maria Abu-Sini, Reinhard Heckel
Motivated by DNA storage systems and 3D fingerprinting, this work studies the adversarial torn paper channel with edit errors. This channel first applies at most edit errors…
Transformer-Based Decoding in Concatenated Coding Schemes Under Synchronization Errors
Julian Streit, Franziska Weindel, Reinhard Heckel
We consider the reconstruction of a codeword from multiple noisy copies that are independently corrupted by insertions, deletions, and substitutions. This problem arises, for examp…
Trace Reconstruction with Language Models
Franziska Weindel, Michael Girsch, Reinhard Heckel
The general trace reconstruction problem seeks to recover an original sequence from its noisy copies independently corrupted by insertions, deletions, and substitutions. This probl…
OpenThoughts: Data Recipes for Reasoning Models
Etash Guha, Ryan Marten, Sedrick Keh +47
Reasoning models have made rapid progress on many benchmarks involving math, code, and science. Yet, there are still many open questions about the best training recipes for reasoni…
LLM-Guided Search for Deletion-Correcting Codes
Franziska Weindel, Reinhard Heckel
Finding deletion-correcting codes of maximum size has been an open problem for over 70 years, even for a single deletion. We adapt FunSearch, a large language model (LLM)-guided ev…