5 papers · 1 filter
Intent-aligned Formal Specification Synthesis via Traceable Refinement
Zhe Ye, Aidan Z. H. Yang, Huangyuan Su +6
Large language models are increasingly used to generate code from natural language, but ensuring correctness remains challenging. Formal verification offers a principled way to obt…
Learning Adaptive LLM Decoding
Chloe H. Su, Zhe Ye, Samuel Tenka +3
Decoding from large language models (LLMs) typically relies on fixed sampling hyperparameters (e.g., temperature, top-p), despite substantial variation in task difficulty and uncer…
BRIDGE: Building Representations In Domain Guided Program Synthesis
Robert Joseph George, Carson Eisenach, Udaya Ghai +3
Large language models can generate plausible code, but remain brittle for formal verification in proof assistants such as Lean. A central scalability challenge is that verified syn…
Outbound Modeling for Inventory Management
Riccardo Savorgnan, Udaya Ghai, Carson Eisenach +1
We study the problem of forecasting the number of units fulfilled (or ``drained'') from each inventory warehouse to meet customer demand, along with the associated outbound shippin…
How Does Critical Batch Size Scale in Pre-training?
Hanlin Zhang, Depen Morwani, Nikhil Vyas +5
Training large-scale models under given resources requires careful design of parallelism strategies. In particular, the efficiency notion of critical batch size (CBS), concerning t…