Tape Programming Models, Sequential Computation, Linear Processing, Storage Abstractions
Is It Thinking or Cheating? Detecting Implicit Reward Hacking by Measuring Reasoning Effort
arxiv.org·17h
Why Can't Transformers Learn Multiplication? Reverse-Engineering Reveals Long-Range Dependency Pitfalls
arxiv.org·1d
Are LLMs Better GNN Helpers? Rethinking Robust Graph Learning under Deficiencies with Iterative Refinement
arxiv.org·17h
Loading...Loading more...