A practical decoding algorithm for code generation is designed and evaluated it alongside CTD on benchmarks including HumanEval and MBPP, showing improvements over standard and adaptive decoding baselines.
Nikolaos Papagiannis, Ananth Grama, Wojciech Szpankowski· 0 citations
The Muon optimizer derives its update rule for hidden linear layers by solving a local linearization of the loss penalized by the spectral norm, motivated by an RMS-stability argument for dense linear layers. Standard Muon implementations, however, exclude the input (embedding table) and output (language model head) la...
Lin-Kai Ma, Xin-Yu Luo, Meng-Bo Wang et al.· 0 citations
Representer explanations rank the training landmarks that most influence a self-supervised representation. At scale, this ranking rests on up to four stacked approximations of the empirical neural tangent kernel (eNTK). These are random output heads, a parameter sketch, landmark sampling and a coefficient fit. Existing...
Jayanta Mukherjee, Shourya Verma, Meng-Bo Wang et al.· 0 citations
The concept of in-context self-evolution is formalized and VALVE, a validated-gated framework for long-horizon skill optimization is introduced, which establishes finite convergence, provides theoretical guarantees for future-task gain and drawdown, and derive the validation and evaluation holdout sizes required for a...
Yi-Fan Wang, Hao Cheng, Xiao-Min Li et al.· 0 citations
A hybrid mechanistic-machine learning framework for reducing and simulating PBEs defined over high-dimensional intracellular coordinates provides a computationally tractable and mechanistically interpretable route for integrating single-cell genomic data with population balance models of cell-state dynamics.
This paper develops a rigorous information-theoretic framework for non-repetitive sequence generation and uses it to provide theoretical underpinnings for temperature-based sampling, and extends it to the practically relevant and novel online setting, where the model’s token distributions evolve and are revealed sequen...
Jin Sima, Nikolaos Papagiannis, Ananth Grama et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.