GitHub

ML-Decoder: Scalable and Versatile Classification Head

In this paper, we introduce ML-Decoder, a new attention-based classification head. ML-Decoder predicts the existence of class labels via queries, and enables better utilization of spatial data ...
IEEE

Design considerations of NAPLPS, the data syntax for VIDEOTEX and TELETEXT in North America

Abstract: Two new information services, VIDEOTEX and TELETEXT, are now being introduced in the United States and Canada. Both are aimed at displaying frames of information retrieved from a database on ...
GitHub

Return of the Encoder: Efficient Small Language Models

We note that our work focuses on architectural comparisons rather than competing with recent SLM developments (e.g., SmolLM, MobileLLM). Our analysis isolates the fundamental advantages of ...
IEEE

Using linear programming to Decode Binary linear codes

Abstract: A new method is given for performing approximate maximum-likelihood (ML) decoding of an arbitrary binary linear code based on observations received from any discrete memoryless symmetric ...