Author

P. Devan

h-index 1 View on Semantic Scholar

3 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

Scaling Post-Training Ternarisation to Qwen3-8B Capability Retention, Reproduction, Lossless Packing, and Packed Execution

Ultra-low-bit language models promise reductions in storage and memory traffic, but a nominal"1.58-bit"label does not specify the deployed representation or its execution cost. We study a scale-up of an aggressive post-training conversion pipeline from Qwen3-4B to Qwen3-8B. The conversion uses KOTMS rotation, E2M-ATQ a...

A. Malik, M. Mehra, P. Devan · 0 citations

#artificial intelligence Preprint Sep 2026

Post-Training Ternarization of Qwen3-4B Capability, Effective Bit Budget, Storage Compression, and Deployment

An end-to-end post-training conversion of Qwen, an instruction-tuned 4B-parameter model, using KOTMS rotation, E2M-ATQ ternarization, and GPTQ-style error compensation from TWLA is studied, finding that compression alone yields faster inference.

A. Malik, M. Mehra, P. Devan · 0 citations

#artificial intelligence Preprint Aug 2026

Capability-Stratified Degradation in Ternary Language Models

Ternary conversion is unsuitable as a drop-in general replacement yet remains valuable as a compact substrate for task-specific models.

A. Malik, M. Mehra, P. Devan · 1 citation