6 papers
From Sweep to Seam: Interleaved Cross-Block Post-Training Quantization
Achille Jacquemond, Yuma Ichikawa, Akira Sakai
Compressing large language models to two bits or fewer is increasingly feasible through block-wise post-training quantization; cross-block variants reconstruct neighboring Transfor…
Sign Lock-In: Randomly Initialized Weight Signs Persist and Bottleneck Sub-Bit Model Compression
Akira Sakai, Yuma Ichikawa
Sub-bit model compression targets storage below one bit per weight; as magnitudes are aggressively compressed, the sign bit becomes a fixed-cost bottleneck. Across Transformers, CN…
Signs Beat Floats: Low-Rank Double-Binary Adaptation for On-Device Fine-Tuning
Yoshihiko Fujisawa, Yuma Ichikawa, Yudai Fujimoto +2
On-device adaptation of large language models commonly keeps a quantized base model frozen while training and deploying a small, task-specific LoRA adapter. In the unmerged adapter…
PHOTON: Hierarchical Autoregressive Modeling for Lightspeed and Memory-Efficient Language Generation
Yuma Ichikawa, Naoya Takagi, Takumi Nakagawa +2
Transformers operate as horizontal token-by-token scanners; at each generation step, attending to an ever-growing sequence of token-level states. This access pattern increases pref…
More Than Bits: Multi-Envelope Double Binary Factorization for Extreme Quantization
Yuma Ichikawa, Yoshihiko Fujisawa, Yudai Fujimoto +2
For extreme low-bit quantization of large language models (LLMs), Double Binary Factorization (DBF) is attractive as it enables efficient inference without sacrificing accuracy. Ho…
LPCD: Unified Framework from Layer-Wise to Submodule Quantization
Yuma Ichikawa, Yudai Fujimoto, Akira Sakai
Post-training quantization (PTQ) aims to preserve model-level behavior; however, most methods focus on individual linear layers. Even recent extensions, such as QEP and LoaQ, which…