We have 4 of 24 papers
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.
Conditional memory layers, such as DeepSeek's Engram, attach large hashed n-gram tables to a language model, and removing them from DeepSeek-V4.1-Flash costs 36.8 PopQA points. Low-bit quantization loses long-tail facts first, and the standard remedy, giving more bits to frequently accessed rows, backfires: refining lo...
By coupling QAD's stable low-bit initialization with OPD's on-policy reasoning recovery, the framework provides a comprehensive sub-3-bit solution that preserves broad capabilities while restoring long-form reasoning.
Fine-grained mixture-of-experts (MoE) architectures have become a mainstream design for open-weight LLMs, with hundreds of experts and increasingly many selected per token. This shift makes dynamic expert pruning an attractive route to cheaper inference. Yet existing evidence comes largely from coarser architectures an...
BiSCo-LLM is presented, a codebook-free binary spherical coding framework for extreme low-bit LLM weight compression and its reported storage budget includes binary codes, neural decoders, protected-channel payloads, LoRA adapters, and metadata.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
