4 accepted papers
Diffusion large language models (dLLMs) have recently gained significant attention due to their inherent support for parallel decoding. Building on this paradigm, Mixture-of-Experts (MoE) dLLMs with autoregressive (AR) initialization have further demonstrated strong performance competitive with main…
Decoder-only models generate tokens autoregressively by caching key/value vectors, but as the cache grows, inference becomes memory-bounded. To address this challenge, we introduce CLOVER (Cross-Layer Orthogonal Vectors) pruning, a novel approach that treats pairs of components of the attention mech…
Existing parameter-efficient fine-tuning (PEFT) methods for large language models (LLMs), such as LoRA and PiSSA, constrain model updates to low-rank subspaces, limiting their expressiveness and leading to suboptimal performance on complex tasks. To address this, we introduce **H**igh-rank **D**istr
Modern large-language models often face communication bottlenecks on current hardware rather than computational limitations. *Multi-head latent attention (MLA)* addresses this by compressing the key-value cache using low-rank matrices, while the Absorb operation prevents the KV cache from reverting…