5 papers
RestoreKV: Recovering Full-Cache Behavior Under Aggressive Query-Agnostic KV Cache Eviction
Changwoo Baek, Seungjun Shin, Kyeongbo Kong
Query-agnostic KV cache eviction compresses a context once and reuses the resulting cache for arbitrary future queries, but performance can collapse under tight budgets. Existing m…
Neural Weight Compression for Language Models
Jegwang Ryu, Minkyu Kim, Seungjun Shin +3
Efficient compression of language model weights is increasingly critical as model scale and deployment grow. Yet, most existing methods rely on handcrafted transforms and heuristic…
OrthoRank: Token Selection via Sink Token Orthogonality for Efficient LLM inference
Seungjun Shin, Jaehoon Oh, Dokwan Oh
Attention mechanisms are central to the success of large language models (LLMs), enabling them to capture intricate token dependencies and implicitly assign importance to each toke…
Efficient Neural Video Representation with Temporally Coherent Modulation
Seungjun Shin, Suji Kim, Dokwan Oh
Implicit neural representations (INR) has found successful applications across diverse domains. To employ INR in real-life, it is important to speed up training. In the field of IN…
House of Cards: Massive Weights in LLMs
Jaehoon Oh, Seungjun Shin, Dokwan Oh
Massive activations, which manifest in specific feature dimensions of hidden states, introduce a significant bias in large language models (LLMs), leading to an overemphasis on the…