Junyoung Park

QuoKA: Query-Oriented KV Selection for Efficient LLM Prefill

KeyDiff: Key Similarity-Based KV Cache Eviction for Long-Context LLM Inference in Resource-Constrained Environments

PARCO: Parallel AutoRegressive Models for Multi-Agent Combinatorial Optimization

RouteFinder: Towards Foundation Models for Vehicle Routing Problems

CAOTE: Efficient Caching through Attention Output based Token Eviction

RL4CO: an Extensive Reinforcement Learning for Combinatorial Optimization Benchmark