6 papers · 1 filter
LKV: End-to-End Learning of Head-wise Budgets and Token Selection for LLM KV Cache Eviction
Enshuai Zhou, Yifan Hao, Chao Wang +7
Long-context inference in Large Language Models (LLMs) is bottlenecked by the linear growth of Key-Value (KV) cache memory. Existing KV cache compression paradigms are fundamentall…
QiMeng-CRUX: Narrowing the Gap Between Natural Language and Verilog via Core Refined Understanding eXpression for Circuit Design
Lei Huang, Rui Zhang, Jiaming Guo +9
Large language models (LLMs) have shown promising capabilities in hardware description language (HDL) generation. However, existing approaches often rely on free-form natural langu…
Segmental Advantage Estimation: Enhancing PPO for Long-Context LLM Training
Xue Gong, Qi Yi, Ziyuan Nan +8
Training Large Language Models (LLMs) for reasoning tasks is increasingly driven by Reinforcement Learning with Verifiable Rewards (RLVR), where Proximal Policy Optimization (PPO)…
QiMeng-SALV: Signal-Aware Learning for Verilog Code Generation
Yang Zhang, Rui Zhang, Jiaming Guo +10
The remarkable progress of Large Language Models (LLMs) presents promising opportunities for Verilog code generation which is significantly important for automated circuit design.…
Efficient Diffusion Planning with Temporal Diffusion
Jiaming Guo, Rui Zhang, Zerun Li +7
Diffusion planning is a promising method for learning high-performance policies from offline data. To avoid the impact of discrepancies between planning and reality on performance,…
Policy Constraint by Only Support Constraint for Offline Reinforcement Learning
Yunkai Gao, Jiaming Guo, Fan Wu +1
Offline reinforcement learning (RL) aims to optimize a policy by using pre-collected datasets, to maximize cumulative rewards. However, offline reinforcement learning suffers chall…