19 papers
PrimitiveVLA: Learning Reusable Motion Primitives for Efficient and Generalizable Robotic Manipulation
Yutai Li, Shaohui Peng, Jiaming Guo +8
Vision-Language-Action (VLA) models offer a promising paradigm for generalist robotic policies, yet their adaptation is hindered by data inefficiency and poor generalization. We ar…
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…
Revisiting Entropy Regularization: Adaptive Coefficient Unlocks Its Potential for LLM Reinforcement Learning
Xiaoyun Zhang, Xiaojian Yuan, Di Huang +6
Reasoning ability has become a defining capability of Large Language Models (LLMs), with Reinforcement Learning with Verifiable Rewards (RLVR) emerging as a key paradigm to enhance…
QiMeng-CodeV-SVA: Training Specialized LLMs for Hardware Assertion Generation via RTL-Grounded Bidirectional Data Synthesis
Yutong Wu, Chenrui Cao, Pengwei Jin +6
SystemVerilog Assertions (SVAs) are crucial for hardware verification. Recent studies leverage general-purpose LLMs to translate natural language properties to SVAs (NL2SVA), but t…
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…
QiMeng-CodeV-R1: Reasoning-Enhanced Verilog Generation
Yaoyu Zhu, Di Huang, Hanqi Lyu +16
Large language models (LLMs) trained via reinforcement learning with verifiable reward (RLVR) have achieved breakthroughs on tasks with explicit, automatable verification, such as…