← Search

Lekai Xing

2 accepted papers

2026

ProtoKV: Long-context Knowledges Are Already Well-Organized Before Your Query

ICLR 2026poster

Modern Large Language Models (LLMs) face fundamental challenges in processing long text sequences due to the quadratic complexity of attention mechanisms. Key-Value (KV) cache retention strategies mitigate this issue by selectively preserving salient KV pairs for autoregressive generation. However,…

Cited by 0SourcecodeScholar
2026

Unifying Perception and Action: A Hybrid-Modality Pipeline with Implicit Visual Chain-of-Thought for Robotic Action Generation

CVPR 2026

Vision-Language-Action (VLA) models built upon Chain-of-Thought (CoT) have achieved remarkable success in advancing general-purpose robotic agents, owing to its significant perceptual comprehension. Recently, since text-only CoT struggles to adequately capture scene details in complex spatial enviro

Cited by 0SourceScholar