Xiaowen Chu

7

Papers

79

Total Citations

Papers (7)

STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs

ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference

CF-NeRF: Camera Parameter Free Neural Radiance Fields with Incremental Learning

The Lottery LLM Hypothesis, Rethinking What Abilities Should LLM Compression Preserve?

ParZC: Parametric Zero-Cost Proxies for Efficient NAS

Multi-Task Domain Adaptation for Language Grounding with 3D Objects

Pruner-Zero: Evolving Symbolic Pruning Metric From Scratch for Large Language Models