Peijie Dong

8

Papers

95

Total Citations

Papers (8)

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

Auto-Prox: Training-Free Vision Transformer Architecture Search via Automatic Proxy Discovery

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

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

DetKDS: Knowledge Distillation Search for Object Detectors