Xia Hu
19 papers · 343 citations
Most-cited papers
- LLM Maybe Longlm: Self-extend LLM Context Window Without Tuning2024 · 165 citations
- Learning To Compress Prompt In Natural Language Formats2024 · 51 citations
- KV Cache Compression, But What Must We Give In Return? A Comprehensive Benchmark Of Long Context Capable Approaches2024 · 44 citations
- Crisissense-llm: Instruction Fine-tuned Large Language Model For Multi-label Social Media Text Classification In Disaster Informatics2024 · 29 citations
- Growlength: Accelerating Llms Pretraining By Progressively Growing Training Length2023 · 16 citations
- Training-free Time Series Classification Via In-context Reasoning With LLM Agents2026
- Lps-bench: Benchmarking Safety Awareness Of Computer-use Agents In Long-horizon Planning Under Benign And Adversarial Scenarios2026
- Benchmarks For Trajectory Safety Evaluation And Diagnosis In Openclaw And Codex: Atbench-claw And Atbench-codex2026
- BLASST: Dynamic Blocked Attention Sparsity Via Softmax Thresholding2026
Topics