Xiang Liu

Xiang Liu on Hugging Face Daily Papers: 16 papers, 5 in the top 3 of their day, 774 upvotes.

1. Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA 334 upvotes, #2 of 2026-08-11
2. On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters 223 upvotes, #1 of 2026-06-02
3. Position: LLM Inference Should Be Evaluated as Energy-to-Token Production 3 upvotes, #34 of 2026-05-14
4. MinT: Managed Infrastructure for Training and Serving Millions of LLMs 216 upvotes, #1 of 2026-05-14
5. δ-mem: Efficient Online Memory for Large Language Models 119 upvotes, #3 of 2026-05-13
6. MDN: Parallelizing Stepwise Momentum for Delta Linear Attention 5 upvotes, #35 of 2026-05-11
7. Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression 5 upvotes, #45 of 2025-05-28
8. The Lottery LLM Hypothesis, Rethinking What Abilities Should LLM Compression Preserve? 8 upvotes, #12 of 2025-02-26
9. Perovskite-LLM: Knowledge-Enhanced Large Language Models for Perovskite Solar Cell Research 2 upvotes, #30 of 2025-02-19
10. Mediator: Memory-efficient LLM Merging with Less Parameter Conflicts and Uncertainty Based Routing 4 upvotes, #19 of 2025-02-13
11. Can LLMs Maintain Fundamental Abilities under KV Cache Compression? 11 upvotes, #6 of 2025-02-05
12. ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference 2 upvotes, #15 of 2025-02-03
13. Should We Really Edit Language Models? On the Evaluation of Edited Language Models 5 upvotes, #23 of 2024-10-25
14. LPZero: Language Model Zero-cost Proxy Search from Zero 2 upvotes, #25 of 2024-10-11
15. LongGenBench: Long-context Generation Benchmark 16 upvotes, #2 of 2024-10-09
16. 3D Question Answering for City Scene Understanding 21 upvotes, #12 of 2024-07-30

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.