Scholar
Jixuan Leng
Google Scholar ID: Jyqbex4AAAAJ
Carnegie Mellon University
Citations & Impact
Citations
66
H-index
4
i10-index
2
Publications
11
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- 2025.09: Survey Paper 'Reliable and Responsible Foundation Models' accepted by TMLR
- 2025.06: Paper 'CrossWordBench: Evaluating the Reasoning Capabilities of LLMs and LVLMs with Controllable Puzzle Generation' accepted by COLM 2025
- 2025.06: Preprints 'Semi-structured LLM Reasoners Can Be Rigorously Audited' and 'PosS: Position Specialist Generates Better Draft for Speculative Decoding' out on arxiv, code also released
- 2025.02: Paper 'Taming Overconfidence in LLMs: Reward Calibration in RLHF' accepted by ICLR 2025 (poster)
- 2024.09: Paper 'S2FT: Efficient, Scalable and Generalizable LLM Fine-tuning by Structured Sparsity' accepted by NIPS 2024 (poster)
Background
- Research interests lie in improving training and inference efficiency as well as model alignment of both LLMs and VLMs.
Miscellany
- Feel free to email me if you are interested in collaborating or discussing research ideas
Co-authors