Poster "post-training alignment" Papers
4 papers found
Conference
Direct Post-Training Preference Alignment for Multi-Agent Motion Generation Model Using Implicit Feedback from Pre-training Demonstrations
Thomas Tian, Kratarth Goel
ICLR 2025arXiv:2503.20105
4
citations
Self Iterative Label Refinement via Robust Unlabeled Learning
Hikaru Asano, Tadashi Kozuno, Yukino Baba
NEURIPS 2025arXiv:2502.12565
1
citations
Style Outweighs Substance: Failure Modes of LLM Judges in Alignment Benchmarking
Benjamin Feuer, Micah Goldblum, Teresa Datta et al.
ICLR 2025arXiv:2409.15268
28
citations
Tracing the Representation Geometry of Language Models from Pretraining to Post-training
Melody Li, Kumar Krishna Agrawal, Arna Ghosh et al.
NEURIPS 2025arXiv:2509.23024
7
citations