2 citations · 2 across the 2 of their papers we have counts for
6 papers
f-GRPO and Beyond: Divergence-Based Reinforcement Learning Algorithms for General LLM Alignment
Rajdeep Haldar, Lantao Mei, Guang Lin +2
Recent work shows that preference alignment objectives can be interpreted as divergence estimators between aligned (preferred) & unaligned (less-preferred) distributions, yielding…
LLMBind: A Unified Modality-Task Integration Framework
Bin Zhu, Munan Ning, Peng Jin +7
Despite recent progress in Multi-Modal Large Language Models (MLLMs), it remains challenging to integrate diverse tasks ranging from pixel-level perception to high-fidelity generat…
LLM Safety Alignment is Divergence Estimation in Disguise
Rajdeep Haldar, Ziyi Wang, Qifan Song +2
We present a theoretical framework showing that popular LLM alignment methods, including RLHF and its variants, can be understood as divergence estimators between aligned (safe or…
Knowledge Distillation Detection for Open-weights Models
Qin Shi, Amber Yijia Zheng, Qifan Song +1
We propose the task of knowledge distillation detection, which aims to determine whether a student model has been distilled from a given teacher, under a practical setting where on…
Adversarial Vulnerability as a Consequence of On-Manifold Inseparibility
Rajdeep Haldar, Yue Xing, Qifan Song +1
Recent works have shown theoretically and empirically that redundant data dimensions are a source of adversarial vulnerability. However, the inverse doesn't seem to hold in practic…
Theoretical Understanding of In-Context Learning in Shallow Transformers with Unstructured Data
Yue Xing, Xiaofeng Lin, Chenheng Xu +3
Large language models (LLMs) are powerful models that can learn concepts at the inference stage via in-context learning (ICL). While theoretical studies, e.g., \cite{zhang2023train…