activity
20242026
most citedLLMBind: A Unified Modality-Task Integration Framework

2 citations · 2 across the 2 of their papers we have counts for

collaborators

6 papers

cs.LG2026

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…

cs.CL20262 cited

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…

cs.LG2025

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…

cs.LG2025

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…

stat.ML2024

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…

cs.LG2024

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…