2 citations · 4 across the 13 of their papers we have counts for
15 papers
Agentic Data Engineering for LLMs: System Design and a Controlled Empirical Study
Ruomeng Ding, Qianli Shen, Zhaoyang Han +3
LLM data engineering requires iterative experimentation to determine how data selection, rewards, and curricula affect model learning, making it a natural setting for AI-for-AI (AI…
Beyond Solvability: Task Learnability as a Static Prior for LLM RL Post-Training
Ting Zhou, Zhenqing Ling, Daoyuan Chen +4
Reinforcement learning (RL) has become a central post-training paradigm for eliciting reasoning capabilities in large language models, yet uniform task sampling allocates compute w…
GradCuit: Credit-Assigned Gradient Flow Enables Robust and Interpretable Test-Time Latent Reasoning
Zhaoxin Yu, Qi Shen, Hengli Li +4
Optimization-based latent reasoning improves large language model outputs by optimizing instance-specific continuous states at test time while keeping model parameters frozen. Exis…
CDR-Bench: Evaluating Faithful Execution of Compositional, Order-Sensitive Data Refinement Recipes
Yuchen Huang, Xiang Li, Zhenqing Ling +5
Data refinement involves executing multi-step recipes over evolving text states, where both composition and execution order of processing operators determine the outcome. While exi…
BARE: Towards Bias-Aware and Reasoning-Enhanced One-Tower Visual Grounding
Hongbing Li, Linhui Xiao, Zihan Zhao +4
Visual Grounding (VG), which aims to locate a specific region referred to by expressions, is a fundamental yet challenging task in the multimodal understanding fields. While recent…
BEDA: Belief Estimation as Probabilistic Constraints for Performing Strategic Dialogue Acts
Hengli Li, Zhaoxin Yu, Qi Shen +8
Strategic dialogue requires agents to execute distinct dialogue acts, for which belief estimation is essential. While prior work often estimates beliefs accurately, it lacks a prin…
BOTS: A Unified Framework for Bayesian Online Task Selection in LLM Reinforcement Finetuning
Qianli Shen, Daoyuan Chen, Yilun Huang +4
Reinforcement finetuning (RFT) is a key technique for aligning Large Language Models (LLMs) with human preferences and enhancing reasoning, yet its effectiveness is highly sensitiv…
LoReUn: Data Itself Implicitly Provides Cues to Improve Machine Unlearning
Xiang Li, Qianli Shen, Haonan Wang +1
Recent generative models face significant risks of producing harmful content, which has underscored the importance of machine unlearning (MU) as a critical technique for eliminatin…
Diversity as a Reward: Fine-Tuning LLMs on a Mixture of Domain-Undetermined Data
Zhenqing Ling, Daoyuan Chen, Liuyi Yao +3
Fine-tuning large language models (LLMs) using diverse datasets is crucial for enhancing their overall performance across various domains. In practical scenarios, existing methods…
State-space models are accurate and efficient neural operators for dynamical systems
Zheyuan Hu, Nazanin Ahmadi Daryakenari, Qianli Shen +2
Physics-informed machine learning (PIML) has emerged as a promising alternative to classical methods for predicting dynamical systems, offering faster and more generalizable soluti…
Memory-Efficient Gradient Unrolling for Large-Scale Bi-level Optimization
Qianli Shen, Yezhen Wang, Zhouhao Yang +6
Bi-level optimization (BO) has become a fundamental mathematical framework for addressing hierarchical machine learning problems. As deep learning models continue to grow in size,…
FinerCut: Finer-grained Interpretable Layer Pruning for Large Language Models
Yang Zhang, Yawei Li, Xinpeng Wang +5
Overparametrized transformer networks are the state-of-the-art architecture for Large Language Models (LLMs). However, such models contain billions of parameters making large compu…
The Stronger the Diffusion Model, the Easier the Backdoor: Data Poisoning to Induce Copyright Breaches Without Adjusting Finetuning Pipeline
Haonan Wang, Qianli Shen, Yao Tong +2
The commercialization of text-to-image diffusion models (DMs) brings forth potential copyright concerns. Despite numerous attempts to protect DMs from copyright issues, the vulnera…
VA3: Virtually Assured Amplification Attack on Probabilistic Copyright Protection for Text-to-Image Generative Models
Xiang Li, Qianli Shen, Kenji Kawaguchi
The booming use of text-to-image generative models has raised concerns about their high risk of producing copyright-infringing content. While probabilistic copyright protection met…
PICProp: Physics-Informed Confidence Propagation for Uncertainty Quantification
Qianli Shen, Wai Hoh Tang, Zhun Deng +2
Standard approaches for uncertainty quantification in deep learning and physics-informed learning have persistent limitations. Indicatively, strong assumptions regarding the data l…