3 citations · 17 across the 25 of their papers we have counts for
28 papers
LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing
Juncheng Dong, Ding Tong, Ishan Gupta +1
Recommendation systems thrive on personalization, where ''correctness'' is rarely a binary truth but a matter of subjective human preference. As Large Language Models (LLMs) are de…
One for All: A Non-Linear Transformer can Enable Cross-Domain Generalization for In-Context Reinforcement Learning
Bowen He, Juncheng Dong, Lin Lin +1
A central challenge in reinforcement learning (RL) is to learn models that generalize beyond the tasks on which they are trained, a goal traditionally pursued through multi-task an…
Rethinking Token Prediction: Tree-Structured Diffusion Language Model
Zihao Wu, Haoming Yang, Juncheng Dong +1
Discrete diffusion language models have emerged as a competitive alternative to auto-regressive language models, but training them efficiently under limited parameter and memory bu…
Learning in Context, Guided by Choice: A Reward-Free Paradigm for Reinforcement Learning with Transformers
Juncheng Dong, Bowen He, Moyang Guo +3
In-context reinforcement learning (ICRL) leverages the in-context learning capabilities of transformer models (TMs) to efficiently generalize to unseen sequential decision-making t…
In-Context Reinforcement Learning From Suboptimal Historical Data
Juncheng Dong, Moyang Guo, Ethan X. Fang +2
Transformer models have achieved remarkable empirical successes, largely due to their in-context learning capabilities. Inspired by this, we explore training an autoregressive tran…
CARE: Turning LLMs Into Causal Reasoning Expert
Juncheng Dong, Yiling Liu, Ahmed Aloui +2
Large language models (LLMs) have recently demonstrated impressive capabilities across a range of reasoning and generation tasks. However, research studies have shown that LLMs lac…
Synergizing Deconfounding and Temporal Generalization For Time-series Counterfactual Outcome Estimation
Yiling Liu, Juncheng Dong, Chen Fu +4
Estimating counterfactual outcomes from time-series observations is crucial for effective decision-making, e.g. when to administer a life-saving treatment, yet remains significantl…
Neuro-Logic Lifelong Learning
Bowen He, Xiaoan Xu, Alper Kamil Bozkurt +2
Solving Inductive Logic Programming (ILP) problems with neural networks is a key challenge in Neural-Symbolic Ar- tificial Intelligence (AI). While most research has focused on des…
STARK: Strategic Team of Agents for Refining Kernels
Juncheng Dong, Yang Yang, Tao Liu +5
The efficiency of GPU kernels is central to the progress of modern AI, yet optimizing them remains a difficult and labor-intensive task due to complex interactions between memory h…
PASTA: A Unified Framework for Offline Assortment Learning
Juncheng Dong, Weibin Mo, Zhengling Qi +3
We study a broad class of assortment optimization problems in an offline and data-driven setting. In such problems, a firm lacks prior knowledge of the underlying choice model, and…
Conditional Average Treatment Effect Estimation Under Hidden Confounders
Ahmed Aloui, Juncheng Dong, Ali Hasan +1
One of the major challenges in estimating conditional potential outcomes and conditional average treatment effects (CATE) is the presence of hidden confounders. Since testing for h…
Boosting In-Context Learning in LLMs Through the Lens of Classical Supervised Learning
Korel Gundem, Juncheng Dong, Dennis Zhang +2
In-Context Learning (ICL) allows Large Language Models (LLMs) to adapt to new tasks with just a few examples, but their predictions often suffer from systematic biases, leading to…
Teleportation With Null Space Gradient Projection for Optimization Acceleration
Zihao Wu, Juncheng Dong, Ahmed Aloui +1
Optimization techniques have become increasingly critical due to the ever-growing model complexity and data scale. In particular, teleportation has emerged as a promising approach,…
S2TX: Cross-Attention Multi-Scale State-Space Transformer for Time Series Forecasting
Zihao Wu, Juncheng Dong, Haoming Yang +1
Time series forecasting has recently achieved significant progress with multi-scale models to address the heterogeneity between long and short range patterns. Despite their state-o…
Score-Based Metropolis-Hastings Algorithms
Ahmed Aloui, Ali Hasan, Juncheng Dong +2
In this paper, we introduce a new approach for integrating score-based models with the Metropolis-Hastings algorithm. While traditional score-based diffusion models excel in accura…
Offline Stochastic Optimization of Black-Box Objective Functions
Juncheng Dong, Zihao Wu, Hamid Jafarkhani +2
Many challenges in science and engineering, such as drug discovery and communication network design, involve optimizing complex and expensive black-box functions across vast search…
CATE Estimation With Potential Outcome Imputation From Local Regression
Ahmed Aloui, Juncheng Dong, Cat P. Le +1
One of the most significant challenges in Conditional Average Treatment Effect (CATE) estimation is the statistical discrepancy between distinct treatment groups. To address this i…
Off-Policy Evaluation for Human Feedback
Qitong Gao, Ge Gao, Juncheng Dong +3
Off-policy evaluation (OPE) is important for closing the gap between offline training and evaluation of reinforcement learning (RL), by estimating performance and/or rank of target…
Robust Reinforcement Learning through Efficient Adversarial Herding
Juncheng Dong, Hao-Lun Hsu, Qitong Gao +2
Although reinforcement learning (RL) is considered the gold standard for policy design, it may not always provide a robust solution in various scenarios. This can result in severe…
Deep Generalized Green's Functions
Rixi Peng, Juncheng Dong, Jordan Malof +2
In this study, we address the challenge of obtaining a Green's function operator for linear partial differential equations (PDEs). The Green's function is well-sought after due to…
Mode-Aware Continual Learning for Conditional Generative Adversarial Networks
Cat P. Le, Juncheng Dong, Ahmed Aloui +1
The main challenge in continual learning for generative models is to effectively learn new target modes with limited samples while preserving previously learned ones. To this end,…
PASTA: Pessimistic Assortment Optimization
Juncheng Dong, Weibin Mo, Zhengling Qi +3
We consider a class of assortment optimization problems in an offline data-driven setting. A firm does not know the underlying customer choice model but has access to an offline da…
Domain Adaptation via Rebalanced Sub-domain Alignment
Yiling Liu, Juncheng Dong, Ziyang Jiang +5
Unsupervised domain adaptation (UDA) is a technique used to transfer knowledge from a labeled source domain to a different but related unlabeled target domain. While many UDA metho…
Transfer Learning for Individual Treatment Effect Estimation
Ahmed Aloui, Juncheng Dong, Cat P. Le +1
This work considers the problem of transferring causal knowledge between tasks for Individual Treatment Effect (ITE) estimation. To this end, we theoretically assess the feasibilit…