Author name cluster

Fan Nie

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

8 papers

2 author rows

NeurIPS Conference 2025 Conference Paper

EvoLM: In Search of Lost Training Dynamics for Language Model Reasoning

Zhenting Qi
Fan Nie
Alexandre Alahi
James Zou
Himabindu Lakkaraju
Yilun Du
Eric Xing
Sham Kakade

Modern language model (LM) training has been divided into multiple stages, making it difficult for downstream developers to evaluate the impact of design choices made at each stage. We present EvoLM, a model suite that enables systematic and transparent analysis of LMs' training dynamics across pre-training, continued pre-training, supervised fine-tuning, and reinforcement learning. By training over 100 LMs with 1B and 4B parameters from scratch, we rigorously evaluate both upstream (language modeling) and downstream (problem-solving) reasoning capabilities, including considerations of both in-domain and out-of-domain generalization. Key insights highlight the diminishing returns from excessive pre-training and post-training, the importance and practices of mitigating forgetting during domain-specific continued pre-training, the crucial role of continued pre-training in bridging pre-training and post-training phases, and various intricate trade-offs when configuring supervised fine-tuning and reinforcement learning. To facilitate open research and reproducibility, we release all pre-trained and post-trained models, training datasets for all stages, and our entire training and evaluation pipeline.

PDF Details

ICML Conference 2025 Conference Paper

FactTest: Factuality Testing in Large Language Models with Finite-Sample and Distribution-Free Guarantees

Fan Nie
Xiaotian Hou
Shuhang Lin
James Y. Zou
Huaxiu Yao
Linjun Zhang

The propensity of large language models (LLMs) to generate hallucinations and non-factual content undermines their reliability in high-stakes domains, where rigorous control over Type I errors (the conditional probability of incorrectly classifying hallucinations as truthful content) is essential. Despite its importance, formal verification of LLM factuality with such guarantees remains largely unexplored. In this paper, we introduce FactTest, a novel framework that statistically assesses whether an LLM can provide correct answers to given questions with high-probability correctness guarantees. We formulate hallucination detection as a hypothesis testing problem to enforce an upper bound of Type I errors at user-specified significance levels. Notably, we prove that FactTest also ensures strong Type II error control under mild conditions and can be extended to maintain its effectiveness when covariate shifts exist. Our approach is distribution-free and works for any number of human-annotated samples. It is model-agnostic and applies to any black-box or white-box LM. Extensive experiments on question-answering (QA) benchmarks demonstrate that FactTest effectively detects hallucinations and enable LLMs to abstain from answering unknown questions, leading to an over 40% accuracy improvement.

Details

ICRA Conference 2025 Conference Paper

Generalizing Motion Planners with Mixture of Experts for Autonomous Driving

Qiao Sun 0001
Huimin Wang
Jiahao Zhan
Fan Nie
Xin Wen
Leimeng Xu
Kun Zhan
Peng Jia 0007

Large real-world driving datasets have sparked significant research into various aspects of learning-based motion planners for autonomous driving. These include data augmentation, model architecture, reward design, training strategies, and planner pipelines. In this paper, we review and benchmark previous methods. Experiments show that many of these approaches have limited generalization abilities in planning performance due to overly complex designs or training paradigms. Experiments further reveal that as models are appropriately scaled, many designs become redundant. Therefore, we introduce StateTransformer-2 (STR2), a scalable, decoder-only motion planner. STR2uses a Vision Transformer (ViT) encoder and a mix-of-experts (MoE) causal transformer architecture. The MoE backbone addresses modality collapse and reward balancing by expert routing during training. Extensive experiments on the NuPlan dataset show that our method generalizes better than previous approaches across different test sets and closed-loop simulations. We evaluate its scalability on billions of real-world urban driving scenarios, demonstrating consistent accuracy improvements as both data and model size grow.

Details

ICML Conference 2025 Conference Paper

TAROT: Targeted Data Selection via Optimal Transport

Lan Feng
Fan Nie
Yuejiang Liu
Alexandre Alahi

We propose TAROT, a targeted data selection framework grounded in Optimal Transport theory. Previous targeted data selection methods primarily rely on influence-based greedy heuristics to enhance domain-specific performance. While effective on limited, unimodal data (i. e. , data following a single pattern), these methods struggle as target data complexity increases. Specifically, in multimodal distributions, such heuristics fail to account for multiple inherent patterns, leading to suboptimal data selection. This work identifies two primary limitations: (i) the disproportionate impact of dominant feature components in high-dimensional influence estimation, and (ii) the restrictive linear additive assumptions in greedy selection strategies. To address these challenges, TAROT incorporates whitened feature distance to mitigate dominant feature bias, offering a more reliable measure of data influence. Building on this, TAROT leverages whitened feature distance to quantify and minimize the optimal transport distance between selected data and target domains. Notably, this minimization also facilitates the estimation of optimal selection ratios. We evaluate TAROT across multiple tasks, including semantic segmentation, motion prediction, and instruction tuning. Results consistently show that TAROT outperforms state-of-the-art methods, demonstrating its versatility across various deep learning tasks. Code is available at: https: //github. com/vita-epfl/TAROT.

Details

ICRA Conference 2024 Conference Paper

Boosting Offline Reinforcement Learning for Autonomous Driving with Hierarchical Latent Skills

Zenan Li
Fan Nie
Qiao Sun 0001
Fang Da
Hang Zhao 0021

Learning-based vehicle planning is receiving increasing attention with the emergence of diverse driving simulators and large-scale driving datasets. While offline reinforcement learning (RL) is well suited for these safety-critical tasks, it still struggles to plan over extended periods. In this work, we present a skill-based framework that enhances offline RL to overcome the long-horizon vehicle planning challenge. Specifically, we design a variational autoencoder (VAE) to learn skills from offline demonstrations. To mitigate posterior collapse of common VAEs, we introduce a two-branch sequence encoder to capture both discrete options and continuous variations of the complex driving skills. The final policy treats learned skills as actions and can be trained by any off-the-shelf offline RL algorithms. This facilitates a shift in focus from per-step actions to temporally extended skills, thereby enabling long-term reasoning into the future. Extensive results on CARLA prove that our model consistently outperforms strong baselines at both training and new scenarios. Additional visualizations and experiments demonstrate the interpretability and transferability of extracted skills.

Details

ICML Conference 2024 Conference Paper

Learning Divergence Fields for Shift-Robust Graph Representations

Qitian Wu
Fan Nie
Chenxiao Yang
Junchi Yan

Real-world data generation often involves certain geometries (e. g. , graphs) that induce instance-level interdependence. This characteristic makes the generalization of learning models more difficult due to the intricate interdependent patterns that impact data-generative distributions and can vary from training to testing. In this work, we propose a geometric diffusion model with learnable divergence fields for the challenging generalization problem with interdependent data. We generalize the diffusion equation with stochastic diffusivity at each time step, which aims to capture the multi-faceted information flows among interdependent data. Furthermore, we derive a new learning objective through causal inference, which can guide the model to learn generalizable patterns of interdependence that are insensitive across domains. Regarding practical implementation, we introduce three model instantiations that can be considered as the generalized versions of GCN, GAT, and Transformers, respectively, which possess advanced robustness against distribution shifts. We demonstrate their promising efficacy for out-of-distribution generalization on diverse real-world datasets. Source codes are available at https: //github. com/fannie1208/GLIND.

Details

NeurIPS Conference 2023 Conference Paper

SGFormer: Simplifying and Empowering Transformers for Large-Graph Representations

Qitian Wu
Wentao Zhao
Chenxiao Yang
Hengrui Zhang
Fan Nie
Haitian Jiang
Yatao Bian
Junchi Yan

Learning representations on large-sized graphs is a long-standing challenge due to the inter-dependence nature involved in massive data points. Transformers, as an emerging class of foundation encoders for graph-structured data, have shown promising performance on small graphs due to its global attention capable of capturing all-pair influence beyond neighboring nodes. Even so, existing approaches tend to inherit the spirit of Transformers in language and vision tasks, and embrace complicated models by stacking deep multi-head attentions. In this paper, we critically demonstrate that even using a one-layer attention can bring up surprisingly competitive performance across node property prediction benchmarks where node numbers range from thousand-level to billion-level. This encourages us to rethink the design philosophy for Transformers on large graphs, where the global attention is a computation overhead hindering the scalability. We frame the proposed scheme as Simplified Graph Transformers (SGFormer), which is empowered by a simple attention model that can efficiently propagate information among arbitrary nodes in one layer. SGFormer requires none of positional encodings, feature/graph pre-processing or augmented loss. Empirically, SGFormer successfully scales to the web-scale graph ogbn-papers100M and yields up to 141x inference acceleration over SOTA Transformers on medium-sized graphs. Beyond current results, we believe the proposed methodology alone enlightens a new technical path of independent interest for building Transformers on large graphs.

PDF Details

NeurIPS Conference 2022 Conference Paper

GraphDE: A Generative Framework for Debiased Learning and Out-of-Distribution Detection on Graphs

Zenan Li
Qitian Wu
Fan Nie
Junchi Yan

Despite the remarkable success of graph neural networks (GNNs) for graph representation learning, they are generally built on the (unreliable) i. i. d. assumption across training and testing data. However, real-world graph data are universally comprised of outliers in training set and out-of-distribution (OOD) testing samples from unseen domains, which solicits effective models for i) debiased learning and ii) OOD detection, towards general trustworthy purpose. In this paper, we first mathematically formulate the two challenging problems for graph data and take an initiative on tackling them under a unified probabilistic model. Specifically, we model the graph generative process to characterize the distribution shifts of graph data together with an additionally introduced latent environment variable as an indicator. We then define a variational distribution, i. e. , a recognition model, to infer the environment during training of GNN. By instantiating the generative models as two-component mixtures, we derive a tractable learning objective and theoretically justify that the model can i) automatically identify and down-weight outliers in the training procedure, and ii) induce an effective OOD detector simultaneously. Experiments on diverse datasets with different types of OOD data prove that our model consistently outperforms strong baselines for both debiasing and OOD detection tasks. The source code has been made publicly available at https: //github. com/Emiyalzn/GraphDE.

PDF Details