Author name cluster

Ge Liu

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.

14 papers

2 author rows

TMLR Journal 2026 Journal Article

Thought-Retriever: Don't Just Retrieve Raw Data, Retrieve Thoughts for Memory-Augmented Agentic Systems

Tao Feng
Pengrui Han
Guanyu Lin
Ge Liu
Jiaxuan You

Large language models (LLMs) have transformed AI research thanks to their powerful internal capabilities and knowledge. However, existing LLMs still fail to effectively incorporate the massive external knowledge when interacting with the world. Although retrieval-augmented LLMs are proposed to mitigate the issue, they are still fundamentally constrained by the context length of LLMs, as they can only retrieve top-K raw data chunks from the external knowledge base which often consists of millions of data chunks. Here we propose Thought-Retriever, a novel model-agnostic algorithm that helps LLMs generate output conditioned on arbitrarily long external data, without being constrained by the context length or number of retrieved data chunks. Our key insight is to let an LLM fully leverage its intermediate responses generated when solving past user queries (thoughts), filtering meaningless and redundant thoughts, organizing them in thought memory, and retrieving the relevant thoughts when addressing new queries. This effectively equips LLM-based agents with a self-evolving long-term memory that grows more capable through continuous interaction. Besides algorithmic innovation, we further meticulously prepare a novel benchmark, AcademicEval, which requires an LLM to faithfully leverage ultra-long context to answer queries based on real-world academic papers. Extensive experiments on AcademicEval and two other public datasets validate that Thought-Retriever remarkably outperforms state-of-the-art baselines, achieving an average increase of at least 7.6% in F1 score and 16% in win rate across various tasks. More importantly, we further demonstrate two exciting findings: (1) Thought-Retriever can indeed help LLM self-evolve after solving more user queries; (2) Thought-Retriever learns to leverage deeper thoughts to answer more abstract user queries.

PDF Details

TMLR Journal 2026 Journal Article

UniRec: Unified Multimodal Encoding for LLM-Based Recommendations

Zijie Lei
Tao Feng
Zhigang Hua
Yan Xie
Guanyu Lin
Shuang Yang
Ge Liu
Jiaxuan You

Large language models (LLMs) have recently shown promise for multimodal recommen- dation, particularly with text and image inputs. Yet real-world recommendation signals extend far beyond these modalities. To reflect this, we formalize recommendation features into four modalities: text, images, categorical features, and numerical attributes, and em- phasize unique challenges this heterogeneity poses for LLMs in understanding multimodal information. In particular, these challenges arise not only across modalities but also within them, as attributes (e.g., price, rating, time) may all be numeric yet carry distinct meanings. Beyond this intra-modality ambiguity, another major challenge is the nested structure of recommendation signals, where user histories are sequences of items, each carrying multiple attributes. To address these challenges, we propose UniRec, a unified multimodal encoder for LLM-based recommendation. UniRec first employs modality-specific encoders to produce consistent embeddings across heterogeneous signals. It then applies a triplet representa- tion—comprising attribute name, type, and value—to separate schema from raw inputs and preserve semantic distinctions. Finally, a hierarchical Q-Former models the nested structure of user interactions while maintaining their layered organization. On multiple real-world benchmarks, UniRec outperforms state-of-the-art multimodal and LLM-based recommenders by up to 15%, while extensive ablation studies further validate the contribu- tions of each component.

PDF Details

NeurIPS Conference 2025 Conference Paper

Adaptive Divergence Regularized Policy Optimization for Fine-tuning Generative Models

Jiajun Fan
Tong Wei
Chaoran Cheng
Yuxin Chen
Ge Liu

Balancing exploration and exploitation during reinforcement learning fine-tuning of generative models presents a critical challenge, as existing approaches rely on fixed divergence regularization that creates an inherent dilemma: strong regularization preserves model capabilities but limits reward optimization, while weak regularization enables greater alignment but risks instability or reward hacking. We introduce Adaptive Divergence Regularized Policy Optimization (ADRPO), which automatically adjusts regularization strength based on advantage estimates—reducing regularization for high-value samples while applying stronger regularization to poor samples, enabling policies to navigate between exploration and aggressive exploitation according to data quality. Our implementation with Wasserstein-2 regularization for flow matching generative models achieves remarkable results on text-to-image generation, achieving better semantic alignment and diversity than offline methods like DPO and online methods with fixed regularization like ORW-CFM-W2. ADRPO enables a 2B parameter SD3 model to surpass much larger models with 4. 8B and 12B parameters in attribute binding, semantic consistency, artistic style transfer, and compositional control while maintaining generation diversity. ADRPO generalizes to KL-regularized fine-tuning of both text-only LLMs and multi-modal reasoning models, enhancing existing online RL methods like GRPO while requiring no additional networks or complex architectural changes. In LLM fine-tuning, ADRPO demonstrates an emergent ability to escape local optima through active exploration, while in multi-modal audio reasoning, it outperforms GRPO through superior step-by-step reasoning, enabling a 7B model to outperform substantially larger commercial models including Gemini 2. 5 Pro and GPT-4o Audio, offering an effective plug-and-play solution to the exploration-exploitation challenge across diverse generative architectures and modalities.

PDF Details

ICLR Conference 2025 Conference Paper

Hotspot-Driven Peptide Design via Multi-Fragment Autoregressive Extension

Jiahan Li
Tong Chen
Shitong Luo
Chaoran Cheng
Jiaqi Guan
Ruihan Guo
Sheng Wang
Ge Liu

Peptides, short chains of amino acids, interact with target proteins, making them a unique class of protein-based therapeutics for treating human diseases. Recently, deep generative models have shown great promise in peptide generation. However, several challenges remain in designing effective peptide binders. First, not all residues contribute equally to peptide-target interactions. Second, the generated peptides must adopt valid geometries due to the constraints of peptide bonds. Third, realistic tasks for peptide drug development are still lacking. To address these challenges, we introduce PepHAR, a hot-spot-driven autoregressive generative model for designing peptides targeting specific proteins. Building on the observation that certain hot spot residues have higher interaction potentials, we first use an energy-based density model to fit and sample these key residues. Next, to ensure proper peptide geometry, we autoregressively extend peptide fragments by estimating dihedral angles between residue frames. Finally, we apply an optimization process to iteratively refine fragment assembly, ensuring correct peptide structures. By combining hot spot sampling with fragment-based extension, our approach enables \textit{de novo} peptide design tailored to a target protein and allows the incorporation of key hot spot residues into peptide scaffolds. Extensive experiments, including peptide design and peptide scaffold generation, demonstrate the strong potential of PepHAR in computational peptide binder design. The source code will be available at https://github.com/Ced3-han/PepHAR.

Details

ICLR Conference 2025 Conference Paper

Online Reward-Weighted Fine-Tuning of Flow Matching with Wasserstein Regularization

Jiajun Fan
Shuaike Shen
Chaoran Cheng
Yuxin Chen
Chumeng Liang
Ge Liu

Recent advancements in reinforcement learning (RL) have achieved great success in fine-tuning diffusion-based generative models. However, fine-tuning continuous flow-based generative models to align with arbitrary user-defined reward functions remains challenging, particularly due to issues such as policy collapse from overoptimization and the prohibitively high computational cost of likelihoods in continuous-time flows. In this paper, we propose an easy-to-use and theoretically sound RL fine-tuning method, which we term Online Reward-Weighted Conditional Flow Matching with Wasserstein-2 Regularization (ORW-CFM-W2). Our method integrates RL into the flow matching framework to fine-tune generative models with arbitrary reward functions, without relying on gradients of rewards or filtered datasets. By introducing an online reward-weighting mechanism, our approach guides the model to prioritize high-reward regions in the data manifold. To prevent policy collapse and maintain diversity, we incorporate Wasserstein-2 (W2) distance regularization into our method and derive a tractable upper bound for it in flow matching, effectively balancing exploration and exploitation of policy optimization. We provide theoretical analyses to demonstrate the convergence properties and induced data distributions of our method, establishing connections with traditional RL algorithms featuring Kullback-Leibler (KL) regularization and offering a more comprehensive understanding of the underlying mechanisms and learning behavior of our approach. Extensive experiments on tasks including target image generation, image compression, and text-image alignment demonstrate the effectiveness of our method, where our method achieves optimal policy convergence while allowing controllable trade-offs between reward maximization and diversity preservation.

Details

NeurIPS Conference 2025 Conference Paper

Riemannian Consistency Model

Chaoran Cheng
Yusong Wang
Yuxin Chen
Xiangxin Zhou
Nanning Zheng
Ge Liu

Consistency models are a class of generative models that enable few-step generation for diffusion and flow matching models. While consistency models have achieved promising results on Euclidean domains like images, their applications to Riemannian manifolds remain challenging due to the curved geometry. In this work, we propose the Riemannian Consistency Model (RCM), which, for the first time, enables few-step consistency modeling while respecting the intrinsic manifold constraint imposed by the Riemannian geometry. Leveraging the covariant derivative and exponential-map-based parameterization, we derive the closed-form solutions for both discrete- and continuous-time training objectives for RCM. We then demonstrate theoretical equivalence between the two variants of RCM: Riemannian consistency distillation (RCD) that relies on a teacher model to approximate the marginal vector field, and Riemannian consistency training (RCT) that utilizes the conditional vector field for training. We further propose a simplified training objective that eliminates the need for the complicated differential calculation. Finally, we provide a unique kinematics perspective for interpreting the RCM objective, offering new theoretical angles. Through extensive experiments, we manifest the superior generative quality of RCM in few-step generation on various non-Euclidean manifolds, including flat-tori, spheres, and the 3D rotation group SO(3), spanning a variety of crucial real-world applications such as RNA and protein generation.

PDF Details

ICLR Conference 2025 Conference Paper

Training Free Guided Flow-Matching with Optimal Control

Luran Wang
Chaoran Cheng
Yizhen Liao
Yanru Qu
Ge Liu

Controlled generation with pre-trained Diffusion and Flow Matching models has vast applications. One strategy for guiding ODE-based generative models is through optimizing a target loss $R(x_1)$ while staying close to the prior distribution. Along this line, some recent work showed the effectiveness of guiding flow model by differentiating through its ODE sampling process. Despite the superior performance, the theoretical understanding of this line of methods is still preliminary, leaving space for algorithm improvement. Moreover, existing methods predominately focus on Euclidean data manifold, and there is a compelling need for guided flow methods on complex geometries such as SO(3), which prevails in high-stake scientific applications like protein design. We present OC-Flow, a general and theoretically grounded training-free framework for guided flow matching using optimal control. Building upon advances in optimal control theory, we develop effective and practical algorithms for solving optimal control in guided ODE-based generation and provide a systematic theoretical analysis of the convergence guarantee in both Euclidean and SO(3). We show that existing backprop-through-ODE methods can be interpreted as special cases of Euclidean OC-Flow. OC-Flow achieved superior performance in extensive experiments on text-guided image manipulation, conditional molecule generation, and all-atom peptide design.

Details

NeurIPS Conference 2025 Conference Paper

Variational Supervised Contrastive Learning

Ziwen Wang
Jiajun Fan
Thao Nguyen
Heng Ji
Ge Liu

Contrastive learning has proven to be highly efficient and adaptable in shaping representation spaces across diverse modalities by pulling similar samples together and pushing dissimilar ones apart. However, two key limitations persist: (1) Without explicit regulation of the embedding distribution, semantically related instances can inadvertently be pushed apart unless complementary signals guide pair selection, and (2) excessive reliance on large in-batch negatives and tailored augmentations hinders generalization. To address these limitations, we propose Variational Supervised Contrastive Learning (VarCon), which reformulates supervised contrastive learning as variational inference over latent class variables and maximizes a posterior-weighted evidence lower bound (ELBO) that replaces exhaustive pair-wise comparisons for efficient class-aware matching and grants fine-grained control over intra-class dispersion in the embedding space. Trained exclusively on image data, our experiments on CIFAR-10, CIFAR-100, ImageNet-100, and ImageNet-1K show that VarCon (1) achieves state-of-the-art performance for contrastive learning frameworks, reaching 79. 36% Top-1 accuracy on ImageNet-1K and 78. 29% on CIFAR-100 with a ResNet-50 encoder while converging in just 200 epochs; (2) yields substantially clearer decision boundaries and semantic organization in the embedding space, as evidenced by KNN classification, hierarchical clustering results, and transfer-learning assessments; and (3) demonstrates superior performance in few-shot learning than supervised baseline and superior robustness across various augmentation strategies.

PDF Details

NeurIPS Conference 2024 Conference Paper

Categorical Flow Matching on Statistical Manifolds

Chaoran Cheng
Jiahan Li
Jian Peng
Ge Liu

We introduce Statistical Flow Matching (SFM), a novel and mathematically rigorous flow-matching framework on the manifold of parameterized probability measures inspired by the results from information geometry. We demonstrate the effectiveness of our method on the discrete generation problem by instantiating SFM on the manifold of categorical distributions whose geometric properties remain unexplored in previous discrete generative models. Utilizing the Fisher information metric, we equip the manifold with a Riemannian structure whose intrinsic geometries are effectively leveraged by following the shortest paths of geodesics. We develop an efficient training and sampling algorithm that overcomes numerical stability issues with a diffeomorphism between manifolds. Our distinctive geometric perspective of statistical manifolds allows us to apply optimal transport during training and interpret SFM as following the steepest direction of the natural gradient. Unlike previous models that rely on variational bounds for likelihood estimation, SFM enjoys the exact likelihood calculation for arbitrary probability measures. We manifest that SFM can learn more complex patterns on the statistical manifold where existing models often fail due to strong prior assumptions. Comprehensive experiments on real-world generative tasks ranging from image, text to biological domains further demonstrate that SFM achieves higher sampling quality and likelihood than other discrete diffusion or flow-based models.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Neural P$^3$M: A Long-Range Interaction Modeling Enhancer for Geometric GNNs

Yusong Wang
Chaoran Cheng
Shaoning Li
Yuxuan Ren
Bin Shao
Ge Liu
Pheng-Ann Heng
Nanning Zheng

Geometric graph neural networks (GNNs) have emerged as powerful tools for modeling molecular geometry. However, they encounter limitations in effectively capturing long-range interactions in large molecular systems. To address this challenge, we introduce **Neural P$^3$M**, a versatile enhancer of geometric GNNs to expand the scope of their capabilities by incorporating mesh points alongside atoms and reimaging traditional mathematical operations in a trainable manner. Neural P$^3$M exhibits flexibility across a wide range of molecular systems and demonstrates remarkable accuracy in predicting energies and forces, outperforming on benchmarks such as the MD22 dataset. It also achieves an average improvement of 22% on the OE62 dataset while integrating with various architectures. Codes are available at https: //github. com/OnlyLoveKFC/Neural_P3M.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Optimal Design for Human Preference Elicitation

Subhojyoti Mukherjee
Anusha Lalitha
Kousha Kalantari
Aniket Deshmukh
Ge Liu
Yifei Ma
Branislav Kveton

Learning of preference models from human feedback has been central to recent advances in artificial intelligence. Motivated by the cost of obtaining high-quality human annotations, we study efficient human preference elicitation for learning preference models. The key idea in our work is to generalize optimal designs, an approach to computing optimal information-gathering policies, to lists of items that represent potential questions with answers. The policy is a distribution over the lists and we elicit preferences from them proportionally to their probabilities. To show the generality of our ideas, we study both absolute and ranking feedback models on items in the list. We design efficient algorithms for both and analyze them. Finally, we demonstrate that our algorithms are practical by evaluating them on existing question-answering problems.

PDF Details DOI

ICLR Conference 2022 Conference Paper

Bridging Recommendation and Marketing via Recurrent Intensity Modeling

Yifei Ma
Ge Liu
Anoop Deoras

This paper studies some under-explored connections between personalized recommendation and marketing systems. Obviously, these two systems are different, in two main ways. Firstly, personalized item-recommendation (ItemRec) is user-centric, whereas marketing recommends the best user-state segments (UserRec) on behalf of its item providers. (We treat different temporal states of the same user as separate marketing opportunities.) To overcome this difference, we realize a novel connection to Marked-Temporal Point Processes (MTPPs), where we view both problems as different projections from a unified temporal intensity model for all user-item pairs. Correspondingly, we derive Recurrent Intensity Models (RIMs) to extend from recurrent ItemRec models with minimal changes. The second difference between recommendation and marketing is in the temporal domains where they operate. While recommendation demands immediate responses in real-time, marketing campaigns are often long-term, setting goals to cover a given percentage of all opportunities for a given item in a given period of time. We formulate both considerations into a constrained optimization problem we call online match (OnlnMtch) and derive a solution we call Dual algorithm. Simply put, Dual modifies the real-time ItemRec scores such that the marketing constraints can be met with least compromises in user-centric utilities. Finally, our connections between recommendation and marketing may lead to novel applications. We run experiments where we use marketing as an alternative to cold-start item exploration, by setting a minimal-exposure constraint for every item in the audience base. Our experiments are available at \url{https://github.com/awslabs/recurrent-intensity-model-experiments}

Details

ICLR Conference 2022 Conference Paper

Maximum n-times Coverage for Vaccine Design

Ge Liu
Alexander Dimitrakakis
Brandon Carter 0001
David K. Gifford

We introduce the maximum $n$-times coverage problem that selects $k$ overlays to maximize the summed coverage of weighted elements, where each element must be covered at least $n$ times. We also define the min-cost $n$-times coverage problem where the objective is to select the minimum set of overlays such that the sum of the weights of elements that are covered at least $n$ times is at least $\tau$. Maximum $n$-times coverage is a generalization of the multi-set multi-cover problem, is NP-complete, and is not submodular. We introduce two new practical solutions for $n$-times coverage based on integer linear programming and sequential greedy optimization. We show that maximum $n$-times coverage is a natural way to frame peptide vaccine design, and find that it produces a pan-strain COVID-19 vaccine design that is superior to 29 other published designs in predicted population coverage and the expected number of peptides displayed by each individual's HLA molecules.

Details

AAAI Conference 2020 Conference Paper

Maximizing Overall Diversity for Improved Uncertainty Estimates in Deep Ensembles

Siddhartha Jain
Ge Liu
Jonas Mueller
David Gifford

The inaccuracy of neural network models on inputs that do not stem from the distribution underlying the training data is problematic and at times unrecognized. Uncertainty estimates of model predictions are often based on the variation in predictions produced by a diverse ensemble of models applied to the same input. Here we describe Maximize Overall Diversity (MOD), an approach to improve ensemble-based uncertainty estimates by encouraging larger overall diversity in ensemble predictions across all possible inputs. We apply MOD to regression tasks including 38 Protein-DNA binding datasets, 9 UCI datasets, and the IMDB-Wiki image dataset. We also explore variants that utilize adversarial training techniques and data density estimation. For out-of-distribution test examples, MOD signiﬁcantly improves predictive performance and uncertainty calibration without sacriﬁcing performance on test data drawn from same distribution as the training data. We also ﬁnd that in Bayesian optimization tasks, the performance of UCB acquisition is improved via MOD uncertainty estimates.

PDF Details