Abstract:Foundation models have revolutionized natural language processing and artificial intelligence, significantly enhancing how machines comprehend and generate human languages. Inspired by the success of these foundation models, researchers have developed foundation models for individual scientific domains, including small molecules, materials, proteins, DNA, and RNA. However, these models are typically trained in isolation, lacking the ability to integrate across different scientific domains. Recognizing that entities within these domains can all be represented as sequences, which together form the "language of nature", we introduce Nature Language Model (briefly, NatureLM), a sequence-based science foundation model designed for scientific discovery. Pre-trained with data from multiple scientific domains, NatureLM offers a unified, versatile model that enables various applications including: (i) generating and optimizing small molecules, proteins, RNA, and materials using text instructions; (ii) cross-domain generation/design, such as protein-to-molecule and protein-to-RNA generation; and (iii) achieving state-of-the-art performance in tasks like SMILES-to-IUPAC translation and retrosynthesis on USPTO-50k. NatureLM offers a promising generalist approach for various scientific tasks, including drug discovery (hit generation/optimization, ADMET optimization, synthesis), novel material design, and the development of therapeutic proteins or nucleotides. We have developed NatureLM models in different sizes (1 billion, 8 billion, and 46.7 billion parameters) and observed a clear improvement in performance as the model size increases.
Abstract:A truly intelligent Large Language Model (LLM) should be capable of correcting errors in its responses through external interactions. However, even the most advanced models often face challenges in improving their outputs. In this paper, we explore how to cultivate LLMs with the self-refinement capability through iterative preference training, and how this ability can be leveraged to improve model performance during inference. To this end, we introduce a novel post-training and inference framework, called ARIES: Adaptive Refinement and Iterative Enhancement Structure. This method iteratively performs preference training and self-refinement-based data collection. During training, ARIES strengthen the model's direct question-answering capability while simultaneously unlocking its self-refinement potential. During inference, ARIES harnesses this self-refinement capability to generate a series of progressively refined responses, which are then filtered using either the Reward Model Scoring or a simple yet effective Rule-Based Selection mechanism, specifically tailored to our approach, to construct a dataset for the next round of preference training. Experimental results demonstrate the remarkable performance of ARIES. When applied to the Llama-3.1-8B model and under the self-refinement setting, ARIES surpasses powerful models such as GPT-4o, achieving 62.3% length-controlled (LC) and a 63.3% raw win rates on AlpacaEval 2, outperforming Iterative DPO by 27.8% and 35.5% respectively, as well as a 50.3% win rate on Arena-Hard, surpassing Iterative DPO by 26.6%. Furthermore, ARIES consistently enhances performance on mathematical reasoning tasks like GSM8K and MATH.
Abstract:Structure-based drug discovery, encompassing the tasks of protein-ligand docking and pocket-aware 3D drug design, represents a core challenge in drug discovery. However, no existing work can deal with both tasks to effectively leverage the duality between them, and current methods for each task are hindered by challenges in modeling 3D information and the limitations of available data. To address these issues, we propose 3DMolFormer, a unified dual-channel transformer-based framework applicable to both docking and 3D drug design tasks, which exploits their duality by utilizing docking functionalities within the drug design process. Specifically, we represent 3D pocket-ligand complexes using parallel sequences of discrete tokens and continuous numbers, and we design a corresponding dual-channel transformer model to handle this format, thereby overcoming the challenges of 3D information modeling. Additionally, we alleviate data limitations through large-scale pre-training on a mixed dataset, followed by supervised and reinforcement learning fine-tuning techniques respectively tailored for the two tasks. Experimental results demonstrate that 3DMolFormer outperforms previous approaches in both protein-ligand docking and pocket-aware 3D drug design, highlighting its promising application in structure-based drug discovery. The code is available at: https://github.com/HXYfighter/3DMolFormer .
Abstract:Planning and conducting chemical syntheses remains a major bottleneck in the discovery of functional small molecules, and prevents fully leveraging generative AI for molecular inverse design. While early work has shown that ML-based retrosynthesis models can predict reasonable routes, their low accuracy for less frequent, yet important reactions has been pointed out. As multi-step search algorithms are limited to reactions suggested by the underlying model, the applicability of those tools is inherently constrained by the accuracy of retrosynthesis prediction. Inspired by how chemists use different strategies to ideate reactions, we propose Chimera: a framework for building highly accurate reaction models that combine predictions from diverse sources with complementary inductive biases using a learning-based ensembling strategy. We instantiate the framework with two newly developed models, which already by themselves achieve state of the art in their categories. Through experiments across several orders of magnitude in data scale and time-splits, we show Chimera outperforms all major models by a large margin, owing both to the good individual performance of its constituents, but also to the scalability of our ensembling strategy. Moreover, we find that PhD-level organic chemists prefer predictions from Chimera over baselines in terms of quality. Finally, we transfer the largest-scale checkpoint to an internal dataset from a major pharmaceutical company, showing robust generalization under distribution shift. With the new dimension that our framework unlocks, we anticipate further acceleration in the development of even more accurate models.
Abstract:In many open environment applications, data are collected in the form of a stream, which exhibits an evolving distribution over time. How to design algorithms to track these evolving data distributions with provable guarantees, particularly in terms of the generalization ability, remains a formidable challenge. To handle this crucial but rarely studied problem and take a further step toward robust artificial intelligence, we propose a novel framework called Distribution Adaptable Learning (DAL). It enables the model to effectively track the evolving data distributions. By Encoding Feature Marginal Distribution Information (EFMDI), we broke the limitations of optimal transport to characterize the environmental changes and enable model reuse across diverse data distributions. It can enhance the reusable and evolvable properties of DAL in accommodating evolving distributions. Furthermore, to obtain the model interpretability, we not only analyze the generalization error bound of the local step in the evolution process, but also investigate the generalization error bound associated with the entire classifier trajectory of the evolution based on the Fisher-Rao distance. For demonstration, we also present two special cases within the framework, together with their optimizations and convergence analyses. Experimental results over both synthetic and real-world data distribution evolving tasks validate the effectiveness and practical utility of the proposed framework.
Abstract:The acquisition of inductive bias through point-level contrastive learning holds paramount significance in point cloud pre-training. However, the square growth in computational requirements with the scale of the point cloud poses a substantial impediment to the practical deployment and execution. To address this challenge, this paper proposes an Effective Point-level Contrastive Learning method for large-scale point cloud understanding dubbed \textbf{EPContrast}, which consists of AGContrast and ChannelContrast. In practice, AGContrast constructs positive and negative pairs based on asymmetric granularity embedding, while ChannelContrast imposes contrastive supervision between channel feature maps. EPContrast offers point-level contrastive loss while concurrently mitigating the computational resource burden. The efficacy of EPContrast is substantiated through comprehensive validation on S3DIS and ScanNetV2, encompassing tasks such as semantic segmentation, instance segmentation, and object detection. In addition, rich ablation experiments demonstrate remarkable bias induction capabilities under label-efficient and one-epoch training settings.
Abstract:Traversability estimation in off-road terrains is an essential procedure for autonomous navigation. However, creating reliable labels for complex interactions between the robot and the surface is still a challenging problem in learning-based costmap generation. To address this, we propose a method that predicts traversability costmaps by leveraging both visual and geometric information of the environment. To quantify the surface properties like roughness and bumpiness, we introduce a novel way of risk-aware labelling with proprioceptive information for network training. We validate our method in costmap prediction and navigation tasks for complex off-road scenarios. Our results demonstrate that our costmap prediction method excels in terms of average accuracy and MSE. The navigation results indicate that using our learned costmaps leads to safer and smoother driving, outperforming previous methods in terms of the highest success rate, lowest normalized trajectory length, lowest time cost, and highest mean stability across two scenarios.
Abstract:In this paper, we develop SE3Set, an SE(3) equivariant hypergraph neural network architecture tailored for advanced molecular representation learning. Hypergraphs are not merely an extension of traditional graphs; they are pivotal for modeling high-order relationships, a capability that conventional equivariant graph-based methods lack due to their inherent limitations in representing intricate many-body interactions. To achieve this, we first construct hypergraphs via proposing a new fragmentation method that considers both chemical and three-dimensional spatial information of molecular system. We then design SE3Set, which incorporates equivariance into the hypergragh neural network. This ensures that the learned molecular representations are invariant to spatial transformations, thereby providing robustness essential for accurate prediction of molecular properties. SE3Set has shown performance on par with state-of-the-art (SOTA) models for small molecule datasets like QM9 and MD17. It excels on the MD22 dataset, achieving a notable improvement of approximately 20% in accuracy across all molecules, which highlights the prevalence of complex many-body interactions in larger molecules. This exceptional performance of SE3Set across diverse molecular structures underscores its transformative potential in computational chemistry, offering a route to more accurate and physically nuanced modeling.
Abstract:Fine-tuning pre-trained Large Language Models (LLMs) is essential to align them with human values and intentions. This process often utilizes methods like pairwise comparisons and KL divergence against a reference LLM, focusing on the evaluation of full answers generated by the models. However, the generation of these responses occurs in a token level, following a sequential, auto-regressive fashion. In this paper, we introduce Token-level Direct Preference Optimization (TDPO), a novel approach to align LLMs with human preferences by optimizing policy at the token level. Unlike previous methods, which face challenges in divergence efficiency, TDPO incorporates forward KL divergence constraints for each token, improving alignment and diversity. Utilizing the Bradley-Terry model for a token-based reward system, TDPO enhances the regulation of KL divergence, while preserving simplicity without the need for explicit reward modeling. Experimental results across various text tasks demonstrate TDPO's superior performance in balancing alignment with generation diversity. Notably, fine-tuning with TDPO strikes a better balance than DPO in the controlled sentiment generation and single-turn dialogue datasets, and significantly improves the quality of generated responses compared to both DPO and PPO-based RLHF methods. Our code is open-sourced at https://github.com/Vance0124/Token-level-Direct-Preference-Optimization.
Abstract:Temporal misalignment (time offset) between sensors is common in low cost visual-inertial odometry (VIO) systems. Such temporal misalignment introduces inconsistent constraints for state estimation, leading to a significant positioning drift especially in high dynamic motion scenarios. In this article, we focus on online temporal calibration to reduce the positioning drift caused by the time offset for high dynamic motion VIO. For the time offset observation model, most existing methods rely on accurate state estimation or stable visual tracking. For the prediction model, current methods oversimplify the time offset as a constant value with white Gaussian noise. However, these ideal conditions are seldom satisfied in real high dynamic scenarios, resulting in the poor performance. In this paper, we introduce online time offset modeling networks (TON) to enhance real-time temporal calibration. TON improves the accuracy of time offset observation and prediction modeling. Specifically, for observation modeling, we propose feature velocity observation networks to enhance velocity computation for features in unstable visual tracking conditions. For prediction modeling, we present time offset prediction networks to learn its evolution pattern. To highlight the effectiveness of our method, we integrate the proposed TON into both optimization-based and filter-based VIO systems. Simulation and real-world experiments are conducted to demonstrate the enhanced performance of our approach. Additionally, to contribute to the VIO community, we will open-source the code of our method on: https://github.com/Franky-X/FVON-TPN.