Jian Peng

Shitong Luo, Jiahan Li, Jiaqi Guan et al. · mit

Equivariance has been a long-standing concern in various fields ranging from computer vision to physical modeling. Most previous methods struggle with generality, simplicity, and expressiveness -- some are designed ad hoc for specific data types, some are too complex to be accessible, and some sacrifice flexible transformations. In this work, we propose a novel and simple framework to achieve equivariance for point cloud analysis based on the message passing (graph neural network) scheme. We find the equivariant property could be obtained by introducing an orientation for each point to decouple the relative position for each point from the global pose of the entire point cloud. Therefore, we extend current message passing networks with a module that learns orientations for each point. Before aggregating information from the neighbors of a point, the networks transforms the neighbors' coordinates based on the point's learned orientations. We provide formal proofs to show the equivariance of the proposed framework. Empirically, we demonstrate that our proposed method is competitive on both point cloud analysis and physical modeling tasks. Code is available at https://github.com/luost26/Equivariant-OrientedMP .

Xingang Peng, Shitong Luo, Jiaqi Guan et al. · mit

Deep generative models have achieved tremendous success in designing novel drug molecules in recent years. A new thread of works have shown the great potential in advancing the specificity and success rate of in silico drug design by considering the structure of protein pockets. This setting posts fundamental computational challenges in sampling new chemical compounds that could satisfy multiple geometrical constraints imposed by pockets. Previous sampling algorithms either sample in the graph space or only consider the 3D coordinates of atoms while ignoring other detailed chemical structures such as bond types and functional groups. To address the challenge, we develop Pocket2Mol, an E(3)-equivariant generative network composed of two modules: 1) a new graph neural network capturing both spatial and bonding relationships between atoms of the binding pockets and 2) a new efficient algorithm which samples new drug candidates conditioned on the pocket representations from a tractable distribution without relying on MCMC. Experimental results demonstrate that molecules sampled from Pocket2Mol achieve significantly better binding affinity and other drug properties such as druglikeness and synthetic accessibility.

Xingchao Liu, Xiwen Zhang, Jianzhu Ma et al.

Diffusion models have revolutionized text-to-image generation with its exceptional quality and creativity. However, its multi-step sampling process is known to be slow, often requiring tens of inference steps to obtain satisfactory results. Previous attempts to improve its sampling speed and reduce computational costs through distillation have been unsuccessful in achieving a functional one-step model. In this paper, we explore a recent method called Rectified Flow, which, thus far, has only been applied to small datasets. The core of Rectified Flow lies in its \emph{reflow} procedure, which straightens the trajectories of probability flows, refines the coupling between noises and images, and facilitates the distillation process with student models. We propose a novel text-conditioned pipeline to turn Stable Diffusion (SD) into an ultra-fast one-step model, in which we find reflow plays a critical role in improving the assignment between noise and images. Leveraging our new pipeline, we create, to the best of our knowledge, the first one-step diffusion-based text-to-image generator with SD-level image quality, achieving an FID (Frechet Inception Distance) of $23.3$ on MS COCO 2017-5k, surpassing the previous state-of-the-art technique, progressive distillation, by a significant margin ($37.2$ $\rightarrow$ $23.3$ in FID). By utilizing an expanded network with 1.7B parameters, we further improve the FID to $22.4$. We call our one-step models \emph{InstaFlow}. On MS COCO 2014-30k, InstaFlow yields an FID of $13.1$ in just $0.09$ second, the best in $\leq 0.1$ second regime, outperforming the recent StyleGAN-T ($13.9$ in $0.1$ second). Notably, the training of InstaFlow only costs 199 A100 GPU days. Codes and pre-trained models are available at \url{github.com/gnobitab/InstaFlow}.

Shitong Luo, Jiaqi Guan, Jianzhu Ma et al. · mit

We study a fundamental problem in structure-based drug design -- generating molecules that bind to specific protein binding sites. While we have witnessed the great success of deep generative models in drug design, the existing methods are mostly string-based or graph-based. They are limited by the lack of spatial information and thus unable to be applied to structure-based design tasks. Particularly, such models have no or little knowledge of how molecules interact with their target proteins exactly in 3D space. In this paper, we propose a 3D generative model that generates molecules given a designated 3D protein binding site. Specifically, given a binding site as the 3D context, our model estimates the probability density of atom's occurrences in 3D space -- positions that are more likely to have atoms will be assigned higher probability. To generate 3D molecules, we propose an auto-regressive sampling scheme -- atoms are sampled sequentially from the learned distribution until there is no room for new atoms. Combined with this sampling scheme, our model can generate valid and diverse molecules, which could be applicable to various structure-based molecular design tasks such as molecule sampling and linker design. Experimental results demonstrate that molecules sampled from our model exhibit high binding affinity to specific targets and good drug properties such as drug-likeness even if the model is not explicitly optimized for them.

Shenggan Cheng, Xuanlei Zhao, Guangyang Lu et al. · berkeley

Protein structure prediction helps to understand gene translation and protein function, which is of growing interest and importance in structural biology. The AlphaFold model, which used transformer architecture to achieve atomic-level accuracy in protein structure prediction, was a significant breakthrough. However, training and inference of the AlphaFold model are challenging due to its high computation and memory cost. In this work, we present FastFold, an efficient implementation of AlphaFold for both training and inference. We propose Dynamic Axial Parallelism and Duality Async Operations to improve the scaling efficiency of model parallelism. Besides, AutoChunk is proposed to reduce memory cost by over 80% during inference by automatically determining the chunk strategy. Experimental results show that FastFold reduces overall training time from 11 days to 67 hours and achieves 7.5X - 9.5X speedup for long-sequence inference. Furthermore, we scale FastFold to 512 GPUs and achieve an aggregate throughput of 6.02 PetaFLOP/s with 90.1% parallel efficiency.

Jiaqi Guan, Wesley Wei Qian, Xingang Peng et al.

Rich data and powerful machine learning models allow us to design drugs for a specific protein target \textit{in silico}. Recently, the inclusion of 3D structures during targeted drug design shows superior performance to other target-free models as the atomic interaction in the 3D space is explicitly modeled. However, current 3D target-aware models either rely on the voxelized atom densities or the autoregressive sampling process, which are not equivariant to rotation or easily violate geometric constraints resulting in unrealistic structures. In this work, we develop a 3D equivariant diffusion model to solve the above challenges. To achieve target-aware molecule design, our method learns a joint generative process of both continuous atom coordinates and categorical atom types with a SE(3)-equivariant network. Moreover, we show that our model can serve as an unsupervised feature extractor to estimate the binding affinity under proper parameterization, which provides an effective way for drug screening. To evaluate our model, we propose a comprehensive framework to evaluate the quality of sampled molecules from different dimensions. Empirical studies show our model could generate molecules with more realistic 3D structures and better affinities towards the protein targets, and improve binding affinity ranking and prediction without retraining.

Heng Xiong, Changrong Guo, Jian Peng et al.

Robotic object packing has broad practical applications in the logistics and automation industry, often formulated by researchers as the online 3D Bin Packing Problem (3D-BPP). However, existing DRL-based methods primarily focus on enhancing performance in limited packing environments while neglecting the ability to generalize across multiple environments characterized by different bin dimensions. To this end, we propose GOPT, a generalizable online 3D Bin Packing approach via Transformer-based deep reinforcement learning (DRL). First, we design a Placement Generator module to yield finite subspaces as placement candidates and the representation of the bin. Second, we propose a Packing Transformer, which fuses the features of the items and bin, to identify the spatial correlation between the item to be packed and available sub-spaces within the bin. Coupling these two components enables GOPT's ability to perform inference on bins of varying dimensions. We conduct extensive experiments and demonstrate that GOPT not only achieves superior performance against the baselines, but also exhibits excellent generalization capabilities. Furthermore, the deployment with a robot showcases the practical applicability of our method in the real world. The source code will be publicly available at https://github.com/Xiong5Heng/GOPT.

Yuanyi Zhong, Haoran Tang, Junkun Chen et al.

Self-supervised contrastive learning is a powerful tool to learn visual representation without labels. Prior work has primarily focused on evaluating the recognition accuracy of various pre-training algorithms, but has overlooked other behavioral aspects. In addition to accuracy, distributional robustness plays a critical role in the reliability of machine learning models. We design and conduct a series of robustness tests to quantify the behavioral differences between contrastive learning and supervised learning to downstream or pre-training data distribution changes. These tests leverage data corruptions at multiple levels, ranging from pixel-level gamma distortion to patch-level shuffling and to dataset-level distribution shift. Our tests unveil intriguing robustness behaviors of contrastive and supervised learning. On the one hand, under downstream corruptions, we generally observe that contrastive learning is surprisingly more robust than supervised learning. On the other hand, under pre-training corruptions, we find contrastive learning vulnerable to patch shuffling and pixel intensity change, yet less sensitive to dataset-level distribution change. We attempt to explain these results through the role of data augmentation and feature space properties. Our insight has implications in improving the downstream robustness of supervised learning.

Dejun Lin, Simon Chu, Vishanth Iyer et al.

Understanding cellular machinery requires atomic-scale reconstruction of large biomolecular assemblies. However, predicting the structures of these systems has been constrained by hardware memory requirements of models like AlphaFold 3, imposing a practical ceiling of a few thousand residues that can be processed on a single GPU. Here we present NVIDIA BioNeMo Fold-CP, a context parallelism framework that overcomes this barrier by distributing the inference and training pipelines of co-folding models across multiple GPUs. We use the Boltz models as open source reference architectures and implement custom multidimensional primitives that efficiently parallelize both the dense triangular updates and the irregular, data-dependent pattern of window-batched local attention. Our approach achieves efficient memory scaling; for an N-token input distributed across P GPUs, per-device memory scales as $O(N^2/P)$, enabling the structure prediction of assemblies exceeding 30,000 residues on 64 NVIDIA B300 GPUs. We demonstrate the scientific utility of this approach through successful developer use cases: Fold-CP enabled the scoring of over 90% of Comprehensive Resource of Mammalian protein complexes (CORUM) database, as well as folding of disease-relevant PI4KA lipid kinase complex bound to an intrinsically disordered region without cropping. By providing a scalable pathway for modeling massive systems with full global context, Fold-CP represents a significant step toward the realization of a virtual cell.

Zhizhou Ren, Anji Liu, Yitao Liang et al.

Learning new task-specific skills from a few trials is a fundamental challenge for artificial intelligence. Meta reinforcement learning (meta-RL) tackles this problem by learning transferable policies that support few-shot adaptation to unseen tasks. Despite recent advances in meta-RL, most existing methods require the access to the environmental reward function of new tasks to infer the task objective, which is not realistic in many practical applications. To bridge this gap, we study the problem of few-shot adaptation in the context of human-in-the-loop reinforcement learning. We develop a meta-RL algorithm that enables fast policy adaptation with preference-based feedback. The agent can adapt to new tasks by querying human's preference between behavior trajectories instead of using per-step numeric rewards. By extending techniques from information theory, our approach can design query sequences to maximize the information gain from human interactions while tolerating the inherent error of non-expert human oracle. In experiments, we extensively evaluate our method, Adaptation with Noisy OracLE (ANOLE), on a variety of meta-RL benchmark tasks and demonstrate substantial improvement over baseline algorithms in terms of both feedback efficiency and error tolerance.

Tanmay Gangwani, Yuan Zhou, Jian Peng

Learning to perform tasks by leveraging a dataset of expert observations, also known as imitation learning from observations (ILO), is an important paradigm for learning skills without access to the expert reward function or the expert actions. We consider ILO in the setting where the expert and the learner agents operate in different environments, with the source of the discrepancy being the transition dynamics model. Recent methods for scalable ILO utilize adversarial learning to match the state-transition distributions of the expert and the learner, an approach that becomes challenging when the dynamics are dissimilar. In this work, we propose an algorithm that trains an intermediary policy in the learner environment and uses it as a surrogate expert for the learner. The intermediary policy is learned such that the state transitions generated by it are close to the state transitions in the expert dataset. To derive a practical and scalable algorithm, we employ concepts from prior work on estimating the support of a probability distribution. Experiments using MuJoCo locomotion tasks highlight that our method compares favorably to the baselines for ILO with transition dynamics mismatch.

Daniel D Kim, Rajat S Chandra, Jian Peng et al.

Deep learning models have demonstrated great potential in medical 3D imaging, but their development is limited by the expensive, large volume of annotated data required. Active learning (AL) addresses this by training a model on a subset of the most informative data samples without compromising performance. We compared different AL strategies and propose a framework that minimizes the amount of data needed for state-of-the-art performance. 638 multi-institutional brain tumor MRI images were used to train a 3D U-net model and compare AL strategies. We investigated uncertainty sampling, annotation redundancy restriction, and initial dataset selection techniques. Uncertainty estimation techniques including Bayesian estimation with dropout, bootstrapping, and margins sampling were compared to random query. Strategies to avoid annotation redundancy by removing similar images within the to-be-annotated subset were considered as well. We determined the minimum amount of data necessary to achieve similar performance to the model trained on the full dataset (α = 0.1). A variance-based selection strategy using radiomics to identify the initial training dataset is also proposed. Bayesian approximation with dropout at training and testing showed similar results to that of the full data model with less than 20% of the training data (p=0.293) compared to random query achieving similar performance at 56.5% of the training data (p=0.814). Annotation redundancy restriction techniques achieved state-of-the-art performance at approximately 40%-50% of the training data. Radiomics dataset initialization had higher Dice with initial dataset sizes of 20 and 80 images, but improvements were not significant. In conclusion, we investigated various AL strategies with dropout uncertainty estimation achieving state-of-the-art performance with the least annotated data.

Julong Young, Junhui Chen, Feihu Huang et al.

Transformers have demonstrated impressive strength in long-term series forecasting. Existing prediction research mostly focused on mapping past short sub-series (lookback window) to future series (forecast window). The longer training dataset time series will be discarded, once training is completed. Models can merely rely on lookback window information for inference, which impedes models from analyzing time series from a global perspective. And these windows used by Transformers are quite narrow because they must model each time-step therein. Under this point-wise processing style, broadening windows will rapidly exhaust their model capacity. This, for fine-grained time series, leads to a bottleneck in information input and prediction output, which is mortal to long-term series forecasting. To overcome the barrier, we propose a brand-new methodology to utilize Transformer for time series forecasting. Specifically, we split time series into patches by day and reform point-wise to patch-wise processing, which considerably enhances the information input and output of Transformers. To further help models leverage the whole training set's global information during inference, we distill the information, store it in time representations, and replace series with time representations as the main modeling entities. Our designed time-modeling Transformer -- Dateformer yields state-of-the-art accuracy on 7 real-world datasets with a 33.6\% relative improvement and extends the maximum forecast range to half-year.

Jiaqi Guan, Xiangxin Zhou, Yuwei Yang et al.

Designing 3D ligands within a target binding site is a fundamental task in drug discovery. Existing structured-based drug design methods treat all ligand atoms equally, which ignores different roles of atoms in the ligand for drug design and can be less efficient for exploring the large drug-like molecule space. In this paper, inspired by the convention in pharmaceutical practice, we decompose the ligand molecule into two parts, namely arms and scaffold, and propose a new diffusion model, DecompDiff, with decomposed priors over arms and scaffold. In order to facilitate the decomposed generation and improve the properties of the generated molecules, we incorporate both bond diffusion in the model and additional validity guidance in the sampling phase. Extensive experiments on CrossDocked2020 show that our approach achieves state-of-the-art performance in generating high-affinity molecules while maintaining proper molecular properties and conformational stability, with up to -8.39 Avg. Vina Dock score and 24.5 Success Rate. The code is provided at https://github.com/bytedance/DecompDiff

Ruidong Wu, Ruihan Guo, Rui Wang et al.

Despite the striking success of general protein folding models such as AlphaFold2(AF2, Jumper et al. (2021)), the accurate computational modeling of antibody-antigen complexes remains a challenging task. In this paper, we first analyze AF2's primary loss function, known as the Frame Aligned Point Error (FAPE), and raise a previously overlooked issue that FAPE tends to face gradient vanishing problem on high-rotational-error targets. To address this fundamental limitation, we propose a novel geodesic loss called Frame Aligned Frame Error (FAFE, denoted as F2E to distinguish from FAPE), which enables the model to better optimize both the rotational and translational errors between two frames. We then prove that F2E can be reformulated as a group-aware geodesic loss, which translates the optimization of the residue-to-residue error to optimizing group-to-group geodesic frame distance. By fine-tuning AF2 with our proposed new loss function, we attain a correct rate of 52.3\% (DockQ $>$ 0.23) on an evaluation set and 43.8\% correct rate on a subset with low homology, with substantial improvement over AF2 by 182\% and 100\% respectively.

Chaoran Cheng, Jian Peng

We propose a general architecture that combines the coefficient learning scheme with a residual operator layer for learning mappings between continuous functions in the 3D Euclidean space. Our proposed model is guaranteed to achieve SE(3)-equivariance by design. From the graph spectrum view, our method can be interpreted as convolution on graphons (dense graphs with infinitely many nodes), which we term InfGCN. By leveraging both the continuous graphon structure and the discrete graph structure of the input data, our model can effectively capture the geometric information while preserving equivariance. Through extensive experiments on large-scale electron density datasets, we observed that our model significantly outperformed the current state-of-the-art architectures. Multiple ablation studies were also carried out to demonstrate the effectiveness of the proposed architecture.

Mingxuan Jia, Wen Huang, Weixin Zhao et al.

How to synthesize a dataset while achieving differential privacy for AI model training is a meaningful but challenging problem. To address this problem, state-of-the-art methods first select original private dataset's multiple low-dimensional distributions that have the potential to approximate the distribution of original private dataset with high precision, and then synthesize a dataset obeying all selected low-dimensional distributions as the synthetic dataset. However, it is difficult to select suitable low-dimensional distributions, which in turn degrades the data utility of resulting synthetic dataset. To improve differentially private dataset synthesis, we propose to train a differentially private AI model for downstream tasks on the original private dataset and utilize the trained model to synthesize datasets. In particular, on the one hand, the AI model satisfies differential privacy so no matter how to use the model does not disclose private information of original private dataset. On the other hand, the AI model is trained to complete the downstream task so the AI model preserves critical information for completing downstream tasks. We utilize the AI model to synthesize datasets to achieve the goal of improving data utility while preserving privacy. Empirical evaluations on four benchmark datasets demonstrate that our proposed DPDSyn consistently outperforms eight state-of-the-art baselines with a maximum improvement of 2.40x in accuracy and 333.73x in synthesis efficiency. Further experiments also validate that DPDSyn has strong scalability across varying data scales.

Wei Shen, Jiangbo Pei, Yi Peng et al.

We introduce Skywork-R1V3, an advanced, open-source vision-language model (VLM) that pioneers a new approach to visual reasoning. Its key innovation lies in effectively transferring reasoning skills from text-only Large Language Models (LLMs) to visual tasks. The strong performance of Skywork-R1V3 primarily stems from our elaborate post-training RL framework, which effectively activates and enhances the model's reasoning ability, without the need for additional continue pre-training. Through this framework, we further uncover the fundamental role of the connector module in achieving robust cross-modal alignment for multimodal reasoning models. In addition, we introduce a unique indicator of reasoning capability, the entropy of critical reasoning tokens, which has proven highly effective for checkpoint selection during RL training. Skywork-R1V3 achieves state-of-the-art results on MMMU, significantly improving from 64.3% to 76.0%. This performance matches entry-level human capabilities. Remarkably, our RL-powered post-training approach enables even the 38B parameter model to rival top closed-source VLMs. The implementation successfully transfers mathematical reasoning to other subject-related reasoning tasks. We also include an analysis of curriculum learning and reinforcement finetuning strategies, along with a broader discussion on multimodal reasoning. Skywork-R1V3 represents a significant leap in multimodal reasoning, showcasing RL as a powerful engine for advancing open-source VLM capabilities.

Jiahan Li, Tong Chen, Shitong Luo et al.

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 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. Source code will be available at https://github.com/Ced3-han/PepHAR.

Jiahan Li, Shitong Luo, Congyue Deng et al.

By folding into particular 3D structures, proteins play a key role in living beings. To learn meaningful representation from a protein structure for downstream tasks, not only the global backbone topology but the local fine-grained orientational relations between amino acids should also be considered. In this work, we propose the Orientation-Aware Graph Neural Networks (OAGNNs) to better sense the geometric characteristics in protein structure (e.g. inner-residue torsion angles, inter-residue orientations). Extending a single weight from a scalar to a 3D vector, we construct a rich set of geometric-meaningful operations to process both the classical and SO(3) representations of a given structure. To plug our designed perceptron unit into existing Graph Neural Networks, we further introduce an equivariant message passing paradigm, showing superior versatility in maintaining SO(3)-equivariance at the global scale. Experiments have shown that our OAGNNs have a remarkable ability to sense geometric orientational features compared to classical networks. OAGNNs have also achieved state-of-the-art performance on various computational biology applications related to protein 3D structures. The code is available at https://github.com/Ced3-han/OAGNN/tree/main.

Yuanyi Zhong, Jianfeng Wang, Jian Peng et al.

In this paper, we propose an effective knowledge transfer framework to boost the weakly supervised object detection accuracy with the help of an external fully-annotated source dataset, whose categories may not overlap with the target domain. This setting is of great practical value due to the existence of many off-the-shelf detection datasets. To more effectively utilize the source dataset, we propose to iteratively transfer the knowledge from the source domain by a one-class universal detector and learn the target-domain detector. The box-level pseudo ground truths mined by the target-domain detector in each iteration effectively improve the one-class universal detector. Therefore, the knowledge in the source dataset is more thoroughly exploited and leveraged. Extensive experiments are conducted with Pascal VOC 2007 as the target weakly-annotated dataset and COCO/ImageNet as the source fully-annotated dataset. With the proposed solution, we achieved an mAP of $59.7\%$ detection performance on the VOC test set and an mAP of $60.2\%$ after retraining a fully supervised Faster RCNN with the mined pseudo ground truths. This is significantly better than any previously known results in related literature and sets a new state-of-the-art of weakly supervised object detection under the knowledge transfer setting. Code: \url{https://github.com/mikuhatsune/wsod_transfer}.

Jie Chen, Ziyang Yuan, Jian Peng et al.

Change detection is a basic task of remote sensing image processing. The research objective is to identity the change information of interest and filter out the irrelevant change information as interference factors. Recently, the rise of deep learning has provided new tools for change detection, which have yielded impressive results. However, the available methods focus mainly on the difference information between multitemporal remote sensing images and lack robustness to pseudo-change information. To overcome the lack of resistance of current methods to pseudo-changes, in this paper, we propose a new method, namely, dual attentive fully convolutional Siamese networks (DASNet) for change detection in high-resolution images. Through the dual-attention mechanism, long-range dependencies are captured to obtain more discriminant feature representations to enhance the recognition performance of the model. Moreover, the imbalanced sample is a serious problem in change detection, i.e. unchanged samples are much more than changed samples, which is one of the main reasons resulting in pseudo-changes. We put forward the weighted double margin contrastive loss to address this problem by punishing the attention to unchanged feature pairs and increase attention to changed feature pairs. The experimental results of our method on the change detection dataset (CDD) and the building change detection dataset (BCDD) demonstrate that compared with other baseline methods, the proposed method realizes maximum improvements of 2.1\% and 3.6\%, respectively, in the F1 score. Our Pytorch implementation is available at https://github.com/lehaifeng/DASNet.

Jian Peng, Bo Tang, Hao Jiang et al.

Artificial neural networks face the well-known problem of catastrophic forgetting. What's worse, the degradation of previously learned skills becomes more severe as the task sequence increases, known as the long-term catastrophic forgetting. It is due to two facts: first, as the model learns more tasks, the intersection of the low-error parameter subspace satisfying for these tasks becomes smaller or even does not exist; second, when the model learns a new task, the cumulative error keeps increasing as the model tries to protect the parameter configuration of previous tasks from interference. Inspired by the memory consolidation mechanism in mammalian brains with synaptic plasticity, we propose a confrontation mechanism in which Adversarial Neural Pruning and synaptic Consolidation (ANPyC) is used to overcome the long-term catastrophic forgetting issue. The neural pruning acts as long-term depression to prune task-irrelevant parameters, while the novel synaptic consolidation acts as long-term potentiation to strengthen task-relevant parameters. During the training, this confrontation achieves a balance in that only crucial parameters remain, and non-significant parameters are freed to learn subsequent tasks. ANPyC avoids forgetting important information and makes the model efficient to learn a large number of tasks. Specifically, the neural pruning iteratively relaxes the current task's parameter conditions to expand the common parameter subspace of the task; the synaptic consolidation strategy, which consists of a structure-aware parameter-importance measurement and an element-wise parameter updating strategy, decreases the cumulative error when learning new tasks. The full source code is available at https://github.com/GeoX-Lab/ANPyC.

Jian Peng, Jiang Hao, Zhuo Li et al.

Catastrophic forgetting is a challenge issue in continual learning when a deep neural network forgets the knowledge acquired from the former task after learning on subsequent tasks. However, existing methods try to find the joint distribution of parameters shared with all tasks. This idea can be questionable because this joint distribution may not present when the number of tasks increase. On the other hand, It also leads to "long-term" memory issue when the network capacity is limited since adding tasks will "eat" the network capacity. In this paper, we proposed a Soft Parameters Pruning (SPP) strategy to reach the trade-off between short-term and long-term profit of a learning model by freeing those parameters less contributing to remember former task domain knowledge to learn future tasks, and preserving memories about previous tasks via those parameters effectively encoding knowledge about tasks at the same time. The SPP also measures the importance of parameters by information entropy in a label free manner. The experiments on several tasks shows SPP model achieved the best performance compared with others state-of-the-art methods. Experiment results also indicate that our method is less sensitive to hyper-parameter and better generalization. Our research suggests that a softer strategy, i.e. approximate optimize or sub-optimal solution, will benefit alleviating the dilemma of memory. The source codes are available at https://github.com/lehaifeng/Learning_by_memory.

Jiaqi Guan, Jiahan Li, Xiangxin Zhou et al.

Molecular docking is a key task in computational biology that has attracted increasing interest from the machine learning community. While existing methods have achieved success, they generally treat each protein-ligand pair in isolation. Inspired by the biochemical observation that ligands binding to the same target protein tend to adopt similar poses, we propose \textsc{GroupBind}, a novel molecular docking framework that simultaneously considers multiple ligands docking to a protein. This is achieved by introducing an interaction layer for the group of ligands and a triangle attention module for embedding protein-ligand and group-ligand pairs. By integrating our approach with diffusion-based docking model, we set a new S performance on the PDBBind blind docking benchmark, demonstrating the effectiveness of our proposed molecular docking paradigm.

Yipu Zhang, Jiawei Liang, Jian Peng et al.

Neural rendering has gained prominence for its high-quality output, which is crucial for AR/VR applications. However, its large voxel grid data size and irregular access patterns challenge real-time processing on edge devices. While previous works have focused on improving data locality, they have not adequately addressed the issue of large voxel grid sizes, which necessitate frequent off-chip memory access and substantial on-chip memory. This paper introduces SpNeRF, a software-hardware co-design solution tailored for sparse volumetric neural rendering. We first identify memory-bound rendering inefficiencies and analyze the inherent sparsity in the voxel grid data of neural rendering. To enhance efficiency, we propose novel preprocessing and online decoding steps, reducing the memory size for voxel grid. The preprocessing step employs hash mapping to support irregular data access while maintaining a minimal memory size. The online decoding step enables efficient on-chip sparse voxel grid processing, incorporating bitmap masking to mitigate PSNR loss caused by hash collisions. To further optimize performance, we design a dedicated hardware architecture supporting our sparse voxel grid processing technique. Experimental results demonstrate that SpNeRF achieves an average 21.07$\times$ reduction in memory size while maintaining comparable PSNR levels. When benchmarked against Jetson XNX, Jetson ONX, RT-NeRF.Edge and NeuRex.Edge, our design achieves speedups of 95.1$\times$, 63.5$\times$, 1.5$\times$ and 10.3$\times$, and improves energy efficiency by 625.6$\times$, 529.1$\times$, 4$\times$, and 4.4$\times$, respectively.

Mohamed Youssef, Jian Peng, Oliver Bimber

Access to below-canopy volumetric vegetation data is crucial for understanding ecosystem dynamics. We address the long-standing limitation of remote sensing to penetrate deep into dense canopy layers. LiDAR and radar are currently considered the primary options for measuring 3D vegetation structures, while cameras can only extract the reflectance and depth of top layers. Using conventional, high-resolution aerial images, our approach allows sensing deep into self-occluding vegetation volumes, such as forests. It is similar in spirit to the imaging process of wide-field microscopy, but can handle much larger scales and strong occlusion. We scan focal stacks by synthetic-aperture imaging with drones and reduce out-of-focus signal contributions using pre-trained 3D convolutional neural networks with mean squared error (MSE) as the loss function. The resulting volumetric reflectance stacks contain low-frequency representations of the vegetation volume. Combining multiple reflectance stacks from various spectral channels provides insights into plant health, growth, and environmental conditions throughout the entire vegetation volume. Compared with simulated ground truth, our correction leads to ~x7 average improvements (min: ~x2, max: ~x12) for forest densities of 220 trees/ha - 1680 trees/ha. In our field experiment, we achieved an MSE of 0.05 when comparing with the top-vegetation layer that was measured with classical multispectral aerial imaging.

Xiaobo Zhang, Congqing He, Ying He et al.

Named Entity Recognition (NER) is a fundamental task in natural language processing. It remains a research hotspot due to its wide applicability across domains. Although recent advances in deep learning have significantly improved NER performance, they rely heavily on large, high-quality annotated datasets. However, building these datasets is expensive and time-consuming, posing a major bottleneck for further research. Current dataset merging approaches mainly focus on strategies like manual label mapping or constructing label graphs, which lack interpretability and scalability. To address this, we propose an automatic label alignment method based on label similarity. The method combines empirical and semantic similarities, using a greedy pairwise merging strategy to unify label spaces across different datasets. Experiments are conducted in two stages: first, merging three existing NER datasets into a unified corpus with minimal impact on NER performance; second, integrating this corpus with a small-scale, self-built dataset in the financial domain. The results show that our method enables effective dataset merging and enhances NER performance in the low-resource financial domain. This study presents an efficient, interpretable, and scalable solution for integrating multi-source NER corpora.

Yifan Jiang, Yibo Xue, Yukun Kang et al.

Slide animations, such as fade-in, fly-in, and wipe, are critical for audience engagement, efficient information delivery, and vivid visual expression. However, most AI-driven slide-generation tools still lack native animation support, and existing vision-language models (VLMs) struggle with animation tasks due to the absence of public datasets and limited temporal-reasoning capabilities. To address this gap, we release the first public dataset for slide-animation modeling: 12,000 triplets of natural-language descriptions, animation JSON files, and rendered videos, collectively covering every built-in PowerPoint effect. Using this resource, we fine-tune Qwen-2.5-VL-7B with Low-Rank Adaptation (LoRA) and achieve consistent improvements over GPT-4.1 and Gemini-2.5-Pro in BLEU-4, ROUGE-L, SPICE, and our Coverage-Order-Detail Assessment (CODA) metric, which evaluates action coverage, temporal order, and detail fidelity. On a manually created test set of slides, the LoRA model increases BLEU-4 by around 60%, ROUGE-L by 30%, and shows significant improvements in CODA-detail. This demonstrates that low-rank adaptation enables reliable temporal reasoning and generalization beyond synthetic data. Overall, our dataset, LoRA-enhanced model, and CODA metric provide a rigorous benchmark and foundation for future research on VLM-based dynamic slide generation.

Jiahan Li, Chaoran Cheng, Zuofan Wu et al.

Peptides, short chains of amino acid residues, play a vital role in numerous biological processes by interacting with other target molecules, offering substantial potential in drug discovery. In this work, we present PepFlow, the first multi-modal deep generative model grounded in the flow-matching framework for the design of full-atom peptides that target specific protein receptors. Drawing inspiration from the crucial roles of residue backbone orientations and side-chain dynamics in protein-peptide interactions, we characterize the peptide structure using rigid backbone frames within the $\mathrm{SE}(3)$ manifold and side-chain angles on high-dimensional tori. Furthermore, we represent discrete residue types in the peptide sequence as categorical distributions on the probability simplex. By learning the joint distributions of each modality using derived flows and vector fields on corresponding manifolds, our method excels in the fine-grained design of full-atom peptides. Harnessing the multi-modal paradigm, our approach adeptly tackles various tasks such as fix-backbone sequence design and side-chain packing through partial sampling. Through meticulously crafted experiments, we demonstrate that PepFlow exhibits superior performance in comprehensive benchmarks, highlighting its significant potential in computational peptide design and analysis.

Jian Peng, Dingqi Ye, Bo Tang et al.

Learning from a sequence of tasks for a lifetime is essential for an agent towards artificial general intelligence. This requires the agent to continuously learn and memorize new knowledge without interference. This paper first demonstrates a fundamental issue of lifelong learning using neural networks, named anterograde forgetting, i.e., preserving and transferring memory may inhibit the learning of new knowledge. This is attributed to the fact that the learning capacity of a neural network will be reduced as it keeps memorizing historical knowledge, and the fact that conceptual confusion may occur as it transfers irrelevant old knowledge to the current task. This work proposes a general framework named Cycled Memory Networks (CMN) to address the anterograde forgetting in neural networks for lifelong learning. The CMN consists of two individual memory networks to store short-term and long-term memories to avoid capacity shrinkage. A transfer cell is designed to connect these two memory networks, enabling knowledge transfer from the long-term memory network to the short-term memory network to mitigate the conceptual confusion, and a memory consolidation mechanism is developed to integrate short-term knowledge into the long-term memory network for knowledge accumulation. Experimental results demonstrate that the CMN can effectively address the anterograde forgetting on several task-related, task-conflict, class-incremental and cross-domain benchmarks.

Zhizhou Ren, Ruihan Guo, Yuan Zhou et al.

Many practical applications of reinforcement learning require agents to learn from sparse and delayed rewards. It challenges the ability of agents to attribute their actions to future outcomes. In this paper, we consider the problem formulation of episodic reinforcement learning with trajectory feedback. It refers to an extreme delay of reward signals, in which the agent can only obtain one reward signal at the end of each trajectory. A popular paradigm for this problem setting is learning with a designed auxiliary dense reward function, namely proxy reward, instead of sparse environmental signals. Based on this framework, this paper proposes a novel reward redistribution algorithm, randomized return decomposition (RRD), to learn a proxy reward function for episodic reinforcement learning. We establish a surrogate problem by Monte-Carlo sampling that scales up least-squares-based reward redistribution to long-horizon problems. We analyze our surrogate loss function by connection with existing methods in the literature, which illustrates the algorithmic properties of our approach. In experiments, we extensively evaluate our proposed method on a variety of benchmark tasks with episodic rewards and demonstrate substantial improvement over baseline algorithms.

Yifan Chang, Wenbo Li, Jian Peng et al.

Humans' continual learning (CL) ability is closely related to Stability Versus Plasticity Dilemma that describes how humans achieve ongoing learning capacity and preservation for learned information. The notion of CL has always been present in artificial intelligence (AI) since its births. This paper proposes a comprehensive review of CL. Different from previous reviews that mainly focus on the catastrophic forgetting phenomenon in CL, this paper surveys CL from a more macroscopic perspective based on the Stability Versus Plasticity mechanism. Analogous to biological counterpart, "smart" AI agents are supposed to i) remember previously learned information (information retrospection); ii) infer on new information continuously (information prospection:); iii) transfer useful information (information transfer), to achieve high-level CL. According to the taxonomy, evaluation metrics, algorithms, applications as well as some open issues are then introduced. Our main contributions concern i) rechecking CL from the level of artificial general intelligence; ii) providing a detailed and extensive overview on CL topics; iii) presenting some novel ideas on the potential development of CL.

Jian Peng, Xian Sun, Min Deng et al.

Remembering and forgetting mechanisms are two sides of the same coin in a human learning-memory system. Inspired by human brain memory mechanisms, modern machine learning systems have been working to endow machine with lifelong learning capability through better remembering while pushing the forgetting as the antagonist to overcome. Nevertheless, this idea might only see the half picture. Up until very recently, increasing researchers argue that a brain is born to forget, i.e., forgetting is a natural and active process for abstract, rich, and flexible representations. This paper presents a learning model by active forgetting mechanism with artificial neural networks. The active forgetting mechanism (AFM) is introduced to a neural network via a "plug-and-play" forgetting layer (P\&PF), consisting of groups of inhibitory neurons with Internal Regulation Strategy (IRS) to adjust the extinction rate of themselves via lateral inhibition mechanism and External Regulation Strategy (ERS) to adjust the extinction rate of excitatory neurons via inhibition mechanism. Experimental studies have shown that the P\&PF offers surprising benefits: self-adaptive structure, strong generalization, long-term learning and memory, and robustness to data and parameter perturbation. This work sheds light on the importance of forgetting in the learning process and offers new perspectives to understand the underlying mechanisms of neural networks.

Michael Wan, Jian Peng, Tanmay Gangwani

Meta-reinforcement learning (meta-RL) algorithms allow for agents to learn new behaviors from small amounts of experience, mitigating the sample inefficiency problem in RL. However, while meta-RL agents can adapt quickly to new tasks at test time after experiencing only a few trajectories, the meta-training process is still sample-inefficient. Prior works have found that in the multi-task RL setting, relabeling past transitions and thus sharing experience among tasks can improve sample efficiency and asymptotic performance. We apply this idea to the meta-RL setting and devise a new relabeling method called Hindsight Foresight Relabeling (HFR). We construct a relabeling distribution using the combination of "hindsight", which is used to relabel trajectories using reward functions from the training task distribution, and "foresight", which takes the relabeled trajectories and computes the utility of each trajectory for each task. HFR is easy to implement and readily compatible with existing meta-RL algorithms. We find that HFR improves performance when compared to other relabeling methods on a variety of meta-RL tasks.

Yuanyi Zhong, Bodi Yuan, Hong Wu et al.

We present a novel semi-supervised semantic segmentation method which jointly achieves two desiderata of segmentation model regularities: the label-space consistency property between image augmentations and the feature-space contrastive property among different pixels. We leverage the pixel-level L2 loss and the pixel contrastive loss for the two purposes respectively. To address the computational efficiency issue and the false negative noise issue involved in the pixel contrastive loss, we further introduce and investigate several negative sampling techniques. Extensive experiments demonstrate the state-of-the-art performance of our method (PC2Seg) with the DeepLab-v3+ architecture, in several challenging semi-supervised settings derived from the VOC, Cityscapes, and COCO datasets.

Yuanyi Zhong, Yuan Zhou, Jian Peng

The control variates (CV) method is widely used in policy gradient estimation to reduce the variance of the gradient estimators in practice. A control variate is applied by subtracting a baseline function from the state-action value estimates. Then the variance-reduced policy gradient presumably leads to higher learning efficiency. Recent research on control variates with deep neural net policies mainly focuses on scalar-valued baseline functions. The effect of vector-valued baselines is under-explored. This paper investigates variance reduction with coordinate-wise and layer-wise control variates constructed from vector-valued baselines for neural net policies. We present experimental evidence suggesting that lower variance can be obtained with such baselines than with the conventional scalar-valued baseline. We demonstrate how to equip the popular Proximal Policy Optimization (PPO) algorithm with these new control variates. We show that the resulting algorithm with proper regularization can achieve higher sample efficiency than scalar control variates in continuous control benchmarks.

Beining Han, Zhizhou Ren, Zuofan Wu et al.

We study deep reinforcement learning (RL) algorithms with delayed rewards. In many real-world tasks, instant rewards are often not readily accessible or even defined immediately after the agent performs actions. In this work, we first formally define the environment with delayed rewards and discuss the challenges raised due to the non-Markovian nature of such environments. Then, we introduce a general off-policy RL framework with a new Q-function formulation that can handle the delayed rewards with theoretical convergence guarantees. For practical tasks with high dimensional state spaces, we further introduce the HC-decomposition rule of the Q-function in our framework which naturally leads to an approximation scheme that helps boost the training efficiency and stability. We finally conduct extensive experiments to demonstrate the superior performance of our algorithms over the existing work and their variants.

Yuanyi Zhong, Jianfeng Wang, Lijuan Wang et al.

This paper presents a detection-aware pre-training (DAP) approach, which leverages only weakly-labeled classification-style datasets (e.g., ImageNet) for pre-training, but is specifically tailored to benefit object detection tasks. In contrast to the widely used image classification-based pre-training (e.g., on ImageNet), which does not include any location-related training tasks, we transform a classification dataset into a detection dataset through a weakly supervised object localization method based on Class Activation Maps to directly pre-train a detector, making the pre-trained model location-aware and capable of predicting bounding boxes. We show that DAP can outperform the traditional classification pre-training in terms of both sample efficiency and convergence speed in downstream detection tasks including VOC and COCO. In particular, DAP boosts the detection accuracy by a large margin when the number of examples in the downstream task is small.

Minkai Xu, Shitong Luo, Yoshua Bengio et al.

We study how to generate molecule conformations (i.e., 3D structures) from a molecular graph. Traditional methods, such as molecular dynamics, sample conformations via computationally expensive simulations. Recently, machine learning methods have shown great potential by training on a large collection of conformation data. Challenges arise from the limited model capacity for capturing complex distributions of conformations and the difficulty in modeling long-range dependencies between atoms. Inspired by the recent progress in deep generative models, in this paper, we propose a novel probabilistic framework to generate valid and diverse conformations given a molecular graph. We propose a method combining the advantages of both flow-based and energy-based models, enjoying: (1) a high model capacity to estimate the multimodal conformation distribution; (2) explicitly capturing the complex long-range dependencies between atoms in the observation space. Extensive experiments demonstrate the superior performance of the proposed method on several benchmarks, including conformation generation and distance modeling tasks, with a significant improvement over existing generative models for molecular conformation sampling.

Tanmay Gangwani, Jian Peng, Yuan Zhou

Quality-Diversity (QD) is a concept from Neuroevolution with some intriguing applications to Reinforcement Learning. It facilitates learning a population of agents where each member is optimized to simultaneously accumulate high task-returns and exhibit behavioral diversity compared to other members. In this paper, we build on a recent kernel-based method for training a QD policy ensemble with Stein variational gradient descent. With kernels based on $f$-divergence between the stationary distributions of policies, we convert the problem to that of efficient estimation of the ratio of these stationary distributions. We then study various distribution ratio estimators used previously for off-policy evaluation and imitation and re-purpose them to compute the gradients for policies in an ensemble such that the resultant population is diverse and of high-quality.

Ziyang Tang, Yihao Feng, Na Zhang et al.

Off-policy evaluation provides an essential tool for evaluating the effects of different policies or treatments using only observed data. When applied to high-stakes scenarios such as medical diagnosis or financial decision-making, it is crucial to provide provably correct upper and lower bounds of the expected reward, not just a classical single point estimate, to the end-users, as executing a poor policy can be very costly. In this work, we propose a provably correct method for obtaining interval bounds for off-policy evaluation in a general continuous setting. The idea is to search for the maximum and minimum values of the expected reward among all the Lipschitz Q-functions that are consistent with the observations, which amounts to solving a constrained optimization problem on a Lipschitz function space. We go on to introduce a Lipschitz value iteration method to monotonically tighten the interval, which is simple yet efficient and provably convergent. We demonstrate the practical efficiency of our method on a range of benchmarks.

Tanmay Gangwani, Yuan Zhou, Jian Peng

Long-term temporal credit assignment is an important challenge in deep reinforcement learning (RL). It refers to the ability of the agent to attribute actions to consequences that may occur after a long time interval. Existing policy-gradient and Q-learning algorithms typically rely on dense environmental rewards that provide rich short-term supervision and help with credit assignment. However, they struggle to solve tasks with delays between an action and the corresponding rewarding feedback. To make credit assignment easier, recent works have proposed algorithms to learn dense "guidance" rewards that could be used in place of the sparse or delayed environmental rewards. This paper is in the same vein -- starting with a surrogate RL objective that involves smoothing in the trajectory-space, we arrive at a new algorithm for learning guidance rewards. We show that the guidance rewards have an intuitive interpretation, and can be obtained without training any additional neural networks. Due to the ease of integration, we use the guidance rewards in a few popular algorithms (Q-learning, Actor-Critic, Distributional-RL) and present results in single-agent and multi-agent tasks that elucidate the benefit of our approach when the environmental rewards are sparse or delayed.

Yuanyi Zhong, Yuan Zhou, Jian Peng

Reinforcement learning from self-play has recently reported many successes. Self-play, where the agents compete with themselves, is often used to generate training data for iterative policy improvement. In previous work, heuristic rules are designed to choose an opponent for the current learner. Typical rules include choosing the latest agent, the best agent, or a random historical agent. However, these rules may be inefficient in practice and sometimes do not guarantee convergence even in the simplest matrix games. In this paper, we propose a new algorithmic framework for competitive self-play reinforcement learning in two-player zero-sum games. We recognize the fact that the Nash equilibrium coincides with the saddle point of the stochastic payoff function, which motivates us to borrow ideas from classical saddle point optimization literature. Our method trains several agents simultaneously, and intelligently takes each other as opponent based on simple adversarial rules derived from a principled perturbation-based saddle optimization method. We prove theoretically that our algorithm converges to an approximate equilibrium with high probability in convex-concave games under standard assumptions. Beyond the theory, we further show the empirical superiority of our method over baseline methods relying on the aforementioned opponent-selection heuristics in matrix games, grid-world soccer, Gomoku, and simulated robot sumo, with neural net policy function approximators.

Xianggen Liu, Yunan Luo, Sen Song et al.

Modeling the effects of mutations on the binding affinity plays a crucial role in protein engineering and drug design. In this study, we develop a novel deep learning based framework, named GraphPPI, to predict the binding affinity changes upon mutations based on the features provided by a graph neural network (GNN). In particular, GraphPPI first employs a well-designed pre-training scheme to enforce the GNN to capture the features that are predictive of the effects of mutations on binding affinity in an unsupervised manner and then integrates these graphical features with gradient-boosting trees to perform the prediction. Experiments showed that, without any annotated signals, GraphPPI can capture meaningful patterns of the protein structures. Also, GraphPPI achieved new state-of-the-art performance in predicting the binding affinity changes upon both single- and multi-point mutations on five benchmark datasets. In-depth analyses also showed GraphPPI can accurately estimate the effects of mutations on the binding affinity between SARS-CoV-2 and its neutralizing antibodies. These results have established GraphPPI as a powerful and useful computational tool in the studies of protein design.

Yi Chen, Jinglin Chen, Jing Dong et al.

Langevin diffusion is a powerful method for nonconvex optimization, which enables the escape from local minima by injecting noise into the gradient. In particular, the temperature parameter controlling the noise level gives rise to a tradeoff between ``global exploration'' and ``local exploitation'', which correspond to high and low temperatures. To attain the advantages of both regimes, we propose to use replica exchange, which swaps between two Langevin diffusions with different temperatures. We theoretically analyze the acceleration effect of replica exchange from two perspectives: (i) the convergence in χ^2-divergence, and (ii) the large deviation principle. Such an acceleration effect allows us to faster approach the global minima. Furthermore, by discretizing the replica exchange Langevin diffusion, we obtain a discrete-time algorithm. For such an algorithm, we quantify its discretization error in theory and demonstrate its acceleration effect in practice.

Michael Wan, Tanmay Gangwani, Jian Peng

Deep reinforcement learning (RL) algorithms have achieved great success on a wide variety of sequential decision-making tasks. However, many of these algorithms suffer from high sample complexity when learning from scratch using environmental rewards, due to issues such as credit-assignment and high-variance gradients, among others. Transfer learning, in which knowledge gained on a source task is applied to more efficiently learn a different but related target task, is a promising approach to improve the sample complexity in RL. Prior work has considered using pre-trained teacher policies to enhance the learning of the student policy, albeit with the constraint that the teacher and the student MDPs share the state-space or the action-space. In this paper, we propose a new framework for transfer learning where the teacher and the student can have arbitrarily different state- and action-spaces. To handle this mismatch, we produce embeddings which can systematically extract knowledge from the teacher policy and value networks, and blend it into the student networks. To train the embeddings, we use a task-aligned loss and show that the representations could be enriched further by adding a mutual information loss. Using a set of challenging simulated robotic locomotion tasks involving many-legged centipedes, we demonstrate successful transfer learning in situations when the teacher and student have different state- and action-spaces.

Jun Han, Fan Ding, Xianglong Liu et al.

Gradient-based approximate inference methods, such as Stein variational gradient descent (SVGD), provide simple and general-purpose inference engines for differentiable continuous distributions. However, existing forms of SVGD cannot be directly applied to discrete distributions. In this work, we fill this gap by proposing a simple yet general framework that transforms discrete distributions to equivalent piecewise continuous distributions, on which the gradient-free SVGD is applied to perform efficient approximate inference. The empirical results show that our method outperforms traditional algorithms such as Gibbs sampling and discontinuous Hamiltonian Monte Carlo on various challenging benchmarks of discrete graphical models. We demonstrate that our method provides a promising tool for learning ensembles of binarized neural network (BNN), outperforming other widely used ensemble methods on learning binarized AlexNet on CIFAR-10 dataset. In addition, such transform can be straightforwardly employed in gradient-free kernelized Stein discrepancy to perform goodness-of-fit (GOF) test on discrete distributions. Our proposed method outperforms existing GOF test methods for intractable discrete distributions.

Tanmay Gangwani, Jian Peng

Imitation Learning (IL) is a popular paradigm for training agents to achieve complicated goals by leveraging expert behavior, rather than dealing with the hardships of designing a correct reward function. With the environment modeled as a Markov Decision Process (MDP), most of the existing IL algorithms are contingent on the availability of expert demonstrations in the same MDP as the one in which a new imitator policy is to be learned. This is uncharacteristic of many real-life scenarios where discrepancies between the expert and the imitator MDPs are common, especially in the transition dynamics function. Furthermore, obtaining expert actions may be costly or infeasible, making the recent trend towards state-only IL (where expert demonstrations constitute only states or observations) ever so promising. Building on recent adversarial imitation approaches that are motivated by the idea of divergence minimization, we present a new state-only IL algorithm in this paper. It divides the overall optimization objective into two subproblems by introducing an indirection step and solves the subproblems iteratively. We show that our algorithm is particularly effective when there is a transition dynamics mismatch between the expert and imitator MDPs, while the baseline IL methods suffer from performance degradation. To analyze this, we construct several interesting MDPs by modifying the configuration parameters for the MuJoCo locomotion tasks from OpenAI Gym.

Yuanyi Zhong, Alexander Schwing, Jian Peng

In many vision-based reinforcement learning (RL) problems, the agent controls a movable object in its visual field, e.g., the player's avatar in video games and the robotic arm in visual grasping and manipulation. Leveraging action-conditioned video prediction, we propose an end-to-end learning framework to disentangle the controllable object from the observation signal. The disentangled representation is shown to be useful for RL as additional observation channels to the agent. Experiments on a set of Atari games with the popular Double DQN algorithm demonstrate improved sample efficiency and game performance (from 222.8% to 261.4% measured in normalized game scores, with prediction bonus reward).