Hang Zheng

Gengmo Zhou, Zhifeng Gao, Zhewei Wei et al. · microsoft-research

Molecular conformation generation (MCG) is a fundamental and important problem in drug discovery. Many traditional methods have been developed to solve the MCG problem, such as systematic searching, model-building, random searching, distance geometry, molecular dynamics, Monte Carlo methods, etc. However, they have some limitations depending on the molecular structures. Recently, there are plenty of deep learning based MCG methods, which claim they largely outperform the traditional methods. However, to our surprise, we design a simple and cheap algorithm (parameter-free) based on the traditional methods and find it is comparable to or even outperforms deep learning based MCG methods in the widely used GEOM-QM9 and GEOM-Drugs benchmarks. In particular, our design algorithm is simply the clustering of the RDKIT-generated conformations. We hope our findings can help the community to revise the deep learning methods for MCG. The code of the proposed algorithm could be found at https://gist.github.com/ZhouGengmo/5b565f51adafcd911c0bc115b2ef027c.

Shuqi Lu, Lin Yao, Xi Chen et al. · microsoft-research

Structure-based drug design, i.e., finding molecules with high affinities to the target protein pocket, is one of the most critical tasks in drug discovery. Traditional solutions, like virtual screening, require exhaustively searching on a large molecular database, which are inefficient and cannot return novel molecules beyond the database. The pocket-based 3D molecular generation model, i.e., directly generating a molecule with a 3D structure and binding position in the pocket, is a new promising way to address this issue. Herein, we propose VD-Gen, a novel pocket-based 3D molecular generation pipeline. VD-Gen consists of several carefully designed stages to generate fine-grained 3D molecules with binding positions in the pocket cavity end-to-end. Rather than directly generating or sampling atoms with 3D positions in the pocket like in early attempts, in VD-Gen, we first randomly initialize many virtual particles in the pocket; then iteratively move these virtual particles, making the distribution of virtual particles approximate the distribution of molecular atoms. After virtual particles are stabilized in 3D space, we extract a 3D molecule from them. Finally, we further refine atoms in the extracted molecule by iterative movement again, to get a high-quality 3D molecule, and predict a confidence score for it. Extensive experiment results on pocket-based molecular generation demonstrate that VD-Gen can generate novel 3D molecules to fill the target pocket cavity with high binding affinities, significantly outperforming previous baselines.

Jun Cen, Shiwei Zhang, Yixuan Pei et al.

2D RGB images and 3D LIDAR point clouds provide complementary knowledge for the perception system of autonomous vehicles. Several 2D and 3D fusion methods have been explored for the LIDAR semantic segmentation task, but they suffer from different problems. 2D-to-3D fusion methods require strictly paired data during inference, which may not be available in real-world scenarios, while 3D-to-2D fusion methods cannot explicitly make full use of the 2D information. Therefore, we propose a Bidirectional Fusion Network with Cross-Modality Knowledge Distillation (CMDFusion) in this work. Our method has two contributions. First, our bidirectional fusion scheme explicitly and implicitly enhances the 3D feature via 2D-to-3D fusion and 3D-to-2D fusion, respectively, which surpasses either one of the single fusion schemes. Second, we distillate the 2D knowledge from a 2D network (Camera branch) to a 3D network (2D knowledge branch) so that the 3D network can generate 2D information even for those points not in the FOV (field of view) of the camera. In this way, RGB images are not required during inference anymore since the 2D knowledge branch provides 2D information according to the 3D LIDAR input. We show that our CMDFusion achieves the best performance among all fusion-based methods on SemanticKITTI and nuScenes datasets. The code will be released at https://github.com/Jun-CEN/CMDFusion.

Yuejiang Yu, Shuqi Lu, Zhifeng Gao et al. · microsoft-research

Molecular docking, given a ligand molecule and a ligand binding site (called ``pocket'') on a protein, predicting the binding mode of the protein-ligand complex, is a widely used technique in drug design. Many deep learning models have been developed for molecular docking, while most existing deep learning models perform docking on the whole protein, rather than on a given pocket as the traditional molecular docking approaches, which does not match common needs. What's more, they claim to perform better than traditional molecular docking, but the approach of comparison is not fair, since traditional methods are not designed for docking on the whole protein without a given pocket. In this paper, we design a series of experiments to examine the actual performance of these deep learning models and traditional methods. For a fair comparison, we decompose the docking on the whole protein into two steps, pocket searching and docking on a given pocket, and build pipelines to evaluate traditional methods and deep learning methods respectively. We find that deep learning models are actually good at pocket searching, but traditional methods are better than deep learning models at docking on given pockets. Overall, our work explicitly reveals some potential problems in current deep learning models for molecular docking and provides several suggestions for future works.

Zhifeng Gao, Xiaohong Ji, Guojiang Zhao et al. · microsoft-research

Recently deep learning based quantitative structure-activity relationship (QSAR) models has shown surpassing performance than traditional methods for property prediction tasks in drug discovery. However, most DL based QSAR models are restricted to limited labeled data to achieve better performance, and also are sensitive to model scale and hyper-parameters. In this paper, we propose Uni-QSAR, a powerful Auto-ML tool for molecule property prediction tasks. Uni-QSAR combines molecular representation learning (MRL) of 1D sequential tokens, 2D topology graphs, and 3D conformers with pretraining models to leverage rich representation from large-scale unlabeled data. Without any manual fine-tuning or model selection, Uni-QSAR outperforms SOTA in 21/22 tasks of the Therapeutic Data Commons (TDC) benchmark under designed parallel workflow, with an average performance improvement of 6.09\%. Furthermore, we demonstrate the practical usefulness of Uni-QSAR in drug discovery domains.

Tengju Ye, Wei Jing, Chunyong Hu et al.

Building a multi-modality multi-task neural network toward accurate and robust performance is a de-facto standard in perception task of autonomous driving. However, leveraging such data from multiple sensors to jointly optimize the prediction and planning tasks remains largely unexplored. In this paper, we present FusionAD, to the best of our knowledge, the first unified framework that fuse the information from two most critical sensors, camera and LiDAR, goes beyond perception task. Concretely, we first build a transformer based multi-modality fusion network to effectively produce fusion based features. In constrast to camera-based end-to-end method UniAD, we then establish a fusion aided modality-aware prediction and status-aware planning modules, dubbed FMSPnP that take advantages of multi-modality features. We conduct extensive experiments on commonly used benchmark nuScenes dataset, our FusionAD achieves state-of-the-art performance and surpassing baselines on average 15% on perception tasks like detection and tracking, 10% on occupancy prediction accuracy, reducing prediction error from 0.708 to 0.389 in ADE score and reduces the collision rate from 0.31% to only 0.12%.

Chunyong Hu, Hang Zheng, Kun Li et al.

Multi-sensor modal fusion has demonstrated strong advantages in 3D object detection tasks. However, existing methods that fuse multi-modal features require transforming features into the bird's eye view space and may lose certain information on Z-axis, thus leading to inferior performance. To this end, we propose a novel end-to-end multi-modal fusion transformer-based framework, dubbed FusionFormer, that incorporates deformable attention and residual structures within the fusion encoding module. Specifically, by developing a uniform sampling strategy, our method can easily sample from 2D image and 3D voxel features spontaneously, thus exploiting flexible adaptability and avoiding explicit transformation to the bird's eye view space during the feature concatenation process. We further implement a residual structure in our feature encoder to ensure the model's robustness in case of missing an input modality. Through extensive experiments on a popular autonomous driving benchmark dataset, nuScenes, our method achieves state-of-the-art single model performance of 72.6% mAP and 75.1% NDS in the 3D object detection task without test time augmentation.

Linfeng Zhang, Siheng Chen, Yuzhu Cai et al.

AI agents are emerging as a practical way to run multi-step scientific workflows that interleave reasoning with tool use and verification, pointing to a shift from isolated AI-assisted steps toward \emph{agentic science at scale}. This shift is increasingly feasible, as scientific tools and models can be invoked through stable interfaces and verified with recorded execution traces, and increasingly necessary, as AI accelerates scientific output and stresses the peer-review and publication pipeline, raising the bar for traceability and credible evaluation. However, scaling agentic science remains difficult: workflows are hard to observe and reproduce; many tools and laboratory systems are not agent-ready; execution is hard to trace and govern; and prototype AI Scientist systems are often bespoke, limiting reuse and systematic improvement from real workflow signals. We argue that scaling agentic science requires an infrastructure-and-ecosystem approach, instantiated in Bohrium+SciMaster. Bohrium acts as a managed, traceable hub for AI4S assets -- akin to a HuggingFace of AI for Science -- that turns diverse scientific data, software, compute, and laboratory systems into agent-ready capabilities. SciMaster orchestrates these capabilities into long-horizon scientific workflows, on which scientific agents can be composed and executed. Between infrastructure and orchestration, a \emph{scientific intelligence substrate} organizes reusable models, knowledge, and components into executable building blocks for workflow reasoning and action, enabling composition, auditability, and improvement through use. We demonstrate this stack with eleven representative master agents in real workflows, achieving orders-of-magnitude reductions in end-to-end scientific cycle time and generating execution-grounded signals from real workloads at multi-million scale.

Eric Alcaide, Zhifeng Gao, Guolin Ke et al.

In recent years, machine learning (ML) methods have emerged as promising alternatives for molecular docking, offering the potential for high accuracy without incurring prohibitive computational costs. However, recent studies have indicated that these ML models may overfit to quantitative metrics while neglecting the physical constraints inherent in the problem. In this work, we present Uni-Mol Docking V2, which demonstrates a remarkable improvement in performance, accurately predicting the binding poses of 77+% of ligands in the PoseBusters benchmark with an RMSD value of less than 2.0 Å, and 75+% passing all quality checks. This represents a significant increase from the 62% achieved by the previous Uni-Mol Docking model. Notably, our Uni-Mol Docking approach generates chemically accurate predictions, circumventing issues such as chirality inversions and steric clashes that have plagued previous ML models. Furthermore, we observe enhanced performance in terms of high-quality predictions (RMSD values of less than 1.0 Å and 1.5 Å) and physical soundness when Uni-Mol Docking is combined with more physics-based methods like Uni-Dock. Our results represent a significant advancement in the application of artificial intelligence for scientific research, adopting a holistic approach to ligand docking that is well-suited for industrial applications in virtual screening and drug design. The code, data and service for Uni-Mol Docking are publicly available for use and further development in https://github.com/dptech-corp/Uni-Mol.

Zixu Yang, Hang Zheng, Nan Jiang et al.

Large language model (LLM) agents have increasingly advanced service applications, such as booking flight tickets. However, these service agents suffer from unreliability in long-horizon tasks, as they often produce policy violations, tool hallucinations, and misaligned actions, which greatly impedes their real-world deployment. To address these challenges, we propose NOD (Navigator-Operator-Director), a heterogeneous multi-agent architecture for service agents. Instead of maintaining task state implicitly in dialogue context as in prior work, we externalize a structured Global State to enable explicit task state tracking and consistent decision-making by the Navigator. Besides, we introduce selective external oversight before critical actions, allowing an independent Director agent to verify execution and intervene when necessary. As such, NOD effectively mitigates error propagation and unsafe behavior in long-horizon tasks. Experiments on $τ^2$-Bench demonstrate that NOD achieves higher task success rates and critical action precision over baselines. More importantly, NOD improves the reliability of service agents by reducing policy violations, tool hallucinations, and user-intent misalignment.

Rong Shan, Te Gao, Hang Zheng et al.

The implicit policy of maintaining relatively stable acceptance rates at top AI conferences, despite exponentially growing submissions, introduces a critical structural vulnerability. This position paper characterizes a new systemic threat we term Agentic Denominator Gaming, in which a malicious actor deploys AI agents to generate and submit a large volume of superficially plausible but low-quality papers. Crucially, their objective is not the acceptance of low-quality papers, but rather to inflate the submission denominator and overwhelm reviewing capacity. Under a relatively stable acceptance rate, this dilution can systematically increase the publication probability of a small, targeted set of legitimate papers. We analyze the practical feasibility of this threat and its broader consequences, including intensified reviewer burnout, degraded review quality, and the emergence of industrialized automated agent mills. Finally, we propose and evaluate a range of mitigation strategies, and argue that durable protection will require system-level policy and incentive reforms, rather than relying primarily on technical detection alone.

Tiancheng Huang, Ruisheng Cao, Yuxin Zhang et al.

The growing volume of academic papers has made it increasingly difficult for researchers to efficiently extract key information. While large language models (LLMs) based agents are capable of automating question answering (QA) workflows for scientific papers, there still lacks a comprehensive and realistic benchmark to evaluate their capabilities. Moreover, training an interactive agent for this specific task is hindered by the shortage of high-quality interaction trajectories. In this work, we propose AirQA, a human-annotated comprehensive paper QA dataset in the field of artificial intelligence (AI), with 13,948 papers and 1,246 questions, that encompasses multi-task, multi-modal and instance-level evaluation. Furthermore, we propose ExTrActor, an automated framework for instruction data synthesis. With three LLM-based agents, ExTrActor can perform example generation and trajectory collection without human intervention. Evaluations of multiple open-source and proprietary models show that most models underperform on AirQA, demonstrating the quality of our dataset. Extensive experiments confirm that ExTrActor consistently improves the multi-turn tool-use capability of small models, enabling them to achieve performance comparable to larger ones.

Wenzhuo Cheng, Menghang Gong, Qixin Guo et al.

Generative recommendation maps each item to a sequence of Semantic IDs (SIDs) and recasts retrieval as autoregressive token generation. In this paradigm the main bottleneck is the tokenizer rather than the Transformer: residual vector quantization with a hard nearest-neighbor assignment at every layer collapses multi-faceted item semantics at cluster boundaries and propagates early errors to later SID positions. A common workaround is to append a dense vector or attribute prefix to the SID, but this dual-representation design inflates inference cost and gives up the simplicity of a generative interface. We address the bottleneck at the tokenizer itself. CAPSID replaces hard residual quantization with capsule routing: at each layer an item probabilistically routes to several semantic capsules, the residual is updated by the routed reconstruction rather than by a single winning code, and the SID terminates once the active capsule's confidence is high enough. On top of CAPSID, SEMANTICBPE composes adjacent SID tokens into reusable subwords by combining their co-occurrence with their embedding compatibility. On Amazon Beauty, Sports, Toys, and a 35M-item proprietary industrial catalog, CAPSID+SEMANTICBPE improves Recall at 10 by 9.6% on average over ReSID, the strongest single-representation baseline, and matches or exceeds a COBRA-style sparse-dense system on every public benchmark while running at 51% of its inference latency. Ablations show that soft routing, iterative agreement, and confidence-driven length each contribute independently, and the gains are largest on tail items where boundary semantics dominate.

Hang Zheng, Hongshen Xu, Yuncong Liu et al.

Large language models (LLMs) are prone to hallucination stemming from misaligned self-awareness, particularly when processing queries exceeding their knowledge boundaries. While existing mitigation strategies employ uncertainty estimation or query rejection mechanisms, they suffer from computational efficiency and sacrificed helpfulness. To address these issues, we propose the Explicit Knowledge Boundary Modeling (EKBM) framework, integrating fast and slow reasoning systems to harmonize reliability and usability. The framework first employs a fast-thinking model to generate confidence-labeled responses, enabling immediate utilization of high-confidence outputs, whereas uncertain predictions trigger a slow refinement model for accuracy improvement. To align model behavior with our proposed object, we propose a hybrid training pipeline, enhancing self-awareness without degrading task performance. Evaluations on dialogue state tracking tasks demonstrate that EKBM achieves superior model reliability over uncertainty-based baselines. Further analysis reveals that refinement substantially boosts accuracy while maintaining low computational overhead. The framework establishes a scalable paradigm for deploying reliable LLMs in error-sensitive applications, effectively balancing accuracy and practical utility.

Lun Wang, Chuanqi Shi, Shaoshui Du et al.

This paper presents a comprehensive performance evaluation of Large Language Models (LLMs) in solving programming challenges from Leetcode, a widely used platform for algorithm practice and technical interviews. We began by crawling the Leetcode website to collect a diverse set of problems encompassing various difficulty levels and topics. Using this dataset, we generated solutions with multiple LLMs, including GPT-4 and GPT-3.5-turbo (ChatGPT-turbo). The generated solutions were systematically evaluated for correctness and efficiency. We employed the pass@k metric to assess the success rates within a given number of attempts and analyzed the runtime performance of the solutions. Our results highlight the strengths and limitations of current LLMs [10] in code generation and problem-solving tasks, providing insights into their potential applications and areas for improvement in automated programming assistance.

Hang Zheng, Hongshen Xu, Yongkai Lin et al.

The proliferation of Large Language Models (LLMs) has created a diverse ecosystem of models with highly varying performance and costs, necessitating effective query routing to balance performance and expense. Current routing systems often rely on a centralized external router trained on a fixed set of LLMs, making them inflexible and prone to poor performance since the small router can not fully understand the knowledge boundaries of different LLMs. We introduce DiSRouter (Distributed Self-Router), a novel paradigm that shifts from centralized control to distributed routing. In DiSRouter, a query traverses a network of LLM agents, each independently deciding whether to answer or route to other agents based on its own self-awareness, its ability to judge its competence. This distributed design offers superior flexibility, scalability, and generalizability. To enable this, we propose a two-stage Self-Awareness Training pipeline that enhances each LLM's self-awareness. Extensive experiments demonstrate that DiSRouter significantly outperforms existing routing methods in utility across various scenarios, effectively distinguishes between easy and hard queries, and shows strong generalization to out-of-domain tasks. Our work validates that leveraging an LLM's intrinsic self-awareness is more effective than external assessment, paving the way for more modular and efficient multi-agent systems.

Xiaohong Ji, Zhen Wang, Zhifeng Gao et al.

In recent years, pretraining models have made significant advancements in the fields of natural language processing (NLP), computer vision (CV), and life sciences. The significant advancements in NLP and CV are predominantly driven by the expansion of model parameters and data size, a phenomenon now recognized as the scaling laws. However, research exploring scaling law in molecular pretraining models remains unexplored. In this work, we present Uni-Mol2 , an innovative molecular pretraining model that leverages a two-track transformer to effectively integrate features at the atomic level, graph level, and geometry structure level. Along with this, we systematically investigate the scaling law within molecular pretraining models, characterizing the power-law correlations between validation loss and model size, dataset size, and computational resources. Consequently, we successfully scale Uni-Mol2 to 1.1 billion parameters through pretraining on 800 million conformations, making it the largest molecular pretraining model to date. Extensive experiments show consistent improvement in the downstream tasks as the model size grows. The Uni-Mol2 with 1.1B parameters also outperforms existing methods, achieving an average 27% improvement on the QM9 and 14% on COMPAS-1D dataset.