论文检索

Applications · Health / Medicine

Cheng Wang, Jinpu Cai, Chongxiao Mao, Yuxuan Wang, Xinzhu Jiang, Yunhao Qiao, Luqi Yang, Luting Zhou, Qiuyu Lian, Hongyi Xin

Geometry-preserving dimension reduction is critical for single-cell transcriptomics, where low-dimensional distances should reflect biological divergence between cell types along the transcriptomic manifold. Due to inadequate metrics, the global structure is not sufficiently preserved in the low-dimensional manifold in standard dimension reduction regimes. We model RNA counts as Multinomial samples, leveraging their hierarchical closure property: gene-level counts refine functional gene-group counts via nested Multinomial distributions. Extending Chentsov's Theorem, we show that the Fisher-Rao metric on coarse (gene-group) and fine (gene) statistical manifolds is isometric. Following this isometry property, we propose InfoGlobe, an information-preserving statistical manifold learning framework that projects cells from high-dimensional hyperspheres (full transcriptome) to low-dimensional hyperspheres (functional groups) while preserving information geometry. Embeddings on the low-dimensional sphere explicitly represent Multinomial distributions by functional gene groups. Benchmarks demonstrate superior preservation of local-and-global cell-type geodesic distances, automatic and robust gene-group discovery, nuanced cell subtype resolution without manual feature engineering and natural batch effect mitigation without explicit alignments.

Applications · Health / Medicine

Haoran liu, Xiaoli Lin, Jing Hu, Yu Zou, Xiaolong Zhang

Polypharmacology provides a powerful strategy for treating complex diseases, but identifying molecules that simultaneously satisfy coupled constraints across multiple biological targets remains difficult. Existing methods typically model protein pockets in isolation and struggle to jointly account for multiple heterogeneous binding sites when designing a single shared ligand. To address these limitations, we propose a pocket-structure-centric generative framework for polypharmacology. This framework introduces a novel protein topological representation that selectively masks ligand-irrelevant residues while explicitly modeling backbone folding geometry and inter-residue spatial proximity within binding pockets. In addition, structural representations are jointly fused with amino acid and nucleotide sequences to capture their complementary information across targets. Experiments on COVID-19, schizophrenia, and tumor targets show that this framework generates valid candidates with significantly improved binding affinities compared to state-of-the-art methods.

Applications · Health / Medicine

Yuchen Hua, Xingang Peng, Jianzhu Ma, Muhan Zhang

Generative modeling of three-dimensional (3D) molecules is a fundamental yet challenging problem in drug discovery and materials science. Existing approaches typically represent molecules as 3D graphs and co-generate discrete atom types with continuous atomic coordinates, leading to intrinsic learning difficulties such as heterogeneous modality entanglement and geometry–chemistry coherence constraints. We propose VecMol, a novel representation that models 3D molecules as continuous vector fields over Euclidean space, where vectors point toward nearby atoms and implicitly encode molecular structure. The vector field is parameterized by a neural field and generated using a latent diffusion model, avoiding explicit graph generation and decoupling structure learning from discrete atom instantiation. Experiments on the QM9 and GEOM-Drugs benchmarks demonstrate that VecMol achieves competitive generation quality, suggesting vector-field-based representations as a promising new direction for 3D molecular generation.

Applications · Health / Medicine

Zitao Chen, Jiatong Ji, Yinjun Jia, Wei-Ying Ma, Yanyan Lan

Recent advances in 3D molecular modeling have achieved high-fidelity structural synthesis, yet these models often lack an explicit and manipulable representation space. To address this, MolFLAE introduced a fixed-dimensional, E(3)-equivariant latent space, providing a novel framework for molecular editing independent of atom counts. However, because its latent space was primarily optimized for geometric reconstruction, it remains semantically shallow and inadequate for comprehensive representation learning. In this work, we propose **MolAlign3D**, which evolves this architecture into a unified semantic-generative engine. By anchoring MolFLAE’s manipulable latents with embeddings from a pre-trained molecular encoder, we yield a manifold that is both semantically dense and geometrically precise. Experiments show that MolAlign3D achieves high-fidelity molecular reconstruction and attains comparable performance on molecular property prediction benchmarks. Notably, the integration of rich semantic priors significantly enhances zero-shot molecular manipulation, including atom-number editing and latent-space interpolation, outperforming prior fixed-dimensional equivariant latent baseline.

Applications · Health / Medicine

Zekai Chen, Xunkai Li, Sirui Zhang, Henan Sun, Jia Li, Qiangqiang Dai, Hongchao Qin, Zhenjun Li, Bing Zhou, Rong-Hua Li 等

De novo ligand design is a fundamental task that seeks to generate protein or molecule candidates that can effectively dock with protein receptors and achieve strong binding affinity entirely from scratch. It holds paramount significance for a wide spectrum of biomedical applications. However, most existing studies are constrained by the \textbf{Pseudo De Novo}, \textbf{Limited Docking Modeling}, and \textbf{Inflexible Ligand Type}. To address these issues, we propose MagicDock, a forward-looking framework grounded in the progressive pipeline and differentiable surface modeling. (1) We adopt a well-designed gradient inversion framework. To begin with, general docking knowledge of receptors and ligands is incorporated into the backbone model. Subsequently, the docking knowledge is instantiated as reverse gradient flows by binding prediction, which iteratively guide the de novo generation of ligands. (2) We emphasize differentiable surface modeling in the \textit{generation process}, leveraging learnable 3D point-cloud representations to precisely capture docking details, thereby ensuring that the generated ligands preserve docking validity through interpretable spatial fingerprints. (3) We introduce customized designs for different ligand types and integrate them into a unified gradient inversion framework with flexible triggers, thereby ensuring broad applicability. Moreover, we provide sufficient theoretical guarantees for MagicDock. Extensive experiments across 9 scenarios demonstrate that MagicDock achieves average improvements of 7.0\% and 7.4\% over SOTA baselines specialized for protein or molecule ligand design, respectively.

Social Aspects · Accountability, Transparency, and Interpretability

Sourav Banerjee, Saikat Saha

This position paper argues that AI leaderboards are structurally ill-suited to serving the Global South because they lack independent governance, conflict-of-interest policies, and mechanisms for metric evolution. The barrier is not missing data; high-quality regional benchmarks already exist: IndicSUPERB, MILU, and LAHAJA for India; IrokoBench for Africa; AlGhafa for Arabic. The barrier is institutional design. Global leaderboards do not include these benchmarks, and no governance mechanism compels them to do so. Commercial pressure corrects leaderboard failures when paying customers in the Global North are affected. The Global South lacks equivalent leverage. Without governance, failures affecting Hindi, Swahili, or Arabic speakers persist indefinitely as documented but unaddressed gaps. Using India as a case study (1.4 billion people, 22 scheduled languages, high-quality benchmarks, but no trusted aggregation), we report findings from a consultation with 58 AI practitioners showing consistent preference for formal governance and disclosure-based conflict management. The solution is not more data but better institutions: regional leaderboards with independent governance from the start.

Applications · Computer Vision

Rongjiang Zhu, Wei Kang, Zeqi Liu, Chen junyu, Shuo Yang, Xinxiao Wu

Traditional 3D visual grounding typically assumes that natural language expressions unambiguously refer to target objects in a 3D scene. However, in practical applications, human instructions are often ambiguous or insufficient, which may lead existing models to associate the query with multiple possible objects, resulting in incorrect results. In this paper, we propose a new task, 3D visual grounding with referential ambiguity, which allows for referential ambiguity in language descriptions, making it more broadly applicable to real-world scenarios. To tackle this task, we propose an interactive grounding framework that performs multi-round question-answer interactions, in which the model actively generates clarifying questions and receives human-provided answers to acquire additional object attributes, spatial relationships, and other contextual information, thereby resolving referential ambiguity and achieving accurate grounding. To support the learning of interactive grounding, we construct a large-scale dataset named AmbiRefer3D, which contains 47,085 samples with 141,255 annotations of question-answer dialogues that capture interactive disambiguation processes, covering 7,316 indoor 3D scenes. Furthermore, we establish multi-round evaluation metrics to measure both disambiguation efficiency and grounding accuracy.

General Machine Learning · Representation Learning

Yilin Chen, Tianyu Lu, Cizhang Zhao, Hannah Wayment-Steele, Po-Ssu Huang

Building physically grounded protein representations is central to computational biology, yet most existing approaches rely on sequence-pretrained language models or backbone-only graphs that overlook side-chain geometry and chemical detail. We present SLAE, a unified all-atom framework for learning protein representations from each residue’s local atomic neighborhood using only atom types and interatomic geometries. To encourage expressive feature extraction, we introduce a novel multi-task autoencoder objective that combines coordinate reconstruction, sequence recovery, and energy regression. SLAE reconstructs allatom structures with high fidelity from latent residue environments and achieves state-of-the-art performance across diverse downstream tasks via transfer learning. SLAE’s latent space is chemically informative and environmentally sensitive, enabling quantitative assessment of structural qualities and smooth interpolation between conformations at all-atom resolution.

Applications · Computer Vision

Chenming Zhu, Peizhou Cao, Jingli Lin, Wenbo Hu, Yunlong Ran, Tai Wang, Jiangmiao Pang, Xihui Liu

Human spatial understanding arises from jointly perceiving geometry and semantics, enabling consistent object identification and localization across viewpoints and time. Current video segmentation models depend on explicit object appearance memory banks for instance tracking, yet they remain vulnerable to large viewpoint changes and long-term occlusions. Leveraging the spatial consistency afforded by modern feed-forward 3D reconstruction models, we propose the Geometry Grounded Tracking Anything Model (G$^2$TAM), a unified framework for promptable instance tracking in 3D using only unordered RGB images or videos. G$^2$TAM employs spatially aligned geometric representations as implicit memory, ensuring stable instance identity and localization across frames and views. At its core is a cross-modal spatial encoder that integrates visual and textual prompts into a shared geometric space, enabling end-to-end spatial reconstruction and instance-consistent mask prediction. To support training and evaluation, we construct InsTrack, a large-scale dataset with a dedicated validation split for benchmarking. Extensive experiments show that G$^2$TAM delivers strong cross-view consistency, promptable instance spatial tracking, video object segmentation, and spatial reconstruction, establishing a foundation for interactive, geometry-grounded spatial reasoning.

Applications · Computer Vision

YiCheng Xiao, Yu Chen, Hao-Xuan Ma, Jiale Hong, Caorui Li, Lingxiang Wu, Haiyun Guo, Jinqiao Wang

While CLIP has achieved strong performance across vision–language tasks, fine-grained image–text alignment remains challenging. Recent efforts improve textual granularity by leveraging long, detailed descriptions and replacing CLIP’s text encoder with LLM, but often overlook the visual-side bottleneck: achieving finer alignment requires region- and pixel-level visual grounding, not just finer text. To address this issue, we propose PixCLIP, a framework that jointly enhances both sides by accommodating visual prompt regions and long-form text within a unified training objective. Firstly, to support training at this granularity, we develop an automated annotation pipeline that produces long-form descriptions with pixel-level localization, and use it to construct LongGRIT, a high-quality dataset with nearly 1.5M samples. Furthermore, we introduce a three-branch pixel–text alignment framework that aligns image regions with corresponding textual descriptions across multiple granularities. Experiments show that PixCLIP achieves state-of-the-art performance on pixel- and region-level alignment tasks while preserving strong results on standard global image–text retrieval benchmarks, even with arbitrarily shaped region prompts and long compositional texts.

Applications · Computer Vision

Shiyan Tong, Jinxia Zhang, Zhiyuan Wang, Hao Tian, YingYing Wang, Kanjian Zhang, Haikun Wei

Recent advances in zero-shot referring image segmentation (RIS), driven by foundation models such as SAM and CLIP, have improved cross-modal alignment between visual regions and natural language expressions. Nevertheless, selecting the correct segmentation proposal remains challenging, as existing methods typically rely on independent proposal scoring and lack contextual reasoning among visually similar candidates. To address this limitation, we propose RefChess, a training-free framework that reformulates proposal selection as a decision-making problem under contextual perturbations rather than a single-step ranking task. RefChess models each proposal as a candidate chess move and applies Monte-Carlo Tree Search to evaluate its robustness by simulating interactions with competing regions, guided by a stability-aware reward that integrates language decomposition, vision–language similarity, object-centric cues, and spatial guidance signals. Experimental results on standard RIS benchmarks indicate that this decision-centric formulation leads to consistent improvements in robustness and referring segmentation performance. Code is available at \url{anonymous URL}.

Deep Learning · Large Language Models

Sangeun Park, Minhae Kwon

A central goal of large language model (LLM) research is to build agentic systems that can plan, act, and adapt through sustained interaction with dynamic environments. While recent LLM-based agents exhibit impressive contextual reasoning, their long-horizon decision-making remains fragile, often suffering from $\textit{objective drift}$, where goals and plans drift over extended interactions. We introduce $\texttt{Multi}^2$, a hierarchical multi-agent decision-making framework that explicitly decomposes agent behavior into complementary roles. A high-level agent ($\texttt{System 1}$) focuses on context-aware sub-goal generation using supervised fine-tuning (SFT), while a low-level agent ($\texttt{System 2}$) executes atomic actions through offline-to-online reinforcement learning (RL) in interactive environments. This separation enables stable long-horizon control, mitigates objective drift, and allows efficient adaptation. Across diverse interactive environments, $\texttt{Multi}^2$ consistently outperforms strong agentic baselines, demonstrating improved robustness and coordination in multi-turn interaction. Beyond performance, we introduce and release three hierarchical benchmark datasets, filling a long-standing gap in training and evaluating hierarchical decision-making for LLM-based agents.

Applications · Time Series

Mengzhou Gao, Kaiwei Wang, Pengfei Jiao

Neural Flows efficiently model irregular multivariate time series by directly learning ODE solution trajectories with neural networks, bypassing step-by-step numerical solvers. Despite their efficiency, many existing approaches treat variables independently, leaving inter-variable interactions underexplored. Moreover, their one-step mapping makes interaction modeling inherently challenging, as it removes the iterative refinement of interactions during learning. To address this challenge, we propose one-step Graph-Structured Neural Flows (GSNF), which introduce two auxiliary-trajectory self-supervision strategies to strengthen interaction learning: (i) interaction-aware trajectory generation via re-initialization, which induces trajectory divergence to expose graph-induced interactions, with a theoretically derived lower bound on divergence; and (ii) reverse-time trajectory generation, which enforces forward–backward consistency to regularize graph learning, enabled by flow invertibility. Experiments on five real-world datasets show that GSNF achieves state-of-the-art classification performance with highly competitive training time and memory usage.

Applications · Computer Vision

Yuxi Liu, Yipeng Hu, Zekun Zhang, Kunze Jiang, Kun Yuan

While Diffusion Transformers (DiTs) have achieved notable progress in video generation, this long-sequence generation task remains constrained by the quadratic complexity inherent to self-attention mechanisms, creating significant barriers to practical deployment. Although sparse attention methods attempt to address this challenge, existing approaches either rely on oversimplified static patterns or require computationally expensive sampling operations to achieve dynamic sparsity, resulting in inaccurate pattern predictions and degraded generation quality. To overcome these limitations, we propose a \underline{\textbf{M}}ixture-\underline{\textbf{O}}f-\underline{\textbf{D}}istribution \textbf{DiT} (\textbf{MOD-DiT}), a novel sampling-free dynamic attention framework that accurately models evolving attention patterns through a two-stage process. First, MOD-DiT leverages prior information from early denoising steps and adopts a {distributed mixing approach} to model an efficient linear approximation model, which is then used to predict mask patterns for a specific denoising interval. Second, an online block masking strategy dynamically applies these predicted masks while maintaining historical sparsity information, eliminating the need for repetitive sampling operations. Extensive evaluations demonstrate consistent acceleration and quality improvements across multiple benchmarks and model architectures, validating MOD-DiT's effectiveness for efficient, high-quality video generation while overcoming the computational limitations of traditional sparse attention approaches.

Applications · Computer Vision

Qiucheng Wu, Handong Zhao, Zhixin Shu, Jing Shi, Yang Zhang, Shiyu Chang

Although recent text-to-video generative models are getting more capable of following external camera controls, imposed by either text descriptions or camera trajectories, they still struggle to generalize to unconventional camera motions, which is crucial in creating truly original and artistic videos. The challenge lies in the difficulty of finding sufficient training videos with the intended uncommon camera motions. To address this challenge, we propose VividCam, a training paradigm that enables diffusion models to learn complex camera motions from synthetic videos, releasing the reliance on collecting realistic training videos. VividCam incorporates multiple disentanglement strategies that isolates camera motion learning from synthetic appearance artifacts, ensuring more robust motion representation and mitigating domain shift. We demonstrate that our design synthesizes a wide range of precisely controlled and complex camera motions using surprisingly simple synthetic data. Notably, this synthetic data often consists of basic geometries within a low-poly 3D scene and can be efficiently rendered by engines like Unity. Our video results can be found in https://anonymoususers196.github.io/VividCamDemo/ .

Applications · Computer Vision

Yuecheng Liu, Junda Cheng, Longliang Liu, Wenjing Liao, Hanrui Cheng, Yuzhou Wang, Xin Yang

Video depth estimation extends monocular prediction into the temporal domain to ensure coherence. However, existing methods often suffer from spatial blurring in fine-detail regions and temporal inconsistencies. We argue that current approaches, which primarily rely on temporal smoothing via Transformers, struggle to maintain strict 3D geometric consistency—particularly under rotations or drastic view changes. To address this, we propose GemDepth, a framework built on the insight that an explicit awareness of camera motion and global 3D structure is a prerequisite for 3D consistency. Distinctively, GemDepth introduces a Geometry-Embedding Module (GEM) that predicts inter-frame camera poses to generate implicit geometric embeddings. This injection of motion priors equips the network with intrinsic 3D perception and alignment capabilities. Guided by these geometric cues, our Alternating Spatio-Temporal Transformer (ASTT) captures latent point-level correspondences to simultaneously enhance spatial precision for sharp details and enforce rigorous temporal consistency. Furthermore, GemDepth employs a data-efficient training strategy, effectively bridging the gap between high efficiency and robust geometric consistency. As shown in Fig.2, comprehensive evaluations demonstrate that GemDepth achieves state-of-the-art performance across multiple datasets, particularly in complex dynamic scenarios.

Applications · Computer Vision

George Webber, Alexander Denker, Riccardo Barbano, Andrew Reader

Flow-based generative models provide strong unconditional priors for inverse problems, but guiding their dynamics for conditional generation remains challenging. Recent work casts training-free conditional generation in flow models as an optimal control problem; however, solving the resulting trajectory optimisation is computationally and memory intensive, requiring differentiation through the flow dynamics or adjoint solves. We propose MPC-Flow, a model predictive control framework that formulates inverse problem solving with flow-based generative models as a sequence of control sub-problems, enabling practical optimal control-based guidance at inference time. We provide theoretical guarantees linking MPC-Flow to the underlying optimal control objective and show how different algorithmic choices yield a spectrum of guidance algorithms, including regimes that avoid backpropagation through the generative model trajectory. We evaluate MPC-Flow on benchmark image restoration tasks, spanning linear and non-linear settings such as in-painting, deblurring, and super-resolution, and demonstrate strong performance and scalability to massive state-of-the-art architectures via training-free guidance of FLUX.2 (32B) in a quantised setting on consumer hardware.

Applications · Computer Vision

Yikai Wang, Chenjie Cao, Ke Fan, Qiaole Dong, Yifan Li, Xiangyang Xue, Yanwei Fu

Current image manipulation primarily centers on static manipulation, such as replacing specific regions within an image or altering its overall style. In this paper, we introduce an innovative dynamic manipulation task, subject repositioning. This task involves relocating a user-specified subject to a desired position while preserving the image's fidelity. Our research reveals that the fundamental sub-tasks of subject repositioning, which include filling the void left by the repositioned subject, reconstructing obscured portions of the subject and blending the subject to be consistent with surrounding areas, can be effectively reformulated as a unified, prompt-guided inpainting task. Consequently, we can employ a single diffusion generative model to address these sub-tasks using various task prompts learned through our proposed task inversion technique. Additionally, we integrate pre-processing and post-processing techniques to further enhance the quality of subject repositioning. These elements together form our SEgment-gEnerate-and-bLEnd (SEELE) framework. To assess SEELE's effectiveness in subject repositioning, we assemble a real-world subject repositioning dataset called ReS. Results of SEELE on ReS demonstrate its efficacy. Code and ReS dataset are available at https://yikai-wang.github.io/seele/.

Applications · Chemistry, Physics, and Earth Sciences

Jiwoong Kim, Jongwon Lee, Sungwoo Park

We introduce Euler–Poincaré Neural Dynamics (EPND), a geometric-mechanics–driven framework that redefines how Koopman-type neural models learn dynamical systems. Unlike conventional operator-learning methods that rely on function-space linearization, EPND places geometric mechanics at the core of its architecture the mathematical engine governing evolution through Lie-group flows. This foundation enables a principled treatment of curvature, symmetry, and conservation, that ensures both interpretability and physical consistency. Building on this foundation, we develop the Euler–Poincaré Parallel Scan, a parallel algorithm that leverages the associative algebra of Lie-group compositions to overcome the inefficiencies of sequential computation. By unifying geometric structure with scalable computation, EPND achieves high accuracy, strong stability, and significant parallel acceleration in modeling long-horizon dynamics of versatile scientific simulation.

Applications · Chemistry, Physics, and Earth Sciences

Jiwoong Kim, Jongwon Lee, Jungwoo Park, Sungwoo Park

We present a Lie-algebraic approach to model Koopman dynamics that integrates algebraic structure with computational scalability. The proposed formulation constrains the neural generators to evolve within prescribed Lie subalgebras and constructs finite-time flows through a neural Magnus expansion construction, thereby maintaining consistency with the associated Lie-group composition over each time segment. To address the computational burden inherent in sequential propagation, we exploit the associativity of Lie-group compositions and construct segmentwise propagators via a prefix-scan algorithm, which reduces the depth of temporal composition from linear to logarithmic. Consequently, the framework enables accurate long-horizon prediction while improving computational efficiency, and provides a principled foundation for scalable Koopman operator learning for nonlinear systems.