arXiv subjects

Shuo Yang

Publications and source records attributed to Shuo Yang.

At least 145 records · Page 8Linked to original sources

arXiv2026

APEX: A Decoupled Memory-based Explorer for Asynchronous Aerial Object Goal Navigation

Aerial Object Goal Navigation, a challenging frontier in Embodied AI, requires an Unmanned Aerial Vehicle (UAV) agent to autonomously explore, reason, and identify a specific target using only visual perception and language description. However, existing methods struggle with the memorization of complex spatial representations in aerial environments, reliable and interpretable action decision-making, and inefficient exploration and information gathering. To address these challenges, we introduce \textbf{APEX} (Aerial Parallel Explorer), a novel hierarchical agent designed for efficient exploration and target acquisition in complex aerial settings. APEX is built upon a modular, three-part architecture: 1) Dynamic Spatio-Semantic Mapping Memory, which leverages the zero-shot capability of a Vision-Language Model (VLM) to dynamically construct high-resolution 3D Attraction, Exploration, and Obstacle maps, serving as an interpretable memory mechanism. 2) Action Decision Module, trained with reinforcement learning, which translates this rich spatial understanding into a fine-grained and robust control policy. 3) Target Grounding Module, which employs an open-vocabulary detector to achieve definitive and generalizable target identification. All these components are integrated into a hierarchical, asynchronous, and parallel framework, effectively bypassing the VLM's inference latency and boosting the agent's proactivity in exploration. Extensive experiments show that APEX outperforms the previous state of the art by +4.2\% SR and +2.8\% SPL on challenging UAV-ON benchmarks, demonstrating its superior efficiency and the effectiveness of its hierarchical asynchronous design. Our source code is provided in \href{https://github.com/4amGodvzx/apex}{GitHub}

cs.RO↗

arXiv2026

ConLA: Contrastive Latent Action Learning from Human Videos for Robotic Manipulation

Vision-Language-Action (VLA) models achieve preliminary generalization through pretraining on large scale robot teleoperation datasets. However, acquiring datasets that comprehensively cover diverse tasks and environments is extremely costly and difficult to scale. In contrast, human demonstration videos offer a rich and scalable source of diverse scenes and manipulation behaviors, yet their lack of explicit action supervision hinders direct utilization. Prior work leverages VQ-VAE based frameworks to learn latent actions from human videos in an unsupervised manner. Nevertheless, since the training objective primarily focuses on reconstructing visual appearances rather than capturing inter-frame dynamics, the learned representations tend to rely on spurious visual cues, leading to shortcut learning and entangled latent representations that hinder transferability. To address this, we propose ConLA, an unsupervised pretraining framework for learning robotic policies from human videos. ConLA introduces a contrastive disentanglement mechanism that leverages action category priors and temporal cues to isolate motion dynamics from visual content, effectively mitigating shortcut learning. Extensive experiments show that ConLA achieves strong performance across diverse benchmarks. Notably, by pretraining solely on human videos, our method for the first time surpasses the performance obtained with real robot trajectory pretraining, highlighting its ability to extract pure and semantically consistent latent action representations for scalable robot learning.

cs.RO↗

arXiv2026

Jet-RL: Enabling On-Policy FP8 Reinforcement Learning with Unified Training and Rollout Precision Flow

Reinforcement learning (RL) is essential for enhancing the complex reasoning capabilities of large language models (LLMs). However, existing RL training pipelines are computationally inefficient and resource-intensive, with the rollout phase accounting for over 70% of total training time. Quantized RL training, particularly using FP8 precision, offers a promising approach to mitigating this bottleneck. A commonly adopted strategy applies FP8 precision during rollout while retaining BF16 precision for training. In this work, we present the first comprehensive study of FP8 RL training and demonstrate that the widely used BF16-training + FP8-rollout strategy suffers from severe training instability and catastrophic accuracy collapse under long-horizon rollouts and challenging tasks. Our analysis shows that these failures stem from the off-policy nature of the approach, which introduces substantial numerical mismatch between training and inference. Motivated by these observations, we propose Jet-RL, an FP8 RL training framework that enables robust and stable RL optimization. The key idea is to adopt a unified FP8 precision flow for both training and rollout, thereby minimizing numerical discrepancies and eliminating the need for inefficient inter-step calibration. Extensive experiments validate the effectiveness of Jet-RL: our method achieves up to 33% speedup in the rollout phase, up to 41% speedup in the training phase, and a 16% end-to-end speedup over BF16 training, while maintaining stable convergence across all settings and incurring negligible accuracy degradation.

cs.LG↗

arXiv2026

Talk2Move: Reinforcement Learning for Text-Instructed Object-Level Geometric Transformation in Scenes

We introduce Talk2Move, a reinforcement learning (RL) based diffusion framework for text-instructed spatial transformation of objects within scenes. Spatially manipulating objects in a scene through natural language poses a challenge for multimodal generation systems. While existing text-based manipulation methods can adjust appearance or style, they struggle to perform object-level geometric transformations-such as translating, rotating, or resizing objects-due to scarce paired supervision and pixel-level optimization limits. Talk2Move employs Group Relative Policy Optimization (GRPO) to explore geometric actions through diverse rollouts generated from input images and lightweight textual variations, removing the need for costly paired data. A spatial reward guided model aligns geometric transformations with linguistic description, while off-policy step evaluation and active step sampling improve learning efficiency by focusing on informative transformation stages. Furthermore, we design object-centric spatial rewards that evaluate displacement, rotation, and scaling behaviors directly, enabling interpretable and coherent transformations. Experiments on curated benchmarks demonstrate that Talk2Move achieves precise, consistent, and semantically faithful object transformations, outperforming existing text-guided editing approaches in both spatial accuracy and scene coherence.

cs.CV↗

arXiv2026

Searching for long-lived axion-like particles via displaced vertices at the HL-LHC

Axion-like particles (ALPs) are well-motivated extensions of the standard model (SM) that appear in numerous new physics scenarios. In this paper, we concentrate on searches for long-lived ALPs predicted by the photophobic scenario at the HL-LHC with the center-of-mass energy $\sqrt{s}=14$ TeV and the integrated luminosity $\mathcal{L}=$ $3$ ab$^{-1}$. We consider the process $pp \to γa$ with the ALP $a$ decaying into a pair of displaced charged leptons and perform a detailed analysis of two types of signals: $π^+ π^- γE\mkern-10.5 mu/_T $ and $\ell^+ \ell^- γE\mkern-10.5 mu/_T $. For the $π^+ π^- γE\mkern-10.5 mu/_T $ signal, we find that the prospective sensitivities of the HL-LHC can reach $g_{aWW}\in [8.72 \times 10^{-3}, 6.42 \times 10^{-2}]$ TeV$^{-1}$ for the ALP mass $m_a \in [4, 10]$ GeV. While for the $\ell^+ \ell^- γE\mkern-10.5 mu/_T $ signal, the HL-LHC can probe a broader parameter space, with the sensitivities covering $m_a \in [4, 10]$ GeV and $g_{aWW} \in [4.17 \times 10^{-3}, 2.00 \times 10^{-1}]$ TeV$^{-1}$. These long-lived searches complement some previous prompt decay studies from LEP and LHC experiments, extending the parameter space explored by the LHCb collaboration. Our results show that the HL-LHC has significant potential to probe long-lived ALPs via their displaced vertex signatures.

hep-ph↗

arXiv2026

Matrix Manifold Neural Networks++

Deep neural networks (DNNs) on Riemannian manifolds have garnered increasing interest in various applied areas. For instance, DNNs on spherical and hyperbolic manifolds have been designed to solve a wide range of computer vision and nature language processing tasks. One of the key factors that contribute to the success of these networks is that spherical and hyperbolic manifolds have the rich algebraic structures of gyrogroups and gyrovector spaces. This enables principled and effective generalizations of the most successful DNNs to these manifolds. Recently, some works have shown that many concepts in the theory of gyrogroups and gyrovector spaces can also be generalized to matrix manifolds such as Symmetric Positive Definite (SPD) and Grassmann manifolds. As a result, some building blocks for SPD and Grassmann neural networks, e.g., isometric models and multinomial logistic regression (MLR) can be derived in a way that is fully analogous to their spherical and hyperbolic counterparts. Building upon these works, we design fully-connected (FC) and convolutional layers for SPD neural networks. We also develop MLR on Symmetric Positive Semi-definite (SPSD) manifolds, and propose a method for performing backpropagation with the Grassmann logarithmic map in the projector perspective. We demonstrate the effectiveness of the proposed approach in the human action recognition and node classification tasks.

stat.ML↗

arXiv2026

Neural Networks on Symmetric Spaces of Noncompact Type

Recent works have demonstrated promising performances of neural networks on hyperbolic spaces and symmetric positive definite (SPD) manifolds. These spaces belong to a family of Riemannian manifolds referred to as symmetric spaces of noncompact type. In this paper, we propose a novel approach for developing neural networks on such spaces. Our approach relies on a unified formulation of the distance from a point to a hyperplane on the considered spaces. We show that some existing formulations of the point-to-hyperplane distance can be recovered by our approach under specific settings. Furthermore, we derive a closed-form expression for the point-to-hyperplane distance in higher-rank symmetric spaces of noncompact type equipped with G-invariant Riemannian metrics. The derived distance then serves as a tool to design fully-connected (FC) layers and an attention mechanism for neural networks on the considered spaces. Our approach is validated on challenging benchmarks for image classification, electroencephalogram (EEG) signal classification, image generation, and natural language inference.

stat.ML↗

arXiv2025

Signature for charged Higgs pair production in 2HDM+a model at CLIC

In this work, we study the search for charged Higgs bosons in the Two-Higgs-Doublet Model plus an additional pseudo-scalar (2HDM+a) at the Compact Linear Collider (CLIC). Focusing on the pair production of charged Higgs bosons, followed by the decays $H^\pm \to a W $ and $ H^\mp \to t b $, we analyze the signal channel of $4j+2b+E_T^{miss}$. Given the center-of-mass energy of CLIC as $ \sqrt{s} = 1500$ GeV, charged Higgs bosons with masses $ m_{H^\pm} < \sqrt{s}/2$ are explored. Simulation results indicate that the signal significance of 400 GeV and 600 GeV charged Higgs bosons can reach $5σ$ in specific parameter spaces, and the $2σ$ exclusion limits in the $m_{H^\pm}- m_a$ plane are presented for $m_{H^\pm}$ in the range of [400, 650] GeV.

hep-ph↗

arXiv2025

Let the Barbarians In: How AI Can Accelerate Systems Performance Research

Artificial Intelligence (AI) is beginning to transform the research process by automating the discovery of new solutions. This shift depends on the availability of reliable verifiers, which AI-driven approaches require to validate candidate solutions. Research focused on improving systems performance is especially well-suited to this paradigm because system performance problems naturally admit such verifiers: candidates can be implemented in real systems or simulators and evaluated against predefined workloads. We term this iterative cycle of generation, evaluation, and refinement AI-Driven Research for Systems (ADRS). Using several open-source ADRS instances (i.e., OpenEvolve, GEPA, and ShinkaEvolve), we demonstrate across ten case studies (e.g., multi-region cloud scheduling, mixture-of-experts load balancing, LLM-based SQL, transaction scheduling) that ADRS-generated solutions can match or even outperform human state-of-the-art designs. Based on these findings, we outline best practices (e.g., level of prompt specification, amount of feedback, robust evaluation) for effectively using ADRS, and we discuss future research directions and their implications. Although we do not yet have a universal recipe for applying ADRS across all of systems research, we hope our preliminary findings, together with the challenges we identify, offer meaningful guidance for future work as researcher effort shifts increasingly toward problem formulation and strategic oversight. Note: This paper is an extension of our prior work [14]. It adds extensive evaluation across multiple ADRS frameworks and provides deeper analysis and insights into best practices.

cs.SE↗

arXiv2025

VI-MMRec: Similarity-Aware Training Cost-free Virtual User-Item Interactions for Multimodal Recommendation

Although existing multimodal recommendation models have shown promising performance, their effectiveness continues to be limited by the pervasive data sparsity problem. This problem arises because users typically interact with only a small subset of available items, leading existing models to arbitrarily treat unobserved items as negative samples. To this end, we propose VI-MMRec, a model-agnostic and training cost-free framework that enriches sparse user-item interactions via similarity-aware virtual user-item interactions. These virtual interactions are constructed based on modality-specific feature similarities of user-interacted items. Specifically, VI-MMRec introduces two different strategies: (1) Overlay, which independently aggregates modality-specific similarities to preserve modality-specific user preferences, and (2) Synergistic, which holistically fuses cross-modal similarities to capture complementary user preferences. To ensure high-quality augmentation, we design a statistically informed weight allocation mechanism that adaptively assigns weights to virtual user-item interactions based on dataset-specific modality relevance. As a plug-and-play framework, VI-MMRec seamlessly integrates with existing models to enhance their performance without modifying their core architecture. Its flexibility allows it to be easily incorporated into various existing models, maximizing performance with minimal implementation effort. Moreover, VI-MMRec introduces no additional overhead during training, making it significantly advantageous for practical deployment. Comprehensive experiments conducted on six real-world datasets using seven state-of-the-art multimodal recommendation models validate the effectiveness of our VI-MMRec.

cs.IR↗

arXiv2025

Learning and Editing Universal Graph Prompt Tuning via Reinforcement Learning

Early graph prompt tuning approaches relied on task-specific designs for Graph Neural Networks (GNNs), limiting their adaptability across diverse pre-training strategies. In contrast, another promising line of research has investigated universal graph prompt tuning, which operates directly in the input graph's feature space and builds a theoretical foundation that universal graph prompt tuning can theoretically achieve an equivalent effect of any prompting function, eliminating dependence on specific pre-training strategies. Recent works propose selective node-based graph prompt tuning to pursue more ideal prompts. However, we argue that selective node-based graph prompt tuning inevitably compromises the theoretical foundation of universal graph prompt tuning. In this paper, we strengthen the theoretical foundation of universal graph prompt tuning by introducing stricter constraints, demonstrating that adding prompts to all nodes is a necessary condition for achieving the universality of graph prompts. To this end, we propose a novel model and paradigm, Learning and Editing Universal GrAph Prompt Tuning (LEAP), which preserves the theoretical foundation of universal graph prompt tuning while pursuing more ideal prompts. Specifically, we first build the basic universal graph prompts to preserve the theoretical foundation and then employ actor-critic reinforcement learning to select nodes and edit prompts. Extensive experiments on graph- and node-level tasks across various pre-training strategies in both full-shot and few-shot scenarios show that LEAP consistently outperforms fine-tuning and other prompt-based approaches.

cs.LG↗

arXiv2025

OnePiece: The Great Route to Generative Recommendation -- A Case Study from Tencent Algorithm Competition

In past years, the OpenAI's Scaling-Laws shows the amazing intelligence with the next-token prediction paradigm in neural language modeling, which pointing out a free-lunch way to enhance the model performance by scaling the model parameters. In RecSys, the retrieval stage is also follows a 'next-token prediction' paradigm, to recall the hunderds of items from the global item set, thus the generative recommendation usually refers specifically to the retrieval stage (without Tree-based methods). This raises a philosophical question: without a ground-truth next item, does the generative recommendation also holds a potential scaling law? In retrospect, the generative recommendation has two different technique paradigms: (1) ANN-based framework, utilizing the compressed user embedding to retrieve nearest other items in embedding space, e.g, Kuaiformer. (2) Auto-regressive-based framework, employing the beam search to decode the item from whole space, e.g, OneRec. In this paper, we devise a unified encoder-decoder framework to validate their scaling-laws at same time. Our empirical finding is that both of their losses strictly adhere to power-law Scaling Laws ($R^2$>0.9) within our unified architecture.

cs.IR↗

arXiv2025

Radial Attention: $O(n\log n)$ Sparse Attention with Energy Decay for Long Video Generation

Recent advances in diffusion models have enabled high-quality video generation, but the additional temporal dimension significantly increases computational costs, making training and inference on long videos prohibitively expensive. In this paper, we identify a phenomenon we term Spatiotemporal Energy Decay in video diffusion models: post-softmax attention scores diminish as spatial and temporal distance between tokens increase, akin to the physical decay of signal or waves over space and time in nature. Motivated by this, we propose Radial Attention, a scalable sparse attention mechanism with $\mathcal{O}(n \log n)$ complexity that translates energy decay into exponentially decaying compute density, which is significantly more efficient than standard $\mathcal{O}(n^2)$ dense attention and more expressive than linear attention. Specifically, Radial Attention employs a simple, static attention mask where each token attends to spatially nearby tokens, with the attention window size shrinking with temporal distance. Moreover, it allows pre-trained video diffusion models to extend their generation length with efficient LoRA-based fine-tuning. Extensive experiments show that Radial Attention maintains video quality across Wan2.1-14B, HunyuanVideo, and Mochi 1, achieving up to a 1.9$\times$ speedup over the original dense attention. With minimal tuning, it enables video generation up to 4$\times$ longer while reducing training costs by up to 4.4$\times$ compared to direct fine-tuning and accelerating inference by up to 3.7$\times$ compared to dense attention inference. Code is released at \href{https://github.com/mit-han-lab/radial-attention}{https://github.com/mit-han-lab/radial-attention}.

cs.CV↗

arXiv2025

SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention

In Diffusion Transformer (DiT) models, particularly for video generation, attention latency is a major bottleneck due to the long sequence length and the quadratic complexity. We find that attention weights can be separated into two parts: a small fraction of large weights with high rank and the remaining weights with very low rank. This naturally suggests applying sparse acceleration to the first part and low-rank acceleration to the second. Based on this finding, we propose SLA (Sparse-Linear Attention), a trainable attention method that fuses sparse and linear attention to accelerate diffusion models. SLA classifies attention weights into critical, marginal, and negligible categories, applying O(N^2) attention to critical weights, O(N) attention to marginal weights, and skipping negligible ones. SLA combines these computations into a single GPU kernel and supports both forward and backward passes. With only a few fine-tuning steps using SLA, DiT models achieve a 20x reduction in attention computation, resulting in significant acceleration without loss of generation quality. Experiments show that SLA reduces attention computation by 95% without degrading end-to-end generation quality, outperforming baseline methods. In addition, we implement an efficient GPU kernel for SLA, which yields a 13.7x speedup in attention computation and a 2.2x end-to-end speedup in video generation on Wan2.1-1.3B. The code is available at https://github.com/thu-ml/SLA.

cs.LG↗

arXiv2025

Multi-modal Dynamic Proxy Learning for Personalized Multiple Clustering

Multiple clustering aims to discover diverse latent structures from different perspectives, yet existing methods generate exhaustive clusterings without discerning user interest, necessitating laborious manual screening. Current multi-modal solutions suffer from static semantic rigidity: predefined candidate words fail to adapt to dataset-specific concepts, and fixed fusion strategies ignore evolving feature interactions. To overcome these limitations, we propose Multi-DProxy, a novel multi-modal dynamic proxy learning framework that leverages cross-modal alignment through learnable textual proxies. Multi-DProxy introduces 1) gated cross-modal fusion that synthesizes discriminative joint representations by adaptively modeling feature interactions. 2) dual-constraint proxy optimization where user interest constraints enforce semantic consistency with domain concepts while concept constraints employ hard example mining to enhance cluster discrimination. 3) dynamic candidate management that refines textual proxies through iterative clustering feedback. Therefore, Multi-DProxy not only effectively captures a user's interest through proxies but also enables the identification of relevant clusterings with greater precision. Extensive experiments demonstrate state-of-the-art performance with significant improvements over existing methods across a broad set of multi-clustering benchmarks.

cs.LG↗

arXiv2025

On Modality Incomplete Infrared-Visible Object Detection: An Architecture Compatibility Perspective

Infrared and visible object detection (IVOD) is essential for numerous around-the-clock applications. Despite notable advancements, current IVOD models exhibit notable performance declines when confronted with incomplete modality data, particularly if the dominant modality is missing. In this paper, we take a thorough investigation on modality incomplete IVOD problem from an architecture compatibility perspective. Specifically, we propose a plug-and-play Scarf Neck module for DETR variants, which introduces a modality-agnostic deformable attention mechanism to enable the IVOD detector to flexibly adapt to any single or double modalities during training and inference. When training Scarf-DETR, we design a pseudo modality dropout strategy to fully utilize the multi-modality information, making the detector compatible and robust to both working modes of single and double modalities. Moreover, we introduce a comprehensive benchmark for the modality-incomplete IVOD task aimed at thoroughly assessing situations where the absent modality is either dominant or secondary. Our proposed Scarf-DETR not only performs excellently in missing modality scenarios but also achieves superior performances on the standard IVOD modality complete benchmarks. Our code will be available at https://github.com/YinghuiXing/Scarf-DETR.

cs.CV↗

arXiv2025

Twilight: Adaptive Attention Sparsity with Hierarchical Top-$p$ Pruning

Leveraging attention sparsity to accelerate long-context large language models (LLMs) has been a hot research topic. However, current algorithms such as sparse attention or key-value (KV) cache compression tend to use a fixed budget, which presents a significant challenge during deployment because it fails to account for the dynamic nature of real-world scenarios, where the optimal balance between accuracy and efficiency can vary greatly. In this paper, we find that borrowing top-$p$ sampling (nucleus sampling) to sparse attention can surprisingly achieve adaptive budgeting. Based on this, we propose Twilight, a framework to bring adaptive sparsity to any existing sparse attention algorithm without sacrificing their accuracy. Empirical results show that Twilight can adaptively prune at most 98% of redundant tokens, leading to $15.4\times$ acceleration in self-attention operations and $3.9\times$ acceleration in end-to-end per token latency in long context LLM decoding.

cs.LG↗

arXiv2025

Accumulative SGD Influence Estimation for Data Attribution

Modern data-centric AI needs precise per-sample influence. Standard SGD-IE approximates leave-one-out effects by summing per-epoch surrogates and ignores cross-epoch compounding, which misranks critical examples. We propose ACC-SGD-IE, a trajectory-aware estimator that propagates the leave-one-out perturbation across training and updates an accumulative influence state at each step. In smooth strongly convex settings it achieves geometric error contraction and, in smooth non-convex regimes, it tightens error bounds; larger mini-batches further reduce constants. Empirically, on Adult, 20 Newsgroups, and MNIST under clean and corrupted data and both convex and non-convex training, ACC-SGD-IE yields more accurate influence estimates, especially over long epochs. For downstream data cleansing it more reliably flags noisy samples, producing models trained on ACC-SGD-IE cleaned data that outperform those cleaned with SGD-IE.

cs.LG↗