arXiv subjects

Tong Zhao

Publications and source records attributed to Tong Zhao.

At least 73 records · Page 4Linked to original sources

arXiv2026

DyWeight: Dynamic Gradient Weighting for Few-Step Diffusion Sampling

Diffusion Models (DMs) have achieved state-of-the-art generative performance across multiple modalities, yet their sampling process remains prohibitively slow due to the need for hundreds of function evaluations. Recent progress in multi-step ODE solvers has greatly improved efficiency by reusing historical gradients, but existing methods rely on handcrafted coefficients that fail to adapt to the non-stationary dynamics of diffusion sampling. To address this limitation, we propose Dynamic Gradient Weighting (DyWeight), a lightweight, learning-based multi-step solver that introduces a streamlined implicit coupling paradigm. By relaxing classical numerical constraints, DyWeight learns unconstrained time-varying parameters that adaptively aggregate historical gradients while intrinsically scaling the effective step size. This implicit time calibration accurately aligns the solver's numerical trajectory with the model's internal denoising dynamics under large integration steps, avoiding complex decoupled parameterizations and optimizations. Extensive experiments on CIFAR-10, FFHQ, AFHQv2, ImageNet64, LSUN-Bedroom, Stable Diffusion and FLUX.1-dev demonstrate that DyWeight achieves superior visual fidelity and stability with significantly fewer function evaluations, establishing a new state-of-the-art among efficient diffusion solvers. Code is available at https://github.com/Westlake-AGI-Lab/DyWeight

cs.CV↗

arXiv2026

FlexRec: Adapting LLM-based Recommenders for Flexible Needs via Reinforcement Learning

Modern recommender systems must adapt to dynamic, need-specific objectives for diverse recommendation scenarios, yet most traditional recommenders are optimized for a single static target and struggle to reconfigure behavior on demand. Recent advances in reinforcement-learning-based post-training have unlocked strong instruction-following and reasoning capabilities in LLMs, suggesting a principled route for aligning them to complex recommendation goals. Motivated by this, we study closed-set autoregressive ranking, where an LLM generates a permutation over a fixed candidate set conditioned on user context and an explicit need instruction. However, applying RL to this setting faces two key obstacles: (i) sequence-level rewards yield coarse credit assignment that fails to provide fine-grained training signals, and (ii) interaction feedback is sparse and noisy, which together lead to inefficient and unstable updates. We propose FlexRec, a post-training RL framework that addresses both issues with (1) a causally grounded item-level reward based on counterfactual swaps within the remaining candidate pool, and (2) critic-guided, uncertainty-aware scaling that explicitly models reward uncertainty and down-weights low-confidence rewards to stabilize learning under sparse supervision. Across diverse recommendation scenarios and objectives, FlexRec achieves substantial gains: it improves NDCG@5 by up to \textbf{59\%} and Recall@5 by up to \textbf{109.4\%} in need-specific ranking, and further achieves up to \textbf{24.1\%} Recall@5 improvement under generalization settings, outperforming strong traditional recommenders and LLM-based baselines.

cs.LG↗

arXiv2026

Exploring the spin dependence on mass inclination and distance for the newly discovered black hole X-ray binary Swift J151857.0-572147

The black hole X-ray binary (BHXRB) Swift J151857.0-572147 was discovered during its first outburst in March 2024. We review the archive of NICER observations from this outburst, focusing on the soft states. We select spectra for which the disk to total flux ratio exceeds 0.8 and the coronal scattering fraction fsc is less than 25%, conditions under which the accretion disk is expected to extend to the innermost stable circular orbit (ISCO) and remains geometrically thin. Through a continuum fitting analysis, we explore the dependence of spin on mass, inclination, and distance. We constrain the spin within the parameter space typical of stellar-mass black holes (sBHs), assuming a mass around 10 solar masses, inclination angles between 20 and 60 degree, and distances between 4 and 16 kpc. For fiducial parameters: a mass of 10 solar masses, a distance of 10 kpc, and an inclination angle of 40 degree, a moderate spin of approximately 0.7 is obtained. However, precise determination of the spin will require accurate measurements of these parameters. Our analysis provides a framework to infer the spin and estimate its uncertainties once more precise measurements of mass, distance, and inclination become available. As we demonstrate, lower inclination angles, greater distances, or larger black hole masses result in higher spin values.

astro-ph.HE↗

arXiv2026

Heuristic Methods are Good Teachers to Distill MLPs for Graph Link Prediction

Link prediction is a crucial graph-learning task with applications including citation prediction and product recommendation. Distilling Graph Neural Networks (GNNs) teachers into Multi-Layer Perceptrons (MLPs) students has emerged as an effective approach to achieve strong performance and reducing computational cost by removing graph dependency. However, existing distillation methods only use standard GNNs and overlook alternative teachers such as specialized model for link prediction (GNN4LP) and heuristic methods (e.g., common neighbors). This paper first explores the impact of different teachers in GNN-to-MLP distillation. Surprisingly, we find that stronger teachers do not always produce stronger students: MLPs distilled from GNN4LP can underperform those distilled from simpler GNNs, while weaker heuristic methods can teach MLPs to near-GNN performance with drastically reduced training costs. Building on these insights, we propose Ensemble Heuristic-Distilled MLPs (EHDM), which eliminates graph dependencies while effectively integrating complementary signals via a gating mechanism. Experiments on ten datasets show an average 7.93% improvement over previous GNN-to-MLP approaches with 1.95-3.32 times less training time, indicating EHDM is an efficient and effective link prediction method. Our code is available at https://github.com/ZongyueQin/EHDM

cs.LG↗

arXiv2026

A Pre-training Framework for Relational Data with Information-theoretic Principles

Relational databases underpin critical infrastructure across a wide range of domains, yet the design of generalizable pre-training strategies for learning from relational databases remains an open challenge due to task heterogeneity. Specifically, there exist many possible downstream tasks, as tasks are defined based on relational schema graphs, temporal dependencies, and SQL-defined label logics. An effective pre-training framework is desired to take these factors into account in order to obtain task-aware representations. By incorporating knowledge of the underlying distribution that drives label generation, downstream tasks can benefit from relevant side-channel information. To bridge this gap, we introduce Task Vector Estimation (TVE), a novel pre-training framework that constructs predictive supervisory signals via set-based aggregation over schema traversal graphs, explicitly modeling next-window relational dynamics. We formalize our approach through an information-theoretic lens, demonstrating that task-informed representations retain more relevant signals than those obtained without task priors. Extensive experiments on the RelBench benchmark show that TVE consistently outperforms traditional pre-training baselines. Our findings advocate for pre-training objectives that encode task heterogeneity and temporal structure as design principles for predictive modeling on relational databases. Our code is publicly available at https://github.com/quang-truong/task-vector-estimation.

cs.LG↗

arXiv2026

CSST Strong Lensing Preparation: Cosmological constraints from double-source-plane strong lensing systems in era of CSST

Double source plane strong lensing (DSPL) systems offer a robust, independent probe of cosmological parameters. The Chinese Space Station Telescope (CSST) is expected to discover hundreds of DSPLs, yet the survey modes and system configurations that best enable cosmological inference remain uncertain. To investigate the impact of varying signal-to-noise ratios (SNR) and Einstein radius ratios of DSPLs (denoted as $β^{-1}$ parameters) on cosmographic inference under different CSST survey modes (Wide Field (WF), Deep Field (DF), and Ultra-Deep Field (UDF)), we simulate and model mock lenses with Singular Isothermal Ellipsoid (SIE) mass profiles and Sérsic sources whose image properties are tailored to CSST specifications. Assuming a flat $w$CDM universe with fiducial values $Ω_{\rm m} = 0.30966$ and $w = -1$, and uniform priors of $Ω_{\rm m} \in [0, 1]$ and $w \in [-2, -1/3$), we find that the constraining power on cosmological parameters for a given DSPL system increases significantly with survey depth. For a representative DSPL system with two prominent arcs and a moderate $β^{-1}=1.17$, the constraints on ($w, Ω_{\rm m}$) improve from ($-1.28_{-1.00}^{+0.64}, 0.50_{-0.32}^{+0.28}$) in the WF to ($-1.59_{-0.32}^{+0.63}, 0.42_{-0.06}^{+0.15}$) in the UDF. Furthermore, we find that systems with smaller $β$ values yield tighter cosmographic constraints. We conclude that DSPL systems identified in UDF observations, particularly those with small $β$, are the most promising candidates for early-stage cosmological studies with CSST.

astro-ph.CO↗

arXiv2026

V2X-Radar: A Multi-modal Dataset with 4D Radar for Cooperative Perception

Modern autonomous vehicle perception systems often struggle with occlusions and limited perception range. Previous studies have demonstrated the effectiveness of cooperative perception in extending the perception range and overcoming occlusions, thereby enhancing the safety of autonomous driving. In recent years, a series of cooperative perception datasets have emerged; however, these datasets primarily focus on cameras and LiDAR, neglecting 4D Radar, a sensor used in single-vehicle autonomous driving to provide robust perception in adverse weather conditions. In this paper, to bridge the gap created by the absence of 4D Radar datasets in cooperative perception, we present V2X-Radar, the first large-scale, real-world multi-modal dataset featuring 4D Radar. V2X-Radar dataset is collected using a connected vehicle platform and an intelligent roadside unit equipped with 4D Radar, LiDAR, and multi-view cameras. The collected data encompasses sunny and rainy weather conditions, spanning daytime, dusk, and nighttime, as well as various typical challenging scenarios. The dataset consists of 20K LiDAR frames, 40K camera images, and 20K 4D Radar data, including 350K annotated boxes across five categories. To support various research domains, we have established V2X-Radar-C for cooperative perception, V2X-Radar-I for roadside perception, and V2X-Radar-V for single-vehicle perception. Furthermore, we provide comprehensive benchmarks across these three sub-datasets. We will release all datasets and benchmark codebase at https://huggingface.co/datasets/yanglei18/V2X-Radar and https://github.com/yanglei18/V2X-Radar.

cs.CV↗

arXiv2026

Approximately Optimal Global Planning for Contact-Rich SE(2) Manipulation on a Graph of Reachable Sets

If we consider human manipulation, it is clear that contact-rich manipulation (CRM)-the ability to use any surface of the manipulator to make contact with objects-can be far more efficient and natural than relying solely on end-effectors (i.e., fingertips). However, state-of-the-art model-based planners for CRM are still focused on feasibility rather than optimality, limiting their ability to fully exploit CRM's advantages. We introduce a new paradigm that computes approximately optimal manipulator plans. This approach has two phases. Offline, we construct a graph of mutual reachable sets, where each set contains all object orientations reachable from a starting object orientation and grasp. Online, we plan over this graph, effectively computing and sequencing local plans for globally optimized motion. On a challenging, representative contact-rich task, our approach outperforms a leading planner, reducing task cost by 61%. It also achieves a 91% success rate across 250 queries and maintains sub-minute query times, ultimately demonstrating that globally optimized contact-rich manipulation is now practical for real-world tasks.

cs.RO↗

arXiv2026

Physics-Driven Data Generation for Contact-Rich Manipulation via Trajectory Optimization

We present a low-cost data generation pipeline that integrates physics-based simulation, human demonstrations, and model-based planning to efficiently generate large-scale, high-quality datasets for contact-rich robotic manipulation tasks. Starting with a small number of embodiment-flexible human demonstrations collected in a virtual reality simulation environment, the pipeline refines these demonstrations using optimization-based kinematic retargeting and trajectory optimization to adapt them across various robot embodiments and physical parameters. This process yields a diverse, physically consistent dataset that enables cross-embodiment data transfer, and offers the potential to reuse legacy datasets collected under different hardware configurations or physical parameters. We validate the pipeline's effectiveness by training diffusion policies from the generated datasets for challenging contact-rich manipulation tasks across multiple robot embodiments, including a floating Allegro hand and bimanual robot arms. The trained policies are deployed zero-shot on hardware for bimanual iiwa arms, achieving high success rates with minimal human input. Project website: https://lujieyang.github.io/physicsgen/.

cs.RO↗

arXiv2026

Limits to Extracting Neutron-Star Physics Constraints from NICER Pulse Profiles

Modeling energy-dependent X-ray pulse profiles from rotation-powered millisecond pulsars observed with NICER has emerged as a promising avenue for measuring neutron star radii and probing the equation of state of cold, ultra-dense matter. However, pulse profile models have often required an unwieldy number of parameters to account for complex surface emission geometries, introducing the risk of overfitting and degeneracies. To explore the number of model parameters that can be inferred uniquely, we perform a quantitative assessment of the information content in X-ray pulse profiles by applying Fourier methods. We determine the number of independent observables that can be reliably extracted from the pulse shapes, as well as from complementary X-ray spectral data obtained with XMM-Newton, for key NICER targets. Our analysis provides a framework for evaluating the match between model complexity and data constraints. It also demonstrates the importance of incorporating in the model the pulsed components of the magnetospheric non-thermal emission, which may often contribute significantly to the observed spectra. Our results highlight limitations in previous inferences of neutron-star radii from NICER observations, which may have incorporated model complexity not supported by the data.

astro-ph.HE↗

arXiv2026

From Failure to Mastery: Generating Hard Samples for Tool-use Agents

The advancement of LLM agents with tool-use capabilities requires diverse and complex training corpora. Existing data generation methods, which predominantly follow a paradigm of random sampling and shallow generation, often yield simple and homogeneous trajectories that fail to capture complex, implicit logical dependencies. To bridge this gap, we introduce HardGen, an automatic agentic pipeline designed to generate hard tool-use training samples with verifiable reasoning. Firstly, HardGen establishes a dynamic API Graph built upon agent failure cases, from which it samples to synthesize hard traces. Secondly, these traces serve as conditional priors to guide the instantiation of modular, abstract advanced tools, which are subsequently leveraged to formulate hard queries. Finally, the advanced tools and hard queries enable the generation of verifiable complex Chain-of-Thought (CoT), with a closed-loop evaluation feedback steering the continuous refinement of the process. Extensive evaluations demonstrate that a 4B parameter model trained with our curated dataset achieves superior performance compared to several leading open-source and closed-source competitors (e.g., GPT-5.2, Gemini-3-Pro and Claude-Opus-4.5). Our code, models, and dataset will be open-sourced to facilitate future research.

cs.CL↗

arXiv2026

Exploiting ID-Text Complementarity via Ensembling for Sequential Recommendation

Modern Sequential Recommendation (SR) models commonly utilize modality features to represent items, motivated in large part by recent advancements in language and vision modeling. To do so, several works completely replace ID embeddings with modality embeddings, claiming that modality embeddings render ID embeddings unnecessary because they can match or even exceed ID embedding performance. On the other hand, many works jointly utilize ID and modality features, but posit that complex fusion strategies, such as multi-stage training and/or intricate alignment architectures, are necessary for this joint utilization. However, underlying both these lines of work is a lack of understanding of the complementarity of ID and modality features. In this work, we address this gap by studying the complementarity of ID- and text-based SR models. We show that these models do learn complementary signals, meaning that either should provide performance gain when used properly alongside the other. Motivated by this, we propose a new SR method that preserves ID-text complementarity through independent model training, then harnesses it through a simple ensembling strategy. Despite this method's simplicity, we show it outperforms several competitive SR baselines, implying that both ID and text features are necessary to achieve state-of-the-art SR performance but complex fusion architectures are not.

cs.LG↗

arXiv2025

Robotic Sorting Systems: Robot Management and Layout Design Optimization

In the contemporary logistics industry, automation plays a pivotal role in enhancing production efficiency and expanding industrial scale. Autonomous mobile robots, in particular, have become integral to the modernization efforts in warehouses. One noteworthy application in robotic warehousing is the robotic sorting system (RSS), distinguished by its characteristics such as cost-effectiveness, simplicity, scalability, and adaptable throughput control. While previous research has focused on analyzing the efficiency of RSS, it often assumed an ideal robot management system ignoring potential queuing delays by assuming constant travel times. This study relaxes this assumption and explores the quantitative relationship between RSS configuration parameters and system throughput. We introduce a novel robot traffic management method, named the rhythmic control for sorting scenario (RC-S), for RSS operations, equipped with an estimation formula establishing the relationship between system performance and configurations. Simulations validate that RC-S reduces average service time by 10.3\% compared to the classical cooperative A* algorithm, while also improving throughput and runtime. Based on the performance analysis of RC-S, we further develop a layout optimization model for RSS, considering RSS configuration, desired throughput, and costs, to minimize expenses and determine the best layout. Numerical studies show that at lower throughput levels, facility costs dominate, while at higher throughput levels, labor costs prevail. Additionally, due to traffic efficiency limitations, RSS is well-suited for small-scale operations like end-of-supply-chain distribution centers.

math.OC↗

arXiv2025

D-GARA: A Dynamic Benchmarking Framework for GUI Agent Robustness in Real-World Anomalies

Developing intelligent agents capable of operating a wide range of Graphical User Interfaces (GUIs) with human-level proficiency is a key milestone on the path toward Artificial General Intelligence. While most existing datasets and benchmarks for training and evaluating GUI agents are static and idealized, failing to reflect the complexity and unpredictability of real-world environments, particularly the presence of anomalies. To bridge this research gap, we propose D-GARA, a dynamic benchmarking framework, to evaluate Android GUI agent robustness in real-world anomalies. D-GARA introduces a diverse set of real-world anomalies that GUI agents commonly face in practice, including interruptions such as permission dialogs, battery warnings, and update prompts. Based on D-GARA framework, we construct and annotate a benchmark featuring commonly used Android applications with embedded anomalies to support broader community research. Comprehensive experiments and results demonstrate substantial performance degradation in state-of-the-art GUI agents when exposed to anomaly-rich environments, highlighting the need for robustness-aware learning. D-GARA is modular and extensible, supporting the seamless integration of new tasks, anomaly types, and interaction scenarios to meet specific evaluation goals.

cs.AI↗

arXiv2025

Hierarchical Token Prepending: Enhancing Information Flow in Decoder-based LLM Embeddings

Large language models produce powerful text embeddings, but their causal attention mechanism restricts the flow of information from later to earlier tokens, degrading representation quality. While recent methods attempt to solve this by prepending a single summary token, they over-compress information, hence harming performance on long documents. We propose Hierarchical Token Prepending (HTP), a method that resolves two critical bottlenecks. To mitigate attention-level compression, HTP partitions the input into blocks and prepends block-level summary tokens to subsequent blocks, creating multiple pathways for backward information flow. To address readout-level over-squashing, we replace last-token pooling with mean-pooling, a choice supported by theoretical analysis. HTP achieves consistent performance gains across 11 retrieval datasets and 30 general embedding benchmarks, especially in long-context settings. As a simple, architecture-agnostic method, HTP enhances both zero-shot and finetuned models, offering a scalable route to superior long-document embeddings.

cs.CL↗

arXiv2025

FunReason-MT Technical Report: Advanced Data Synthesis Solution for Real-world Multi-Turn Tool-use

Function calling (FC) empowers large language models (LLMs) and autonomous agents to interface with external tools, a critical capability for solving complex, real-world problems. As this ability becomes increasingly central to advanced AI systems, the need for high-quality, multi-turn training data to develop and refine it cannot be overstated. Existing data synthesis methods, such as random environment sampling or multi-agent role-playing, are not powerful enough to generate high-quality data in real-world environments. Practical challenges come in three folds: targeted data synthesis, hard query construction, and multi-turn logical dependency. To address these structural deficiencies, we present FunReason-MT, a novel data synthesis framework for real-world multi-turn tool use. FunReason-MT resolves the complexity barrier in multi-turn FC data by employing 1) Environment-API Graph Interactions to gather varied high-quality trajectories with targeted tool, 2) Advanced Tool-Query Synthesis to simplify hard query construction, and 3) Guided Iterative Chain for sophisticated CoT generation. Evaluations on Berkeley Function-Calling Leaderboard (BFCLv3) demonstrate the power of our framework: a 4B model built upon FunReason-MT generated data achieves state-of-the-art performance among comparable-sized models. Further performance improvements on BFCLv4 confirm that FunReason-MT provides a reliable and robust source for agentic learning.

cs.AI↗

arXiv2025

Every Activation Boosted: Scaling General Reasoner to 1 Trillion Open Language Foundation

We introduce Ling 2.0, a series reasoning-oriented language foundation built upon the principle that every activation boosts reasoning capability. Designed to scale from tens of billions to one trillion parameters under a unified Mixture-of-Experts (MoE) paradigm, Ling 2.0 emphasizes high sparsity, cross-scale consistency, and efficiency guided by empirical scaling laws. The series includes three non-thinking (instruct) models - Ling-mini-2.0, Ling-flash-2.0, and Ling-1T - ranging from 16B to 1T total parameters and achieving up to 7-fold active-compute efficiency compared with dense counterparts. Ling 2.0 integrates coordinated innovations across model architecture, pre-training, post-training, and infrastructure: a high-sparsity MoE with MTP for efficient reasoning, reasoning-oriented data and mid-training CoT activation, reinforcement-based fine-tuning (DFT, Evo-CoT), and full-scale FP8 training with fine-grained heterogeneous pipelines. At the trillion scale, Ling-1T establishes a new Pareto frontier of reasoning accuracy versus computational efficiency, demonstrating that sparse activation, when properly aligned with reasoning objectives, enables scalable and efficient intelligence. Collectively, Ling 2.0 provides a coherent, open, and efficient foundation for advancing future reasoning and thinking models, including the Ring series built upon the same base.

cs.CL↗

arXiv2025

Representational power of selected neural network quantum states in second quantization

Neural network quantum states emerge as a promising tool for solving quantum many-body problems. However, its successes and limitations are still not well-understood in particular for Fermions with complex sign structures. Based on our recent work [J. Chem. Theory Comput. 21, 10252-10262 (2025)], we generalizes the restricted Boltzmann machine to a more general class of states for Fermions, formed by product of `neurons' and hence will be referred to as neuron product states (NPS). NPS builds correlation in a very different way, compared with the closely related correlator product states (CPS) [H. J. Changlani, et al. Phys. Rev. B, 80, 245116 (2009)], which use full-rank local correlators. In constrast, each correlator in NPS contains long-range correlations across all the sites, with its representational power constrained by the simple function form. We prove that products of such simple nonlocal correlators can approximate any wavefunction arbitrarily well under certain mild conditions on the form of activation functions. In addition, we also provide elementary proofs for the universal approximation capabilities of feedforward neural network (FNN) and neural network backflow (NNBF) in second quantization. Together, these results provide a deeper insight into the neural network representation of many-body wavefunctions in second quantization.

quant-ph↗