arXiv subjects

Ying Qian

Publications and source records attributed to Ying Qian.

16 recordsLinked to original sources

arXiv2026

DexArena: A Unified Benchmark for Long-Horizon Dexterous Manipulation

Long-horizon dexterous manipulation remains a fundamental challenge for robot learning, requiring the composition of multiple skills, precise bimanual coordination, generalizable visual understanding, and robust skill transitions. Yet existing manipulation benchmarks largely emphasize isolated skills or support only a limited range of end-effectors, making these capabilities difficult to evaluate systematically. We introduce DexArena, a benchmark designed to evaluate learning and generalization in long-horizon bimanual dexterous manipulation. DexArena features 10 long-horizon tasks and 30 stage-level tasks spanning diverse household and industrial scenarios. Each long-horizon task is composed of explicitly defined stages with physically grounded success conditions, enabling reliable evaluation of both intermediate progress and end-to-end task completion. A unified benchmark interface and verified human-teleoperated demonstrations enable testing different policy learning algorithms, with standardized simulation configurations, scene randomization, trajectory replay, and task-level evaluation. Through extensive baseline experiments, we identify substantial challenges in precise manipulation, generalization to scene variation, and skill composition. DexArena establishes a challenging and reproducible benchmark for developing robot learning methods that move toward generalizable long-horizon dexterous behavior.

cs.RO↗

arXiv2026

OneDemo: Unified Policy Learning and Data Generation from a Single Demonstration

Learning robot policies from demonstrations is often limited by the cost of collecting diverse, high-quality expert data. While an appealing alternative is to expand a single successful demonstration into a diverse set of successful trajectories, existing augmentation methods typically rely on manually designed transformation rules or complex trajectory planning, requiring substantial task-specific engineering and human effort. We introduce OneDemo, a reinforcement learning framework that learns to edit a single successful demonstration for new task configurations. We formulate demonstration editing as a structured reinforcement learning problem, in which an editor learns, from sparse task-success rewards, both when to transition between object-centric trajectory segments and how to geometrically adapt each segment. The learned editor serves both as a task policy and as a reusable demonstration generator. Across 15 Meta-World tasks, OneDemo reaches a 92.7% success rate within 53.7k environment interactions on average. Across 9 DexMimicGen tasks, it generates successful demonstrations with a 98.4% average success rate, and BC-RNN policies trained on the generated data achieve 99.6% average success at matched dataset scale. These results show that learning to edit a single successful demonstration provides a structured and effective basis for both policy learning and scalable demonstration generation.

cs.RO↗

arXiv2026

Forecasting Without Full Identification: Reliability and Computational Cost in Clot-Growth Simulation

We forecast clot growth from sparse early measurements with incomplete biochemical information. Using 1,000 simulated trajectories, we compare inverse search, which weights candidate inputs by their agreement with early observations, with a direct multilayer perceptron (MLP) predicting future clot size. Inverse search is more accurate when tissue factor alone, or tissue factor and fibrinogen, are unknown. When all five inputs are unknown, direct prediction achieves 2.16% pooled relative $L_2$ forecast error, outperforming search with 8,192 candidates using a forward MLP (3.25%) or latent neural ordinary differential equation model (3.36%). A conditional error bound separates candidate disagreement, weight on poor early fits, surrogate error, and candidate coverage. Increasing randomized quasi-Monte Carlo candidate budgets from 512 to 32,768 reduces numerical variation. A covariance score ranks additional assays by expected forecast value while accounting for measurement noise. At 10% range-scaled assay noise, incorporating assay uncertainty reduces forecast error from about 5% to below 3% for both surrogates. An independent reaction cascade verifies candidate integration against tensor quadrature, with mean normalized forecast-integration error below $10^{-5}$ at 32,768 candidates. These results demonstrate accurate clot-growth forecasting without full biochemical identification and support selecting prediction strategies and additional measurements according to accuracy, reliability, and computational cost.

cs.LG↗

arXiv2026

AMO: Operator-level Adaptive Muon Orthogonalization

Muon has recently emerged as a competitive alternative to AdamW for large-scale pre-training, with orthogonalization via Newton-Schulz (NS) iteration as its core operation. Standard Muon applies a uniform NS schedule to all parameter matrices, overlooking possible differences in orthogonalization difficulty and its impact on performance. Through a systematic empirical study, we show that this per-matrix heterogeneity is pervasive and strongly associated with matrix geometry, which evolves dynamically across operator types, training stages, and network depths. Therefore, uniform NS schedules can lead to uneven orthogonalization quality across the model. Motivated by these findings, we propose Operator-level Adaptive Muon Orthogonalization (AMO), an observe-then-commit method that measures weight geometry by operator type early in training and then uses these signals to allocate the NS budget for the remainder of training. AMO delivers consistent improvements over uniform-schedule Muon across standard, prolonged, and continual pre-training, surpassing the strongest baseline by +0.76 on Llama3.1-1.4B and +0.51 on Qwen3-1.7B in average downstream performance of 12 evaluation tasks, with gains persisting at Llama3.1-4B scale.

cs.LG↗

arXiv2026

ConfRetro: a 3D-aware template-free method for enhancing retrosynthesis via molecular conformer information

Motivation: Retrosynthesis plays a crucial role in organic synthesis and drug discovery, focusing on identifying a set of reactants capable of synthesizing a target product molecule. Although the existing approaches have shown promising results, they do not fully exploit 3D conformer information and molecular spatial structure, which can hinder stereochemically consistent and chemically plausible predictions. Results: To tackle this problem, we propose ConfRetro, a Transformer-based template-free method that integrates molecular conformer information and spatial structure. We devise an Atom-align Fusion module to combine 3D positional information at the model input stage, ensuring alignment between atom tokens and corresponding 3D representations. Furthermore, we design a Distance-weighted Attention mechanism to guide self-attention, constraining the receptive field of model and emphasizing chemically relevant atom pairs in 3D space. Experiments conducted on the USPTO-50K and USPTO-FULL datasets demonstrate that ConfRetro significantly outperforms existing template-free approaches, achieving a new state-of-the-art performance. Case studies further highlight its capability to predict accurate and chemically plausible reactants, even for target molecules with intricate structures. Moreover, when plugged into a standard retrosynthetic search, ConfRetro recovers feasible synthetic routes for multiple representative drug molecules (e.g. Camptothecin). Availability and implementation: ConfRetro is available at https://github.com/Jesse-zjx/ConfRetro. Archival snapshot is available at https://doi.org/10.5281/zenodo.20785018.

cs.LG↗

arXiv2026

CHIPS: Efficient CLIP Adaptation via Curvature-aware Hybrid Influence-based Data Selection

Adapting CLIP to vertical domains is typically approached by novel fine-tuning strategies or by continual pre-training (CPT) on large domain-specific datasets. Yet, data itself remains an underexplored factor in this process. We revisit this task from a data-centric perspective: Can effective data selection substitute for large-scale datasets in CPT? We introduce CHIPS (Curvature-aware Hybrid Influence in Projection Subspace), which assigns each image-text pair a utility score that integrates three complementary factors aligned with three goals: faithfulness via a curvature-aware and Newton-style alignment computed in CLIP's end-point subspace; scalability via an InfoNCE-aware curvature estimator with Johnson-Lindenstrauss (JL) sketching; and retention via a selection-aware relevance weight combined with learnability to balance target adaptation against general-domain preservation. We justify this design theoretically by proving a lower-bound guarantee on the proxy's correlation with full-parameter alignment and by characterizing the bias-variance trade-offs introduced by curvature mixing and JL sketching. We evaluate CHIPS empirically across various settings: 1) CHIPS attains state-of-the-art performance among selection baselines on 17 medical benchmarks, matches full-dataset CPT with 30% of the data, and outperforms half-dataset CPT using only 10%; 2) on 31 general-domain benchmarks, CHIPS yields the least performance drop under all retention ratios.

cs.LG↗

arXiv2026

Towards Efficient Medical Reasoning with Minimal Fine-Tuning Data

Supervised Fine-Tuning (SFT) of the language backbone plays a pivotal role in adapting Vision-Language Models (VLMs) to specialized domains such as medical reasoning. However, existing SFT practices often rely on unfiltered textual datasets that contain redundant and low-quality samples, leading to substantial computational costs and suboptimal performance in complex clinical scenarios. Although existing methods attempt to alleviate this problem by selecting data based on sample difficulty, defined by knowledge and reasoning complexity, they overlook each sample's optimization utility reflected in its gradient. Interestingly, we find that gradient-based influence alone favors easy-to-optimize samples that cause large parameter shifts but lack deep reasoning chains, while difficulty alone selects noisy or overly complex textual cases that fail to guide stable optimization. Based on this observation, we propose a data selection strategy, Difficulty-Influence Quadrant (DIQ), which prioritizes samples in the "high-difficulty-high-influence" quadrant to balance complex clinical reasoning with substantial gradient influence. This enables efficient medical reasoning for VLMs with minimal fine-tuning data. Furthermore, Human and LLM-as-a-judge evaluations show that DIQ-selected subsets demonstrate higher data quality and generate clinical reasoning that is more aligned with expert practices in differential diagnosis, safety check, and evidence citation, as DIQ emphasizes samples that foster expert-like reasoning patterns. Extensive experiments on medical reasoning benchmarks demonstrate that DIQ enables VLM backbones fine-tuned on only 1% of selected data to match full-dataset performance, while using 10% consistently outperforms baseline methods, highlighting the superiority of principled data selection over brute-force scaling. The code is available at https://github.com/mihara-bot/DIQ.

cs.CL↗

arXiv2026

APEX: Learning Adaptive Priorities for Multi-Objective Alignment in Vision-Language Generation

Multi-objective alignment for text-to-image generation is commonly implemented via static linear scalarization, but fixed weights often fail under heterogeneous rewards, leading to optimization imbalance where models overfit high-variance, high-responsiveness objectives (e.g., OCR) while under-optimizing perceptual goals. We identify two mechanistic causes: variance hijacking, where reward dispersion induces implicit reweighting that dominates the normalized training signal, and gradient conflicts, where competing objectives produce opposing update directions and trigger seesaw-like oscillations. We propose APEX (Adaptive Priority-based Efficient X-objective Alignment), which stabilizes heterogeneous rewards with Dual-Stage Adaptive Normalization and dynamically schedules objectives via P^3 Adaptive Priorities that combine learning potential, conflict penalty, and progress need. On Stable Diffusion 3.5, APEX achieves improved Pareto trade-offs across four heterogeneous objectives, with balanced gains of +1.31 PickScore, +0.35 DeQA, and +0.53 Aesthetics while maintaining competitive OCR accuracy, mitigating the instability of multi-objective alignment.

cs.CV↗

arXiv2025

Copy-Augmented Representation for Structure Invariant Template-Free Retrosynthesis

Retrosynthesis prediction is fundamental to drug discovery and chemical synthesis, requiring the identification of reactants that can produce a target molecule. Current template-free methods struggle to capture the structural invariance inherent in chemical reactions, where substantial molecular scaffolds remain unchanged, leading to unnecessarily large search spaces and reduced prediction accuracy. We introduce C-SMILES, a novel molecular representation that decomposes traditional SMILES into element-token pairs with five special tokens, effectively minimizing editing distance between reactants and products. Building upon this representation, we incorporate a copy-augmented mechanism that dynamically determines whether to generate new tokens or preserve unchanged molecular fragments from the product. Our approach integrates SMILES alignment guidance to enhance attention consistency with ground-truth atom mappings, enabling more chemically coherent predictions. Comprehensive evaluation on USPTO-50K and large-scale USPTO-FULL datasets demonstrates significant improvements: 67.2% top-1 accuracy on USPTO-50K and 50.8% on USPTO-FULL, with 99.9% validity in generated molecules. This work establishes a new paradigm for structure-aware molecular generation with direct applications in computational drug discovery.

cs.LG↗

arXiv2025

Reasoning-Enhanced Large Language Models for Molecular Property Prediction

Molecular property prediction is crucial for drug discovery and materials science, yet existing approaches suffer from limited interpretability, poor cross-task generalization, and lack of chemical reasoning capabilities. Traditional machine learning models struggle with task transferability, while specialized molecular language models provide little insight into their decision-making processes. To address these limitations, we propose \textbf{MPPReasoner}, a multimodal large language model that incorporates chemical reasoning for molecular property prediction. Our approach, built upon Qwen2.5-VL-7B-Instruct, integrates molecular images with SMILES strings to enable comprehensive molecular understanding. We develop a two-stage training strategy: supervised fine-tuning (SFT) using 16,000 high-quality reasoning trajectories generated through expert knowledge and multiple teacher models, followed by Reinforcement Learning from Principle-Guided Rewards (RLPGR). RLPGR employs verifiable, rule-based rewards that systematically evaluate chemical principle application, molecular structure analysis, and logical consistency through computational verification. Extensive experiments across 8 datasets demonstrate significant performance improvements, with MPPReasoner outperforming the best baselines by 7.91\% and 4.53\% on in-distribution and out-of-distribution tasks respectively. MPPReasoner exhibits exceptional cross-task generalization and generates chemically sound reasoning paths that provide valuable insights into molecular property analysis, substantially enhancing both interpretability and practical utility for chemists. Code is available at https://anonymous.4open.science/r/MPPReasoner-12687.

cs.LG↗

arXiv2025

Meta-rater: A Multi-dimensional Data Selection Method for Pre-training Language Models

The composition of pre-training datasets for large language models (LLMs) remains largely undisclosed, hindering transparency and efforts to optimize data quality, a critical driver of model performance. Current data selection methods, such as natural language quality assessments, diversity-based filters, and classifier-based approaches, are limited by single-dimensional evaluation or redundancy-focused strategies. To address these gaps, we propose four dimensions to evaluate data quality: professionalism, readability, reasoning, and cleanliness. We further introduce Meta-rater,a multi-dimensional data selection method that integrates these dimensions with existing quality metrics through learned optimal weightings. Meta-rater employs proxy models to train a regression model that predicts validation loss, enabling the identification of optimal combinations of quality scores. Experiments demonstrate that Meta-rater doubles convergence speed for 1.3B parameter models and improves downstream task performance by 3.23, with advantages that scale to models as large as 7.2B parameters. Our work establishes that holistic, multi-dimensional quality integration significantly outperforms conventional single-dimension approaches, offering a scalable paradigm for enhancing pre-training efficiency and model capability. To advance future research, we release scripts, data, and models at https://github.com/opendatalab/Meta-rater.

cs.CL↗

arXiv2025

SID: Benchmarking Guided Instruction Capabilities in STEM Education with a Socratic Interdisciplinary Dialogues Dataset

Fostering students' abilities for knowledge integration and transfer in complex problem-solving scenarios is a core objective of modern education, and interdisciplinary STEM is a key pathway to achieve this, yet it requires expert guidance that is difficult to scale. While LLMs offer potential in this regard, their true capability for guided instruction remains unclear due to the lack of an effective evaluation benchmark. To address this, we introduce SID, the first benchmark designed to systematically evaluate the higher-order guidance capabilities of LLMs in multi-turn, interdisciplinary Socratic dialogues. Our contributions include a large-scale dataset of 10,000 dialogue turns across 48 complex STEM projects, a novel annotation schema for capturing deep pedagogical features, and a new suite of evaluation metrics (e.g., X-SRG). Baseline experiments confirm that even state-of-the-art LLMs struggle to execute effective guided dialogues that lead students to achieve knowledge integration and transfer. This highlights the critical value of our benchmark in driving the development of more pedagogically-aware LLMs.

cs.AI↗

arXiv2025

Physics-informed deep learning for infectious disease forecasting

Accurate forecasting of contagious diseases is critical for public health policymaking and pandemic preparedness. We propose a new infectious disease forecasting model based on physics-informed neural networks (PINNs), an emerging scientific machine learning approach. By embedding a compartmental model into the loss function, our method integrates epidemiological theory with data, helping to prevent model overfitting. We further enhance the model with a sub-network that accounts for covariates such as mobility and cumulative vaccine doses, which influence the transmission rate. Using state-level COVID-19 data from California, we demonstrate that the PINN model accurately predicts cases, deaths, and hospitalizations, aligning well with existing benchmarks. Notably, the PINN model outperforms naive baseline forecasts and several sequence deep learning models, including Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM) networks, Gated Recurrent Units (GRUs), and Transformers. It also achieves performance comparable to a sophisticated Gaussian infection state forecasting model that combines compartmental dynamics, a data observation model, and parameter regression. However, the PINN model features a simpler structure and is easier to implement. In summary, we systematically evaluate the PINN model's ability to forecast infectious disease dynamics, demonstrating its potential as an efficient computational tool to strengthen forecasting capabilities.

cs.LG↗

arXiv2024

multiPI-TransBTS: A Multi-Path Learning Framework for Brain Tumor Image Segmentation Based on Multi-Physical Information

Brain Tumor Segmentation (BraTS) plays a critical role in clinical diagnosis, treatment planning, and monitoring the progression of brain tumors. However, due to the variability in tumor appearance, size, and intensity across different MRI modalities, automated segmentation remains a challenging task. In this study, we propose a novel Transformer-based framework, multiPI-TransBTS, which integrates multi-physical information to enhance segmentation accuracy. The model leverages spatial information, semantic information, and multi-modal imaging data, addressing the inherent heterogeneity in brain tumor characteristics. The multiPI-TransBTS framework consists of an encoder, an Adaptive Feature Fusion (AFF) module, and a multi-source, multi-scale feature decoder. The encoder incorporates a multi-branch architecture to separately extract modality-specific features from different MRI sequences. The AFF module fuses information from multiple sources using channel-wise and element-wise attention, ensuring effective feature recalibration. The decoder combines both common and task-specific features through a Task-Specific Feature Introduction (TSFI) strategy, producing accurate segmentation outputs for Whole Tumor (WT), Tumor Core (TC), and Enhancing Tumor (ET) regions. Comprehensive evaluations on the BraTS2019 and BraTS2020 datasets demonstrate the superiority of multiPI-TransBTS over the state-of-the-art methods. The model consistently achieves better Dice coefficients, Hausdorff distances, and Sensitivity scores, highlighting its effectiveness in addressing the BraTS challenges. Our results also indicate the need for further exploration of the balance between precision and recall in the ET segmentation task. The proposed framework represents a significant advancement in BraTS, with potential implications for improving clinical outcomes for brain tumor patients.

eess.IV↗

arXiv2024

Adaptive Inference: Theoretical Limits and Unexplored Opportunities

This paper introduces the first theoretical framework for quantifying the efficiency and performance gain opportunity size of adaptive inference algorithms. We provide new approximate and exact bounds for the achievable efficiency and performance gains, supported by empirical evidence demonstrating the potential for 10-100x efficiency improvements in both Computer Vision and Natural Language Processing tasks without incurring any performance penalties. Additionally, we offer insights on improving achievable efficiency gains through the optimal selection and design of adaptive inference state spaces.

cs.LG↗

arXiv2023

CasCIFF: A Cross-Domain Information Fusion Framework Tailored for Cascade Prediction in Social Networks

Existing approaches for information cascade prediction fall into three main categories: feature-driven methods, point process-based methods, and deep learning-based methods. Among them, deep learning-based methods, characterized by its superior learning and representation capabilities, mitigates the shortcomings inherent of the other methods. However, current deep learning methods still face several persistent challenges. In particular, accurate representation of user attributes remains problematic due to factors such as fake followers and complex network configurations. Previous algorithms that focus on the sequential order of user activations often neglect the rich insights offered by activation timing. Furthermore, these techniques often fail to holistically integrate temporal and structural aspects, thus missing the nuanced propagation trends inherent in information cascades.To address these issues, we propose the Cross-Domain Information Fusion Framework (CasCIFF), which is tailored for information cascade prediction. This framework exploits multi-hop neighborhood information to make user embeddings robust. When embedding cascades, the framework intentionally incorporates timestamps, endowing it with the ability to capture evolving patterns of information diffusion. In particular, the CasCIFF seamlessly integrates the tasks of user classification and cascade prediction into a consolidated framework, thereby allowing the extraction of common features that prove useful for all tasks, a strategy anchored in the principles of multi-task learning.

cs.SI↗