arXiv subjects

Yong Chen

Publications and source records attributed to Yong Chen.

At least 109 records · Page 6Linked to original sources

arXiv2025

Convert Language Model into a Value-based Strategic Planner

Emotional support conversation (ESC) aims to alleviate the emotional distress of individuals through effective conversations. Although large language models (LLMs) have obtained remarkable progress on ESC, most of these studies might not define the diagram from the state model perspective, therefore providing a suboptimal solution for long-term satisfaction. To address such an issue, we leverage the Q-learning on LLMs, and propose a framework called straQ*. Our framework allows a plug-and-play LLM to bootstrap the planning during ESC, determine the optimal strategy based on long-term returns, and finally guide the LLM to response. Substantial experiments on ESC datasets suggest that straQ* outperforms many baselines, including direct inference, self-refine, chain of thought, finetuning, and finite state machines.

cs.CL↗

arXiv2025

Efficient Semiparametric Inference for Distributed Data with Blockwise Missingness

We consider statistical inference for a finite-dimensional parameter in a regular semiparametric model under a distributed setting with blockwise missingness, where entire blocks of variables are unavailable at certain sites and sharing individual-level data is not allowed. To improve efficiency of the internal study, we propose a class of augmented one-step estimators that incorporate information from external sites through ``transfer functions.'' The proposed approach has several advantages. First, it is communication-efficient, requiring only one-round communication of summary-level statistics. Second, it satisfies a do-no-harm property in the sense that the augmented estimator is no less efficient than the original one based solely on the internal data. Third, it is statistically optimal, achieving the semiparametric efficiency bound when the transfer function is appropriately estimated from data. Finally, it is scalable, remaining asymptotically normal even when the number of external sites and the data dimension grow exponentially with the internal sample size. Simulation studies confirm both the statistical efficiency and computational feasibility of our method in distributed settings.

stat.ME↗

arXiv2025

Asymmetrical Filtering Impairments Mitigation for Digital- Subcarrier-Multiplexing Transmissions Enabled by Multiplication-free K-State Reserved Complex MLSE

We propose a multiplication-free K-state reserved complex maximum-likelihood-sequence-estimation (MLSE) to mitigate asymmetrical filtering impairments in digital-subcarrier-multiplexing transmissions. A required optical-to-noise ratio of 1.63dB over the conventional real MLSE is obtained after transmitting 90 GBaud DSCM DP-16QAM signal over 14 WSSs without multiplications.

physics.optics↗

arXiv2025

In-flight Characteristics and Modelling of the Instrumental Background of EP/FXT

The in-flight instrumental background of the Follow-up X-ray Telescope (FXT) onboard Einstein Probe (EP) mission is analysed in this work by utilizing observations collected during Performance Verification phase and subsequent dedicated filter wheel closed observations. The instrumental backgrounds of the two FXT modules are consistent with each other, with an average rate of $\sim 4\times10^{-2}$\,counts/s/keV in the 0.5--10\,keV band for each module. The background is nearly uniformly distributed across the detector area, with a minor increase ($<8\%$) observed along rows. The spatial distribution shows significant modulation by the geomagnetic field. The spectral shapes remain unchanged in 0.5--10\,keV at different rates. The long-term temporal variation indicates a periodic change associated with the orbital precession ($\sim 57$ days). The innovative design of FXT full-frame readout mode enables simultaneous recording of events in both the imaging area (IMG) and the frame store area (FSA) of the pnCCD. FSA event rates show a strong linear correlation with the IMG, based on which the IMG instrumental background modelling is established.

astro-ph.IM↗

arXiv2025

Enabling Inclusive Systematic Reviews: Incorporating Preprint Articles with Large Language Model-Driven Evaluations

Background. Systematic reviews in comparative effectiveness research require timely evidence synthesis. Preprints accelerate knowledge dissemination but vary in quality, posing challenges for systematic reviews. Methods. We propose AutoConfidence (automated confidence assessment), an advanced framework for predicting preprint publication, which reduces reliance on manual curation and expands the range of predictors, including three key advancements: (1) automated data extraction using natural language processing techniques, (2) semantic embeddings of titles and abstracts, and (3) large language model (LLM)-driven evaluation scores. Additionally, we employed two prediction models: a random forest classifier for binary outcome and a survival cure model that predicts both binary outcome and publication risk over time. Results. The random forest classifier achieved AUROC 0.692 with LLM-driven scores, improving to 0.733 with semantic embeddings and 0.747 with article usage metrics. The survival cure model reached AUROC 0.716 with LLM-driven scores, improving to 0.731 with semantic embeddings. For publication risk prediction, it achieved a concordance index of 0.658, increasing to 0.667 with semantic embeddings. Conclusion. Our study advances the framework for preprint publication prediction through automated data extraction and multiple feature integration. By combining semantic embeddings with LLM-driven evaluations, AutoConfidence enhances predictive performance while reducing manual annotation burden. The framework has the potential to facilitate incorporation of preprint articles during the appraisal phase of systematic reviews, supporting researchers in more effective utilization of preprint resources.

cs.CL↗

arXiv2025

Deep Hashing with Semantic Hash Centers for Image Retrieval

Deep hashing is an effective approach for large-scale image retrieval. Current methods are typically classified by their supervision types: point-wise, pair-wise, and list-wise. Recent point-wise techniques (e.g., CSQ, MDS) have improved retrieval performance by pre-assigning a hash center to each class, enhancing the discriminability of hash codes across various datasets. However, these methods rely on data-independent algorithms to generate hash centers, which neglect the semantic relationships between classes and may degrade retrieval performance. This paper introduces the concept of semantic hash centers, building on the idea of traditional hash centers. We hypothesize that hash centers of semantically related classes should have closer Hamming distances, while those of unrelated classes should be more distant. To this end, we propose a three-stage framework, SHC, to generate hash codes that preserve semantic structure. First, we develop a classification network to identify semantic similarities between classes using a data-dependent similarity calculation that adapts to varying data distributions. Second, we introduce an optimization algorithm to generate semantic hash centers, preserving semantic relatedness while enforcing a minimum distance between centers to avoid excessively similar hash codes. Finally, a deep hashing network is trained using these semantic centers to convert images into binary hash codes. Experimental results on large-scale retrieval tasks across several public datasets show that SHC significantly improves retrieval performance. Specifically, SHC achieves average improvements of +7.26%, +7.62%, and +11.71% in MAP@100, MAP@1000, and MAP@ALL metrics, respectively, over state-of-the-art methods.

cs.CV↗

arXiv2025

M3-JEPA: Multimodal Alignment via Multi-gate MoE based on the Joint-Embedding Predictive Architecture

Current multimodal learning strategies primarily optimize in the original token space. Such a framework is easy to incorporate with the backbone of pretrained language model, but might result in modality collapse. To alleviate such issues, we leverage the Joint-Embedding Predictive Architecture (JEPA) on the multimodal tasks, which converts the input embedding into the output embedding space by a predictor and then conducts the cross-modal alignment on the latent space. We implement this predictor by a Multi-Gate Mixture of Experts (MMoE) and name the framework as M3-JEPA, accordingly. The gating function disentangles the modality-specific and shared information and derives information-theoretic optimality. The framework is implemented with both contrastive and regularization loss, and solved by alternative gradient descent (AGD) between different multimodal tasks. By thoroughly designed experiments, we show that M3-JEPA can obtain state-of-the-art performance on different modalities and tasks, generalize to unseen datasets and domains, and is computationally efficient in both training and inference. Our observation suggests that M3-JEPA might become a new basis to self-supervised learning in the open world.

cs.LG↗

arXiv2025

Multi-Party Supervised Fine-tuning of Language Models for Multi-Party Dialogue Generation

Large Language Models (LLM) are usually fine-tuned to participate in dyadic or two-party dialogues, which can not adapt well to multi-party dialogues (MPD), which hinders their applications in such scenarios including multi-personal meetings, discussions and daily communication. Previous LLM-based researches mainly focus on the multi-agent framework, while their base LLMs are still pairwisely fine-tuned. In this work, we design a multi-party fine-tuning framework (MuPaS) for LLMs on the multi-party dialogue datasets, and prove such a straightforward framework can let the LLM align with the multi-party conversation style efficiently and effectively. We also design two training strategies which can convert MuPaS into the MPD simulator. Substantial experiments show that MuPaS can achieve state-of-the-art multi-party response, higher accuracy of the-next-speaker prediction, higher human and automatic evaluated utterance qualities, and can even generate reasonably with out-of-distribution scene, topic and role descriptions. The MuPaS framework bridges the LLM training with more complicated multi-party applications, such as conversation generation, virtual rehearsal or meta-universe.

cs.CL↗

arXiv2025

SAFER: A Calibrated Risk-Aware Multimodal Recommendation Model for Dynamic Treatment Regimes

Dynamic treatment regimes (DTRs) are critical to precision medicine, optimizing long-term outcomes through personalized, real-time decision-making in evolving clinical contexts, but require careful supervision for unsafe treatment risks. Existing efforts rely primarily on clinician-prescribed gold standards despite the absence of a known optimal strategy, and predominantly using structured EHR data without extracting valuable insights from clinical notes, limiting their reliability for treatment recommendations. In this work, we introduce SAFER, a calibrated risk-aware tabular-language recommendation framework for DTR that integrates both structured EHR and clinical notes, enabling them to learn from each other, and addresses inherent label uncertainty by assuming ambiguous optimal treatment solution for deceased patients. Moreover, SAFER employs conformal prediction to provide statistical guarantees, ensuring safe treatment recommendations while filtering out uncertain predictions. Experiments on two publicly available sepsis datasets demonstrate that SAFER outperforms state-of-the-art baselines across multiple recommendation metrics and counterfactual mortality rate, while offering robust formal assurances. These findings underscore SAFER potential as a trustworthy and theoretically grounded solution for high-stakes DTR applications.

cs.LG↗

arXiv2025

Remote entanglement generation via enhanced quantum state transfer

Achieving robust and scalable remote quantum entanglement is a fundamental challenge for the development of distributed quantum networks and modular quantum computing systems. Along this, perfect state transfer (PST) and fractional state transfer (FST) have emerged as promising schemes for quantum state transfer and remote entanglement generation using only nearest-neighbor couplings. However, the current implementations suffer from quantum loss and limited parameter tunability. In this work, we propose a new quantum state transfer scheme based on a zig-zag configuration, which introduces a controlling parameter for PST and FST. We show that this new parameter can suppress the population in the intermediate qubits, thereby reducing losses. We experimentally demonstrate the dynamics of different configurations on a superconducting quantum processor, achieving an $18\%$ reduction in error for remote Bell state generation in a 1D ($1\times5$) qubit chain, and exhibit robustness against certain types of noise. Then we extend our approach to a 2D network, successfully generating a W state among the four corner qubits. These results highlight the potential of our enhanced quantum state transfer scheme for scalable and noise-resilient quantum communication and computing.

quant-ph↗

arXiv2025

FreeTimeGS: Free Gaussian Primitives at Anytime and Anywhere for Dynamic Scene Reconstruction

This paper addresses the challenge of reconstructing dynamic 3D scenes with complex motions. Some recent works define 3D Gaussian primitives in the canonical space and use deformation fields to map canonical primitives to observation spaces, achieving real-time dynamic view synthesis. However, these methods often struggle to handle scenes with complex motions due to the difficulty of optimizing deformation fields. To overcome this problem, we propose FreeTimeGS, a novel 4D representation that allows Gaussian primitives to appear at arbitrary time and locations. In contrast to canonical Gaussian primitives, our representation possesses the strong flexibility, thus improving the ability to model dynamic 3D scenes. In addition, we endow each Gaussian primitive with an motion function, allowing it to move to neighboring regions over time, which reduces the temporal redundancy. Experiments results on several datasets show that the rendering quality of our method outperforms recent methods by a large margin. Project page: https://zju3dv.github.io/freetimegs/ .

cs.CV↗

arXiv2025

Challenger: Affordable Adversarial Driving Video Generation

Generating photorealistic driving videos has seen significant progress recently, but current methods largely focus on ordinary, non-adversarial scenarios. Meanwhile, efforts to generate adversarial driving scenarios often operate on abstract trajectory or BEV representations, falling short of delivering realistic sensor data that can truly stress-test autonomous driving (AD) systems. In this work, we introduce Challenger, a framework that produces physically plausible yet photorealistic adversarial driving videos. Generating such videos poses a fundamental challenge: it requires jointly optimizing over the space of traffic interactions and high-fidelity sensor observations. Challenger makes this affordable through two techniques: (1) a physics-aware multi-round trajectory refinement process that narrows down candidate adversarial maneuvers, and (2) a tailored trajectory scoring function that encourages realistic yet adversarial behavior while maintaining compatibility with downstream video synthesis. As tested on the nuScenes dataset, Challenger generates a diverse range of aggressive driving scenarios-including cut-ins, sudden lane changes, tailgating, and blind spot intrusions-and renders them into multiview photorealistic videos. Extensive evaluations show that these scenarios significantly increase the collision rate of state-of-the-art end-to-end AD models (UniAD, VAD, SparseDrive, and DiffusionDrive), and importantly, adversarial behaviors discovered for one model often transfer to others.

cs.CV↗

arXiv2025

Sage Deer: A Super-Aligned Driving Generalist Is Your Copilot

The intelligent driving cockpit, an important part of intelligent driving, needs to match different users' comfort, interaction, and safety needs. This paper aims to build a Super-Aligned and GEneralist DRiving agent, SAGE DeeR. Sage Deer achieves three highlights: (1) Super alignment: It achieves different reactions according to different people's preferences and biases. (2) Generalist: It can understand the multi-view and multi-mode inputs to reason the user's physiological indicators, facial emotions, hand movements, body movements, driving scenarios, and behavioral decisions. (3) Self-Eliciting: It can elicit implicit thought chains in the language space to further increase generalist and super-aligned abilities. Besides, we collected multiple data sets and built a large-scale benchmark. This benchmark measures the deer's perceptual decision-making ability and the super alignment's accuracy.

cs.CV↗

arXiv2025

Insight-HXMT observations of the extremely bright GRB 221009A

The Hard X-ray Modulation Telescope (\insight) detected GRB 221009A, the brightest gamma-ray burst observed to date, with all its three telescopes, i.e. High Energy telescope (HE, 20-250 keV), Medium Energy telescope (ME, 5-30 keV), and Low Energy telescope (LE, 1-10 keV). Here we present the detailed observation results of all three telescopes of \insight~ on the prompt emission of GRB 221009A. After dead-time and data saturation correction, we recovered the light curves of HE, ME and LE telescopes and find that they generally track the GECAM-C low gain light curves that are free of data saturation issues. Particularly, the ME light curve matches the GECAM-C light curve in low gain mode above 400 keV, while the LE light curve is more consistent with the GECAM-C above 1.5 MeV. Based on simulation, we find that the signals recorded by the ME and LE are actually caused by the secondary particles produced by the interaction between GRB gamma-ray photons and the material of the satellite. Interestingly, the consistency between ME and LE light curves and GECAM-C demonstrates that ME and LE data could be used to characterize the GRB properties. Espeically, the high time resolution light curve of ME allowed us, for the first time, to calculate the minimum variability timescale (MVT = 0.10 s) of the main burst episode of GRB 221009A.

astro-ph.HE↗

arXiv2025

MAP: Low-compute Model Merging with Amortized Pareto Fronts via Quadratic Approximation

Model merging has emerged as an effective approach to combine multiple single-task models into a multitask model. This process typically involves computing a weighted average of the model parameters without any additional training. Existing model-merging methods focus on enhancing average task accuracy. However, interference and conflicts between the objectives of different tasks can lead to trade-offs during the merging process. In real-world applications, a set of solutions with various trade-offs can be more informative, helping practitioners make decisions based on diverse preferences. In this paper, we introduce a novel and low-compute algorithm, Model Merging with Amortized Pareto Front (MAP). MAP efficiently identifies a Pareto set of scaling coefficients for merging multiple models, reflecting the trade-offs involved. It amortizes the substantial computational cost of evaluations needed to estimate the Pareto front by using quadratic approximation surrogate models derived from a pre-selected set of scaling coefficients. Experimental results on vision and natural language processing tasks demonstrate that MAP can accurately identify the Pareto front, providing practitioners with flexible solutions to balance competing task objectives. We also introduce Bayesian MAP for scenarios with a relatively low number of tasks and Nested MAP for situations with a high number of tasks, further reducing the computational cost of evaluation.

cs.LG↗

arXiv2025

Complexity and Approximation Algorithms for Fixed Charge Transportation Problems

The Fixed Charge Transportation (FCT) problem models transportation scenarios where we need to send a commodity from $n$ sources to $m$ sinks, and the cost of sending a commodity from a source to a sink consists of a linear component and a fixed component. Despite extensive research on exponential time exact algorithms and heuristic algorithms for FCT and its variants, their approximability and computational complexity are not well understood. In this work, we initiate a systematic study of the approximability and complexity of these problems. When there are no linear costs, we call the problem the Pure Fixed Charge Transportation (PFCT) problem. We also distinguish between cases with general, sink-independent, and uniform fixed costs; we use the suffixes ``-S'' and ``-U'' to denote the latter two cases, respectively. This gives us six variants of the FCT problem. We give a complete characterization of the existence of $O(1)$-approximation algorithms for these variants. In particular, we give $2$-approximation algorithms for FCT-U and PFCT-S, and a $(6/5 + ε)$-approximation for PFCT-U. On the negative side, we prove that FCT and PFCT are NP-hard to approximate within a factor of $O(\log^{2-ε} (\max\{n, m\}))$ for any constant $ε> 0$, FCT-S is NP-hard to approximate within a factor of $c\log (\max\{n, m\})$ for some constant $c> 0$, and PFCT-U is APX-hard. Additionally, we design an Efficient Parameterized Approximation Scheme (EPAS) for PFCT when parameterized by the number $n$ of sources, and an $O(1/ε)$-bicriteria approximation for the FCT problem, when we are allowed to violate the demand constraints for sinks by a factor of $1\pm ε$.

cs.DS↗

arXiv2025

Realizing Scalable Conditional Operations through Auxiliary Energy Levels

In the noisy intermediate-scale quantum (NISQ) era, flexible quantum operations are essential for advancing large-scale quantum computing, as they enable shorter circuits that mitigate decoherence and reduce gate errors. However, the complex control of quantum interactions poses significant experimental challenges that limit scalability. Here, we propose a transition composite gate scheme based on transition pathway engineering, which digitally implements conditional operations with reduced complexity by leveraging auxiliary energy levels. Experimentally, we demonstrate the controlled-unitary (CU) family and its applications. In entangled state preparation, our CU gate reduces the circuit depth for three-qubit Greenberger-Horne-Zeilinger (GHZ) and W states by approximately 40-44% compared to circuits using only CZ gates, leading to fidelity improvements of 1.5% and 4.2%, respectively. Furthermore, with a 72% reduction in circuit depth, we successfully implement a quantum comparator-a fundamental building block for quantum algorithms requiring conditional logic, which has remained experimentally challenging due to its inherent circuit complexity. These results demonstrate the scalability and practicality of our scheme, laying a solid foundation for the implementation of large-scale quantum algorithms in future quantum processors.

quant-ph↗

arXiv2025

Revisiting Computational Storage for Data Integrity and Security

The idea of computational storage device (CSD) has come a long way since at least 1990s [1], [2]. By embedding computing resources within storage devices, CSDs could potentially offload computational tasks from CPUs and enable near-data processing (NDP), reducing data movements and/or energy consumption significantly. While the initial hard-disk-based CSDs suffer from severe limitations in terms of on-drive resources, programmability, etc., the storage market has witnessed the commercialization of solid-state-drive (SSD) based CSDs (e.g., Samsung SmartSSD [3], ScaleFlux CSDs [4]) recently, which has enabled CSD-based optimizations for avariety of application scenarios (e.g., [5], [6], [7]).

cs.DC↗