arXiv subjects

Xue Feng

Publications and source records attributed to Xue Feng.

At least 55 records · Page 3Linked to original sources

arXiv2025

Are the Values of LLMs Structurally Aligned with Humans? A Causal Perspective

As large language models (LLMs) become increasingly integrated into critical applications, aligning their behavior with human values presents significant challenges. Current methods, such as Reinforcement Learning from Human Feedback (RLHF), typically focus on a limited set of coarse-grained values and are resource-intensive. Moreover, the correlations between these values remain implicit, leading to unclear explanations for value-steering outcomes. Our work argues that a latent causal value graph underlies the value dimensions of LLMs and that, despite alignment training, this structure remains significantly different from human value systems. We leverage these causal value graphs to guide two lightweight value-steering methods: role-based prompting and sparse autoencoder (SAE) steering, effectively mitigating unexpected side effects. Furthermore, SAE provides a more fine-grained approach to value steering. Experiments on Gemma-2B-IT and Llama3-8B-IT demonstrate the effectiveness and controllability of our methods.

cs.CL↗

arXiv2025

A Unified Knowledge-Distillation and Semi-Supervised Learning Framework to Improve Industrial Ads Delivery Systems

Industrial ads ranking systems conventionally rely on labeled impression data, which leads to challenges such as overfitting, slower incremental gain from model scaling, and biases due to discrepancies between training and serving data. To overcome these issues, we propose a Unified framework for Knowledge-Distillation and Semi-supervised Learning (UKDSL) for ads ranking, empowering the training of models on a significantly larger and more diverse datasets, thereby reducing overfitting and mitigating training-serving data discrepancies. We provide detailed formal analysis and numerical simulations on the inherent miscalibration and prediction bias of multi-stage ranking systems, and show empirical evidence of the proposed framework's capability to mitigate those. Compared to prior work, UKDSL can enable models to learn from a much larger set of unlabeled data, hence, improving the performance while being computationally efficient. Finally, we report the successful deployment of UKDSL in an industrial setting across various ranking models, serving users at multi-billion scale, across various surfaces, geological locations, clients, and optimize for various events, which to the best of our knowledge is the first of its kind in terms of the scale and efficiency at which it operates.

cs.LG↗

arXiv2025

Beyond Self-Consistency: Loss-Balanced Perturbation-Based Regularization Improves Industrial-Scale Ads Ranking

Perturbation-based regularization techniques address many challenges in industrial-scale large models, particularly with sparse labels, and emphasize consistency and invariance for perturbation in model predictions. One of the popular regularization techniques has been various forms of self-consistency, which involve making small modifications to input data while preserving contextual information and enforcing similar predictions through auxiliary loss functions. In this work, we explore the first successful application of perturbation-based regularization algorithms in large-scale ads ranking models, and further propose a novel regularization algorithm, namely, Loss-Balanced Small Perturbation Regularization (LSPR) that can be used in potentially any deep learning model. We have successfully demonstrate that both Self-Consistency Regularization approaches (SCR) and LSPR are scalable and can improve ads delivery systems. By conducting industrial-scale experiments, and numerical analysis, we additionally show that our proposed LSPR, performs consistently better compared to SCR, across various groups and signal availability setups. Finally, we report a successful application of the proposed LSPR in a billion-scale industrial ranking system, which to the best of our knowledge, is the first of its kind, and it is specially designed to address the various scalability challenges (e.g, various surfaces, geological locations, clients and so on) as we will mention in this paper.

cs.IR↗

arXiv2025

AdaSociety: An Adaptive Environment with Social Structures for Multi-Agent Decision-Making

Traditional interactive environments limit agents' intelligence growth with fixed tasks. Recently, single-agent environments address this by generating new tasks based on agent actions, enhancing task diversity. We consider the decision-making problem in multi-agent settings, where tasks are further influenced by social connections, affecting rewards and information access. However, existing multi-agent environments lack a combination of adaptive physical surroundings and social connections, hindering the learning of intelligent behaviors. To address this, we introduce AdaSociety, a customizable multi-agent environment featuring expanding state and action spaces, alongside explicit and alterable social structures. As agents progress, the environment adaptively generates new tasks with social structures for agents to undertake. In AdaSociety, we develop three mini-games showcasing distinct social structures and tasks. Initial results demonstrate that specific social structures can promote both individual and collective benefits, though current reinforcement learning and LLM-based algorithms show limited effectiveness in leveraging social structures to enhance performance. Overall, AdaSociety serves as a valuable research platform for exploring intelligence in diverse physical and social settings. The code is available at https://github.com/bigai-ai/AdaSociety.

cs.MA↗

arXiv2025

Demonstration of Time-reversal Symmetric Two-Dimensional Photonic Topological Anderson Insulator

Recently, the impact of disorder on topological properties has attracted significant attention in photonics, especially the intriguing disorder-induced topological phase transitions in photonic topological Anderson insulators (PTAIs). However, the reported PTAIs are based on time-reversal symmetry broken systems or quasi-three-dimensional time-reversal invariant system, both of which would limit the applications in integrated optics. Here, we realize a time-reversal symmetric two-dimensional PTAI on silicon platform within the near-IR wavelength range, taking the advantageous valley degree of freedom of photonic crystal. A low-threshold topological Anderson phase transition is observed by applying disorder to the critical topologically trivial phase. Conversely, we have also realized extremely robust topologically protected edge states based on the stable topological phase. Both two phenomena are validated through theoretical Dirac Hamiltonian analysis, numerical simulations, and experimental measurements. Our proposed structure holds promise to achieve near-zero topological phase transition thresholds, which breaks the conventional cognition that strong disorder is required to induce the phase transition. It significantly alleviates the difficulty of manipulating disorder and could be extended to other systems, such as condensed matter systems where strong disorder is hard to implement. This work is also beneficial to construct highly robust photonic integrated circuits serving for on-chip photonic and quantum optic information processing. Moreover, this work also provides an outstanding platform to investigate on-chip integrated disordered systems.

physics.optics↗

arXiv2025

Learning to Balance Altruism and Self-interest Based on Empathy in Mixed-Motive Games

Real-world multi-agent scenarios often involve mixed motives, demanding altruistic agents capable of self-protection against potential exploitation. However, existing approaches often struggle to achieve both objectives. In this paper, based on that empathic responses are modulated by inferred social relationships between agents, we propose LASE Learning to balance Altruism and Self-interest based on Empathy), a distributed multi-agent reinforcement learning algorithm that fosters altruistic cooperation through gifting while avoiding exploitation by other agents in mixed-motive games. LASE allocates a portion of its rewards to co-players as gifts, with this allocation adapting dynamically based on the social relationship -- a metric evaluating the friendliness of co-players estimated by counterfactual reasoning. In particular, social relationship measures each co-player by comparing the estimated $Q$-function of current joint action to a counterfactual baseline which marginalizes the co-player's action, with its action distribution inferred by a perspective-taking module. Comprehensive experiments are performed in spatially and temporally extended mixed-motive games, demonstrating LASE's ability to promote group collaboration without compromising fairness and its capacity to adapt policies to various types of interactive co-players.

cs.AI↗

arXiv2024

Chip-to-chip photonic quantum teleportation over optical fibers of 12.3km

Quantum teleportation is a crucial function in quantum networks. The implementation of photonic quantum teleportation could be highly simplified by quantum photonic circuits. To extend chip-to-chip teleportation distance, more effort is needed on both chip design and system implementation. In this work, we demonstrate a chip-to-chip photonic quantum teleportation over optical fibers under the scenario of star-topology quantum network. Time-bin encoded quantum states are used to achieve a long teleportation distance. Three photonic quantum circuits are designed and fabricated on a single chip, each serving specific functions: heralded single-photon generation at the user node, entangled photon pair generation and Bell state measurement at the relay node, and projective measurement of the teleported photons at the central node. The unbalanced Mach-Zehnder interferometers (UMZI) for time-bin encoding in these quantum photonic circuits are optimized to reduce insertion losses and suppress noise photons generated on the chip. Besides, an active feedback system is employed to suppress the impact of fiber length fluctuation between the circuits, achieving a stable quantum interference for the Bell state measurement in the relay node. As the result, a photonic quantum teleportation over optical fibers of 12.3km is achieved based on these quantum photonic circuits, showing the potential of chip integration on the development of quantum networks.

quant-ph↗

arXiv2024

Spectral Convolutional Neural Network Chip for In-sensor Edge Computing of Incoherent Natural Light

Convolutional neural networks (CNNs) are representative models of artificial neural networks (ANNs). However, the considerable power consumption and limited computing speed of electrical computing platforms restrict further CNN development on edge devices. Optical neural networks are considered next-generation physical implementations of ANNs, but their capabilities are limited by on-chip integration scale and requirement for coherent light sources. This study proposes a spectral convolutional neural network (SCNN) of incoherent natural light by an optical convolutional layer (OCL) and a reconfigurable electrical backend. The OCL is implemented by integrating very large-scale, pixel-aligned spectral filters on a CMOS image sensor on a 12-inch wafer, facilitating highly parallel spectral vector-inner products of incident light. It accepts broadband incoherent natural light containing two spatial and one spectral dimension directly as input with the function of matter meta-imaging. This unique optoelectronic framework empowers in-sensor optical analog computing at extremely high energy efficiency because the OCL is driven by the energy of the information carrier, i. e. natural light. To the best of our knowledge, this is the first integrated optical computing utilizing natural light. We employ the same SCNN chip for completely different real-world complex tasks,and achieve accuracies of over 96% for pathological diagnosis and almost 100% for face anti-spoofing at video rates. The SCNN framework has an unprecedented new function of substance identification, provides a feasible optoelectronic and integrated optical CNN implementation for edge devices or cellphones, providing them with practical and powerful edge computing abilities and facilitating diverse applications, such as intelligent robotics, industrial automation, medical diagnosis, and remote sensing.

physics.optics↗

arXiv2024

Map Optical Properties to Subwavelength Structures Directly via a Diffusion Model

Subwavelength photonic structures and metamaterials provide revolutionary approaches for controlling light. The inverse design methods proposed for these subwavelength structures are vital to the development of new photonic devices. However, most of the existing inverse design methods cannot realize direct mapping from optical properties to photonic structures but instead rely on forward simulation methods to perform iterative optimization. In this work, we exploit the powerful generative abilities of artificial intelligence (AI) and propose a practical inverse design method based on latent diffusion models. Our method maps directly the optical properties to structures without the requirement of forward simulation and iterative optimization. Here, the given optical properties can work as "prompts" and guide the constructed model to correctly "draw" the required photonic structures. Experiments show that our direct mapping-based inverse design method can generate subwavelength photonic structures at high fidelity while following the given optical properties. This may change the method used for optical design and greatly accelerate the research on new photonic devices.

physics.optics↗

arXiv2024

Unifying Generative and Dense Retrieval for Sequential Recommendation

Sequential dense retrieval models utilize advanced sequence learning techniques to compute item and user representations, which are then used to rank relevant items for a user through inner product computation between the user and all item representations. However, this approach requires storing a unique representation for each item, resulting in significant memory requirements as the number of items grow. In contrast, the recently proposed generative retrieval paradigm offers a promising alternative by directly predicting item indices using a generative model trained on semantic IDs that encapsulate items' semantic information. Despite its potential for large-scale applications, a comprehensive comparison between generative retrieval and sequential dense retrieval under fair conditions is still lacking, leaving open questions regarding performance, and computation trade-offs. To address this, we compare these two approaches under controlled conditions on academic benchmarks and propose LIGER (LeveragIng dense retrieval for GEnerative Retrieval), a hybrid model that combines the strengths of these two widely used methods. LIGER integrates sequential dense retrieval into generative retrieval, mitigating performance differences and enhancing cold-start item recommendation in the datasets evaluated. This hybrid approach provides insights into the trade-offs between these approaches and demonstrates improvements in efficiency and effectiveness for recommendation systems in small-scale benchmarks.

cs.IR↗

arXiv2024

MultiBalance: Multi-Objective Gradient Balancing in Industrial-Scale Multi-Task Recommendation System

In industrial recommendation systems, multi-task learning (learning multiple tasks simultaneously on a single model) is a predominant approach to save training/serving resources and improve recommendation performance via knowledge transfer between the joint learning tasks. However, multi-task learning often suffers from negative transfer: one or several tasks are less optimized than training them separately. To carefully balance the optimization, we propose a gradient balancing approach called MultiBalance, which is suitable for industrial-scale multi-task recommendation systems. It balances the per-task gradients to alleviate the negative transfer, while saving the huge cost for grid search or manual explorations for appropriate task weights. Moreover, compared with prior work that normally balance the per-task gradients of shared parameters, MultiBalance is more efficient since only requiring to access per-task gradients with respect to the shared feature representations. We conduct experiments on Meta's large-scale ads and feeds multi-task recommendation system, and observe that MultiBalance achieves significant gains (e.g., 0.738% improvement for normalized entropy (NE)) with neutral training cost in Queries Per Second (QPS), which is significantly more efficient than prior methods that balance per-task gradients of shared parameters with 70~80% QPS degradation.

cs.IR↗

arXiv2024

SUANPAN: Scalable Photonic Linear Vector Machine

Photonic linear operation is a promising approach to handle the extensive vector multiplications in artificial intelligence techniques due to the natural bosonic parallelism and high-speed information transmission of photonics. Although it is believed that maximizing the interaction of the light beams is necessary to fully utilize the parallelism and tremendous efforts have been made in past decades, the achieved dimensionality of vector-matrix multiplication is very limited due to the difficulty of scaling up a tightly interconnected or highly coupled optical system. Additionally, there is still a lack of a universal photonic computing architecture that can be readily merged with existing computing system to meet the computing power demand of AI techniques. Here, we propose a programmable and reconfigurable photonic linear vector machine to perform only the inner product of two vectors, formed by a series of independent basic computing units, while each unit is just one pair of light-emitter and photodetector. Since there is no interaction among light beams inside, extreme scalability could be achieved by simply duplicating the independent basic computing unit while there is no requirement of large-scale analog-to-digital converter and digital-to-analog converter arrays. Our architecture is inspired by the traditional Chinese Suanpan or abacus and thus is denoted as photonic SUANPAN. As a proof of principle, SUANPAN architecture is implemented with an 8*8 vertical cavity surface emission laser array and an 8*8 MoTe2 two-dimensional material photodetector array. We believe that our proposed photonic SUANPAN is capable of serving as a fundamental linear vector machine that can be readily merged with existing electronic digital computing system and is potential to enhance the computing power for future various AI applications.

physics.optics↗

arXiv2024

EXACT-Net:EHR-guided lung tumor auto-segmentation for non-small cell lung cancer radiotherapy

Lung cancer is a devastating disease with the highest mortality rate among cancer types. Over 60% of non-small cell lung cancer (NSCLC) patients, which accounts for 87% of diagnoses, require radiation therapy. Rapid treatment initiation significantly increases the patient's survival rate and reduces the mortality rate. Accurate tumor segmentation is a critical step in the diagnosis and treatment of NSCLC. Manual segmentation is time and labor-consuming and causes delays in treatment initiation. Although many lung nodule detection methods, including deep learning-based models, have been proposed, there is still a long-standing problem of high false positives (FPs) with most of these methods. Here, we developed an electronic health record (EHR) guided lung tumor auto-segmentation called EXACT-Net (EHR-enhanced eXACtitude in Tumor segmentation), where the extracted information from EHRs using a pre-trained large language model (LLM), was used to remove the FPs and keep the TP nodules only. The auto-segmentation model was trained on NSCLC patients' computed tomography (CT), and the pre-trained LLM was used with the zero-shot learning approach. Our approach resulted in a 250% boost in successful nodule detection using the data from ten NSCLC patients treated in our institution.

eess.IV↗

arXiv2024

Efficient Adaptation in Mixed-Motive Environments via Hierarchical Opponent Modeling and Planning

Despite the recent successes of multi-agent reinforcement learning (MARL) algorithms, efficiently adapting to co-players in mixed-motive environments remains a significant challenge. One feasible approach is to hierarchically model co-players' behavior based on inferring their characteristics. However, these methods often encounter difficulties in efficient reasoning and utilization of inferred information. To address these issues, we propose Hierarchical Opponent modeling and Planning (HOP), a novel multi-agent decision-making algorithm that enables few-shot adaptation to unseen policies in mixed-motive environments. HOP is hierarchically composed of two modules: an opponent modeling module that infers others' goals and learns corresponding goal-conditioned policies, and a planning module that employs Monte Carlo Tree Search (MCTS) to identify the best response. Our approach improves efficiency by updating beliefs about others' goals both across and within episodes and by using information from the opponent modeling module to guide planning. Experimental results demonstrate that in mixed-motive environments, HOP exhibits superior few-shot adaptation capabilities when interacting with various unseen agents, and excels in self-play scenarios. Furthermore, the emergence of social intelligence during our experiments underscores the potential of our approach in complex multi-agent environments.

cs.AI↗

arXiv2024

Low-Voltage Electron Emission by Graphene-hBN-graphene Heterostructure

Scanning Electron Microscopes (SEM) with low energy electron sources (accelerating voltage of less than 1000V) have important application requirements in many application scenarios. Tunneling junction can potentially achieve low-voltage and planar-type electron sources with good emission current density. However, further lower the extracting voltage while ensure the emission current density remains challenging. In this paper, we report a low-voltage planar-type electron source based on graphene-hBN-graphene heterostructures (GBGH) under a really low out-plane extracting voltage. The external electric field strength applied to the electron sources is only 4 times 10^4V/m and the accelerating voltage as low as 20V is realized. Steady electron emission of over 1nA and operating duration of several hours is observed from the GBGH with size of 59.29um^2 in our experiments, and thus the maximum emission current density reaches 7mA/cm^2. Great electrical contacts, extremely low thickness, and excellent layer properties of two-dimensional (2D) materials lead to easy-fabrication and miniature on-chip electron sources, which would significantly contribute to the development of next-generation free electron devices.

physics.app-ph↗

arXiv2024

16-channel Photonic Solver for Optimization Problems on a Silicon Chip

In this article, we proposed a programmable 16-channel photonic solver for quadratic unconstrained binary optimization (QUBO) problems. The solver is based on a hybrid optoelectronic scheme including a photonic chip and the corresponding electronic driving circuit. The photonic chip is fabricated on silicon on insulator (SOI) substrate and integrates high-speed electro-optic modulators, thermo-optic phase shifters and photodetectors to conduct the 16-dimensional optical vector-matrix multiplication (OVMM). Due to the parallel and low latency propagation of lightwave, the calculation of the QUBO cost function can be accelerated. Besides, the electronic processor is employed to run the heuristic algorithm to search the optimal solution. In the experiment, two 16-dimensional randomly generated QUBO problems are solved with high successful probabilities. To our knowledge, it is the largest scale of programmable and on-chip photonic solver ever reported. Moreover, the computing speed of the OVMM on photonic chip is ~2 TFLOP/s. It shows the potential of fast solving such optimization problems with integrated photonic systems.

cs.ET↗

arXiv2024

Electrically switchable $2^N$-channel wave-front control with N cascaded polarization-dependent metasurfaces

Metasurfaces with tunable functionalities are greatly desired for modern optical system and various applications. To increase the operating channels of polarization-multiplexed metasurfaces, we proposed a structure of N cascaded dual-channel metasurfaces to achieve 2^N electrically switchable functional channels without intrinsic noise or cross-talk. As proof of principles, we have implemented a 3-layer setup to achieve 8 channels. In success, we have demonstrated two typical functionalities of vortex beam generation with switchable topological charge of l=-3 ~ +4 or l=-1~ -8, and beam steering with the deflecting direction switchable in an 8*1 line or a 4*2 grid. We believe that our proposal would provide a practical way to significantly increase the scalability and extend the functionality of polarization-multiplexed metasurfaces, which are potential for the applications of LiDAR, glasses-free 3D display, OAM (de)multiplexing, and varifocal meta-lens.

physics.optics↗

arXiv2024

On-demand Photonic Ising Machine with Simplified Hamiltonian Calculation by Phase encoding and Intensity Detection

The photonic Ising machine is a new paradigm of optical computing that takes advantage of the unique properties of light wave propagation, parallel processing, and low-loss transmission. Thus, the process of solving combinatorial optimization problems can be accelerated through photonic/optoelectronic devices, but implementing photonic Ising machines that can solve arbitrary large-scale Ising problems with fast speed remains challenging. In this work, we have proposed and demonstrated the Phase Encoding and Intensity Detection Ising Annealer (PEIDIA) capable of solving arbitrary Ising problems on demand. The PEIDIA employs the heuristic algorithm and requires only one step of optical linear transformation with simplified Hamiltonian calculation by encoding the Ising spins on the phase term of the optical field and performing intensity detection during the solving process. As a proof of principle, several 20 and 30-spin Ising problems have been solved with high ground state probability (>0.97/0.85 for the 20/30-spin Ising model).

cs.ET↗