arXiv subjects

Lu Ren

Publications and source records attributed to Lu Ren.

16 recordsLinked to original sources

arXiv2026

OneReason Technical Report

Generative recommendation models in the OneRec family have been widely deployed in many real-world services, such as short-video, live-streaming, advertising, and e-commerce. However, these generative models can only benefit from the scaling advantage, while their reasoning ability is hard to activate, since we cannot construct meaningful Chain-of-Thought (CoT) sequences consisting of itemic tokens only. Inspired by the success of the reasoning-style ``think before answer'' paradigm in the LLM field, we conduct preliminary studies (i.e., OneRec-Think, OpenOneRec) to explore reasoning capability in generative recommendation. Nevertheless, we notice an unexpected phenomenon: the thinking mode does not show advantages over the non-thinking mode. Drawing insights from recent findings on CoT robustness in multi-modal language models, we argue that effective reasoning in recommendation rests on two factors: perception, the ability to ground itemic tokens in their underlying language semantics, and cognition, the ability to reorganize a user's behavior sequence into coherent latent interest points. We therefore propose OneReason, which includes: (1) strong itemic token perception in pre-training, (2) a three-level cognition-enhanced CoT format for recommendation tasks in SFT, and (3) a specialize-then-unify training recipe in RL to enhance the thinking ability.

cs.IR↗

arXiv2026

Kwai Summary Attention Technical Report

Long-context ability, has become one of the most important iteration direction of next-generation Large Language Models, particularly in semantic understanding/reasoning, code agentic intelligence and recommendation system. However, the standard softmax attention exhibits quadratic time complexity with respect to sequence length. As the sequence length increases, this incurs substantial overhead in long-context settings, leading the training and inference costs of extremely long sequences deteriorate rapidly. Existing solutions mitigate this issue through two technique routings: i) Reducing the KV cache per layer, such as from the head-level compression GQA, and the embedding dimension-level compression MLA, but the KV cache remains linearly dependent on the sequence length at a 1:1 ratio. ii) Interleaving with KV Cache friendly architecture, such as local attention SWA, linear kernel GDN, but often involve trade-offs among KV Cache and long-context modeling effectiveness. Besides the two technique routings, we argue that there exists an intermediate path not well explored: {Maintaining a linear relationship between the KV cache and sequence length, but performing semantic-level compression through a specific ratio $k$}. This $O(n/k)$ path does not pursue a ``minimum KV cache'', but rather trades acceptable memory costs for complete, referential, and interpretable retention of long distant dependency. Motivated by this, we propose Kwai Summary Attention (KSA), a novel attention mechanism that reduces sequence modeling cost by compressing historical contexts into learnable summary tokens.

cs.CL↗

arXiv2026

ALPBench: A Benchmark for Attribution-level Long-term Personal Behavior Understanding

Recent advances in large language models have highlighted their potential for personalized recommendation, where accurately capturing user preferences remains a key challenge. Leveraging their strong reasoning and generalization capabilities, LLMs offer new opportunities for modeling long-term user behavior. To systematically evaluate this, we introduce ALPBench, a Benchmark for Attribution-level Long-term Personal Behavior Understanding. Unlike item-focused benchmarks, ALPBench predicts user-interested attribute combinations, enabling ground-truth evaluation even for newly introduced items. It models preferences from long-term historical behaviors rather than users' explicitly expressed requests, better reflecting enduring interests. User histories are represented as natural language sequences, allowing interpretable, reasoning-based personalization. ALPBench enables fine-grained evaluation of personalization by focusing on the prediction of attribute combinations task that remains highly challenging for current LLMs due to the need to capture complex interactions among multiple attributes and reason over long-term user behavior sequences.

cs.IR↗

arXiv2025

OpenOneRec Technical Report

While the OneRec series has successfully unified the fragmented recommendation pipeline into an end-to-end generative framework, a significant gap remains between recommendation systems and general intelligence. Constrained by isolated data, they operate as domain specialists-proficient in pattern matching but lacking world knowledge, reasoning capabilities, and instruction following. This limitation is further compounded by the lack of a holistic benchmark to evaluate such integrated capabilities. To address this, our contributions are: 1) RecIF Bench & Open Data: We propose RecIF-Bench, a holistic benchmark covering 8 diverse tasks that thoroughly evaluate capabilities from fundamental prediction to complex reasoning. Concurrently, we release a massive training dataset comprising 96 million interactions from 160,000 users to facilitate reproducible research. 2) Framework & Scaling: To ensure full reproducibility, we open-source our comprehensive training pipeline, encompassing data processing, co-pretraining, and post-training. Leveraging this framework, we demonstrate that recommendation capabilities can scale predictably while mitigating catastrophic forgetting of general knowledge. 3) OneRec-Foundation: We release OneRec Foundation (1.7B and 8B), a family of models establishing new state-of-the-art (SOTA) results across all tasks in RecIF-Bench. Furthermore, when transferred to the Amazon benchmark, our models surpass the strongest baselines with an average 26.8% improvement in Recall@10 across 10 diverse datasets (Figure 1). This work marks a step towards building truly intelligent recommender systems. Nonetheless, realizing this vision presents significant technical and theoretical challenges, highlighting the need for broader research engagement in this promising direction.

cs.IR↗

arXiv2025

OneRec-Think: In-Text Reasoning for Generative Recommendation

The powerful generative capacity of Large Language Models (LLMs) has instigated a paradigm shift in recommendation. However, existing generative models (e.g., OneRec) operate as implicit predictors, critically lacking the capacity for explicit and controllable reasoning-a key advantage of LLMs. To bridge this gap, we propose OneRec-Think, a unified framework that seamlessly integrates dialogue, reasoning, and personalized recommendation. OneRec-Think incorporates: (1) Itemic Alignment: cross-modal Item-Textual Alignment for semantic grounding; (2) Reasoning Activation: Reasoning Scaffolding to activate LLM reasoning within the recommendation context; and (3) Reasoning Enhancement, where we design a recommendation-specific reward function that accounts for the multi-validity nature of user preferences. Experiments across public benchmarks show state-of-the-art performance. Moreover, our proposed "Think-Ahead" architecture enables effective industrial deployment on Kuaishou, achieving a 0.159\% gain in APP Stay Time and validating the practical efficacy of the model's explicit reasoning capability.

cs.IR↗

arXiv2025

OneRec-V2 Technical Report

Recent breakthroughs in generative AI have transformed recommender systems through end-to-end generation. OneRec reformulates recommendation as an autoregressive generation task, achieving high Model FLOPs Utilization. While OneRec-V1 has shown significant empirical success in real-world deployment, two critical challenges hinder its scalability and performance: (1) inefficient computational allocation where 97.66% of resources are consumed by sequence encoding rather than generation, and (2) limitations in reinforcement learning relying solely on reward models. To address these challenges, we propose OneRec-V2, featuring: (1) Lazy Decoder-Only Architecture: Eliminates encoder bottlenecks, reducing total computation by 94% and training resources by 90%, enabling successful scaling to 8B parameters. (2) Preference Alignment with Real-World User Interactions: Incorporates Duration-Aware Reward Shaping and Adaptive Ratio Clipping to better align with user preferences using real-world feedback. Extensive A/B tests on Kuaishou demonstrate OneRec-V2's effectiveness, improving App Stay Time by 0.467%/0.741% while balancing multi-objective recommendations. This work advances generative recommendation scalability and alignment with real-world feedback, representing a step forward in the development of end-to-end recommender systems.

cs.IR↗

arXiv2025

A Constraint-Preserving Neural Network Approach for Solving Mean-Field Games Equilibrium

Neural network-based methods have demonstrated effectiveness in solving high-dimensional Mean-Field Games (MFG) equilibria, yet ensuring mathematically consistent density-coupled evolution remains a major challenge. This paper proposes the NF-MKV Net, a neural network approach that integrates process-regularized normalizing flow (NF) with state-policy-connected time-series neural networks to solve MKV FBSDEs and their associated fixed-point formulations of MFG equilibria. The method first reformulates MFG equilibria as MKV FBSDEs, embedding density evolution into equation coefficients within a probabilistic framework. Neural networks are then employed to approximate value functions and their gradients. To enforce volumetric invariance and temporal continuity, NF architectures impose loss constraints on each density transfer function.

cs.LG↗

arXiv2025

Reducing Action Space for Deep Reinforcement Learning via Causal Effect Estimation

Intelligent decision-making within large and redundant action spaces remains challenging in deep reinforcement learning. Considering similar but ineffective actions at each step can lead to repetitive and unproductive trials. Existing methods attempt to improve agent exploration by reducing or penalizing redundant actions, yet they fail to provide quantitative and reliable evidence to determine redundancy. In this paper, we propose a method to improve exploration efficiency by estimating the causal effects of actions. Unlike prior methods, our approach offers quantitative results regarding the causality of actions for one-step transitions. We first pre-train an inverse dynamics model to serve as prior knowledge of the environment. Subsequently, we classify actions across the entire action space at each time step and estimate the causal effect of each action to suppress redundant actions during exploration. We provide a theoretical analysis to demonstrate the effectiveness of our method and present empirical results from simulations in environments with redundant actions to evaluate its performance. Our implementation is available at https://github.com/agi-brain/cee.git.

cs.LG↗

arXiv2024

Enhance Hyperbolic Representation Learning via Second-order Pooling

Hyperbolic representation learning is well known for its ability to capture hierarchical information. However, the distance between samples from different levels of hierarchical classes can be required large. We reveal that the hyperbolic discriminant objective forces the backbone to capture this hierarchical information, which may inevitably increase the Lipschitz constant of the backbone. This can hinder the full utilization of the backbone's generalization ability. To address this issue, we introduce second-order pooling into hyperbolic representation learning, as it naturally increases the distance between samples without compromising the generalization ability of the input features. In this way, the Lipschitz constant of the backbone does not necessarily need to be large. However, current off-the-shelf low-dimensional bilinear pooling methods cannot be directly employed in hyperbolic representation learning because they inevitably reduce the distance expansion capability. To solve this problem, we propose a kernel approximation regularization, which enables the low-dimensional bilinear features to approximate the kernel function well in low-dimensional space. Finally, we conduct extensive experiments on graph-structured datasets to demonstrate the effectiveness of the proposed method.

cs.LG↗

arXiv2024

Linear Quadratic Mean Field Games under Heterogeneous Erroneous Initial Information

We study a finite-horizon linear--quadratic mean field game with heterogeneous observations of the initial mean field. These observations may be erroneous and are used by agents to construct their feedback laws. At the population level, the heterogeneous error profile is generally infinite-dimensional. We derive exact linear sensitivity formulas showing that its closed-loop effects nevertheless admit a finite-dimensional closure: for each agent, the deviations are governed by only two n-dimensional error channels, its private error E_i and the population-average error \bar E. The population-average error determines the displacement of the actual mean field, whereas centered private errors determine agent-specific deviations and the additional cross-sectional covariance. The same representation yields quadratic cost identities and a uniform $O(N^{-1})$ mean-square approximation of the empirical aggregate. In the deterministic model, the private state history induces a linear observation problem for the initial errors. Nonsingularity of the associated observability Gramian is necessary and sufficient for exact recovery. The recovered errors reconstruct the actual mean-field state at the revision time and initialize a revised correct-information continuation from that state. We obtain an exact continuation-cost comparison; when the population-average error vanishes, revision does not increase the continuation cost. For stochastic dynamics, we take a two-component revision signal as given and study the resulting one-shot feedback relative to an oracle continuation initialized with the actual current mean field. The actual mean-field deviation is driven only by the population-average signal error, while individual deviations also retain the private signal error. Exact covariance and quadratic continuation-cost identities quantify these effects.

math.OC↗

arXiv2024

Social optimum of finite mean field games: existence and uniqueness of equilibrium solutions in the finite horizon and stationary solutions in the infinite horizon

In this paper, we consider the social optimal problem of discrete time finite state space mean field games (referred to as finite mean field games [1]). Unlike the individual optimization of their own cost function in competitive models, in the problem we consider, individuals aim to optimize the social cost by finding a fixed point of the state distribution to achieve equilibrium in the mean field game. We provide a sufficient condition for the existence and uniqueness of the individual optimal strategies used to minimize the social cost. According to the definition of social optimum and the derived properties of social optimal cost, the existence and uniqueness conditions of equilibrium solutions under initial-terminal value constraints in the finite horizon and the existence and uniqueness conditions of stable solutions in the infinite horizon are given. Finally, two examples that satisfy the conditions for the above solutions are provided.

math.OC↗

arXiv2024

DmADs-Net: Dense multiscale attention and depth-supervised network for medical image segmentation

Deep learning has made important contributions to the development of medical image segmentation. Convolutional neural networks, as a crucial branch, have attracted strong attention from researchers. Through the tireless efforts of numerous researchers, convolutional neural networks have yielded numerous outstanding algorithms for processing medical images. The ideas and architectures of these algorithms have also provided important inspiration for the development of later technologies.Through extensive experimentation, we have found that currently mainstream deep learning algorithms are not always able to achieve ideal results when processing complex datasets and different types of datasets. These networks still have room for improvement in lesion localization and feature extraction. Therefore, we have created the Dense Multiscale Attention and Depth-Supervised Network (DmADs-Net).We use ResNet for feature extraction at different depths and create a Multi-scale Convolutional Feature Attention Block to improve the network's attention to weak feature information. The Local Feature Attention Block is created to enable enhanced local feature attention for high-level semantic information. In addition, in the feature fusion phase, a Feature Refinement and Fusion Block is created to enhance the fusion of different semantic information.We validated the performance of the network using five datasets of varying sizes and types. Results from comparative experiments show that DmADs-Net outperformed mainstream networks. Ablation experiments further demonstrated the effectiveness of the created modules and the rationality of the network architecture.

eess.IV↗

arXiv2024

Leveraging Cross-Modal Neighbor Representation for Improved CLIP Classification

CLIP showcases exceptional cross-modal matching capabilities due to its training on image-text contrastive learning tasks. However, without specific optimization for unimodal scenarios, its performance in single-modality feature extraction might be suboptimal. Despite this, some studies have directly used CLIP's image encoder for tasks like few-shot classification, introducing a misalignment between its pre-training objectives and feature extraction methods. This inconsistency can diminish the quality of the image's feature representation, adversely affecting CLIP's effectiveness in target tasks. In this paper, we view text features as precise neighbors of image features in CLIP's space and present a novel CrOss-moDal nEighbor Representation(CODER) based on the distance structure between images and their neighbor texts. This feature extraction method aligns better with CLIP's pre-training objectives, thereby fully leveraging CLIP's robust cross-modal capabilities. The key to construct a high-quality CODER lies in how to create a vast amount of high-quality and diverse texts to match with images. We introduce the Auto Text Generator(ATG) to automatically generate the required texts in a data-free and training-free manner. We apply CODER to CLIP's zero-shot and few-shot image classification tasks. Experiment results across various datasets and models confirm CODER's effectiveness. Code is available at:https://github.com/YCaigogogo/CVPR24-CODER.

cs.CV↗

arXiv2023

ZhiJian: A Unifying and Rapidly Deployable Toolbox for Pre-trained Model Reuse

The rapid expansion of foundation pre-trained models and their fine-tuned counterparts has significantly contributed to the advancement of machine learning. Leveraging pre-trained models to extract knowledge and expedite learning in real-world tasks, known as "Model Reuse", has become crucial in various applications. Previous research focuses on reusing models within a certain aspect, including reusing model weights, structures, and hypothesis spaces. This paper introduces ZhiJian, a comprehensive and user-friendly toolbox for model reuse, utilizing the PyTorch backend. ZhiJian presents a novel paradigm that unifies diverse perspectives on model reuse, encompassing target architecture construction with PTM, tuning target model with PTM, and PTM-based inference. This empowers deep learning practitioners to explore downstream tasks and identify the complementary advantages among different methods. ZhiJian is readily accessible at https://github.com/zhangyikaii/lamda-zhijian facilitating seamless utilization of pre-trained models and streamlining the model reuse process for researchers and developers.

cs.LG↗

arXiv2012

Cologne: A Declarative Distributed Constraint Optimization Platform

This paper presents Cologne, a declarative optimization platform that enables constraint optimization problems (COPs) to be declaratively specified and incrementally executed in distributed systems. Cologne integrates a declarative networking engine with an off-the-shelf constraint solver. We have developed the Colog language that combines distributed Datalog used in declarative networking with language constructs for specifying goals and constraints used in COPs. Cologne uses novel query processing strategies for processing Colog programs, by combining the use of bottom-up distributed Datalog evaluation with top-down goal-oriented constraint solving. Using case studies based on cloud and wireless network optimizations, we demonstrate that Cologne (1) can flexibly support a wide range of policy-based optimizations in distributed systems, (2) results in orders of magnitude less code compared to imperative implementations, and (3) is highly efficient with low overhead and fast convergence times.

cs.DB↗

arXiv2010

Flavor Violating Transitions of Charged Leptons from a Seesaw Mechanism of Dimension Seven

A mechanism has been suggested recently to generate the neutrino mass out of a dimension-seven operator. This is expected to relieve the tension between the occurrence of a tiny neutrino mass and the observability of other physics effects beyond it. Such a mechanism would inevitably entail lepton flavor violating effects. We study in this work the radiative and purely leptonic transitions of the light charged leptons. In so doing we make a systematic analysis of the flavor structure by providing a convenient parametrization of the mass matrices in terms of independent physical parameters and diagonalizing them explicitly. We illustrate our numerical results by sampling over two CP phases and one Yukawa coupling which are the essential parameters in addition to the heavy lepton mass. We find that with the stringent constraints coming from the muon decays and the muon-electron conversion in nuclei taken into account the decays of the tau lepton are severely suppressed in the majority of parameter space. There exist, however, small regions in which some tau decays can reach a level that is about 2 orders of magnitude below their current bounds.

hep-ph↗