arXiv subjects

Yuchen Li

Publications and source records attributed to Yuchen Li.

At least 91 records · Page 5Linked to original sources

arXiv2025

Taming Imperfect Process Verifiers: A Sampling Perspective on Backtracking

Test-time algorithms that combine the generative power of language models with process verifiers that assess the quality of partial generations offer a promising lever for eliciting new reasoning capabilities, but the algorithmic design space and computational scaling properties of such approaches are still opaque, and their benefits are far from apparent when one accounts for the cost of learning a high-quality verifier. Our starting point is the observation that seemingly benign errors in a learned verifier can lead to catastrophic failures for standard decoding techniques due to error amplification during the course of generation. We then ask: can this be improved with more sophisticated decoding strategies? We introduce a new process-guided test-time sampling algorithm, VGB, which uses theoretically grounded backtracking to achieve provably better robustness to verifier errors. VGB interprets autoregressive generation as a random walk on a tree of partial generations, with transition probabilities guided by the process verifier and base model; crucially, backtracking occurs probabilistically. This process generalizes the seminal Sinclair-Jerrum random walk (Sinclair & Jerrum, 1989) from the literature on approximate counting and sampling in theoretical computer science, and a conceptual contribution of our work is to highlight parallels with this literature. Empirically, we demonstrate on both synthetic and real language modeling tasks that VGB outperforms baselines on a variety of metrics.

cs.LG↗

arXiv2025

Expanding Horizons of Level Diversity via Multi-objective Evolutionary Learning

In recent years, the generation of diverse game levels has gained increasing interest, contributing to a richer and more engaging gaming experience. A number of level diversity metrics have been proposed in literature, which are naturally multi-dimensional, leading to conflicted, complementary, or both relationships among these dimensions. However, existing level generation approaches often fail to comprehensively assess diversity across those dimensions. This paper aims to expand horizons of level diversity by considering multi-dimensional diversity when training generative models. We formulate the model training as a multi-objective learning problem, where each diversity metric is treated as a distinct objective. Furthermore, a multi-objective evolutionary learning framework that optimises multiple diversity metrics simultaneously throughout the model training process is proposed. Our case study on the commonly used benchmark Super Mario Bros. demonstrates that our proposed framework can enhance multi-dimensional diversity and identify a Pareto front of generative models, which provides a range of tradeoffs among playability and two representative diversity metrics, including a content-based one and a player-centered one. Such capability enables decision-makers to make informed choices when selecting generators accommodating a variety of scenarios and the diverse needs of players and designers.

cs.LG↗

arXiv2025

Enhancing Intent Understanding for Ambiguous prompt: A Human-Machine Co-Adaption Strategy

Current image generation systems produce high-quality images but struggle with ambiguous user prompts, making interpretation of actual user intentions difficult. Many users must modify their prompts several times to ensure the generated images meet their expectations. While some methods focus on enhancing prompts to make the generated images fit user needs, the model is still hard to understand users' real needs, especially for non-expert users. In this research, we aim to enhance the visual parameter-tuning process, making the model user-friendly for individuals without specialized knowledge and better understand user needs. We propose a human-machine co-adaption strategy using mutual information between the user's prompts and the pictures under modification as the optimizing target to make the system better adapt to user needs. We find that an improved model can reduce the necessity for multiple rounds of adjustments. We also collect multi-round dialogue datasets with prompts and images pairs and user intent. Various experiments demonstrate the effectiveness of the proposed method in our proposed dataset. Our dataset and annotation tools will be available.

cs.CV↗

arXiv2025

SCORE: Story Coherence and Retrieval Enhancement for AI Narratives

Large Language Models (LLMs) can generate creative and engaging narratives from user-specified input, but maintaining coherence and emotional depth throughout these AI-generated stories remains a challenge. In this work, we propose SCORE, a framework for Story Coherence and Retrieval Enhancement, designed to detect and resolve narrative inconsistencies. By tracking key item statuses and generating episode summaries, SCORE uses a Retrieval-Augmented Generation (RAG) approach to identify related episodes and enhance the overall story structure. Experimental results from testing multiple LLM-generated stories demonstrate that SCORE significantly improves the consistency and stability of narrative coherence compared to baseline GPT models, providing a more robust method for evaluating and refining AI-generated narratives.

cs.CL↗

arXiv2025

Ethical Considerations of Large Language Models in Game Playing

Large language models (LLMs) have demonstrated tremendous potential in game playing, while little attention has been paid to their ethical implications in those contexts. This work investigates and analyses the ethical considerations of applying LLMs in game playing, using Werewolf, also known as Mafia, as a case study. Gender bias, which affects game fairness and player experience, has been observed from the behaviour of LLMs. Some roles, such as the Guard and Werewolf, are more sensitive than others to gender information, presented as a higher degree of behavioural change. We further examine scenarios in which gender information is implicitly conveyed through names, revealing that LLMs still exhibit discriminatory tendencies even in the absence of explicit gender labels. This research showcases the importance of developing fair and ethical LLMs. Beyond our research findings, we discuss the challenges and opportunities that lie ahead in this field, emphasising the need for diving deeper into the ethical implications of LLMs in gaming and other interactive domains.

cs.CL↗

arXiv2025

Improving DAPO from a Mixed-Policy Perspective

This paper introduces two novel modifications to the Dynamic sAmpling Policy Optimization (DAPO) algorithm [1], approached from a mixed-policy perspective. Standard policy gradient methods can suffer from instability and sample inefficiency, particularly in sparse reward settings. To address this, we first propose a method that incorporates a pre-trained, stable guiding policy ($\piphi$) to provide off-policy experience, thereby regularizing the training of the target policy ($\pion$). This approach improves training stability and convergence speed by adaptively adjusting the learning step size. Secondly, we extend this idea to re-utilize zero-reward samples, which are often discarded by dynamic sampling strategies like DAPO's. By treating these samples as a distinct batch guided by the expert policy, we further enhance sample efficiency. We provide a theoretical analysis for both methods, demonstrating that their objective functions converge to the optimal solution within the established theoretical framework of reinforcement learning. The proposed mixed-policy framework effectively balances exploration and exploitation, promising more stable and efficient policy optimization.

cs.LG↗

arXiv2025

Enhancing Code LLMs with Reinforcement Learning in Code Generation: A Survey

With the rapid evolution of large language models (LLM), reinforcement learning (RL) has emerged as a pivotal technique for code generation and optimization in various domains. This paper presents a systematic survey of the application of RL in code optimization and generation, highlighting its role in enhancing compiler optimization, resource allocation, and the development of frameworks and tools. Subsequent sections first delve into the intricate processes of compiler optimization, where RL algorithms are leveraged to improve efficiency and resource utilization. The discussion then progresses to the function of RL in resource allocation, emphasizing register allocation and system optimization. We also explore the burgeoning role of frameworks and tools in code generation, examining how RL can be integrated to bolster their capabilities. This survey aims to serve as a comprehensive resource for researchers and practitioners interested in harnessing the power of RL to advance code generation and optimization techniques.

cs.SE↗

arXiv2025

RecGPT Technical Report

Recommender systems are among the most impactful applications of artificial intelligence, serving as critical infrastructure connecting users, merchants, and platforms. However, most current industrial systems remain heavily reliant on historical co-occurrence patterns and log-fitting objectives, i.e., optimizing for past user interactions without explicitly modeling user intent. This log-fitting approach often leads to overfitting to narrow historical preferences, failing to capture users' evolving and latent interests. As a result, it reinforces filter bubbles and long-tail phenomena, ultimately harming user experience and threatening the sustainability of the whole recommendation ecosystem. To address these challenges, we rethink the overall design paradigm of recommender systems and propose RecGPT, a next-generation framework that places user intent at the center of the recommendation pipeline. By integrating large language models (LLMs) into key stages of user interest mining, item retrieval, and explanation generation, RecGPT transforms log-fitting recommendation into an intent-centric process. To effectively align general-purpose LLMs to the above domain-specific recommendation tasks at scale, RecGPT incorporates a multi-stage training paradigm, which integrates reasoning-enhanced pre-alignment and self-training evolution, guided by a Human-LLM cooperative judge system. Currently, RecGPT has been fully deployed on the Taobao App. Online experiments demonstrate that RecGPT achieves consistent performance gains across stakeholders: users benefit from increased content diversity and satisfaction, merchants and the platform gain greater exposure and conversions. These comprehensive improvement results across all stakeholders validates that LLM-driven, intent-centric design can foster a more sustainable and mutually beneficial recommendation ecosystem.

cs.IR↗

arXiv2025

LLMATCH: A Unified Schema Matching Framework with Large Language Models

Schema matching is a foundational task in enterprise data integration, aiming to align disparate data sources. While traditional methods handle simple one-to-one table mappings, they often struggle with complex multi-table schema matching in real-world applications. We present LLMatch, a unified and modular schema matching framework. LLMatch decomposes schema matching into three distinct stages: schema preparation, table-candidate selection, and column-level alignment, enabling component-level evaluation and future-proof compatibility. It includes a novel two-stage optimization strategy: a Rollup module that consolidates semantically related columns into higher-order concepts, followed by a Drilldown module that re-expands these concepts for fine-grained column mapping. To address the scarcity of complex semantic matching benchmarks, we introduce SchemaNet, a benchmark derived from real-world schema pairs across three enterprise domains, designed to capture the challenges of multi-table schema alignment in practical settings. Experiments demonstrate that LLMatch significantly improves matching accuracy in complex schema matching settings and substantially boosts engineer productivity in real-world data integration.

cs.DB↗

arXiv2025

Frequency-Resolved Forward Capacitance in GaN-based LEDs

This study establishes a unified framework for interpreting dynamic capacitive responses in InGaN-based light-emitting diodes (LEDs) through forward-bias capacitance-voltage-frequency spectroscopy. A hybrid impedance model integrating series RL components and parallel C-G networks was developed to resolve distinct frequency-dependent capacitive regimes. The low-frequency regime (<1 kHz) is governed by interfacial capacitance with characteristic reciprocal frequency dependence, while the mid-frequency range(10 kHz-6.4 MHz) demonstrates carrier diffusion and recombination dynamics. At MHz frequencies, negative capacitance manifests due to delayed carrier emission mediated by deep-level traps. The model achieved sub-1% fitting errors (R^2 > 0.99)across a broad bandwidth(10 kHz-6.4 MHz) , conclusively attributing negative capacitance to intrinsic trap processes rather than extrinsic artifacts. Critical advances include quantum well cap thickness modulation reducing mid-frequency capacitance by 30% and the dominance of trap-mediated inductance over parasitic contributions by three orders of magnitude. This framework resolves persistent controversies in LED impedance interpretation. By bridging semiconductor physics with device engineering, this methodology provides essential tools for designing next-generation optoelectronic systems requiring ultralow-latency operation and precise charge-state control.

physics.app-ph↗

arXiv2025

Spherical Pendulum with Quad-Rotor Thrust Vectoring Actuation -- A Novel Mechatronics and Control Benchmark Platform

Motor-actuated pendulums have been established as arguably the most common laboratory prototypes used in control system education because of the relevance to robot manipulator control in industry. Meanwhile, multi-rotor drones like quadcopters have become popular in industrial applications but have not been broadly employed in control education laboratory. Platforms with pendulums and multi-rotor copters present classical yet intriguing multi-degree of freedom (DoF) dynamics and coordinate systems for the control system investigation. In this paper, we introduce a novel control platform in which a 2-DoF pendulum capable of azimuth and elevation rotation is actuated through vectored thrust generated by a quadcopter. Designed as a benchmark for mechatronics and nonlinear control education and research, the system integrates detailed mechatronic implementation with different control strategies. Specifically, we apply and compare small perturbation linearization (SPL), state feedback linearization (SFL), and partial feedback linearization (PFL) to the nonlinear system dynamics. The performances are evaluated by time specifications of step response and Root-Mean-Square (RMS) error of trajectory tracking. The robustness of the closed-loop system is validated under external disturbances, and both simulation and experimental results are presented to highlight the strengths and limitations of the nonlinear model-based control approaches.

eess.SY↗

arXiv2025

FALCON: Feedback-driven Adaptive Long/short-term memory reinforced Coding Optimization system

Recently, large language models (LLMs) have achieved significant progress in automated code generation. Despite their strong instruction-following capabilities, these models frequently struggled to align with user intent in coding scenarios. In particular, they were hampered by datasets that lacked diversity and failed to address specialized tasks or edge cases. Furthermore, challenges in supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF) led to failures in generating precise, human-intent-aligned code. To tackle these challenges and improve the code generation performance for automated programming systems, we propose Feedback-driven Adaptive Long/short-term memory reinforced Coding Optimization (i.e., FALCON). FALCON is structured into two hierarchical levels. From the global level, long-term memory improves code quality by retaining and applying learned knowledge. At the local level, short-term memory allows for the incorporation of immediate feedback from compilers and AI systems. Additionally, we introduce meta-reinforcement learning with feedback rewards to solve the global-local bi-level optimization problem and enhance the model's adaptability across diverse code generation tasks. Extensive experiments demonstrate that our technique achieves state-of-the-art performance, leading other reinforcement learning methods by more than 4.5 percentage points on the MBPP benchmark and 6.1 percentage points on the Humaneval benchmark. The open-sourced code is publicly available at https://github.com/titurte/FALCON.

cs.LG↗

arXiv2025

On the Query Complexity of Verifier-Assisted Language Generation

Recently, a plethora of works have proposed inference-time algorithms (e.g. best-of-n), which incorporate verifiers to assist the generation process. Their quality-efficiency trade-offs have been empirically benchmarked on a variety of constrained generation tasks, but the algorithmic design landscape is still largely poorly understood. In this paper, we develop a mathematical framework for reasoning about constrained generation using a pre-trained language model generator oracle and a process verifier--which can decide whether a prefix can be extended to a string which satisfies the constraints of choice. We show that even in very simple settings, access to a verifier can render an intractable problem (information-theoretically or computationally) to a tractable one. In fact, we show even simple algorithms, like tokenwise rejection sampling, can enjoy significant benefits from access to a verifier. Empirically, we show that a natural modification of tokenwise rejection sampling, in which the sampler is allowed to "backtrack" (i.e., erase the final few generated tokens) has robust and substantive benefits over natural baselines (e.g. (blockwise) rejection sampling, nucleus sampling)--both in terms of computational efficiency, accuracy and diversity.

cs.CL↗

arXiv2025

Bias as a Virtue: Rethinking Generalization under Distribution Shifts

Machine learning models often degrade when deployed on data distributions different from their training data. Challenging conventional validation paradigms, we demonstrate that higher in-distribution (ID) bias can lead to better out-of-distribution (OOD) generalization. Our Adaptive Distribution Bridge (ADB) framework implements this insight by introducing controlled statistical diversity during training, enabling models to develop bias profiles that effectively generalize across distributions. Empirically, we observe a robust negative correlation where higher ID bias corresponds to lower OOD error--a finding that contradicts standard practices focused on minimizing validation error. Evaluation on multiple datasets shows our approach significantly improves OOD generalization. ADB achieves robust mean error reductions of up to 26.8% compared to traditional cross-validation, and consistently identifies high-performing training strategies, evidenced by percentile ranks often exceeding 74.4%. Our work provides both a practical method for improving generalization and a theoretical framework for reconsidering the role of bias in robust machine learning.

cs.LG↗

arXiv2025

Bootstrapping your behavior: a new pretraining strategy for user behavior sequence data

User Behavior Sequence (UBS) modeling is crucial in industrial applications. As data scale and task diversity grow, UBS pretraining methods have become increasingly pivotal. State-of-the-art UBS pretraining methods rely on predicting behavior distributions. The key step in these methods is constructing a selected behavior vocabulary. However, this manual step is labor-intensive and prone to bias. The limitation of vocabulary capacity also directly affects models' generalization ability. In this paper, we introduce Bootstrapping Your Behavior (\model{}), a novel UBS pretraining strategy that predicts an automatically constructed supervision embedding summarizing all behaviors' information within a future time window, eliminating the manual behavior vocabulary selection. In implementation, we incorporate a student-teacher encoder scheme to construct the pretraining supervision effectively. Experiments on two real-world industrial datasets and eight downstream tasks demonstrate that \model{} achieves an average improvement of 3.9\% in AUC and 98.9\% in training throughput. Notably, the model exhibits meaningful attention patterns and cluster representations during pretraining without any label supervision. In our online deployment over two months, the pretrained model improves the KS by about 2.7\% and 7.1\% over the baseline model for two financial overdue risk prediction tasks in the Alipay mobile application, which reduces bad debt risk by millions of dollars for Ant group.

cs.LG↗

arXiv2025

GS2E: Gaussian Splatting is an Effective Data Generator for Event Stream Generation

We introduce GS2E (Gaussian Splatting to Event), a large-scale synthetic event dataset for high-fidelity event vision tasks, captured from real-world sparse multi-view RGB images. Existing event datasets are often synthesized from dense RGB videos, which typically lack viewpoint diversity and geometric consistency, or depend on expensive, difficult-to-scale hardware setups. GS2E overcomes these limitations by first reconstructing photorealistic static scenes using 3D Gaussian Splatting, and subsequently employing a novel, physically-informed event simulation pipeline. This pipeline generally integrates adaptive trajectory interpolation with physically-consistent event contrast threshold modeling. Such an approach yields temporally dense and geometrically consistent event streams under diverse motion and lighting conditions, while ensuring strong alignment with underlying scene structures. Experimental results on event-based 3D reconstruction demonstrate GS2E's superior generalization capabilities and its practical value as a benchmark for advancing event vision research.

cs.CV↗

arXiv2025

Pipelining Kruskal's: A Neuromorphic Approach for Minimum Spanning Tree

Neuromorphic computing, characterized by its event-driven computation and massive parallelism, is particularly effective for handling data-intensive tasks in low-power environments, such as computing the minimum spanning tree (MST) for large-scale graphs. The introduction of dynamic synaptic modifications provides new design opportunities for neuromorphic algorithms. Building on this foundation, we propose an SNN-based union-sort routine and a pipelined version of Kruskal's algorithm for MST computation. The event-driven nature of our method allows for the concurrent execution of two completely decoupled stages: neuromorphic sorting and union-find. Our approach demonstrates superior performance compared to state-of-the-art Prim 's-based methods on large-scale graphs from the DIMACS10 dataset, achieving speedups by 269.67x to 1283.80x, with a median speedup of 540.76x. We further evaluate the pipelined implementation against two serial variants of Kruskal's algorithm, which rely on neuromorphic sorting and neuromorphic radix sort, showing significant performance advantages in most scenarios.

cs.ET↗

arXiv2025

3DCoMPaT$^{++}$: An improved Large-scale 3D Vision Dataset for Compositional Recognition

In this work, we present 3DCoMPaT$^{++}$, a multimodal 2D/3D dataset with 160 million rendered views of more than 10 million stylized 3D shapes carefully annotated at the part-instance level, alongside matching RGB point clouds, 3D textured meshes, depth maps, and segmentation masks. 3DCoMPaT$^{++}$ covers 41 shape categories, 275 fine-grained part categories, and 293 fine-grained material classes that can be compositionally applied to parts of 3D objects. We render a subset of one million stylized shapes from four equally spaced views as well as four randomized views, leading to a total of 160 million renderings. Parts are segmented at the instance level, with coarse-grained and fine-grained semantic levels. We introduce a new task, called Grounded CoMPaT Recognition (GCR), to collectively recognize and ground compositions of materials on parts of 3D objects. Additionally, we report the outcomes of a data challenge organized at CVPR2023, showcasing the winning method's utilization of a modified PointNet$^{++}$ model trained on 6D inputs, and exploring alternative techniques for GCR enhancement. We hope our work will help ease future research on compositional 3D Vision.

cs.CV↗