Searcharxiv⌕ Search

arXiv subjects

Guoyin Wang

Publications and source records attributed to Guoyin Wang.

At least 37 records · Page 2Linked to original sources
arXiv2026

FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization

We present Future-KL Influenced Policy Optimization (FIPO), a reinforcement learning algorithm designed to overcome reasoning bottlenecks in large language models. While GRPO style training scales effectively, it typically relies on outcome-based rewards (ORM) that distribute a global advantage uniformly across every token in a trajectory. We argue that this coarse-grained credit assignment imposes a performance ceiling by failing to distinguish critical logical pivots from trivial tokens. FIPO addresses this by incorporating discounted future-KL divergence into the policy update, creating a dense advantage formulation that re-weights tokens based on their influence on subsequent trajectory behavior. Empirically, FIPO enables models to break through the length stagnation seen in standard baselines. Evaluated on Qwen2.5-32B, FIPO extends the average chain-of-thought length from roughly 4,000 to over 10,000 tokens and increases AIME 2024 Pass@1 accuracy from 50.0% to a peak of 58.0% (converging at approximately 56.0\%). This outperforms both DeepSeek-R1-Zero-Math-32B (around 47.0%) and o1-mini (approximately 56.0%). Our results suggest that establishing dense advantage formulations is a vital path for evolving ORM-based algorithms to unlock the full reasoning potential of base models. We open-source our training system, built on the verl framework.

cs.LG↗
arXiv2026

Square Superpixel Generation and Representation Learning via Granular Ball Computing

Superpixels provide a compact region-based representation that preserves object boundaries and local structures, and have therefore been widely used in a variety of vision tasks to reduce computational cost. However, most existing superpixel algorithms produce irregularly shaped regions, which are not well aligned with regular operators such as convolutions. Consequently, superpixels are often treated as an offline preprocessing step, limiting parallel implementation and hindering end-to-end optimization within deep learning pipelines. Motivated by the adaptive representation and coverage property of granular-ball computing, we develop a square superpixel generation approach. Specifically, we approximate superpixels using multi-scale square blocks to avoid the computational and implementation difficulties induced by irregular shapes, enabling efficient parallel processing and learnable feature extraction. For each block, a purity score is computed based on pixel-intensity similarity, and high-quality blocks are selected accordingly. The resulting square superpixels can be readily integrated as graph nodes in graph neural networks (GNNs) or as tokens in Vision Transformers (ViTs), facilitating multi-scale information aggregation and structured visual representation. Experimental results on downstream tasks demonstrate consistent performance improvements, validating the effectiveness of the proposed method.

cs.CV↗
arXiv2026

Bridging Perception and Reasoning: Token Reweighting for RLVR in Multimodal LLMs

Extending Reinforcement Learning with Verifiable Rewards (RLVR) to multimodal large language models (MLLMs) faces a fundamental challenge: their responses inherently interleave perception-related tokens, which ground visual content, with reasoning-related tokens, which construct reasoning chains. These token types instantiate distinct yet interdependent capacities -- visual grounding and symbolic reasoning -- making isolated optimization insufficient. Through token-level empirical analysis, we demonstrate that optimizing either perception- or reasoning-only tokens consistently underperforms full optimization, underscoring their inherent coupling. To address this, we propose a plug-and-play Token-Reweighting (ToR) strategy that explicitly models this interdependence by identifying critical tokens of both types and dynamically reweighting them during RLVR training. Applied on top of existing methods (e.g., GRPO and DAPO), ToR delivers consistent performance gains across multiple multi-modal reasoning benchmarks, achieving state-of-the-art performance with both accurate visual grounding and coherent reasoning.

cs.CV↗
arXiv2026

On the Direction of RLVR Updates for LLM Reasoning: Identification and Exploitation

Reinforcement learning with verifiable rewards (RLVR) has substantially improved the reasoning capabilities of large language models. While existing analyses identify that RLVR-induced changes are sparse, they primarily focus on the \textbf{magnitude} of these updates, largely overlooking their \textbf{direction}. In this work, we argue that the direction of updates is a more critical lens for understanding RLVR's effects, which can be captured by the signed, token-level log probability difference $Δ\log p$ between the base and final RLVR models. Through statistical analysis and token-replacement interventions, we demonstrate that $Δ\log p$ more effectively identifies sparse, yet reasoning-critical updates than magnitude-based metrics (\eg divergence or entropy). Building on this insight, we propose two practical applications: (1) a \textit{test-time extrapolation} method that amplifies the policy along the learned $Δ\log p$ direction to improve reasoning accuracy without further training; (2) a \textit{training-time reweighting} method that focuses learning on low-probability (corresponding to higher $Δ\log p$) tokens, which improves reasoning performance across models and benchmarks. Our work establishes the direction of change as a key principle for analyzing and improving RLVR.

cs.LG↗
arXiv2026

Sparse but Critical: A Token-Level Analysis of Distributional Shifts in RLVR Fine-Tuning of LLMs

Reinforcement learning with verifiable rewards (RLVR) has significantly improved reasoning in large language models (LLMs), yet the token-level mechanisms underlying these improvements remain unclear. We present a systematic empirical study of RLVR's distributional effects organized around three main analyses: (1) token-level characterization of distributional shifts between base and RL models, (2) the impact of token-level distributional shifts on sequence-level reasoning performance through cross-sampling interventions, and (3) fine-grained mechanics of these shifts at the token level. We find that RL fine-tuning induces highly sparse and targeted changes, with only a small fraction of token distributions exhibiting meaningful divergence between the base and RL policies. We further characterize the structure and evolution of these shifts through analyses of token entropy, positional concentration, and reallocation of probability mass. To assess the functional importance of these sparse changes, we conduct cross-sampling experiments that selectively swap token choices between the base and RL models with varying intervention budgets. We show that inserting only a small fraction of RL-sampled tokens into base generations progressively recovers RL performance gains, while injecting a similarly small number of base token choices into otherwise RL-generated sequences collapses performance to base levels, isolating a small set of token-level decisions directly responsible for RLVR's performance gains. Finally, we explore divergence-weighted variants of the advantage signal as a diagnostic intervention, finding that they can yield improvements over baselines. Together, our results shed light on the distributional changes induced by RLVR and provide a fine-grained, token-level lens for understanding RLVR fine-tuning as a targeted refinement process.

cs.CL↗
arXiv2026

On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting

Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) are two prominent post-training paradigms for refining the capabilities and aligning the behavior of Large Language Models (LLMs). Existing approaches that integrate SFT and RL often face the risk of disrupting established response patterns and inducing overfitting to expert data. To address this, we present a novel investigation into the unified view of SFT and RL through an off-policy versus on-policy lens. We propose CHORD, a framework for Controllable Harmonization of On- and Off-Policy Reinforcement Learning via Dynamic Weighting, which reframes SFT not as a separate stage but as a dynamically weighted auxiliary objective within the on-policy RL process. Based on an analysis of off-policy expert data's influence at both holistic and granular levels, we incorporate a dual-control mechanism in CHORD. Specifically, the framework first employs a global coefficient to holistically guide the transition from off-policy imitation to on-policy exploration, and then applies a token-wise weighting function that enables granular learning from the expert, which promotes on-policy exploration and mitigates disruption from off-policy data. We conduct extensive experiments across various practical tasks, providing empirical evidence that CHORD achieves a stable and efficient learning process. By effectively harmonizing off-policy expert data with on-policy exploration, CHORD demonstrates significant improvements over baselines. We release the implementation at https://github.com/modelscope/Trinity-RFT/tree/main/examples/mix_chord to inspire further research.

cs.LG↗
arXiv2026

Mastering the Minority: An Uncertainty-guided Multi-Expert Framework for Challenging-tailed Sequence Learning

Imbalanced data distribution remains a critical challenge in sequential learning, leading models to easily recognize frequent categories while failing to detect minority classes adequately. The Mixture-of-Experts model offers a scalable solution, yet its application is often hindered by parameter inefficiency, poor expert specialization, and difficulty in resolving prediction conflicts. To Master the Minority classes effectively, we propose the Uncertainty-based Multi-Expert fusion network (UME) framework. UME is designed with three core innovations: First, we employ Ensemble LoRA for parameter-efficient modeling, significantly reducing the trainable parameter count. Second, we introduce Sequential Specialization guided by Dempster-Shafer Theory (DST), which ensures effective specialization on the challenging-tailed classes. Finally, an Uncertainty-Guided Fusion mechanism uses DST's certainty measures to dynamically weigh expert opinions, resolving conflicts by prioritizing the most confident expert for reliable final predictions. Extensive experiments across four public hierarchical text classification datasets demonstrate that UME achieves state-of-the-art performance. We achieve a performance gain of up to 17.97\% over the best baseline on individual categories, while reducing trainable parameters by up to 10.32\%. The findings highlight that uncertainty-guided expert coordination is a principled strategy for addressing challenging-tailed sequence learning. Our code is available at https://github.com/CQUPTWZX/Multi-experts.

cs.LG↗
arXiv2026

AgentIF-OneDay: A Task-level Instruction-Following Benchmark for General AI Agents in Daily Scenarios

The capacity of AI agents to effectively handle tasks of increasing duration and complexity continues to grow, demonstrating exceptional performance in coding, deep research, and complex problem-solving evaluations. However, in daily scenarios, the perception of these advanced AI capabilities among general users remains limited. We argue that current evaluations prioritize increasing task difficulty without sufficiently addressing the diversity of agentic tasks necessary to cover the daily work, life, and learning activities of a broad demographic. To address this, we propose AgentIF-OneDay, aimed at determining whether general users can utilize natural language instructions and AI agents to complete a diverse array of daily tasks. These tasks require not only solving problems through dialogue but also understanding various attachment types and delivering tangible file-based results. The benchmark is structured around three user-centric categories: Open Workflow Execution, which assesses adherence to explicit and complex workflows; Latent Instruction, which requires agents to infer implicit instructions from attachments; and Iterative Refinement, which involves modifying or expanding upon ongoing work. We employ instance-level rubrics and a refined evaluation pipeline that aligns LLM-based verification with human judgment, achieving an 80.1% agreement rate using Gemini-3-Pro. AgentIF-OneDay comprises 104 tasks covering 767 scoring points. We benchmarked four leading general AI agents and found that agent products built based on APIs and ChatGPT agents based on agent RL remain in the first tier simultaneously. Leading LLM APIs and open-source models have internalized agentic capabilities, enabling AI application teams to develop cutting-edge Agent products.

cs.CL↗
arXiv2026

Implicit Non-Causal Factors are Out via Dataset Splitting for Domain Generalization Object Detection

Open world object detection faces a significant challenge in domain-invariant representation, i.e., implicit non-causal factors. Most domain generalization (DG) methods based on domain adversarial learning (DAL) pay much attention to learn domain-invariant information, but often overlook the potential non-causal factors. We unveil two critical causes: 1) The domain discriminator-based DAL method is subject to the extremely sparse domain label, i.e., assigning only one domain label to each dataset, thus can only associate explicit non-causal factor, which is incredibly limited. 2) The non-causal factors, induced by unidentified data bias, are excessively implicit and cannot be solely discerned by conventional DAL paradigm. Based on these key findings, inspired by the Granular-Ball perspective, we propose an improved DAL method, i.e., GB-DAL. The proposed GB-DAL utilizes Prototype-based Granular Ball Splitting (PGBS) module to generate more dense domains from limited datasets, akin to more fine-grained granular balls, indicating more potential non-causal factors. Inspired by adversarial perturbations akin to non-causal factors, we propose a Simulated Non-causal Factors (SNF) module as a means of data augmentation to reduce the implicitness of non-causal factors, and facilitate the training of GB-DAL. Comparative experiments on numerous benchmarks demonstrate that our method achieves better generalization performance in novel circumstances.

cs.CV↗
arXiv2026

Granular Ball Guided Masking: Structure-aware Data Augmentation

Deep learning models have achieved remarkable success in computer vision but still rely heavily on large-scale labeled data and tend to overfit when data is limited or distributions shift. Data augmentation -- particularly mask-based information dropping -- can enhance robustness by forcing models to explore complementary cues; however, existing approaches often lack structural awareness and risk discarding essential semantics. We propose Granular Ball Guided Masking (GBGM), a structure-aware augmentation strategy guided by Granular Ball Computing (GBC). GBGM adaptively preserves semantically rich, structurally important regions while suppressing redundant areas through a coarse-to-fine hierarchical masking process, producing augmentations that are both representative and discriminative. Extensive experiments on multiple benchmarks demonstrate consistent improvements not only in image classification and masked image reconstruction, but also in image tampering detection, validating the effectiveness and generalization of GBGM across both recognition and forensic scenarios. Simple and model-agnostic, GBGM integrates seamlessly into CNNs and Vision Transformers, offering a practical paradigm for structure-aware data augmentation.

cs.CV↗
arXiv2025

Instruction Tuning for Large Language Models: A Survey

This paper surveys research works in the quickly advancing field of instruction tuning (IT), which can also be referred to as supervised fine-tuning (SFT)\footnote{In this paper, unless specified otherwise, supervised fine-tuning (SFT) and instruction tuning (IT) are used interchangeably.}, a crucial technique to enhance the capabilities and controllability of large language models (LLMs). Instruction tuning refers to the process of further training LLMs on a dataset consisting of \textsc{(instruction, output)} pairs in a supervised fashion, which bridges the gap between the next-word prediction objective of LLMs and the users' objective of having LLMs adhere to human instructions. In this work, we make a systematic review of the literature, including the general methodology of SFT, the construction of SFT datasets, the training of SFT models, and applications to different modalities, domains and application, along with analysis on aspects that influence the outcome of SFT (e.g., generation of instruction outputs, size of the instruction dataset, etc). We also review the potential pitfalls of SFT along with criticism against it, along with efforts pointing out current deficiencies of existing strategies and suggest some avenues for fruitful research. Project Page: github.com/xiaoya-li/Instruction-Tuning-Survey

cs.CL↗
arXiv2025

GBSK: Skeleton Clustering via Granular-ball Computing and Multi-Sampling for Large-Scale Data

To effectively handle clustering task for large-scale datasets, we propose a novel scalable skeleton clustering algorithm, namely GBSK, which leverages the granular-ball technique to capture the underlying structure of data. By multi-sampling the dataset and constructing multi-grained granular-balls, GBSK progressively uncovers a statistical "skeleton" -- a spatial abstraction that approximates the essential structure and distribution of the original data. This strategy enables GBSK to dramatically reduce computational overhead while maintaining high clustering accuracy. In addition, we introduce an adaptive version, AGBSK, with simplified parameter settings to enhance usability and facilitate deployment in real-world scenarios. Extensive experiments conducted on standard computing hardware demonstrate that GBSK achieves high efficiency and strong clustering performance on large-scale datasets, including one with up to 100 million instances across 256 dimensions. Our implementation and experimental results are available at: https://github.com/XFastDataLab/GBSK/.

cs.LG↗
arXiv2025

Aligning Instruction Tuning with Pre-training

Instruction tuning enhances large language models (LLMs) to follow human instructions across diverse tasks, relying on high-quality datasets to guide behavior. However, these datasets, whether manually curated or synthetically generated, are often narrowly focused and misaligned with the broad distributions captured during pre-training, limiting LLM generalization and effective use of pre-trained knowledge. We propose Aligning Instruction Tuning with Pre-training (AITP), a method that bridges this gap by identifying coverage shortfalls in instruction-tuning datasets and rewriting underrepresented pre-training data into high-quality instruction-response pairs. This approach enriches dataset diversity while preserving task-specific objectives. Evaluations on three fully open LLMs across eight benchmarks demonstrate consistent performance improvements with AITP. Ablations highlight the benefits of adaptive data selection, controlled rewriting, and balanced integration, emphasizing the importance of aligning instruction tuning with pre-training distributions to unlock the full potential of LLMs.

cs.AI↗
arXiv2025

Granular-Ball-Induced Multiple Kernel K-Means

Most existing multi-kernel clustering algorithms, such as multi-kernel K-means, often struggle with computational efficiency and robustness when faced with complex data distributions. These challenges stem from their dependence on point-to-point relationships for optimization, which can lead to difficulty in accurately capturing data sets' inherent structure and diversity. Additionally, the intricate interplay between multiple kernels in such algorithms can further exacerbate these issues, effectively impacting their ability to cluster data points in high-dimensional spaces. In this paper, we leverage granular-ball computing to improve the multi-kernel clustering framework. The core of granular-ball computing is to adaptively fit data distribution by balls from coarse to acceptable levels. Each ball can enclose data points based on a density consistency measurement. Such ball-based data description thus improves the computational efficiency and the robustness to unknown noises. Specifically, based on granular-ball representations, we introduce the granular-ball kernel (GBK) and its corresponding granular-ball multi-kernel K-means framework (GB-MKKM) for efficient clustering. Using granular-ball relationships in multiple kernel spaces, the proposed GB-MKKM framework shows its superiority in efficiency and clustering performance in the empirical evaluation of various clustering tasks.

cs.LG↗
arXiv2025

Cloud Model Characteristic Function Auto-Encoder: Integrating Cloud Model Theory with MMD Regularization for Enhanced Generative Modeling

We introduce Cloud Model Characteristic Function Auto-Encoder (CMCFAE), a novel generative model that integrates the cloud model into the Wasserstein Auto-Encoder (WAE) framework. By leveraging the characteristic functions of the cloud model to regularize the latent space, our approach enables more accurate modeling of complex data distributions. Unlike conventional methods that rely on a standard Gaussian prior and traditional divergence measures, our method employs a cloud model prior, providing a more flexible and realistic representation of the latent space, thus mitigating the homogenization observed in reconstructed samples. We derive the characteristic function of the cloud model and propose a corresponding regularizer within the WAE framework. Extensive quantitative and qualitative evaluations on MNIST, FashionMNIST, CIFAR-10, and CelebA demonstrate that CMCFAE outperforms existing models in terms of reconstruction quality, latent space structuring, and sample diversity. This work not only establishes a novel integration of cloud model theory with MMD-based regularization but also offers a promising new perspective for enhancing autoencoder-based generative models.

cs.LG↗
arXiv2025

OS Agents: A Survey on MLLM-based Agents for General Computing Devices Use

The dream to create AI assistants as capable and versatile as the fictional J.A.R.V.I.S from Iron Man has long captivated imaginations. With the evolution of (multi-modal) large language models ((M)LLMs), this dream is closer to reality, as (M)LLM-based Agents using computing devices (e.g., computers and mobile phones) by operating within the environments and interfaces (e.g., Graphical User Interface (GUI)) provided by operating systems (OS) to automate tasks have significantly advanced. This paper presents a comprehensive survey of these advanced agents, designated as OS Agents. We begin by elucidating the fundamentals of OS Agents, exploring their key components including the environment, observation space, and action space, and outlining essential capabilities such as understanding, planning, and grounding. We then examine methodologies for constructing OS Agents, focusing on domain-specific foundation models and agent frameworks. A detailed review of evaluation protocols and benchmarks highlights how OS Agents are assessed across diverse tasks. Finally, we discuss current challenges and identify promising directions for future research, including safety and privacy, personalization and self-evolution. This survey aims to consolidate the state of OS Agents research, providing insights to guide both academic inquiry and industrial development. An open-source GitHub repository is maintained as a dynamic resource to foster further innovation in this field. We present a 9-page version of our work, accepted by ACL 2025, to provide a concise overview to the domain.

cs.AI↗
arXiv2025

P-Aligner: Enabling Pre-Alignment of Language Models via Principled Instruction Synthesis

Large Language Models (LLMs) are expected to produce safe, helpful, and honest content during interaction with human users, but they frequently fail to align with such values when given flawed instructions, e.g., missing context, ambiguous directives, or inappropriate tone, leaving substantial room for improvement along multiple dimensions. A cost-effective yet high-impact way is to pre-align instructions before the model begins decoding. Existing approaches either rely on prohibitive test-time search costs or end-to-end model rewrite, which is powered by a customized training corpus with unclear objectives. In this work, we demonstrate that the goal of efficient and effective preference alignment can be achieved by P-Aligner, a lightweight module generating instructions that preserve the original intents while being expressed in a more human-preferred form. P-Aligner is trained on UltraPrompt, a new dataset synthesized via a proposed principle-guided pipeline using Monte-Carlo Tree Search, which systematically explores the space of candidate instructions that are closely tied to human preference. Experiments across different methods show that P-Aligner generally outperforms strong baselines across various models and benchmarks, including average win-rate gains of 28.35% and 8.69% on GPT-4-turbo and Gemma-2-SimPO, respectively. Further analyses validate its effectiveness and efficiency through multiple perspectives, including data quality, search strategies, iterative deployment, and time overhead.

cs.CL↗
arXiv2025

GBGC: Efficient and Adaptive Graph Coarsening via Granular-ball Computing

The objective of graph coarsening is to generate smaller, more manageable graphs while preserving key information of the original graph. Previous work were mainly based on the perspective of spectrum-preserving, using some predefined coarsening rules to make the eigenvalues of the Laplacian matrix of the original graph and the coarsened graph match as much as possible. However, they largely overlooked the fact that the original graph is composed of subregions at different levels of granularity, where highly connected and similar nodes should be more inclined to be aggregated together as nodes in the coarsened graph. By combining the multi-granularity characteristics of the graph structure, we can generate coarsened graph at the optimal granularity. To this end, inspired by the application of granular-ball computing in multi-granularity, we propose a new multi-granularity, efficient, and adaptive coarsening method via granular-ball (GBGC), which significantly improves the coarsening results and efficiency. Specifically, GBGC introduces an adaptive granular-ball graph refinement mechanism, which adaptively splits the original graph from coarse to fine into granular-balls of different sizes and optimal granularity, and constructs the coarsened graph using these granular-balls as supernodes. In addition, compared with other state-of-the-art graph coarsening methods, the processing speed of this method can be increased by tens to hundreds of times and has lower time complexity. The accuracy of GBGC is almost always higher than that of the original graph due to the good robustness and generalization of the granular-ball computing, so it has the potential to become a standard graph data preprocessing method.

cs.AI↗