AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

ICML 2026

What Does Flow-Matching Bring to TD-Learning?

Bhavya Kumar Agrawalla, Michal Nauman, Aviral Kumar

Recent work shows that flow-matching networks can be effective for value function estimation in reinforcement learning, but it remains unclear why they work well or whether flow-matching Q-functions differ fundamentally from standard critics. We show that their success is not explained by distributional RL: explicitly modeling return distributions often degrades performance. Instead, we argue that flow-matching Q-functions are effective because they couple a learned velocity field with an integration procedure that is used both during training and to read out Q-values at inference time. This coupling enables robust value prediction through \emph{test-time recovery} from imperfect intermediate estimates where errors dampen out as more integration steps are performed. This mechanism is absent in monolithic critics. Beyond test-time recovery, training with the integration procedure induces more \emph{plastic} representations, allowing critics to represent non-stationary future TD targets without overwriting previous features. We formalize these effects and validate them empirically, showing that flow-matching critics outperform monolithic critics by over $2\times$ in performance and achieve $5$–$10\times$ higher sample efficiency in high-UTD regimes.

ICML 2026

Long Live The Balance: Information Bottleneck Driven Tree-based Policy Optimization

Hao Jiang, Shurui Li, Tianpeng Bu, Bowen Xu, Xin Liu, Qihua Chen, hongtao duan, lulu hu, Bin Yang, Minying Zhang

Recent advances in online reinforcement learning (RL) for large language models (LLMs) have demonstrated promising performance in complex reasoning tasks. However, they often exhibit an imbalanced exploration–exploitation trade-off, resulting in unstable optimization and sub-optimal performance. We introduce IB-Score, a novel metric grounded in Information Bottleneck (IB) theory that evaluates policy’s exploration-exploitation balance by quantifying the trade-off between step-level reasoning diversity and mutual information shared with the correct answer. Analysis based on IB-Score shows that popular online RL approaches (e.g., GRPO) with common regularization methods fail to consistently maintain balance during training with suboptimal results. To address this, we propose Information Bottleneck-driven Tree-based Policy Optimization (IB-TPO), a principled framework that formulates IB-Score as a fine-grained optimization objective and utilizes a novel IB-guided tree sampling strategy that not only improves the efficiency of online sampling with 50\% more trajectories under same token budget, but also reuses the tree structure for effective IB-Score Monte Carlo estimation. Extensive experiments across standard benchmarks show that our method significantly outperforms GRPO baseline by 2.9% to 3.6% and also outperforms other state-of-the-art online RL approaches.

ICML 2026

Q-DiT4SR: Exploration of Detail-Preserving Diffusion Transformer Quantization for Real-World Image Super-Resolution

Xun Zhang, Kaicheng Yang, Hongliang Lu, Haotong Qin, Yong Guo, Yulun Zhang

Recently, Diffusion Transformers (DiTs) have emerged in Real-World Image Super-Resolution (Real-ISR) to generate high-quality textures, yet their heavy inference burden hinders real-world deployment. While Post-Training Quantization (PTQ) is a promising solution for acceleration, existing methods in super-resolution mostly focus on U-Net architectures, whereas generic DiT quantization is typically designed for text-to-image tasks. Directly applying these methods to DiT-based super-resolution models leads to severe degradation of local textures. Therefore, we propose **Q-DiT4SR**, the first PTQ framework specifically tailored for DiT-based Real-ISR. We propose **H-SVD**, a hierarchical SVD that integrates a global low-rank branch with a local block-wise rank-1 branch under a matched parameter budget. We further propose **V**ariance-**a**ware **S**patio-**T**emporal **M**ixed **P**recision: **VaSMP** allocates cross-layer weight bit-widths in a data-free manner based on rate-distortion theory, while **VaTMP** schedules intra-layer activation precision across diffusion timesteps via dynamic programming (DP) with minimal calibration. Experiments on multiple real-world datasets demonstrate that our Q-DiT4SR achieves SOTA performance under both **W4A6** and **W4A4** settings. Notably, the W4A4 quantization configuration reduces model size by **5.8**$\times$ and computational operations by **6.14**$\times$. Our code and models will be available at https://github.com/xunzhang1128/Q-DiT4SR.

ICML 2026

Efficient Neural Controlled Differential Equations via Attentive Kernel Smoothing

Egor Serov, Ilya Kuleshov, Alexey Zaytsev

Neural Controlled Differential Equations (Neural CDEs) provide a powerful continuous-time framework for sequence modeling, yet the roughness of the driving control path often restricts their efficiency. Standard splines introduce high-frequency variations that force adaptive solvers to take excessively small steps, driving up the Number of Function Evaluations (NFE). We propose a novel approach to Neural CDE path construction that replaces exact interpolation with Kernel and Gaussian Process (GP) smoothing, enabling explicit control over trajectory regularity. To recover details lost during smoothing, we propose an attention-based Multi-View CDE (MV-CDE) and its convolutional extension (MVC-CDE), which employ learnable queries to inform path reconstruction. This framework allows the model to distribute representational capacity across multiple trajectories, each capturing distinct temporal patterns. Empirical results demonstrate that our method, MVC-CDE with GP, achieves state-of-the-art accuracy while significantly reducing NFEs and total inference time compared to spline-based baselines.

ICML 2026

Hyperbolic Multimodal Continual Learning

Jiahong Liu, Ming Shen, Xiaohao Liu, Rex Ying, Menglin Yang, Tat-Seng Chua, Tat-Seng Chua, Irwin King

Hyperbolic geometry has recently emerged as a powerful representation space for multimodal learning, as it naturally captures hierarchical semantic structure across modalities. Despite this progress, how such representations behave under continual learning poses fundamentally different challenges that remain underexplored. This work provides a geometric perspective on this problem and establishes a theoretical foundation for representation preservation in hyperbolic space, showing that preventing forgetting requires cross-modal invariance under a shared hyperbolic isometry. We further show that forgetting in hyperbolic continual learning involves both semantic relation drift and hierarchy-related distortion, motivating preservation of both cross-modal relational structure and hierarchical geometry. Guided by these insights, a principled continual learning framework is derived that preserves essential geometric structure while allowing effective adaptation to new tasks. Experiments on continual multimodal benchmarks corroborate the effectiveness of the proposed approach.

ICML 2026

Cardio-mmFlow: A Gaussian-Prior-Free Physics-Informed Flow Matching Framework for Electrocardiogram to mmWave Radar Synthesis

Ziyang Liu, Ruiqiang Xiao, Chang Huang, KIEREN YU, Siyuan HE, Kaishun Wu

Continuous ECG monitoring is clinically valuable, but scaling it beyond electrodes to comfortable long-term use motivates contactless mmWave sensing. In practice, mmWave-to-ECG reconstruction is severely constrained by the scarcity of high-quality synchronized recordings. Therefore, we propose \textbf{Cardio-mmFlow}, a Gaussian-prior-free physics-informed flow matching framework that synthesizes mmWave radar signals from clinical ECG. It learns a direct transport trajectory between the latent manifolds of ECG and radar. Considering subject-dependent propagation differences, we incorporate a simplified mass--spring--damper inspired modulation and inject it into the flow dynamics via feature-wise linear modulation for personalization. Extensive experiments show that our system generates high fidelity radar data in both signal and latent domains. It significantly improves zero-shot downstream mmWave to ECG task, and enable Atrial Fibrillation classification with synthetic data. Further analyses evaluate the model interpretability.

ICML 2026

Proxy Compression for Language Modeling

Lin Zheng, Xinyu Li, Qian Liu, Xiachong Feng, Lingpeng Kong

Modern language models are trained almost exclusively on token sequences produced by a fixed tokenizer, an external lossless compressor often over UTF‑8 byte sequences, thereby coupling the model to that compressor. This work introduces proxy compression, an alternative training scheme that preserves the efficiency benefits of compressed inputs while providing an end-to-end, raw-byte interface at inference time. During training, one language model is jointly trained on raw byte sequences and compressed views generated by external compressors; through the process, the model learns to internally align compressed sequences and raw bytes. This alignment enables strong transfer between the two formats, even when training predominantly on compressed inputs which are discarded at inference. Extensive experiments on code language modeling demonstrate that proxy compression substantially improves training efficiency and significantly outperforms pure byte-level baselines given fixed compute budgets. As model scale increases, these gains become more pronounced, and proxy-trained models eventually match or rival tokenizer approaches, all while operating solely on raw bytes and retaining the inherent robustness of byte-level modeling.

ICML 2026

MRPO: Magnitude-Regularized Policy Optimization via L1 Constraints

Wei Han, Yuanxing Liu, Mingda Li, Ruiyu Xiao, Weinan Zhang, Ting Liu

Reinforcement learning (RL) for large language models (LLMs) relies on imperfect reward supervision, necessitating constraints on policy updates to prevent overfitting. Nevertheless, the widely adopted KL constraint over-penalizes actions with low reference probabilities and lacks the sparsity to discard marginal policy shifts. In contrast, the L1-norm offers a distinct mechanism that is more tolerant of low-probability actions yet strictly suppresses minor probability perturbations. Motivated by this, we propose Magnitude-Regularized Policy Optimization (MRPO), which enforces an L1-norm constraint on policy updates. We demonstrate that MRPO permits substantial probability boosts for low-probability actions and induces sparse updates, ensuring invariance to noise that preserves the top-ranking order. Furthermore, MRPO admits a TRPO-style monotonic improvement bound under standard regularity assumptions and achieves a tighter approach to optimality than KL-based methods in single-step scenarios. Empirically, MRPO delivers exceptional results across diverse scenarios, notably doubling the performance gains of GRPO in preference alignment, outperforming DAPO in mathematical reasoning, and surpassing DPO in offline settings using only binary rewards.

ICML 2026

HoloFair: Unified T2I Fairness Evaluation and Fair-GRPO Debiasing

Ruyi Chen, Lu Zhou, Xiaogang Xu, Chiyu Zhang, Jiafei Wu, Liming Fang

Text-to-Image (T2I) models have made significant strides in visual realism and semantic consistency, yet they often perpetuate and amplify societal biases. Existing evaluation methods typically address only single-dimensional biases, lacking perspectives to uncover model biases at social-related deeper semantic levels. We introduce HoloFair, a comprehensive benchmark framework for multidimensional demographic bias analysis. Built upon our large-scale fairness-oriented dataset and the SpaFreq (Spatial-Frequency) attribute classifier, this framework proposes the Multi-attribute, Group-wise Bias Index (MGBI) metric, designed to assess both intrinsic diversity and conditional biases. Beyond evaluation, we further introduce Fair-GRPO, a reinforcement-learning-based debiasing method that alters the distribution of generative models through a designed multi-objective reward function. E.g., experiments on the SD3.5-Medium model demonstrate that Fair-GRPO significantly improves multidimensional fairness while maintaining high image quality. We also analyze potential reward hacking phenomena and provide corresponding mitigation strategies.

ICML 2026

Multimodal Meta-Verifier with Explicit Structured Recalibration

Xinchen Zhang, Bowei Liu, Jiale Liu, Chufan Shi, Yizhen Zhang, Junhong Liu, Youliang Zhang, Zhiheng Li, Yujiu Yang, Ling Yang

Visual outcomes are increasingly central to multimodal large language models, making reliable and fine-grained verification essential for scaling generalist foundation models. In this work, we investigate ***multimodal meta-verification***, which leverages verifier-generated rationales rather than decision-only signals, and explore how to effectively incorporate meta-verification feedback into multimodal verifier training. We identify two key findings. First, symbolic verifier outputs (e.g., bounding boxes) outperform textual explanations as meta-verification rationales, enabling efficient rule-based reinforcement learning rewards while avoiding reliance on model-based rewards from auxiliary judge models. Second, decoupling reinforcement learning objectives for binary judgment and meta-verification substantially outperforms joint reward optimization, due to intrinsic differences in output structure and learning dynamics. Based on these insights, we train **OmniVerifier-M1**, a generalist visual verifier leveraging symbolic meta-verification and decoupled reinforcement learning. OmniVerifier-M1 provides robust verification and fine-grained error localization, and further enables **M1-TTS**, a verifier-driven agentic generation system achieving dynamic region-level self-correction. This approach paves the way for more reliable, interpretable, and fine-grained multimodal verification, supporting safer and more controllable foundation model deployment.

ICML 2026

Fantastic Reasoning Behaviors and Where to Find Them: Unsupervised Discovery of the Reasoning Process

Zhenyu Zhang, Shujian Zhang, John Wheatley Lambert, Wenxuan Zhou, Zhangyang Wang, Mingqing Chen, Andrew Hard, Rajiv Mathews, Lun Wang

Despite the growing reasoning capabilities of recent large language models (LLMs), their internal mechanisms during the reasoning process remain underexplored. Prior approaches often rely on human-defined concepts (e.g., overthinking, reflection) at the word level to analyze reasoning in a supervised manner. However, such methods are limited, as it is infeasible to capture the full spectrum of potential reasoning behaviors, many of which are difficult to define in token space. In this work, we propose an unsupervised framework (namely, RISE: Reasoning behavior Interpretability via Sparse auto-Encoder) for discovering reasoning vectors, which we define as directions in the activation space that encode distinct reasoning behaviors. By segmenting chain-of-thought traces into sentence-level 'steps' and training sparse auto-encoders (SAEs) on step-level activations, we uncover disentangled features corresponding to interpretable behaviors such as reflection and backtracking. Visualization and clustering analyses show that these behaviors occupy separable regions in the decoder column space. Moreover, targeted interventions on SAE-derived vectors can controllably amplify or suppress specific reasoning behaviors, altering inference trajectories without retraining. Beyond behavior-specific disentanglement, SAEs capture structural properties such as response length, revealing clusters of long versus short reasoning traces. More interestingly, SAEs enable the discovery of novel behaviors beyond human supervision. We demonstrate the ability to control response confidence by identifying confidence-related vectors in the SAE decoder space. These findings underscore the potential of unsupervised latent discovery for both interpreting and controllably steering reasoning in LLMs.

ICML 2026

Let Language Constrain Geometry: Vision–Language Models as Semantic and Spatial Critics for 3D Generation

Weimin Bai, Yubo Li, Weijian Luo, Zeqiang Lai, Yequan Wang, Wenzheng Chen, He Sun

Text-to-3D generation has advanced rapidly, yet state-of-the-art models, encompassing both optimization-based and feed-forward architectures, still face two fundamental limitations. First, they struggle with coarse semantic alignment, often failing to capture fine-grained prompt details. Second, they lack robust 3D spatial understanding, leading to geometric inconsistencies and catastrophic failures in part assembly and spatial relationships. To address these challenges, we propose VLM3D, a general framework that repurposes large vision-language models (VLMs) as powerful, differentiable {semantic and spatial critics}. Our core contribution is a {dual-query critic signal} derived from the VLM's "Yes/No" log-odds, which assesses both semantic fidelity and geometric coherence. We demonstrate the generality of this guidance signal across two distinct paradigms: (1) As a reward objective for optimization-based pipelines, VLM3D significantly outperforms existing methods on standard benchmarks. (2) As a test-time guidance module for feed-forward pipelines, it actively steers the iterative sampling process of SOTA native 3D models to correct severe spatial errors. VLM3D establishes a principled and generalizable path to inject the VLM's rich, language-grounded understanding of both semantics and space into diverse 3D generative pipelines.

ICML 2026

LECTOR: Joint Learning of Scientific Reasoning Graphs and Introduction Generation

Jiabei Xiao, Yizhou Wang, Chen Tang, Pengze Li, Wanli Ouyang, Shixiang Tang

AI Scientists have shown promising progress across multiple stages of the research pipeline, among which automatic scientific paper writing remains a formidable challenge. The Introduction writing is especially challenging, which demands not only linguistic fluency, but logical soundness and verifiable faithfulness. Most AI-assisted methods treat the task as text generation instead of reasoning and structuring, leading to severe drawbacks, *e.g.*, hallucinating citations. To address this, we first formulate the Content-Conditional Introduction Generation (CCIG) task, which requires grounding the Introduction in the paper's core evidence. We then propose **LECTOR**, a novel **Logic-Expression Co-Reinforcement Learning** framework that can strictly follow the scientist's logic, add high-quality citations and keep structured expressions. LECTOR first constructs a logic-reasoning graph from the paper's main body to serve as a verifiable logical blueprint. Subsequently, it employs a Logic-Expression Co-Rewarding mechanism to jointly optimize for both the graph's structural fidelity and the final narrative's quality. We conduct a dataset from *Nature Communications* papers to assess our method. Extensive experiments show consistent improvements in both logic fidelity and Introduction generation quality metrics, *e.g.*, Graph Quality **(+26.7%)**, Citation Quality **(+8.6%)**, and Paper Consistency **(+3.3%)**. Code and data are available at: https://github.com/Xiao-Youth/LECTOR

ICML 2026

Identifying Latent Concepts and Structures for Generalized Category Discovery

Boyang Dai, Chaoqi Chen, Yizhou Yu

Generalized Category Discovery (GCD) aims to recognize known classes while autonomously discovering novel ones in open-world settings. However, current approaches primarily focus on designing clustering objectives, often overlooking a critical bottleneck: standard vision backbones yield high-rank, entangled token representations that are ill-suited for unsupervised discovery of latent concepts and structures. In this paper, we propose Compositional Primitive Fields (CPF-GCD), a novel representation learning framework that reshapes the feature space to make such latent structure identifiable by enforcing a low-rank compositional organization. Our core hypothesis is that all categories, whether known or novel, can be expressed as compositions and spatial arrangements of a finite set of learnable visual primitives that capture reusable concepts. CPF instantiates this geometric constraint via a spatial field mechanism. Inserted between the backbone and the head, it rewrites noisy patch tokens through low-rank primitive mixtures, effectively decomposing images into reusable atomic parts and their spatial layouts. By explicitly modeling the spatial distribution of primitives, CPF enables novel categories to emerge naturally as new activation patterns over a shared vocabulary. This shifts the focus of representation from merely partitioning global embeddings to constructing a structured and separable primitive field. Extensive experiments demonstrate that CPF serves as a generic, plug-and-play module that consistently boosts performance across diverse GCD baselines, validating that identifying and leveraging low-rank compositional structure is a crucial inductive bias for open-world recognition.

ICML 2026

Text-Driven Fusion for Infrared and Visible Images: Achieving Image Scene Adaptation on Hyperbolic Space

Huan Kang, Hui Li, Tianyang Xu, Tao Zhou, Xiaojun Wu, Josef Kittler

Infrared and visible image fusion aims to integrate complementary modalities, while existing Euclidean methods impose rigid distance metrics that distort multi-modal interactions and parent-to-child semantic hierarchies. To overcome these limitations, we introduce a text-driven fusion framework empowered by hyperbolic manifold learning. During training, BLIP-extracted text prompts serve as topological anchors within the hyperbolic space, guiding vision-attribute alignment through hyperbolic embeddings that naturally accommodate varying semantic granularities. By exploiting the exponential volume growth dictated by the Poincaré ball's negative curvature, this approach seamlessly embeds hierarchical trees to encode coarse-to-fine semantics without metric saturation, while the vast peripheral space prevents texture distortion during cross-modal fusion. At inference, the fusion process autonomously adapts to input content using the learned text-attribute priors, completely eliminating the need for textual input. Experimental results show our method outperforms state-of-the-art approaches on benchmark datasets, with code available at https://github.com/Shaoyun2023/TEDFusion.

ICML 2026

A Tight Theory of Error Feedback Algorithms in Distributed Optimization

Daniel Berg Thomsen, Adrien Taylor, Aymeric Dieuleveut

Communication costs are a major bottleneck in distributed learning and first-order optimization. A common approach to alleviate this issue is to compress the gradient information exchanged between agents. However, such compression typically degrades the convergence guarantees of gradient-based methods. Error feedback mechanisms provide a simple and computationally cheap remedy for this issue, but numerous variants have been proposed, and their relative performance remains poorly understood. This paper provides tight convergence analyses for two of the main error-feedback algorithms from the literature, the classic Error Feedback method (EF) and Error Feedback 21 (EF21), by identifying optimal step-size choices and constructing optimal Lyapunov functions tailored to each method. The results hold independently of the number of agents and recover the known best guarantees possible in the single-agent regime.

ICML 2026

Shapley Regularized Neural Granger Causality

Maolin Yang, Zhoufan Zhu, Yuanhe Tian, Kun Gao, MUYI LI

Identifying temporal causal structure is fundamental to understanding complex systems. Neural Granger causality has emerged as a powerful paradigm for this task, leveraging the expressiveness of neural networks to model intricate nonlinear dynamics. Although complex architectures excel at predictive modeling, existing methods typically rely on simple local measures for causal discovery, which extract only partial information from the learned model and may miss global dependencies. To address this issue, we reformulate Granger causality as a feature attribution problem and propose the Information-Theoretic Shapley value (Info-Shap) to measure global feature importance. We first establish the theoretical equivalence between zero Info-Shap and Granger non-causality. On top of this, we construct two novel regularizers to suppress spurious relationships and mitigate overfitting. These regularizers are model-agnostic and can be seamlessly integrated into the training of any differentiable neural network. Through extensive experiments on synthetic and realistic datasets, we demonstrate that our method robustly recovers the underlying causal relationships, providing a flexible tool for causal discovery in high-dimensional nonlinear time series.

ICML 2026

REAL: Regression-Aware Reinforcement Learning for LLM-as-a-Judge

Yasi Zhang, Tianyu Chen, Mingyuan Zhou, Oscar Leong, Ying Nian Wu, Michal Lukasik

Large language models (LLMs) are increasingly deployed as automated evaluators that assign numeric scores to model outputs, a paradigm known as LLM-as-a-Judge. However, standard Reinforcement Learning (RL) methods typically rely on binary rewards (e.g., 0-1 accuracy), thereby ignoring the ordinal structure inherent in regression tasks; for instance, they fail to recognize that predicting 4 is significantly better than predicting 1 when the ground truth is 5. Conversely, existing regression-aware approaches are often confined to Supervised Fine-Tuning (SFT), limiting their ability to explore optimal reasoning paths. To bridge this gap, we propose REAL (Regression-Aware Reinforcement Learning), a principled RL framework designed to optimize regression rewards, and also proven to be optimal for correlation metrics. A key technical challenge is that the regression objective is explicitly policy-dependent, thus invalidating standard policy gradient methods. To address this, we employ the generalized policy gradient estimator, which naturally decomposes optimization into two complementary components: (1) exploration over Chain-of-Thought (CoT) trajectory, and (2) regression-aware prediction refinement of the final score. Extensive experiments across model scales (8B to 32B) demonstrate that REAL consistently outperforms both regression-aware SFT baselines and standard RL methods, exhibiting significantly better generalization on out-of-domain benchmarks. On Qwen3-32B specifically, we achieve gains of +8.40 Pearson and +7.20 Spearman correlation over the SFT baseline, and +18.30/+11.20 over the base model. These findings highlight the critical value of integrating regression objectives into RL exploration for accurate LLM evaluation.

ICML 2026

LoBCD-GW: A Fast and Data-Dependent Algorithm for Computing Gromov-Wasserstein Distance via Localized Block Coordinate Descent

Jingni Song, Jiawei Huang, Kangke Cheng, Bangxian Han, Hu Ding

The Gromov-Wasserstein (GW) distance provides a powerful framework for aligning structured data by comparing the intrinsic geometries of metric measure spaces, and has become a fundamental tool in machine learning. Most existing methods leverage entropy regularization to reduce the computational complexity to $\boldsymbol{\mathrm{O}}(n^3)$, where $n$ is the number of samples. However, this cubic time complexity remains a major bottleneck in large-scale applications, severely limiting the scalability. To address this challenge, we propose LoBCD-GW, an efficient GW optimization algorithm. Specifically, we reveal the data-dependent sparsity of large-magnitude updates to the coupling matrix and introduce a localized block coordinate selection strategy. This confines the optimization to a "selected set" of size $r$ (which is a parameter that depends on the given data set, and usually is much less than $n$), thereby reducing the complexity to $\boldsymbol{\mathrm{O}}(r^3)$. In addition, unlike prior acceleration methods often based on constraint relaxation, our method can guarantee the strict feasibility through a novel "marginal compensation mechanism" to synchronize local mass redistribution with global constraints. Finally, we conduct a set of experiments on various datasets, and the results demonstrate that our method achieves a $5.8\times$ speedup on large-scale graph alignment benchmarks, while maintaining state-of-the-art accuracy.

ICML 2026

Optimizing Visual Generative Models via Distribution-wise Rewards

Ruihang Li, Mengde Xu, Shuyang Gu, Leigang Qu, Fuli Feng, Han Hu, Wenjie Wang

Conventional reinforcement learning strategies for visual generation typically employ sample-wise reward functions, yet this practice frequently results in reward hacking that degrades image diversity and introduces visual anomalies. To address these limitations, we present a novel framework that finetunes generative models using distribution-wise rewards, ensuring better alignment with real-world data distributions. Unlike rewards that evaluate samples individually, distribution-wise reward accounts for the data distribution of the samples, mitigating the mode collapse problem that occurs when all samples optimize towards the same direction independently. To overcome the prohibitive computational cost of estimating these rewards, we introduce a subset-replace strategy that efficiently provides reward signals by updating only a small subset of a generated reference set. Additionally, we apply RL to optimize post-hoc model merging coefficients, potentially mitigating the train-inference inconsistency caused by introducing stochastic differential equation (SDE) in regular RL practices. Extensive experiments show our approach significantly improves FID-50K across various base models, from 8.30 to 5.77 for SiT and from 3.74 to 3.52 for EDM2. Qualitative evaluation also confirms that our method enhances perceptual quality while preserving sample diversity.

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.