Curriculum-RLAIF: Curriculum Alignment with Reinforcement Learning from AI Feedback

Reward models trained with conventional Reinforcement Learning from AI Feedback (RLAIF) methods suffer from limited generalizability, which hinders the alignment performance of the policy model during reinforcement learning (RL). This challenge stems from various issues, including distribution shift, preference label noise, and mismatches between overly challenging samples and model capacity. In this paper, we attempt to enhance the generalizability of reward models through a data-centric approach, driven by the insight that these issues are inherently intertwined from the perspective of data difficulty. To address this, we propose a novel framework, $\textit{Curriculum-RLAIF}$, which constructs preference pairs with varying difficulty levels and produces a curriculum that progressively incorporates preference pairs of increasing difficulty for reward model training. Our experimental results suggest that reward models trained with Curriculum-RLAIF achieve improved generalizability, significantly increasing the alignment performance of the policy model by a large margin without incurring additional inference costs compared to various non-curriculum baselines. Detailed analysis and comparisons with alternative approaches, including data selection via external pretrained reward models or internal self-selection mechanisms, as well as other curriculum strategies, further demonstrate the superiority of our approach in terms of simplicity, efficiency, and effectiveness.

MSDformer: Multi-scale Discrete Transformer For Time Series Generation

Discrete Token Modeling (DTM), which employs vector quantization techniques, has demonstrated remarkable success in modeling non-natural language modalities, particularly in time series generation. While our prior work SDformer established the first DTM-based framework to achieve state-of-the-art performance in this domain, two critical limitations persist in existing DTM approaches: 1) their inability to capture multi-scale temporal patterns inherent to complex time series data, and 2) the absence of theoretical foundations to guide model optimization. To address these challenges, we proposes a novel multi-scale DTM-based time series generation method, called Multi-Scale Discrete Transformer (MSDformer). MSDformer employs a multi-scale time series tokenizer to learn discrete token representations at multiple scales, which jointly characterize the complex nature of time series data. Subsequently, MSDformer applies a multi-scale autoregressive token modeling technique to capture the multi-scale patterns of time series within the discrete latent space. Theoretically, we validate the effectiveness of the DTM method and the rationality of MSDformer through the rate-distortion theorem. Comprehensive experiments demonstrate that MSDformer significantly outperforms state-of-the-art methods. Both theoretical analysis and experimental results demonstrate that incorporating multi-scale information and modeling multi-scale patterns can substantially enhance the quality of generated time series in DTM-based approaches. The code will be released upon acceptance.

Self-Bootstrapping for Versatile Test-Time Adaptation

In this paper, we seek to develop a versatile test-time adaptation (TTA) objective for a variety of tasks - classification and regression across image-, object-, and pixel-level predictions. We achieve this through a self-bootstrapping scheme that optimizes prediction consistency between the test image (as target) and its deteriorated view. The key challenge lies in devising effective augmentations/deteriorations that: i) preserve the image's geometric information, e.g., object sizes and locations, which is crucial for TTA on object/pixel-level tasks, and ii) provide sufficient learning signals for TTA. To this end, we analyze how common distribution shifts affect the image's information power across spatial frequencies in the Fourier domain, and reveal that low-frequency components carry high power and masking these components supplies more learning signals, while masking high-frequency components can not. In light of this, we randomly mask the low-frequency amplitude of an image in its Fourier domain for augmentation. Meanwhile, we also augment the image with noise injection to compensate for missing learning signals at high frequencies, by enhancing the information power there. Experiments show that, either independently or as a plug-and-play module, our method achieves superior results across classification, segmentation, and 3D monocular detection tasks with both transformer and CNN models.

Right Question is Already Half the Answer: Fully Unsupervised LLM Reasoning Incentivization

While large language models (LLMs) have demonstrated exceptional capabilities in challenging tasks such as mathematical reasoning, existing methods to enhance reasoning ability predominantly rely on supervised fine-tuning (SFT) followed by reinforcement learning (RL) on reasoning-specific data after pre-training. However, these approaches critically depend on external supervisions--such as human labelled reasoning traces, verified golden answers, or pre-trained reward models--which limits scalability and practical applicability. In this work, we propose Entropy Minimized Policy Optimization (EMPO), which makes an early attempt at fully unsupervised LLM reasoning incentivization. EMPO does not require any supervised information for incentivizing reasoning capabilities (i.e., neither verifiable reasoning traces, problems with golden answers, nor additional pre-trained reward models). By continuously minimizing the predictive entropy of LLMs on unlabeled user queries in a latent semantic space, EMPO enables purely self-supervised evolution of reasoning capabilities with strong flexibility and practicality. Our experiments demonstrate competitive performance of EMPO on both mathematical reasoning and free-form commonsense reasoning tasks. Specifically, without any supervised signals, EMPO boosts the accuracy of Qwen2.5-Math-7B Base from 30.7\% to 48.1\% on mathematical benchmarks and improves truthfulness accuracy of Qwen2.5-7B Instruct from 87.16\% to 97.25\% on TruthfulQA.

3D Point Cloud Generation via Autoregressive Up-sampling

We introduce a pioneering autoregressive generative model for 3D point cloud generation. Inspired by visual autoregressive modeling (VAR), we conceptualize point cloud generation as an autoregressive up-sampling process. This leads to our novel model, PointARU, which progressively refines 3D point clouds from coarse to fine scales. PointARU follows a two-stage training paradigm: first, it learns multi-scale discrete representations of point clouds, and then it trains an autoregressive transformer for next-scale prediction. To address the inherent unordered and irregular structure of point clouds, we incorporate specialized point-based up-sampling network modules in both stages and integrate 3D absolute positional encoding based on the decoded point cloud at each scale during the second stage. Our model surpasses state-of-the-art (SoTA) diffusion-based approaches in both generation quality and parameter efficiency across diverse experimental settings, marking a new milestone for autoregressive methods in 3D point cloud generation. Furthermore, PointARU demonstrates exceptional performance in completing partial 3D shapes and up-sampling sparse point clouds, outperforming existing generative models in these tasks.

Injecting Imbalance Sensitivity for Multi-Task Learning

Multi-task learning (MTL) has emerged as a promising approach for deploying deep learning models in real-life applications. Recent studies have proposed optimization-based learning paradigms to establish task-shared representations in MTL. However, our paper empirically argues that these studies, specifically gradient-based ones, primarily emphasize the conflict issue while neglecting the potentially more significant impact of imbalance/dominance in MTL. In line with this perspective, we enhance the existing baseline method by injecting imbalance-sensitivity through the imposition of constraints on the projected norms. To demonstrate the effectiveness of our proposed IMbalance-sensitive Gradient (IMGrad) descent method, we evaluate it on multiple mainstream MTL benchmarks, encompassing supervised learning tasks as well as reinforcement learning. The experimental results consistently demonstrate competitive performance.

TS-LIF: A Temporal Segment Spiking Neuron Network for Time Series Forecasting

Spiking Neural Networks (SNNs) offer a promising, biologically inspired approach for processing spatiotemporal data, particularly for time series forecasting. However, conventional neuron models like the Leaky Integrate-and-Fire (LIF) struggle to capture long-term dependencies and effectively process multi-scale temporal dynamics. To overcome these limitations, we introduce the Temporal Segment Leaky Integrate-and-Fire (TS-LIF) model, featuring a novel dual-compartment architecture. The dendritic and somatic compartments specialize in capturing distinct frequency components, providing functional heterogeneity that enhances the neuron's ability to process both low- and high-frequency information. Furthermore, the newly introduced direct somatic current injection reduces information loss during intra-neuronal transmission, while dendritic spike generation improves multi-scale information extraction. We provide a theoretical stability analysis of the TS-LIF model and explain how each compartment contributes to distinct frequency response characteristics. Experimental results show that TS-LIF outperforms traditional SNNs in time series forecasting, demonstrating better accuracy and robustness, even with missing data. TS-LIF advances the application of SNNs in time-series forecasting, providing a biologically inspired approach that captures complex temporal dynamics and offers potential for practical implementation in diverse forecasting scenarios. The source code is available at https://github.com/kkking-kk/TS-LIF.

Continual Optimization with Symmetry Teleportation for Multi-Task Learning

Multi-task learning (MTL) is a widely explored paradigm that enables the simultaneous learning of multiple tasks using a single model. Despite numerous solutions, the key issues of optimization conflict and task imbalance remain under-addressed, limiting performance. Unlike existing optimization-based approaches that typically reweight task losses or gradients to mitigate conflicts or promote progress, we propose a novel approach based on Continual Optimization with Symmetry Teleportation (COST). During MTL optimization, when an optimization conflict arises, we seek an alternative loss-equivalent point on the loss landscape to reduce conflict. Specifically, we utilize a low-rank adapter (LoRA) to facilitate this practical teleportation by designing convergent, loss-invariant objectives. Additionally, we introduce a historical trajectory reuse strategy to continually leverage the benefits of advanced optimizers. Extensive experiments on multiple mainstream datasets demonstrate the effectiveness of our approach. COST is a plug-and-play solution that enhances a wide range of existing MTL methods. When integrated with state-of-the-art methods, COST achieves superior performance.

Inverse Materials Design by Large Language Model-Assisted Generative Framework

Deep generative models hold great promise for inverse materials design, yet their efficiency and accuracy remain constrained by data scarcity and model architecture. Here, we introduce AlloyGAN, a closed-loop framework that integrates Large Language Model (LLM)-assisted text mining with Conditional Generative Adversarial Networks (CGANs) to enhance data diversity and improve inverse design. Taking alloy discovery as a case study, AlloyGAN systematically refines material candidates through iterative screening and experimental validation. For metallic glasses, the framework predicts thermodynamic properties with discrepancies of less than 8% from experiments, demonstrating its robustness. By bridging generative AI with domain knowledge and validation workflows, AlloyGAN offers a scalable approach to accelerate the discovery of materials with tailored properties, paving the way for broader applications in materials science.

Measuring Diversity in Synthetic Datasets

Large language models (LLMs) are widely adopted to generate synthetic datasets for various natural language processing (NLP) tasks, such as text classification and summarization. However, accurately measuring the diversity of these synthetic datasets-an aspect crucial for robust model performance-remains a significant challenge. In this paper, we introduce DCScore, a novel method for measuring synthetic dataset diversity from a classification perspective. Specifically, DCScore formulates diversity evaluation as a sample classification task, leveraging mutual relationships among samples. We further provide theoretical verification of the diversity-related axioms satisfied by DCScore, highlighting its role as a principled diversity evaluation method. Experimental results on synthetic datasets reveal that DCScore enjoys a stronger correlation with multiple diversity pseudo-truths of evaluated datasets, underscoring its effectiveness. Moreover, both empirical and theoretical evidence demonstrate that DCScore substantially reduces computational costs compared to existing approaches. Code is available at: https://github.com/BlueWhaleLab/DCScore.