Adaptive Replay Buffer for Offline-to-Online Reinforcement Learning

Offline-to-Online Reinforcement Learning (O2O RL) faces a critical dilemma in balancing the use of a fixed offline dataset with newly collected online experiences. Standard methods, often relying on a fixed data-mixing ratio, struggle to manage the trade-off between early learning stability and asymptotic performance. To overcome this, we introduce the Adaptive Replay Buffer (ARB), a novel approach that dynamically prioritizes data sampling based on a lightweight metric we call 'on-policyness'. Unlike prior methods that rely on complex learning procedures or fixed ratios, ARB is designed to be learning-free and simple to implement, seamlessly integrating into existing O2O RL algorithms. It assesses how closely collected trajectories align with the current policy's behavior and assigns a proportional sampling weight to each transition within that trajectory. This strategy effectively leverages offline data for initial stability while progressively focusing learning on the most relevant, high-rewarding online experiences. Our extensive experiments on D4RL benchmarks demonstrate that ARB consistently mitigates early performance degradation and significantly improves the final performance of various O2O RL algorithms, highlighting the importance of an adaptive, behavior-aware replay buffer design.

Low-Rank Curvature for Zeroth-Order Optimization in LLM Fine-Tuning

We introduce LOREN, a curvature-aware zeroth-order (ZO) optimization method for fine-tuning large language models (LLMs). Existing ZO methods, which estimate gradients via finite differences using random perturbations, often suffer from high variance and suboptimal search directions. Our approach addresses these challenges by: (i) reformulating the problem of gradient preconditioning as that of adaptively estimating an anisotropic perturbation distribution for gradient estimation, (ii) capturing curvature through a low-rank block diagonal preconditioner using the framework of natural evolution strategies, and (iii) applying a REINFORCE leave-one-out (RLOO) gradient estimator to reduce variance. Experiments on standard LLM benchmarks show that our method outperforms state-of-the-art ZO methods by achieving higher accuracy and faster convergence, while cutting peak memory usage by up to 27.3% compared with MeZO-Adam.

Geometric Backstepping Control of Omnidirectional Tiltrotors Incorporating Servo-Rotor Dynamics for Robustness against Sudden Disturbances

This work presents a geometric backstepping controller for a variable-tilt omnidirectional multirotor that explicitly accounts for both servo and rotor dynamics. Considering actuator dynamics is essential for more effective and reliable operation, particularly during aggressive flight maneuvers or recovery from sudden disturbances. While prior studies have investigated actuator-aware control for conventional and fixed-tilt multirotors, these approaches rely on linear relationships between actuator input and wrench, which cannot capture the nonlinearities induced by variable tilt angles. In this work, we exploit the cascade structure between the rigid-body dynamics of the multirotor and its nonlinear actuator dynamics to design the proposed backstepping controller and establish exponential stability of the overall system. Furthermore, we reveal parametric uncertainty in the actuator model through experiments, and we demonstrate that the proposed controller remains robust against such uncertainty. The controller was compared against a baseline that does not account for actuator dynamics across three experimental scenarios: fast translational tracking, rapid rotational tracking, and recovery from sudden disturbance. The proposed method consistently achieved better tracking performance, and notably, while the baseline diverged and crashed during the fastest translational trajectory tracking and the recovery experiment, the proposed controller maintained stability and successfully completed the tasks, thereby demonstrating its effectiveness.

Diffusion Alignment as Variational Expectation-Maximization

Diffusion alignment aims to optimize diffusion models for the downstream objective. While existing methods based on reinforcement learning or direct backpropagation achieve considerable success in maximizing rewards, they often suffer from reward over-optimization and mode collapse. We introduce Diffusion Alignment as Variational Expectation-Maximization (DAV), a framework that formulates diffusion alignment as an iterative process alternating between two complementary phases: the E-step and the M-step. In the E-step, we employ test-time search to generate diverse and reward-aligned samples. In the M-step, we refine the diffusion model using samples discovered by the E-step. We demonstrate that DAV can optimize reward while preserving diversity for both continuous and discrete tasks: text-to-image synthesis and DNA sequence design.

MAC: An Efficient Gradient Preconditioning using Mean Activation Approximated Curvature

Second-order optimization methods for training neural networks, such as KFAC, exhibit superior convergence by utilizing curvature information of loss landscape. However, it comes at the expense of high computational burden. In this work, we analyze the two components that constitute the layer-wise Fisher information matrix (FIM) used in KFAC: the Kronecker factors related to activations and pre-activation gradients. Based on empirical observations on their eigenspectra, we propose efficient approximations for them, resulting in a computationally efficient optimization method called MAC. To the best of our knowledge, MAC is the first algorithm to apply the Kronecker factorization to the FIM of attention layers used in transformers and explicitly integrate attention scores into the preconditioning. We also study the convergence property of MAC on nonlinear neural networks and provide two conditions under which it converges to global minima. Our extensive evaluations on various network architectures and datasets show that the proposed method outperforms KFAC and other state-of-the-art methods in terms of accuracy, end-to-end training time, and memory usage. Code is available at https://github.com/hseung88/mac.

NysAct: A Scalable Preconditioned Gradient Descent using Nystrom Approximation

Adaptive gradient methods are computationally efficient and converge quickly, but they often suffer from poor generalization. In contrast, second-order methods enhance convergence and generalization but typically incur high computational and memory costs. In this work, we introduce NysAct, a scalable first-order gradient preconditioning method that strikes a balance between state-of-the-art first-order and second-order optimization methods. NysAct leverages an eigenvalue-shifted Nystrom method to approximate the activation covariance matrix, which is used as a preconditioning matrix, significantly reducing time and memory complexities with minimal impact on test accuracy. Our experiments show that NysAct not only achieves improved test accuracy compared to both first-order and second-order methods but also demands considerably less computational resources than existing second-order methods. Code is available at https://github.com/hseung88/nysact.

An Adaptive Method Stabilizing Activations for Enhanced Generalization

We introduce AdaAct, a novel optimization algorithm that adjusts learning rates according to activation variance. Our method enhances the stability of neuron outputs by incorporating neuron-wise adaptivity during the training process, which subsequently leads to better generalization -- a complementary approach to conventional activation regularization methods. Experimental results demonstrate AdaAct's competitive performance across standard image classification benchmarks. We evaluate AdaAct on CIFAR and ImageNet, comparing it with other state-of-the-art methods. Importantly, AdaAct effectively bridges the gap between the convergence speed of Adam and the strong generalization capabilities of SGD, all while maintaining competitive execution times. Code is available at https://github.com/hseung88/adaact.

TAMP: Token-Adaptive Layerwise Pruning in Multimodal Large Language Models

Multimodal Large Language Models (MLLMs) have shown remarkable versatility in understanding diverse multimodal data and tasks. However, these capabilities come with an increased model scale. While post-training pruning reduces model size in unimodal models, its application to MLLMs often yields limited success. Our analysis discovers that conventional methods fail to account for the unique token attributes across layers and modalities inherent to MLLMs. Inspired by this observation, we propose TAMP, a simple yet effective pruning framework tailored for MLLMs, featuring two key components: (1) Diversity-Aware Sparsity, which adjusts sparsity ratio per layer based on diversities among multimodal output tokens, preserving more parameters in high-diversity layers; and (2) Adaptive Multimodal Input Activation, which identifies representative multimodal input tokens using attention scores to guide unstructured weight pruning. We validate our method on two state-of-the-art MLLMs: LLaVA-NeXT, designed for vision-language tasks, and VideoLLaMA2, capable of processing audio, visual, and language modalities. Empirical experiments across various multimodal evaluation benchmarks demonstrate that each component of our approach substantially outperforms existing pruning techniques.

Posterior Inference with Diffusion Models for High-dimensional Black-box Optimization

Optimizing high-dimensional and complex black-box functions is crucial in numerous scientific applications. While Bayesian optimization (BO) is a powerful method for sample-efficient optimization, it struggles with the curse of dimensionality and scaling to thousands of evaluations. Recently, leveraging generative models to solve black-box optimization problems has emerged as a promising framework. However, those methods often underperform compared to BO methods due to limited expressivity and difficulty of uncertainty estimation in high-dimensional spaces. To overcome these issues, we introduce \textbf{DiBO}, a novel framework for solving high-dimensional black-box optimization problems. Our method iterates two stages. First, we train a diffusion model to capture the data distribution and an ensemble of proxies to predict function values with uncertainty quantification. Second, we cast the candidate selection as a posterior inference problem to balance exploration and exploitation in high-dimensional spaces. Concretely, we fine-tune diffusion models to amortize posterior inference. Extensive experiments demonstrate that our method outperforms state-of-the-art baselines across various synthetic and real-world black-box optimization tasks. Our code is publicly available \href{https://github.com/umkiyoung/DiBO}{here}

Unified Multi-Modal Interleaved Document Representation for Information Retrieval

Information Retrieval (IR) methods aim to identify relevant documents in response to a given query, which have gained remarkable attention due to their successful application in various natural language tasks. However, existing approaches typically consider only the textual information within the documents, which overlooks the fact that documents can contain multiple modalities, including texts, images, and tables. Further, they often segment each long document into multiple discrete passages for embedding, preventing them from capturing the overall document context and interactions between paragraphs. We argue that these two limitations lead to suboptimal document representations for retrieval. In this work, to address them, we aim to produce more comprehensive and nuanced document representations by holistically embedding documents interleaved with different modalities. Specifically, we achieve this by leveraging the capability of recent vision-language models that enable the processing and integration of text, images, and tables into a unified format and representation. Moreover, to mitigate the information loss from segmenting documents into passages, instead of representing and retrieving passages individually, we further merge the representations of segmented passages into one single document representation, while we additionally introduce a reranking strategy to decouple and identify the relevant passage within the document if necessary. Then, through extensive experiments on diverse information retrieval scenarios considering both the textual and multimodal queries, we show that our approach substantially outperforms relevant baselines, thanks to the consideration of the multimodal information interleaved within the documents in a unified way.