Abstract In recent decades, visual simultaneous localization and mapping (vSLAM) has gained significant interest in both academia and industry. It estimates camera motion and reconstructs the environment concurrently using visual sensors on a moving robot. However, conventional cameras are limited by hardware, including motion blur and low dynamic range, which can negatively impact performance in challenging scenarios like high-speed motion and high dynamic range illumination. Recent studies have demonstrated that event cameras, a new type of bio-inspired visual sensor, offer advantages such as high temporal resolution, dynamic range, low power consumption, and low latency. This paper presents a timely and comprehensive review of event-based vSLAM algorithms that exploit the benefits of asynchronous and irregular event streams for localization and mapping tasks. The review covers the working principle of event cameras and various event representations for preprocessing event data. It also categorizes event-based vSLAM methods into four main categories: feature-based, direct, motion-compensation, and deep learning methods, with detailed discussions and practical guidance for each approach. Furthermore, the paper evaluates the state-of-the-art methods on various benchmarks, highlighting current challenges and future opportunities in this emerging research area. A public repository will be maintained to keep track of the rapid developments in this field at https://github.com/kun150kun/ESLAM-survey .

Few-step diffusion models enable efficient high-resolution image synthesis but struggle to align with specific downstream objectives due to limitations of existing reinforcement learning (RL) methods in low-step regimes with limited state spaces and suboptimal sample quality. To address this, we propose Stepwise Diffusion Policy Optimization (SDPO), a novel RL framework tailored for few-step diffusion models. SDPO introduces a dual-state trajectory sampling mechanism, tracking both noisy and predicted clean states at each step to provide dense reward feedback and enable low-variance, mixed-step optimization. For further efficiency, we develop a latent similarity-based dense reward prediction strategy to minimize costly dense reward queries. Leveraging these dense rewards, SDPO optimizes a dense reward difference learning objective that enables more frequent and granular policy updates. Additional refinements, including stepwise advantage estimates, temporal importance weighting, and step-shuffled gradient updates, further enhance long-term dependency, low-step priority, and gradient stability. Our experiments demonstrate that SDPO consistently delivers superior reward-aligned results across diverse few-step settings and tasks.

Face sketch synthesis is a technique aimed at converting face photos into sketches. Existing face sketch synthesis research mainly relies on training with numerous photo–sketch sample pairs from existing datasets. However, these large-scale discriminative learning methods will have to face problems, such as data scarcity and high human labor costs. Once the training data become scarce, their generative performance significantly degrades. In this article, we propose a one-shot face sketch synthesis method based on diffusion models. We optimize text instructions on a diffusion model using face photo–sketch image pairs. Then, the instructions derived through gradient-based optimization are used for inference. To simulate real-world scenarios more accurately and evaluate method effectiveness more comprehensively, we introduce a new benchmark named One-shot Face Sketch Dataset (OS-Sketch). The benchmark consists of 400 pairs of face photo–sketch images, including sketches with different styles and photos with different backgrounds, ages, sexes, expressions, illumination, and so on. For a solid out-of-distribution evaluation, we select only one pair of images for training at each time, with the rest used for inference. Extensive experiments demonstrate that the proposed method can convert various photos into realistic and highly consistent sketches in a one-shot context. Compared to other methods, our approach offers greater convenience and broader applicability. The dataset will be available at: https://github.com/HanWu3125/OS-Sketch .

Time series modeling presents unique challenges due to autocorrelation in both historical data and future sequences. While current research predominantly addresses autocorrelation within historical data, the correlations among future labels are often overlooked. Specifically, modern forecasting models primarily adhere to the Direct Forecast (DF) paradigm, generating multi-step forecasts independently and disregarding label correlations over time. In this work, we demonstrate that the learning objective of DF is biased in the presence of label correlation. To address this issue, we propose the Frequency-enhanced Direct Forecast (FreDF), which mitigates label correlation by learning to forecast in the frequency domain, thereby reducing estimation bias. Our experiments show that FreDF significantly outperforms existing state-of-the-art methods and is compatible with a variety of forecast models. Code is available at https://github.com/Master-PLC/FreDF.

Hallucinations in Large Language Models (LLMs) remain a major obstacle, particularly in high-stakes applications where factual accuracy is critical. While representation editing and reading methods have made strides in reducing hallucinations, their heavy reliance on specialised tools and training on in-domain samples, makes them difficult to scale and prone to overfitting. This limits their accuracy gains and generalizability to diverse datasets. This paper presents a lightweight method, Norm Voting (NoVo), which harnesses the untapped potential of attention head norms to dramatically enhance factual accuracy in zero-shot multiple-choice questions (MCQs). NoVo begins by automatically selecting truth-correlated head norms with an efficient, inference-only algorithm using only 30 random samples, allowing NoVo to effortlessly scale to diverse datasets. Afterwards, selected head norms are employed in a simple voting algorithm, which yields significant gains in prediction accuracy. On TruthfulQA MC1, NoVo surpasses the current state-of-the-art and all previous methods by an astounding margin---at least 19 accuracy points. NoVo demonstrates exceptional generalization to 20 diverse datasets, with significant gains in over 90\% of them, far exceeding all current representation editing and reading methods. NoVo also reveals promising gains to finetuning strategies and building textual adversarial defence. NoVo's effectiveness with head norms opens new frontiers in LLM interpretability, robustness and reliability. Our code is available at: https://github.com/hozhengyi/novo

This work identifies the *Energy Loss Phenomenon* in Reinforcement Learning from Human Feedback (RLHF) and its connection to reward hacking. Specifically, energy loss in the final layer of a Large Language Model (LLM) gradually increases during the RL process, with an *excessive* increase in energy loss characterizing reward hacking. Beyond empirical analysis, we further provide a theoretical foundation by proving that, under mild conditions, the increased energy loss reduces the upper bound of contextual relevance in LLMs, which is a critical aspect of reward hacking as the reduced contextual relevance typically indicates overfitting to reward model-favored patterns in RL. To address this issue, we propose an *Energy loss-aware PPO algorithm (EPPO)* which penalizes the increase in energy loss in the LLM's final layer during reward calculation to prevent excessive energy loss, thereby mitigating reward hacking. We theoretically show that EPPO can be conceptually interpreted as an entropy-regularized RL algorithm, which provides deeper insights into its effectiveness. Extensive experiments across various LLMs and tasks demonstrate the commonality of the energy loss phenomenon, as well as the effectiveness of EPPO in mitigating reward hacking and improving RLHF performance.

Reward finetuning has emerged as a powerful technique for aligning diffusion models with specific downstream objectives or user preferences. However, current approaches suffer from a persistent challenge of reward overoptimization, where models exploit imperfect reward feedback at the expense of overall performance. In this work, we identify three key contributors to overoptimization: (1) a granularity mismatch between the multi-step diffusion process and sparse rewards; (2) a loss of plasticity that limits the model's ability to adapt and generalize; and (3) an overly narrow focus on a single reward objective that neglects complementary performance criteria. Accordingly, we introduce Constrained Diffusion Policy Optimization (CDPO), a novel reinforcement learning framework that addresses reward overoptimization from multiple angles. Firstly, CDPO tackles the granularity mismatch through a temporal policy optimization strategy that delivers step-specific rewards throughout the entire diffusion trajectory, thereby reducing the risk of overfitting to sparse final-step rewards. Then we incorporate a neuron reset strategy that selectively resets overactive neurons in the model, preventing overoptimization induced by plasticity loss. Finally, to avoid overfitting to a narrow reward objective, we integrate constrained reinforcement learning with auxiliary reward objectives serving as explicit constraints, ensuring a balanced optimization across diverse performance metrics.

Plasticity, the ability of a neural network to evolve with new data, is crucial for high-performance and sample-efficient visual reinforcement learning (VRL). Although methods like resetting and regularization can potentially mitigate plasticity loss, the influences of various components within the VRL framework on the agent's plasticity are still poorly understood. In this work, we conduct a systematic empirical exploration focusing on three primary underexplored facets and derive the following insightful conclusions: (1) data augmentation is essential in maintaining plasticity; (2) the critic's plasticity loss serves as the principal bottleneck impeding efficient training; and (3) without timely intervention to recover critic's plasticity in the early stages, its loss becomes catastrophic. These insights suggest a novel strategy to address the high replay ratio (RR) dilemma, where exacerbated plasticity loss hinders the potential improvements of sample efficiency brought by increased reuse frequency. Rather than setting a static RR for the entire training process, we propose Adaptive RR, which dynamically adjusts the RR based on the critic’s plasticity level. Extensive evaluations indicate that Adaptive RR not only avoids catastrophic plasticity loss in the early stages but also benefits from more frequent reuse in later phases, resulting in superior sample efficiency.

This paper tackles the emerging challenge of training generative models within a self-consuming loop, wherein successive generations of models are recursively trained on mixtures of real and synthetic data from previous generations. We construct a theoretical framework to rigorously evaluate how this training procedure impacts the data distributions learned by future models, including parametric and non-parametric models. Specifically, we derive bounds on the total variation (TV) distance between the synthetic data distributions produced by future models and the original real data distribution under various mixed training scenarios for diffusion models with a one-hidden-layer neural network score function. Our analysis demonstrates that this distance can be effectively controlled under the condition that mixed training dataset sizes or proportions of real data are large enough. Interestingly, we further unveil a phase transition induced by expanding synthetic data amounts, proving theoretically that while the TV distance exhibits an initial ascent, it declines beyond a threshold point. Finally, we present results for kernel density estimation, delivering nuanced insights such as the impact of mixed data training on error propagation.

Bridging the gap between diffusion models and human preferences is crucial for their integration into practical generative workflows. While optimizing downstream reward models has emerged as a promising alignment strategy, concerns arise regarding the risk of excessive optimization with learned reward models, which potentially compromises ground-truth performance. In this work, we confront the reward overoptimization problem in diffusion model alignment through the lenses of both inductive and primacy biases. We first identify a mismatch between current methods and the temporal inductive bias inherent in the multi-step denoising process of diffusion models, as a potential source of reward overoptimization. Then, we surprisingly discover that dormant neurons in our critic model act as a regularization against reward overoptimization while active neurons reflect primacy bias. Motivated by these observations, we propose Temporal Diffusion Policy Optimization with critic active neuron Reset (TDPO-R), a policy gradient algorithm that exploits the temporal inductive bias of diffusion models and mitigates the primacy bias stemming from active neurons. Empirical results demonstrate the superior efficacy of our methods in mitigating reward overoptimization. Code is avaliable at https://github.com/ZiyiZhang27/tdpo.

Massive reinforcement learning (RL) data are typically collected to train policies offline without the need for interactions, but the large data volume can cause training inefficiencies. To tackle this issue, we formulate offline behavior distillation (OBD), which synthesizes limited expert behavioral data from sub-optimal RL data, enabling rapid policy learning. We propose two naive OBD objectives, DBC and PBC, which measure distillation performance via the decision difference between policies trained on distilled data and either offline data or a near-expert policy. Due to intractable bi-level optimization, the OBD objective is difficult to minimize to small values, which deteriorates PBC by its distillation performance guarantee with quadratic discount complexity $\mathcal{O}(1/(1-\gamma)^2)$. We theoretically establish the equivalence between the policy performance and action-value weighted decision difference, and introduce action-value weighted PBC (Av-PBC) as a more effective OBD objective. By optimizing the weighted decision difference, Av-PBC achieves a superior distillation guarantee with linear discount complexity $\mathcal{O}(1/(1-\gamma))$. Extensive experiments on multiple D4RL datasets reveal that Av-PBC offers significant improvements in OBD performance, fast distillation convergence speed, and robust cross-architecture/optimizer generalization.

Despite the success of reinforcement learning from human feedback (RLHF) in aligning language models with human values, reward hacking, also termed reward overoptimization, remains a critical challenge. This issue primarily arises from reward misgeneralization, where reward models (RMs) compute reward using spurious features that are irrelevant to human preferences. In this work, we tackle this problem from an information-theoretic perspective and propose a framework for reward modeling, namely InfoRM, by introducing a variational information bottleneck objective to filter out irrelevant information. Notably, we further identify a correlation between overoptimization and outliers in the IB latent space of InfoRM, establishing it as a promising tool for detecting reward overoptimization. Inspired by this finding, we propose the Cluster Separation Index (CSI), which quantifies deviations in the IB latent space, as an indicator of reward overoptimization to facilitate the development of online mitigation strategies. Extensive experiments on a wide range of settings and RM scales (70M, 440M, 1.4B, and 7B) demonstrate the effectiveness of InfoRM. Further analyses reveal that InfoRM's overoptimization detection mechanism is not only effective but also robust across a broad range of datasets, signifying a notable advancement in the field of RLHF. The code will be released upon acceptance.

Robust audio anti-spoofing has been increasingly challenging due to the recent advancements on deepfake techniques. While spectrograms have demonstrated their capability for anti-spoofing, complementary information presented in multi-order spectral patterns have not been well explored, which limits their effectiveness for varying spoofing attacks. Therefore, we propose a novel deep learning method with a spectral fusion-reconstruction strategy, namely S2pecNet, to utilise multi-order spectral patterns for robust audio anti-spoofing representations. Specifically, spectral patterns up to second-order are fused in a coarse-to-fine manner and two branches are designed for the fine-level fusion from the spectral and temporal contexts. A reconstruction from the fused representation to the input spectrograms further reduces the potential fused information loss. Our method achieved the state-of-the-art performance with an EER of 0.77% on a widely used dataset: ASVspoof2019 LA Challenge.

Monocular visual odometry (VO) has attracted extensive research attention by providing real-time vehicle motion from cost-effective camera images. However, state-of-the-art optimization-based monocular VO methods suffer from the scale inconsistency problem for long-term predictions. Deep learning has recently been introduced to address this issue by leveraging stereo sequences or ground-truth motions in the training dataset. However, it comes at an additional cost for data collection, and such training data may not be available in all datasets. In this work, we propose VRVO, a novel framework for retrieving the absolute scale from virtual data that can be easily obtained from modern simulation environments, whereas in the real domain no stereo or ground-truth data are required in either the training or inference phases. Specifically, we first train a scale-aware disparity network using both monocular real images and stereo virtual data. The virtual-to-real domain gap is bridged by using an adversarial training strategy to map images from both domains into a shared feature space. The resulting scale-consistent disparities are then integrated with a direct VO system by constructing a virtual stereo objective that ensures the scale consistency over long trajectories. Additionally, to address the suboptimality issue caused by the separate optimization backend and the learning process, we further propose a mutual reinforcement pipeline that allows bidirectional information flow between learning and optimization, which boosts the robustness and accuracy of each other. We demonstrate the effectiveness of our framework on the KITTI and vKITTI2 datasets.

Unpaired image-to-image translation aims to find a mapping between the source domain and the target domain. To alleviate the problem of the lack of supervised labels for the source images, cycle-consistency based methods have been proposed for image structure preservation by assuming a reversible relationship between unpaired images. However, this assumption only uses limited correspondence between image pairs. Recently, contrastive learning (CL) has been used to further investigate the image correspondence in unpaired image translation by using patch-based positive/negative learning. Patch-based contrastive routines obtain the positives by self-similarity computation and recognize the rest patches as negatives. This flexible learning paradigm obtains auxiliary contextualized information at a low cost. As the negatives own an impressive sample number, with curiosity, we make an investigation based on a question: are all negatives necessary for feature contrastive learning? Unlike previous CL approaches that use negatives as much as possible, in this paper, we study the negatives from an information-theoretic perspective and introduce a new negative Pruning technology for Unpaired image-to-image Translation (PUT) by sparsifying and ranking the patches. The proposed algorithm is efficient, flexible and enables the model to learn essential information between corresponding patches stably. By putting quality over quantity, only a few negative patches are required to achieve better results. Lastly, we validate the superiority, stability, and versatility of our model through comparative experiments.

Abstract In this paper, we propose a unified information theoretic framework for learning-motivated methods aimed at odometry estimation, a crucial component of many robotics and vision tasks such as navigation and virtual reality where relative camera poses are required in real time. We formulate this problem as optimizing a variational information bottleneck objective function, which eliminates pose-irrelevant information from the latent representation. The proposed framework provides an elegant tool for performance evaluation and understanding in information-theoretic language. Specifically, we bound the generalization errors of the deep information bottleneck framework and the predictability of the latent representation. These provide not only a performance guarantee but also practical guidance for model design, sample collection, and sensor selection. Furthermore, the stochastic latent representation provides a natural uncertainty measure without the needs for extra structures or computations. Experiments on two well-known odometry datasets demonstrate the effectiveness of our method.

Real-scene image super-resolution aims to restore real-world low-resolution images into their high-quality versions. A typical RealSR framework usually includes the optimization of multiple criteria which are designed for different image properties, by making the implicit assumption that the ground-truth images can provide a good trade-off between different criteria. However, this assumption could be easily violated in practice due to the inherent contrastive relationship between different image properties. Contrastive learning (CL) provides a promising recipe to relieve this problem by learning discriminative features using the triplet contrastive losses. Though CL has achieved significant success in many computer vision tasks, it is non-trivial to introduce CL to RealSR due to the difficulty in defining valid positive image pairs in this case. Inspired by the observation that the contrastive relationship could also exist between the criteria, in this work, we propose a novel training paradigm for RealSR, named Criteria Comparative Learning (Cria-CL), by developing contrastive losses defined on criteria instead of image patches. In addition, a spatial projector is proposed to obtain a good view for Cria-CL in RealSR. Our experiments demonstrate that compared with the typical weighted regression strategy, our method achieves a significant improvement under similar parameter settings.

Non-parallel text style transfer has attracted increasing research interests in recent years. Despite successes in transferring the style based on the encoder-decoder framework, current approaches still lack the ability to preserve the content and even logic of original sentences, mainly due to the large unconstrained model space or too simplified assumptions on latent embedding space. Since language itself is an intelligent product of humans with certain grammars and has a limited rule-based model space by its nature, relieving this problem requires reconciling the model capacity of deep neural networks with the intrinsic model constraints from human linguistic rules. To this end, we propose a method called Graph Transformer–based Auto-Encoder, which models a sentence as a linguistic graph and performs feature extraction and style transfer at the graph level, to maximally retain the content and the linguistic structure of original sentences. Quantitative experiment results on three non-parallel text style transfer tasks show that our model outperforms state-of-the-art methods in content preservation, while achieving comparable performance on transfer accuracy and sentence naturalness.