Spiking neural networks (SNNs) represent a promising approach to developing artificial neural networks that are both energy-efficient and biologically plausible. However, applying SNNs to sequential tasks, such as text classification and time-series forecasting, has been hindered by the challenge of creating an effective and hardware-friendly spike-form positional encoding (PE) strategy. Drawing inspiration from the central pattern generators (CPGs) in the human brain, which produce rhythmic patterned outputs without requiring rhythmic inputs, we propose a novel PE technique for SNNs, termed CPG-PE. We demonstrate that the commonly used sinusoidal PE is mathematically a specific solution to the membrane potential dynamics of a particular CPG. Moreover, extensive experiments across various domains, including time-series forecasting, natural language processing, and image classification, show that SNNs with CPG-PE outperform their conventional counterparts. Additionally, we perform analysis experiments to elucidate the mechanism through which SNNs encode positional information and to explore the function of CPGs in the human brain. This investigation may offer valuable insights into the fundamental principles of neural computation.

Inverse Reinforcement Learning (IRL) is a powerful paradigm for inferring a reward function from expert demonstrations. Many IRL algorithms require a known transition model and sometimes even a known expert policy, or they at least require access to a generative model. However, these assumptions are too strong for many real-world applications, where the environment can be accessed only through sequential interaction. We propose a novel IRL algorithm: Active exploration for Inverse Reinforcement Learning (AceIRL), which actively explores an unknown environment and expert policy to quickly learn the expert's reward function and identify a good policy. AceIRL uses previous observations to construct confidence intervals that capture plausible reward functions and find exploration policies that focus on the most informative regions of the environment. AceIRL is the first approach to active IRL with sample-complexity bounds that does not require a generative model of the environment. AceIRL matches the sample complexity of active IRL with a generative model in the worst case. Additionally, we establish a problem-dependent bound that relates the sample complexity of AceIRL to the suboptimality gap of a given IRL problem. We empirically evaluate AceIRL in simulations and find that it significantly outperforms more naive exploration strategies.

Constructing fast samplers for unconditional diffusion and flow-matching models has received much attention recently; however, existing methods for solving inverse problems, such as super-resolution, inpainting, or deblurring, still require hundreds to thousands of iterative steps to obtain high-quality results. We propose a plug-andplay framework for constructing efficient samplers for inverse problems, requiring only pre-trained diffusion or flow-matching models. We present Conditional Conjugate Integrators, which leverage the specific form of the inverse problem to project the respective conditional diffusion/flow dynamics into a more amenable space for sampling. Our method complements popular posterior approximation methods for solving inverse problems using diffusion/flow models. We evaluate the proposed method's performance on various linear image restoration tasks across multiple datasets, employing diffusion and flow-matching models. Notably, on challenging inverse problems like 4 super-resolution on the ImageNet dataset, our method can generate high-quality samples in as few as 5 conditional sampling steps and outperforms competing baselines requiring 20-1000 steps.

Graph based semi-supervised learning is the problem of learning a labeling function for the graph nodes given a few example nodes, often called seeds, usually under the assumption that the graph's edges indicate similarity of labels. This is closely related to the local graph clustering or community detection problem of finding a cluster or community of nodes around a given seed. For this problem, we propose a novel generalization of random walk, diffusion, or smooth function methods in the literature to a convex p-norm cut function. The need for our p-norm methods is that, in our study of existing methods, we find those principled methods based on eigenvector, spectral, random walk, or linear system often have difficulty capturing the correct boundary of a target label or target cluster. In contrast, 1-norm or maxflow-mincut based methods capture the boundary, but cannot grow from small seed set; hybrid procedures that use both have many hard to set parameters.

We evaluate our DNR method on four action recognition datasets following standard training/testing splits and protocols. Kinetics-400 [1] is a large scale action recognition dataset with trimmed video clips of around 10-second durations. It is collected from realistic YouTube videos, which covers 400 categories of human activities. In total, it contains around 240K training videos and 20K validation videos. Because of the expirations of some YouTube video links, the sizes of kinetics-400 dataset copies used in existing works may be different.

Convolutional Neural Networks (CNNs) have been the dominant model for video action recognition. Due to the huge memory and compute demand, popular action recognition networks need to be trained with small batch sizes, which makes learning discriminative spatial-temporal representations for videos become a challenging problem. In this paper, we present Dynamic Normalization and Relay (DNR), an improved normalization design, to augment the spatial-temporal representation learning of any deep action recognition model, adapting to small batch size training settings. We observe that state-of-the-art action recognition networks usually apply the same normalization parameters to all video data, and ignore the dependencies of the estimated normalization parameters between neighboring frames (at the same layer) and between neighboring layers (with all frames of a video clip). Inspired by this, DNR introduces two dynamic normalization relay modules to explore the potentials of cross-temporal and cross-layer feature distribution dependencies for estimating accurate layer-wise normalization parameters. These two DNR modules are instantiated as a light-weight recurrent structure conditioned on the current input features, and the normalization parameters estimated from the neighboring frames based features at the same layer or from the whole video clip based features at the preceding layers. We first plug DNR into prevailing 2D CNN backbones and test its performance on public action recognition datasets including Kinetics and Something-Something. Experimental results show that DNR brings large performance improvements to the baselines, achieving over 4.4% absolute margins in top-1 accuracy without training bells and whistles.

We study the problem of reward shaping to accelerate the training process of a reinforcement learning agent. Existing works have considered a number of different reward shaping formulations; however, they either require external domain knowledge or fail in environments with extremely sparse rewards.

Warning: This paper contains unfiltered and potentially harmful content. Recent studies developed jailbreaking attacks, which construct jailbreaking prompts to "fool" LLMs into responding to harmful questions. Early-stage jailbreaking attacks require access to model internals or significant human efforts. More advanced attacks utilize genetic algorithms for automatic and black-box attacks. However, the random nature of genetic algorithms significantly limits the effectiveness of these attacks.

A.1 q-Hamiltonian dynamics We can define a continuum of dynamics with Newtonian dynamics at one extreme and energysampling dynamics at the other via Tsallis statistics. H(x, v) =E(x)+K(v) The potential energy function, E(x), is the target distribution that we would like to sample and is defined by our problem. The kinetic energy, K, can be chosen in a variety of ways, but we consider the following class. However, we found it interesting that Newtonian and ESH kinetic energy terms could be viewed as opposite ends of a spectrum defined by Tsallis statistics. The situation mathematically resembles the thermodynamic continuum that emerges from Tsallis statistics. In that case, standard thermodynamics with Brownian motion corresponds to one extreme for q and in the other extreme so-called "anomalous diffusion" occurs [23]. Analogously, we can refer to the q-logarithmic counterpart of Newtonian momentum as anomalous momentum.