We present a novel actor-critic algorithm for an environment with delayed feedback, which addresses the state-space explosion problem of conventional approaches. Conventional approaches use an augmented state constructed from the last observed state and actions executed since visiting the last observed state Using the augmented state space, the correct Markov decision process for delayed environments can be constructed; however, this causes the state space to explode as the number of delayed timesteps increases, leading to slow convergence. Our proposed algorithm, called Belief-Projection-Based Q-learning (BPQL), addresses the state-space explosion problem by evaluating the values of the critic for which the input state size is equal to the original state-space size rather than that of the augmented one. We compare BPQL to traditional approaches in continuous control tasks and demonstrate that it significantly outperforms other algorithms in terms of asymptotic performance and sample efficiency. We also show that BPQL solves long-delayed environments, which conventional approaches are unable to do.

Modern language models excel at integrating across long temporal scales needed to encode linguistic meaning and show non-trivial similarities to biological neural systems. Prior work suggests that human brain responses to language exhibit hierarchically organized "integration windows" that substantially constrain the overall influence of an input token (e.g., a word) on the neural response. However, little prior work has attempted to use integration windows to characterize computations in large language models (LLMs). We developed a simple word-swap procedure for estimating integration windows from black-box language models that does not depend on access to gradients or knowledge of the model architecture (e.g., attention weights). Using this method, we show that trained LLMs exhibit stereotyped integration windows that are well-fit by a convex combination of an exponential and a power-law function, with a partial transition from exponential to power-law dynamics across network layers. We then introduce a metric for quantifying the extent to which these integration windows vary with structural boundaries (e.g., sentence boundaries), and using this metric, we show that integration windows become increasingly yoked to structure at later network layers. None of these findings were observed in an untrained model, which as expected integrated uniformly across its input. These results suggest that LLMs learn to integrate information in natural language using a stereotyped pattern: integrating across position-yoked, exponential windows at early layers, followed by structure-yoked, power-law windows at later layers. The methods we describe in this paper provide a general-purpose toolkit for understanding temporal integration in language models, facilitating cross-disciplinary research at the intersection of biological and artificial intelligence.

Data-Free Model Extraction (DFME) aims to clone a black-box model without knowing its original training data distribution, making it much easier for attackers to steal commercial models. Defense against DFME faces several challenges: (i) effectiveness; (ii) efficiency; (iii) no prior on the attacker's query data distribution and strategy. However, existing defense methods: (1) are highly computation and memory inefficient; or (2) need strong assumptions about attack data distribution; or (3) can only delay the attack or prove a model theft after the model stealing has happened. In this work, we propose a Memory and Computation efficient defense approach, named MeCo, to prevent DFME from happening while maintaining the model utility simultaneously by distributionally robust defensive training on the target victim model. Specifically, we randomize the input so that it: (1) causes a mismatch of the knowledge distillation loss for attackers; (2) disturbs the zerothorder gradient estimation; (3) changes the label prediction for the attack query data. Therefore, the attacker can only extract misleading information from the black-box model. Extensive experiments on defending against both decision-based and scorebased DFME demonstrate that MeCo can significantly reduce the effectiveness of existing DFME methods and substantially improve running efficiency.

China's DeepSeek unveils latest models a year after upending global tech China's DeepSeek has unveiled the latest versions of its signature artificial intelligence-powered chatbot, a year after its flagship model sent shockwaves through the global tech scene. The Chinese start-up launched preview versions of DeepSeek-V4-Pro and DeepSeek-V4-Flash on Friday as it touted its ability to go toe-to-toe with US rivals such as OpenAI and Google. The "flash" model has similar reasoning abilities to the "pro" version, while offering faster response times and more cost-effective pricing, the Hangzhou-based startup said. Like DeepSeek's previous chatbots, V4-Pro and V4-Flash follow an open-source model, meaning developers are free to use and modify them at will. The release comes after DeepSeek-R1 stunned the tech sector upon its launch in January last year with capabilities broadly comparable with those of ChatGPT and Gemini.

Causal identification is at the core of the causal inference literature, where complete algorithms have been proposed to identify causal queries of interest. The validity of these algorithms hinges on the restrictive assumption of having access to a correctly specified causal structure. In this work, we study the setting where a probabilistic model of the causal structure is available. Specifically, the edges in a causal graph exist with uncertainties which may, for example, represent degree of belief from domain experts. Alternatively, the uncertainty about an edge may reflect the confidence of a particular statistical test. The question that naturally arises in this setting is: Given such a probabilistic graph and a specific causal effect of interest, what is the subgraph which has the highest plausibility and for which the causal effect is identifiable? We show that answering this question reduces to solving an NP-complete combinatorial optimization problem which we call the edge ID problem. We propose efficient algorithms to approximate this problem and evaluate them against both real-world networks and randomly generated graphs.

Quantum many-body physics simulation has important impacts on understanding fundamental science and has applications to quantum materials design and quantum technology. However, due to the exponentially growing size of the Hilbert space with respect to the particle number, a direct simulation is intractable. While representing quantum states with tensor networks and neural networks are the two state-of-the-art methods for approximate simulations, each has its own limitations in terms of expressivity and inductive bias. To address these challenges, we develop a novel architecture, Autoregressive Neural TensorNet (ANTN), which bridges tensor networks and autoregressive neural networks. We show that Autoregressive Neural TensorNet parameterizes normalized wavefunctions, allows for exact sampling, generalizes the expressivity of tensor networks and autoregressive neural networks, and inherits a variety of symmetries from autoregressive neural networks. We demonstrate our approach on quantum state learning as well as finding the ground state of the challenging 2DJ1-J2 Heisenberg model with different systems sizes and coupling parameters, outperforming both tensor networks and autoregressive neural networks. Our work opens up new opportunities for quantum many-body physics simulation, quantum technology design, and generative modeling in artificial intelligence.