Quantum or quantum-inspired Ising machines have recently shown promise in solving combinatorial optimization problems in a short time. Real-world applications, such as time division multiple access (TDMA) scheduling for wireless multi-hop networks and financial trading, require solving those problems sequentially where the size and characteristics change dynamically. However, using Ising machines involves challenges to shorten system-wide latency due to the transfer of large Ising model or the cloud access and to determine the parameters for each problem. Here we show a combinatorial optimization method using embedded Ising machines, which enables solving diverse problems at high speed without runtime parameter tuning. We customize the algorithm and circuit architecture of the simulated bifurcation-based Ising machine to compress the Ising model and accelerate computation and then built a machine learning model to estimate appropriate parameters using extensive training data. In TDMA scheduling for wireless multi-hop networks, our demonstration has shown that the sophisticated system can adapt to changes in the problem and showed that it has a speed advantage over conventional methods.

Reasoning is a cognitive ability which allows humans to solve problems with previously unseen combinations of constraints. For a long time, it has been debated whether artificial neural networks can obtain such generalization skills or whether they can only learn to detect superficial patterns Fodor and Pylyshyn [1988], Marcus [2003, 2018] without being able to generalize to novel combinations of constraints. With the arrival of Large Language Models (LLMs) specially trained for reasoning Guo et al. [2025], Jaech et al. [2024], it became harder and harder to claim that these models can only detect superficial patterns. Nevertheless, the exact mechanism by which they are able to solve tasks that typically require reasoning is largely unknown and the robustness of the solving process is also not understood. In this contribution, we focus on a restricted class of problems that require reasoning, concretely on solving Boolean formulas in CNF form. This could be viewed as a prototypical task where the goal is to solve problems with novel combinations of constraints, and where detecting superficial patterns seen during training would be insufficient. It has already been demonstrated that Graph Neural Networks (GNNs) can successfully learn to solve such problems and generalize to larger problems Selsam et al. [2018], even though they are still not competitive when compared to state of the art SAT solvers. Understanding the underlying mechanisms GNNs employ to successfully solve problems, as well as their limitations, would offer significant practical and theoretical value.

To develop a trustworthy AI system, which aim to identify the input regions that most influence the models decisions. The primary task of existing attribution methods lies in efficiently and accurately identifying the relationships among input-prediction interactions. Particularly when the input data is discrete, such as images, analyzing the relationship between inputs and outputs poses a significant challenge due to the combinatorial explosion. In this paper, we propose a novel and efficient black-box attribution mechanism, LiMA (Less input is More faithful for Attribution), which reformulates the attribution of important regions as an optimization problem for submodular subset selection. First, to accurately assess interactions, we design a submodular function that quantifies subset importance and effectively captures their impact on decision outcomes. Then, efficiently ranking input sub-regions by their importance for attribution, we improve optimization efficiency through a novel bidirectional greedy search algorithm. LiMA identifies both the most and least important samples while ensuring an optimal attribution boundary that minimizes errors. Extensive experiments on eight foundation models demonstrate that our method provides faithful interpretations with fewer regions and exhibits strong generalization, shows an average improvement of 36.3% in Insertion and 39.6% in Deletion. Our method also outperforms the naive greedy search in attribution efficiency, being 1.6 times faster. Furthermore, when explaining the reasons behind model prediction errors, the average highest confidence achieved by our method is, on average, 86.1% higher than that of state-of-the-art attribution algorithms. The code is available at https://github.com/RuoyuChen10/LIMA.

With the scale capability of increasing training data, model size, and computational cost, video generation has achieved impressive results in digital creation, enabling users to express creativity across various domains. Recently, researchers in Large Language Models (LLMs) have expanded the scaling to test-time, which can significantly improve LLM performance by using more inference-time computation. Instead of scaling up video foundation models through expensive training costs, we explore the power of Test-Time Scaling (TTS) in video generation, aiming to answer the question: if a video generation model is allowed to use non-trivial amount of inference-time compute, how much can it improve generation quality given a challenging text prompt. In this work, we reinterpret the test-time scaling of video generation as a searching problem to sample better trajectories from Gaussian noise space to the target video distribution. Specifically, we build the search space with test-time verifiers to provide feedback and heuristic algorithms to guide searching process. Given a text prompt, we first explore an intuitive linear search strategy by increasing noise candidates at inference time. As full-step denoising all frames simultaneously requires heavy test-time computation costs, we further design a more efficient TTS method for video generation called Tree-of-Frames (ToF) that adaptively expands and prunes video branches in an autoregressive manner. Extensive experiments on text-conditioned video generation benchmarks demonstrate that increasing test-time compute consistently leads to significant improvements in the quality of videos. Project page: https://liuff19.github.io/Video-T1

Finding deletion-correcting codes of maximum size has been an open problem for over 70 years, even for a single deletion. In this paper, we propose a novel approach for constructing deletion-correcting codes. A code is a set of sequences satisfying certain constraints, and we construct it by greedily adding the highest-priority sequence according to a priority function. To find good priority functions, we leverage FunSearch, a large language model (LLM)-guided evolutionary search proposed by Romera et al., 2024. FunSearch iteratively generates, evaluates, and refines priority functions to construct large deletion-correcting codes. For a single deletion, our evolutionary search finds functions that construct codes which match known maximum sizes, reach the size of the largest (conjectured optimal) Varshamov-Tenengolts codes where the maximum is unknown, and independently rediscover them in equivalent form. For two deletions, we find functions that construct codes with new best-known sizes for code lengths \( n = 12, 13 \), and \( 16 \), establishing improved lower bounds. These results demonstrate the potential of LLM-guided search for information theory and code design and represent the first application of such methods for constructing error-correcting codes.

Machine learning (ML) techniques have become ubiquitous in the financial industry due to their powerful predictive performance. However, ML model outputs may lead to certain types of unintended bias, which are measures of unfairness that impact protected sub-populations. Predictive models, and strategies that rely on such models, are subject to laws and regulations that ensure fairness. For instance, financial institutions (FIs) in the U.S. that are in the business of extending credit to applicants are subject to the Equal Credit Opportunity Act (ECOA) [14] and the Fair Housing Act (FHA) [13], which prohibit discrimination in credit offerings and housing transactions. The protected classes identified in the laws, including race, gender, age (subject to very limited exceptions), ethnicity, national origin, and material status, cannot be used as attributes in lending decisions.

Existing hardware-aware NAS (HW-NAS) methods typically assume access to precise information circa the target device, either via analytical approximations of the post-compilation latency model, or through learned latency predictors. Such approximate approaches risk introducing estimation errors that may prove detrimental in risk-sensitive applications. In this work, we propose a two-stage HW-NAS framework, in which we first learn an architecture controller on a distribution of synthetic devices, and then directly deploy the controller on a target device. At test-time, our network controller deploys directly to the target device without relying on any pre-collected information, and only exploits direct interactions. In particular, the pre-training phase on synthetic devices enables the controller to design an architecture for the target device by interacting with it through a small number of high-fidelity latency measurements. To guarantee accessibility of our method, we only train our controller with training-free accuracy proxies, allowing us to scale the meta-training phase without incurring the overhead of full network training. We benchmark on HW-NATS-Bench, demonstrating that our method generalizes to unseen devices and searches for latency-efficient architectures by in-context adaptation using only a few real-world latency evaluations at test-time.

Hypergraphs offer a powerful framework for modeling higher-order interactions that traditional pairwise graphs cannot fully capture. However, practical constraints often lead to their simplification into projected graphs, resulting in substantial information loss and ambiguity in representing higher-order relationships. In this work, we propose MARIOH, a supervised approach for reconstructing the original hypergraph from its projected graph by leveraging edge multiplicity. To overcome the difficulties posed by the large search space, MARIOH integrates several key ideas: (a) identifying provable size-2 hyperedges, which reduces the candidate search space, (b) predicting the likelihood of candidates being hyperedges by utilizing both structural and multiplicity-related features, and (c) not only targeting promising hyperedge candidates but also examining less confident ones to explore alternative possibilities. Together, these ideas enable MARIOH to efficiently and effectively explore the search space. In our experiments using 10 real-world datasets, MARIOH achieves up to 74.51% higher reconstruction accuracy compared to state-of-the-art methods.

Clifford circuit optimization is an important step in the quantum compilation pipeline. Major compilers employ heuristic approaches. While they are fast, their results are often suboptimal. Minimization of noisy gates, like 2-qubit CNOT gates, is crucial for practical computing. Exact approaches have been proposed to fill the gap left by heuristic approaches. Among these are SAT based approaches that optimize gate count or depth, but they suffer from scalability issues. Further, they do not guarantee optimality on more important metrics like CNOT count or CNOT depth. A recent work proposed an exhaustive search only on Clifford circuits in a certain normal form to guarantee CNOT count optimality. But an exhaustive approach cannot scale beyond 6 qubits. In this paper, we incorporate search restricted to Clifford normal forms in a SAT encoding to guarantee CNOT count optimality. By allowing parallel plans, we propose a second SAT encoding that optimizes CNOT depth. By taking advantage of flexibility in SAT based approaches, we also handle connectivity restrictions in hardware platforms, and allow for qubit relabeling. We have implemented the above encodings and variations in our open source tool Q-Synth. In experiments, our encodings significantly outperform existing SAT approaches on random Clifford circuits. We consider practical VQE and Feynman benchmarks to compare with TKET and Qiskit compilers. In all-to-all connectivity, we observe reductions up to 32.1% in CNOT count and 48.1% in CNOT depth. Overall, we observe better results than TKET in the CNOT count and depth. We also experiment with connectivity restrictions of major quantum platforms. Compared to Qiskit, we observe up to 30.3% CNOT count and 35.9% CNOT depth further reduction.

We consider a multi-robot setting, where we have a fleet of multi-capacity autonomous robots that must service spatially distributed pickup-and-delivery requests with fixed maximum wait times. Requests can be either scheduled ahead of time or they can enter the system in real-time. In this setting, stability for a routing policy is defined as the cost of the policy being uniformly bounded over time. Most previous work either solve the problem offline to theoretically maintain stability or they consider dynamically arriving requests at the expense of the theoretical guarantees on stability. In this paper, we aim to bridge this gap by proposing a novel proactive rollout-based routing framework that adapts to real-time demand while still provably maintaining the stability of the learned routing policy. We derive provable stability guarantees for our method by proposing a fleet sizing algorithm that obtains a sufficiently large fleet that ensures stability by construction. To validate our theoretical results, we consider a case study on real ride requests for Harvard's evening Van System. We also evaluate the performance of our framework using the currently deployed smaller fleet size. In this smaller setup, we compare against the currently deployed routing algorithm, greedy heuristics, and Monte-Carlo-Tree-Search-based algorithms. Our empirical results show that our framework maintains stability when we use the sufficiently large fleet size found in our theoretical results. For the smaller currently deployed fleet size, our method services 6% more requests than the closest baseline while reducing median passenger wait times by 33%.