Robotics
Papers
Fresh from arXiv, typeset properly. Highlighted words trade on the market.
All of arXiv
Tuesday 15 September
Action Chunking Transformers (ACT) are widely used to learn robot manipulation from demonstrations. Their conditional variational autoencoder includes an encoder meant to capture differences between demonstrations during training. The original ACT paper reported that encoder removal dropped the mean success rate from 35% to 2% on two simulated tasks with human demonstrations. We re-ran this ablation in the original code and checked whether the findings depend on the implementation or training data. The published drop does not reappear in our tests, although smaller gains or losses in success rate remain uncertain. To investigate the discrepancy, we varied training length and how checkpoints are selected for evaluation. Both can reverse which policy scores higher, but the published drop's cause remains unknown. Success rates alone leave open whether the encoder provides information that helps the policy reconstruct demonstrated actions. On the tested ACT benchmark, the sampled latent provides little reconstruction benefit at every tested nonzero weight of the penalty on latent information. At inference, ACT leaves this latent unused and sets it to zero. Skipping the encoder increases training throughput in both implementations we timed. We release code, evaluation tools and results so others can repeat the comparisons and test the encoder on other tasks.
Machine Learning
A Systematic Evaluation of Machine Learning Methods for Fault Detection and Line Identification in Electrical Power Grids
The integration of renewable energy sources into the electrical grid introduces complex challenges in fault detection and coordination of grid recovery mechanisms. Traditional relay protection systems, which operate based on static rules and predefined thresholds, are inadequate for addressing these challenges, particularly in detecting and isolating faults such as short circuits. Consequently, the conventional methodologies applied to electrical network protection frequently fail to achieve optimal performance in fault detection, especially in terms of adherence to safety standards and the selective limitation of damage. Recent research indicates that machine learning (ML)-based approaches can effectively tackle these issues; however, variations in grid configurations and analysis windows have impeded consistent comparative assessments. In this study, we assess the efficacy of various ML models in detecting electrical faults and pinpointing defective transmission lines within a 10 ms measurement interval - a critical time-frame for real-time operational viability, for the first time. The most effective model attained an F1 score of 0.991 +/- 0.018 and demonstrated a processing time of 0.342ms +/- 0.509ms.
Read the full abstract
Quantum Physics
Experimental Private Quantum Networked Sensing
Entangling distant quantum sensors is a key application of future quantum networks, allowing for the estimation of global functions of local parameters, with precision that is not possible with stand-alone, individual, quantum sensors. However, with this advantage comes the risk of information leakage over the network via possible malicious parties. It is often particularly important that local parameters remain unknown and that only the global function is shared across the network. Recently, the notion of privacy has been introduced in this context, which ensures that only the agreed function of parameters is shared over the network, even when malicious parties control the network itself, whilst maintaining the estimation advantage. In this work, we introduce a noise-robust protocol for private quantum networked sensing, which we realise using a high-fidelity Greenberger-Horne-Zeilinger (GHZ) state source. We further run a comparative analysis and simulate attacks using three different quantum states, a four-qubit GHZ state, two Bell pairs, and a fully separable state. Our results highlight the clear advantage of GHZ states in maintaining high precision, accuracy, and privacy for the distributed estimation task.
Read the full abstract
Hardware Architecture
Carry-Through Checksum: A Lightweight Fault-Detection for CNN Inference at the Edge
Convolutional Neural Networks (CNNs) are increasingly deployed in safety-critical edge applications, where soft errors can silently corrupt inference outputs and lead to unsafe decisions. Such applications typically rely on resource-constrained embedded GPUs, requiring fault detection and mitigation techniques that add minimal compute, memory, and latency overhead while integrating seamlessly with the standard GPU inference pipeline. Existing algorithm-based fault tolerance techniques rely on matrix augmentation and per-operation checksum verification, imposing substantial overhead that is prohibitive for CNN inference on embedded GPUs. In this work, we propose carry-through checksum, a fundamentally new scheme for soft-error detection in CNN inference on embedded GPUs. The method embeds dedicated carry-through filters into the convolutional layers, which compute a checksum from the CNN's own operations and propagate it through inference, enabling end-to-end error detection with a single output verification. Experimental results on multiple CNN architectures show that the proposed method detects 95.86% and 86.56% of critical faults for FP32 and FP16, respectively, at almost no additional per-image overhead. Detected faults are mitigated through re-execution, incurring only 2.27% run-time overhead across the entire test set on an NVIDIA Jetson Orin NX GPU.
Read the full abstract
Commutative Algebra
Strongly multiplicative sets, idempotent localizations, and $S$-prime phenomena
A multiplicative set $S$ of a commutative ring $R$ is strongly multiplicative if every family $(s_i)_{i \in I}$ of elements of $S$ admits a common multiple in $S \cap \bigcap_{i \in I} s_iR$. We combine the structural results on strongly multiplicative sets with their prime-theoretic and module-theoretic applications. We prove that $S$ is strongly multiplicative if and only if localization at $S$ commutes with arbitrary intersections of ideals, if and only if $R_S$ is the localization at an idempotent, and if and only if $D(S)$ is clopen in $\Spec(R)$. We then develop permanence results under homomorphisms, products, factor rings, trivial extensions, and amalgamations; describe the associated split torsion theory; show that almost multiplicative sets contribute no new cases beyond their multiplicative hull; and record a Mittag–Leffler refinement for intersections of submodules in finitely generated modules. On the prime-theoretic side, we relate strongly multiplicative sets to strongly prime ideals and strongly zero-dimensional rings, answer the Hamed–Malek question on the role of strong multiplicativity for chains of $S$-prime ideals, prove a strong Krull separation lemma together with a maximal-ideal correspondence for $R_S$, and connect the theory with the regular $m$-complement operator. In particular, every nontrivial strongly multiplicative localization must invert a zero divisor.
Read the full abstract
Astrophysics of Galaxies
Lower central dark matter densities in nearby galaxies than predicted by simulations
Baryonic feedback in hydrodynamical simulations is typically invoked to alleviate the core–cusp problem in dwarf galaxies. Yet baryonic processes also induce adiabatic contraction of dark matter, producing overly steep density profiles and excessively high dark matter fractions in the inner regions of massive galaxies. The dark matter distribution of galaxies across a wide stellar-mass range is therefore a critical test for such simulations, but a comprehensive benchmark has remained absent. Here, we consistently measure the dark matter distribution from galaxy centres out to radii of 20–50 kpc for 136 nearby galaxies that together span the local mass–size relation over the stellar mass interval $10^9$–$10^{11.5}\,M_{\odot}$. We identify central regions with lower dark matter densities relative to $\Lambda$CDM simulation expectations—whose extent grows from about 10 kpc to $>50$ kpc as stellar mass increases from $10^{10} M_{\odot}$ to $10^{11.5} M_{\odot}$. Although their physical origin remains unclear, these low–dark matter regions are clearly indicated by the data. Our results provide an important observational benchmark for future hydrodynamical simulations that explore alternative dark matter models and feedback processes.
Read the full abstract
Computation and Language
Japanese Stroke LLM Evaluation: A Conversational Benchmark for Safe Stroke Care in Japanese Using Large Language Models
Background: Large language models (LLMs) have achieved physician-comparable performance on multiple-choice medical knowledge examinations, but their capabilities in clinical history taking, urgency assessment, and safety remain insufficiently evaluated. We proposed Japanese Stroke LLM Evaluation, a multi-turn conversational benchmark for stroke care in Japanese, and evaluated LLM performance and safety under practice-oriented conditions. Methods: We created 10 stroke and related-condition cases and evaluated LLMs in multi-turn Japanese conversations. The LLM acted as physician, while a board-certified neurosurgeon acted as simulated patient and evaluator. Each case comprised history-taking and action phases scored using pre-specified criteria. Errors that could directly threaten life were defined as critical mistakes. The safety threshold was at least 80% overall with zero critical mistakes. Eighteen models were evaluated in October 2025 and June 2026. Results: Claude Fable 5 achieved the highest score (87.4%) with zero critical mistakes, followed by Claude Opus 4.7 (80.3%) and GLM-5.2 (75.6%). Two leaders met the safety threshold. Eleven models made 17 critical mistakes, including failure to confirm laboratory results or blood glucose before t-PA, surgery before airway stabilization, omission of cervical vascular evaluation, and t-PA outside its indication. History-taking question count correlated with history-taking score (r = 0.648, p = 0.007). Conclusions: Japanese Stroke LLM Evaluation provides a benchmark for LLM performance under practice-oriented conditions, including a cap on history-taking questions. Cases and evaluations were created by neurosurgical specialists rather than using an LLM-as-judge approach. Performance improved across cloud-based and on-premise models in 2026, with some exceeding the safety threshold. Further evaluation using real-world cases is required.
Read the full abstract
Systems and Control
Unified Heterogeneous Graph Neural Network solver for Power Flow, Optimal Power Flow and State Estimation
Power Flow (PF), Optimal Power Flow (OPF), and State Estimation (SE) are fundamental problems in power system analysis, but solving them is computationally expensive. Graph Neural Networks (GNNs) have been proposed as fast surrogates, yet existing solvers are trained for a single problem at a time, producing narrow models that must be rebuilt for each new task. We propose a more general approach: a single Heterogeneous Residual Gated Graph Convolutional Network that solves all three problems with one shared backbone. Rather than learning one mapping, the model learns a reusable representation of how the network behaves, from which PF, OPF, and SE can each be estimated. Trained jointly on the three problems across diverse topologies and loading conditions, and evaluated on the IEEE 14-bus and 118-bus systems, the shared model matches the accuracy of task-specific GNN solvers and stays robust on unseen loading levels and topologies. These results show that a single model can capture the basic operation of a power network and serve several analysis tasks at once, a first step toward a foundation model for power systems.
Read the full abstract
Robotics
Visual Cue Guided Video Planning for Generalizable Robot Navigation
Generative video models can serve as a promising backbone for robot navigation by predicting future observations as video plans. Recent approaches often condition video planning on short-horizon guidance and recover geometric waypoints through scene reconstruction, leaving longer-horizon planning and precise video-to-action translation less explored. We present CueNav, a video model-based navigation framework combining visual cue guided video planning with an embodiment-specific Inverse-Dynamics Model (IDM). As visual cues, we use a Bird's-Eye View (BEV) map to convey global task context and retain part of the robot body in the egocentric observation to expose embodiment context. These cues guide the video planner, while the IDM translates dense flow fields extracted from the video plan into robot actions. With the visual cue encoding global task context, CueNav achieves nearly 2x higher success in maze navigation than planning without the cue. The body-aware view with the IDM enables precise navigation with 70% success in a narrow passage where comparison methods largely fail to complete the task. We further demonstrate zero-shot semantic-conditioned navigation and deployment of the same video planner across different robot platforms. Our results show that visual cue-guided video planning with embodiment-specific action grounding paves the way toward a generalizable navigation framework for longer-horizon planning and embodiment-aware control. Additional results and code are available on our project website: https://cuenav.github.io.
Read the full abstract
Computers and Society
Dataset repurposing and disruptive AI research
Technological advancements are enabling increasingly systematic and large-scale data collection across all areas of science, driving scientific innovation. In particular, AI research exemplifies this trend, having advanced rapidly through the assembly of massive datasets used to train and evaluate machine learning models. However, the escalating demand for data, the difficulty of creating high-quality datasets, and the exhaustion of easily accessible data sources in AI research raise important questions about how to maximize the value of existing datasets through recombination and repurposing. Here, we draw on two theoretical frameworks—recombinational novelty and transformational creativity—to examine the practice of data repurposing and its scientific impact. Focusing on AI, we analyze scientific outcomes associated with data repurposing across more than 10,000 machine learning papers. First, we find that although most repurposed datasets do not achieve broad visibility in the short term, data repurposing is associated with greater disruption. Second, when repurposed data is adopted by subsequent research, the repurposing paper is associated with higher disruption and increased citation impact. Third, repurposing teams tend to be more experienced, more institutionally prestigious, and involve academic–industry collaboration. However, team characteristics poorly predict which repurposed datasets will be adopted by the community. These findings suggest that data repurposing may be an important approach to scientific discovery, and that its successful adoption is more common among larger teams and collaborations spanning academia and industry.
Read the full abstract
Functional Analysis
Subspaces of $L^1$ spanned by the even and odd levels of the Haar system
We prove that the closed subspace of $L^1[0,1]$ spanned by the even (respectively, odd) levels of the Haar system is not isomorphic to $L^1[0,1]$.
Materials Science
The Closer, the Better: Engineering RGB Thermometric Performance in Tb3+, Eu3+-Doped MOFs
The effectiveness of luminescence thermometry, which exploits temperature-induced changes in the spectroscopic properties of phosphor materials for temperature sensing, has been extensively demonstrated. However, from a practical perspective, monitoring temperature-induced variations in the color of the emitted light offers a considerably more straightforward and user-friendly alternative to conventional spectral analysis. In this context, establishing a clear relationship between the thermal evolution of the emission color and the structure of the phosphor is essential for the rational design of visual luminescence thermometers. In this work, we investigate the correlation between the temperature-dependent emission color and the structural characteristics of Tb3+, Eu3+-co-doped metal-organic frameworks (MOFs), with particular emphasis on their potential for filter-free, camera-based thermal sensing. The obtained results demonstrate that, within the investigated series of materials, decreasing the interionic distance between Eu3+ and Tb3+ ions increases the probability of energy transfer and consequently enhances the thermal sensitivity of the camera-based readout derived from the ratio of luminescence intensities recorded in the blue and red channels. These findings establish a direct relationship between the structural characteristics of the luminescent material, the underlying energy-transfer processes, and its thermometric performance. More broadly, this study provides a foundation for the rational design of visual luminescence thermometers with predefined sensing characteristics, opening a pathway toward structure-guided optimization of filter-free, camera-based thermal sensing platforms.
Read the full abstract
Differential Geometry
Finite time singularities of the Ricci flow on compact Kähler surfaces are of Type I
For any volume-collapsing finite-time singularity of a Kähler-Ricci flow on a compact Kähler surface, we show the flow satisfies a Type I curvature bound and classify the corresponding tangent flows. Combined with previous results, this shows that any finite-time singularity of a Kähler-Ricci flow on a compact Kähler surface is of Type I.
Read the full abstract
Cryptography and Security
When Agents See Differently: Exposing UI Desynchronization Threats in Mobile Agents
Mobile agents may act on interface content that users cannot see or easily notice, making their actions harder to oversee. We characterize this gap as human-agent UI desynchronization and investigate how attackers can exploit it through perturbations embedded in applications before deployment. Beyond accessibility metadata, we identify two mechanisms that expose misleading cues to screenshot-based agents: content rendered in display-occluded regions under compatible device configurations, and low-contrast text that remains encoded in screenshots but is difficult for users to notice. We develop an automated framework that searches application-specific perturbation strategies, optimizes their content using representative tasks, and realizes the perturbations in deployable applications. The perturbation content remains fixed at runtime and requires neither access to future user instructions nor detection of agent use. Using a benchmark of 546 tasks across 13 applications, we evaluate five mobile-agent frameworks and three backbone models. The attacks achieve average misleading rates of 77.4% in static observation-space evaluation and 67.2% in dynamic application-level evaluation, where success denotes selection of an attacker-designated decoy control. We invited 195 participants to assess the perceptibility of our visual perturbations and found that none spontaneously noticed the low-contrast text. These findings expose a security gap between human-visible interfaces and agent-observable representations, showing that inconspicuous application content can redirect delegated actions even without runtime adaptation.
Read the full abstract
Distributed Computing
The Price of Random Access: Measuring Block Granularity Across Four Compressed Formats
Random access into compressed data is normally bought with density. We measure the exchange rate. Across four formats and nine axes on a common corpus, the cost of cutting a 254 MB archive into independently addressable 16 KiB units is 1.632% of the archive for an absolute-offset format against 6.57% for seekable zstd, and the gap widens as the unit shrinks: at 4 KiB, 5.33% against 10.06%. Because the cost is small, several properties follow that are usually unavailable: splitting an archive is free and occasionally profitable (-0.28% on tiled input), append needs no format change, seek latency does not depend on position, and one archive is read by both a CPU and a GPU decoder. We give three structural results with proofs and bit-perfect verification - that the repeat-distance chain of an LZ77 parse forms a substitution monoid and is therefore prefix-scannable without touching the bitstream, that self-overlapping matches are periodic rather than chained, and that dependency depth admits an encoder-enforced bound - and we report each measured limit together with the mechanism that sets it. Seventeen rejected directions are listed with their numbers, including one that improved density by 26% and was declined. Every claim carries a level: reproducible by command, measured with a stated reason, or estimated. The measurement tool is released separately (DOI 10.5281/zenodo.22713364) with 435 provenanced records.
Read the full abstract
Artificial Intelligence
LSREP: A Longitudinal State-Replay Protocol for Evaluating Conversational Memory, with ICE v2 as an Audited Local-First Architecture
Conversational memory changes during use, so endpoint question answering alone cannot establish how a persistent state accumulates, ages, or incorporates revisions. We introduce LSREP, a Longitudinal State-Replay Evaluation Protocol combining ordered replay, explicit lifecycle schedules, repeated probes, evolving reference answers, and mechanism-fidelity checks. Its architectural case study is ICE v2, a local-first memory middleware with typed stores, retrieval fusion, and dynamic context budgets. The private, single-user instantiation contains 1,985 turns, 219 distinct probes, and 1,211 probe-checkpoint observations across 52 checkpoints. On three ordinary-density datasets, ICE v2 has a near-zero mean quality difference from vector-RAG while selecting 32% fewer fragments but using 6.6% more estimated prompt tokens. A fourth, dense dataset exposes catastrophic failures of the unbudgeted baseline. The fidelity audit limits attribution: procedural retrieval is defective, several mechanisms are unexercised, and graph utility is not established. In a complementary matched public diagnostic, ICE v2 loses decisively to pure vector-RAG on LongMemEval: 50.8% versus 72.8% in the evidence-only oracle and 43.0% versus 69.5% in full-S. Paired differences are -22.0 points (95% CI [-26.6, -17.4]) and -26.5 ([-31.3, -21.8]). Conservative abstention accompanies severe multi-session and temporal failures. ICE uses less context in this diagnostic, establishing a quality-cost trade-off rather than superior efficiency. Together, replay, fidelity auditing, and public endpoint testing expose distinct failure modes that neither architectural descriptions nor aggregate scores identify alone.
Read the full abstract
Hardware Architecture
SpecLens: LLM-Based Verilog Generation with Specification-Derived Constraints via Behavioral Divergence
Large language models (LLMs) have recently shown promise in Verilog generation, but producing functionally correct RTL directly from natural-language specifications remains a highly challenging task. Existing approaches improve LLM-based Verilog generation mainly with retrieval-augmented generation (RAG), self-planning, or few-shot prompting. However, these methods focus primarily on external or generic forms of enhancement rather than strengthening the specification with task-specific constraints. In this work, we propose SpecLens, an automated framework for LLM-based Verilog generation that derives specification-driven constraints by analyzing behavioral divergence among multiple candidate implementations, using the original specification as the only external semantic source during generation. On the VerilogEval v2.0 spec-to-RTL benchmark, SpecLens achieves a functional pass@1 ratio of 86.2% with o3-mini-medium and 89.4% with o3-mini-high. This corresponds to a 3.6 percentage-point gain over the SOTA prompting method with o3-mini-medium and a 3.8 percentage-point gain over the SOTA behavioral divergence method with o3-mini-high. In addition, on RTLLM v1.1 and v2.0, analysis shows that SpecLens is more specification-faithful and less prone to benchmark-aligned priors. SpecLens achieves 100% syntactic correctness on VerilogEval v2.0, 86.2% on RTLLM v1.1, and 88% on RTLLM v2.0, even without using costly compile-repair loops to revise generated code iteratively. The code is open source and available at https://anonymous.4open.science/r/SpecLens-4632/readme.md.
Read the full abstract
High Energy Physics (Phenomenology)
Searching for new physics with contact-free transitions in muonic atoms
We present a feasibility study demonstrating how recent advances in quantum-sensing technologies can facilitate stringent comparisons between theoretical predictions and experimental measurements of contact-free transitions in muonic atoms. Such comparisons can probe previously unexplored regions of the parameter space governing spin-independent muon-proton interactions and disentangle the extraction of fundamental constants from searches for physics beyond the Standard Model.
Read the full abstract
Computer Vision
PriorPose: Reference-Guided Joint Deformation and Alignment for Category-Level Object Pose Estimation
Category-level object pose estimation seeks to recover a similarity transform $(R,t,s)$ for unseen instances without instance-specific CAD models. Most competitive methods are correspondence-based: prior-free variants regress canonical (NOCS) coordinates directly from local observations and implicitly memorize the canonical frame in the weights, which ties the parameters to category-typical orientations and hurts generalization under distribution shift; prior-based variants introduce a category prior but typically follow a serial deform-then-align pipeline, where underconstrained canonical completion can corrupt correspondences and induce error cascades in pose. We propose PriorPose, a reference-guided correspondence framework that keeps the category prior explicit and solves canonicalization and alignment jointly in a shared feature space. A reference-guided seeded transformer embeds the partial observation and the category prior as token sets and fuses them via geometry-aware seeds, from which the network jointly predicts a per-point NOCS field for visible points and a canonical deformation of the prior that reconstructs a full canonical instance, while a deep pose head regresses $(R,t,s)$ from the induced correspondences. A two-part shape consistency objective, with canonical-space and camera-space consistency losses, couples correspondence, deformation, and pose, reducing reliance on memorized canonical orientations and avoiding deform-then-align error cascades. Experiments on standard and larger-category benchmarks demonstrate that PriorPose sets new state-of-the-art results on most evaluated metrics, especially under strict pose thresholds, while remaining competitive on relaxed pose and IoU metrics and showing improved robustness under shape variation and domain shift.
Read the full abstract
Quantum Physics
Improved Separations between Quantum and Classical Communication Complexity of Total Functions
We refine Gavinsky's framework (arXiv:2608.18784) for exponential separations between quantum and randomized communication complexity of total functions and obtain larger separations: polylogarithmic quantum communication versus $\tilde\Omega(\sqrt n)$ randomized communication with two quantum messages, and versus $\Omega(n^{1-\varepsilon})$ for every fixed $0<\varepsilon<1$ with more quantum messages.
Read the full abstract
Materials Science
Electrical Probing of Sub-Néel Spin Dynamics in Two-Dimensional Antiferromagnets Using Graphene Heterostructures
Low-dimensional antiferromagnetic van der Waals materials have emerged as a versatile platform for exploring exotic spin dynamics and magnetic phases, yet electrically accessing these phenomena remains a major challenge because of their vanishing net magnetization and highly insulating nature. Here, we demonstrate that graphene can act as an ultrasensitive electrical transducer of hidden spin dynamics in two-dimensional antiferromagnets. By integrating graphene with the van der Waals antiferromagnet FePS$_3$, low-temperature transport measurements combined with magnetic-field and gate-voltage control reveal multiple resistance anomalies well below the Néel temperature. Their distinct temperature, magnetic-field, and carrier-density dependences enable us to associate these anomalies with magnon excitations and with a low-temperature magnetic reconfiguration of the antiferromagnetic state, both of which remain largely inaccessible to conventional magnetometry. Density functional theory calculations further show that competing antiferromagnetic spin configurations in FePS$_3$ are nearly degenerate in energy while producing markedly different electronic responses in the adjacent graphene layer. The pronounced electrostatic tunability of these signatures demonstrates that graphene directly transduces interfacial magnetic dynamics into an electrical signal. Our work establishes graphene/antiferromagnetic van der Waals heterostructures as a versatile platform for the electrical readout of spin dynamics in two-dimensional magnets.
Read the full abstract
Robotics
CorrRisk-WM: Corridor-Conditioned Risk World Modeling for Safety-Critical Trajectory Planning
Safe local planning requires forecasting surrounding-agent motion and evaluating candidate-specific risks, since identical agent motion can pose different risks to different ego trajectories. We present CorrRisk-WM, a planning-oriented partial world model coupling environment evolution with supervised intrusion and near-miss prediction over bounded candidate-trajectory corridors. A latent environment model recursively predicts agent states and updates agent-agent and agent-map interactions. Each candidate queries the evolving environment through footprint- aware geometry and learned agent-corridor representations. A lightweight recurrent risk module uses temporal context to estimate per-slice hazards; survival aggregation yields first-entry and horizon-level event probabilities. On 29,176 scenarios from 100 Waymo validation shards, CorrRisk-WM achieves intrusion average precision (AP) of 0.8567 and 1-m near-miss first-entry AP of 0.8671. In baseline comparisons, it attains the highest near-miss AP at all three distance thresholds and the lowest observed open-loop collision rate (4.88%), with route progress of 15.35 m. Across three seeds, removing dynamic environment modeling or candidate-conditioned geometric interaction reduces mean intrusion AP from 0.8590 to 0.7624 and 0.7252, respectively. These results support coupling environment evolution with candidate-conditioned geometric reasoning for risk prediction and safety-oriented candidate selection.
Read the full abstract
Data Structures and Algorithms
A deterministic $(2 + \varepsilon)$-approximation for directed feedback vertex sets in tournaments
We nearly settle the polynomial-time approximability of the Directed Feedback Vertex Set problem in tournaments. This problem is Vertex Cover-hard, and thus cannot have a $(2 - \varepsilon)$-approximation for any $\varepsilon > 0$ in polynomial time assuming the Unique Games Conjecture. In the past 28 years, several works have attempted to attain this approximability barrier of 2, and have designed algorithms with smaller and smaller approximation factors. This includes a $5/2$-approximation by Cai, Deng and Zang (FOCS 1998, SICOMP 2001); a $7/3$-approximation by Mnich, Vassilevska Williams and Végh (ESA 2016), another $7/3$-approximation by Aprile, Drescher, Fiorini and Huynh (DAM 2023), and a $9/4$-approximation by Ghorbani and Mnich (ICALP 2026). Our main result improves upon all of those works: we give the first deterministic polynomial-time $(2+\varepsilon)$-approximation for Directed Feedback Vertex Set in tournaments, for all $\varepsilon > 0$. We thereby almost answer an open question by Lokshtanov, Misra, Mukherjee, Panolan, Philip and Saurabh (SODA 2020) who asked for a deterministic 2-approximation in polynomial time. Furthermore, we extend our result to the broader class of quasi-transitive digraphs
Read the full abstract
Artificial Intelligence
VideoMM: Adaptive Macro-Micro Inference for Efficient Video MLLMs
Scaling Multimodal Large Language Models (MLLMs) to long-form video understanding is bottlenecked by the explosion of visual tokens, which saturates context windows and incurs prohibitive costs. Current solutions predominantly rely on auxiliary models for token reduction but face a fundamental dilemma: lightweight encoder-driven approaches often overlook critical semantic information, whereas heavyweight MLLM-driven reduction negates the efficiency gains. {In this work, we identify a more fundamental inefficiency underlying this dilemma: while fine-grained visual details are essential for detailed understanding, they are largely redundant for the preliminary task of selecting semantically relevant regions. } Motivated by this, we introduce VideoMM, which marks a paradigm shift from model-centric downsizing to adaptive perceptual granularity. Specifically, our framework {decouples selection from reasoning} by executing semantic filtering on a cost-effective Macro Proxy (derived from downscaled frames), and projecting the selected regions onto high-fidelity Micro Tokens for detailed understanding only when necessary. Extensive evaluations show that VideoMM significantly outperforms existing solutions. It achieves a 6.13$\times$ speedup and a 7.4% accuracy gain over full-context baselines on LongVideoBench, and further accelerates inference by 2.73$\times$ over current leading methods, establishing a highly scalable paradigm for long-video understanding. Our code is available at: https://github.com/adfh917k/VideoMM.
Read the full abstract
Fluid Dynamics
Rotation Collision based Quantum Lattice Boltzmann Methods
In the existing quantum algorithms for the lattice Boltzmann method, resolving the unitarity problem of the BGK collision operator from first principles remains a fundamental challenge, and a systematically constructed unitary alternative that reproduces the BGK relaxation structure to leading order has not yet been established in the literature. In this work, we propose a novel quantum lattice Boltzmann method (QLBM) based on the rotation collision operator, in which the non-unitary BGK relaxation is replaced by a unitary rotation in the amplitude space of the distribution function, and the corresponding gate-level quantum circuits are also constructed. Specifically, the rotation collision operator is developed for both the D2Q5 model of the convection-diffusion equation and the D2Q9 model of the incompressible Navier–Stokes equations. It is worth noting that, for the D2Q5 model, the equilibrium-state preparation circuit can be precompiled and reused, and the resulting unitary blocks can be sequentially composed once the state-dependent collision parameters are specified. Finally, some numerical experiments are performed to validate the developed QLBM, demonstrating its accuracy and effectiveness.
Read the full abstract
Earth and Planetary Astrophysics
Discovery of radio emission from the exoplanet $\beta$ Pictoris b
Planetary magnetic fields shape atmospheric escape, mediate interactions with stellar winds, and encode information about planetary interiors, yet they have not been directly measured for planets beyond the Solar System. A direct observable signature is auroral radio emission produced by the electron cyclotron maser instability, whose highest emitted frequency is set by the magnetic field strength at its source. Although auroral radio bursts are observed in Solar System planets and in some ultracool dwarfs, no radio detection has previously been unambiguously localized to an extrasolar planet rather than its host star. Here, we report the first direct detection of auroral radio emission from an exoplanet, the giant planet $\beta$ Pictoris b, with the MeerKAT array. We detect rapid, recurring, and highly circularly polarized bursts, as well as persistent emission, at frequencies of 0.85 to 3.5 GHz. We identify the emission as electron cyclotron maser radiation, which implies a magnetic field of $\gtrsim 1.25$ kG at the planet, the first such direct field strength measurement for an exoplanet.
Read the full abstract
Cosmology and Nongalactic Astrophysics
Cosmological information from field-level analysis in redshift space
The field-level analysis of galaxy clustering with a forward model based on the Effective Field Theory of Large Scale structure provides cosmological measurements at optimal statistical precision which are simultaneously robust with respect to theoretical uncertainties regarding galaxy formation. Yet, the quantitative gains of field-level analysis in the perturbative regime over the current state-of-the-art, set by the combination of power- and bispectrum, are not obvious, and they depend on analysis choices, the cosmological model, and the observed galaxy population. We therefore quantify the precision improvement from field-level analysis over power- and bispectrum from redshift-space snapshots that closely resemble the DESI LRG sample. Our mock data are created with the LEFTfield forward model, which we also use for the subsequent field-level analysis and for a Fisher forecast of the power- and bispectrum precision. We find significant improvements from the field-level analysis over the power- and bispectrum for a $\Lambda$CDM cosmology; in particular the primordial fluctuation amplitude can be measured twice as precisely. Precision gains at the field-level are even more pronounced for extended cosmologies with a more flexible dependence between power spectrum shape and structure growth; they reach up to a factor of three in the primordial amplitude and a factor of two in parameters that capture deviations from $\Lambda$CDM. Our results highlight the potential of field-level analysis for future discoveries. Realizing this potential will require substantial developments on the modeling of observations and observational systematics as well as on the numerical inference techniques.
Read the full abstract
Optics
Singly resonant InGaP microresonators for efficient, low-threshold second-order nonlinear optics
Strong $\chi^{(2)}$ interactions at low optical powers are key to scalable nonlinear and quantum photonics. Although doubly resonant microresonators exhibit exceptional efficiencies, they require simultaneous resonance and phase matching of widely separated optical frequencies, making them inherently sensitive to fabrication and operating conditions. Singly resonant cavities eliminate this constraint by resonating at only the fundamental frequency while the second-harmonic field propagates in a single pass, but they have traditionally sacrificed nonlinear efficiency. Here, we demonstrate a singly resonant InGaP-on-insulator microresonator that overcomes this tradeoff. Combining the large $\chi^{(2)}$ nonlinearity of InGaP with high-quality-factor resonators, we achieve efficient and widely tunable second-harmonic generation, broadband quantum-frequency-comb generation, and low-threshold optical parametric oscillation. Unlike conventional centimeter-long singly resonant devices, our millimeter-scale InGaP devices deliver nonlinear performance comparable to, and even exceeding, doubly resonant systems. By overcoming the conventional efficiency-robustness tradeoff of singly resonant devices, this work opens a new route to low-power, broadband, and widely tunable $\chi^{(2)}$ nonlinear and quantum photonics.
Read the full abstract
Analysis of PDEs
Local Well-posedness of Free Boundary Problems for the Euler–Monge–Ampère Equations
We study the free-boundary Euler–Monge–Ampère system as a conservative relaxation of ideal incompressible fluid motion. The force is determined on the actual fluid domain by a Monge–Ampère equation coupled to a nonlinear boundary condition. For each fixed relaxation parameter, we establish local well-posedness for uniformly convex initial domains of class $C^{2,\alpha}$, densities in $C^{1,\alpha}$, and arbitrary initial velocities in $C^{2,\alpha}$. The solution retains these spatial regularities, and the force potential belongs to $C^{3,\alpha}$ up to the moving boundary. Within uniformly bounded data families, the solution depends continuously on the initial data at every lower Hölder exponent.
Read the full abstract
Number Theory
Distribution of squarefree integers with double congruence conditions
Given a positive integer $M$ with reduced residue system $\Phi_M$, we partition the set of squarefree integers according to some congruence conditions on the number of prime factors in each class $\phi \in \Phi_M$, and prove two relevant equidsitribution results in this setting. We discover the bias phenomenon in some special cases, and formulate a conjecture with numerical support.