Machine Learning
SpecBraM: What Should an EEG Foundation Model Predict? Masked Band-Power Prediction versus Waveform Reconstruction
Peng Xie, Yequan Bie, Jianda Mao et al. (+1 more)
Self-supervised
EEG models often reconstruct masked waveforms or predict discrete codes. We study a task-aligned alternative: masked band-power prediction (MBP), which predicts fixed narrow-band log spectral energy for masked channel-time patches. This target retains rhythm power relevant to sleep staging while avoiding phase-sensitive waveform reconstruction and a learned codebook. Across three pretraining seeds, we compare band-power and waveform targets with matched backbones, pretraining data (2,388 hours), and training steps, including a 2x2 tokenizer-by-target design. On ISRUC and HMC sleep staging, MBP exceeds raw- and band-waveform reconstruction by 1.6-2.8 balanced-accuracy points with all labels and 4.7-7.3 points with 1% of labels under a strict linear probe; the target effect exceeds the tokenizer effect. Its frozen features reach 0.7916/0.7425 balanced accuracy, versus 0.7636/0.7227 for a matched rich handcrafted spectral baseline, although the gap is about one point with 1% of labels. Full fine-tuning reaches 0.8107/0.7669. The gains do not extend to every task with spectral cues, including motor imagery, depression screening, and vigilance regression. These results support choosing pretraining targets to match the physical quantities and spatial and temporal scales relevant to downstream labels.
Read the full abstract ▾
All authors Peng Xie, Yequan Bie, Jianda Mao, Kani Chen
Human-Computer Interaction
From Written Response to Dialogue with AI: How Activity Format, Interaction Modality, and Language Impact Student Learning and Engagement
Deepak Varuvel Dennison, Connie Zhang, Rene Kizilcec et al. (+1 more)
The widespread availability of LLMs is challenging written learning activities, as students can increasingly generate responses without necessarily engaging with the learning content. Conversational AI creates an opportunity to redesign these activities as dialogue, while
multilingual capabilities may make such dialogue more accessible to students learning through a non-native
language. We conducted a field study with 305 native Kannada-speaking undergraduate students at English-medium institutions in Karnataka, India. We compared written response activities with text- and voice-based dialogic activities with AI, each conducted in English-only or bilingual Kannada-English settings. Students who completed dialogic activities spent more time on the activities, contributed more, and reported greater interest and self-efficacy than those completing written responses, although fewer students completed the dialogic activities overall. Knowledge increased across all conditions, with no reliable differences in gains between activity formats or
languages.
Language shaped participation differently across modalities: bilingual interaction was particularly beneficial in voice dialogue, where it reduced articulation difficulties, increased turns demonstrating understanding, and reduced conversation abandonment. However, students also valued English because of its connection to their academic and professional aspirations. These findings show that designing dialogic learning with AI requires more than choosing between writing and dialogue, voice and text, or English and students' native
languages. We highlight opportunities to give learners greater control over modality, information, and pace, and to use native
languages as translanguaging support rather than as a replacement for English.
Read the full abstract ▾
All authors Deepak Varuvel Dennison, Connie Zhang, Rene Kizilcec, Aditya Vashistha
Instrumentation and Methods for Astrophysics
The First Decade of Breakthrough Listen
David H.E. MacMahon and Daniel J Czech
Breakthrough Listen (BL), launched in July 2015 with a 10-year, \$100M commitment from the Breakthrough Prize Foundation, is the most comprehensive search for technosignatures ever conducted. This paper reviews the program's first decade from the facilities and instrumentation perspective: the digital backends and data recorders, the signal-processing pipelines, the data archive, and the observatory partnerships that made the science possible. We organize the decade into three architectural eras. In Generation 1 (2016--2019), BL deployed packetized raw-voltage wideband recorders on the 100-m Green Bank Telescope and the 64-m Parkes telescope, enabling targeted surveys of thousands of nearby stars across $\sim$0.7--8 GHz. In a network-expansion phase (2020--2023), BL extended its instrumentation to partner facilities including the Sardinia Radio Telescope and international LOFAR stations, and developed verification frameworks that proved essential when the program's highest-profile signal candidates emerged. Since 2023, BL has operated in a fully commensal era: Ethernet-based, commodity-GPU backends riding on routine observatory operations: COSMIC at the Karl G. Jansky VLA, a revived Allen Telescope Array with deployed real-time deep-learning pipelines, and an autonomous multi-beam commensal survey at MeerKAT (BLUSE; $>$1.2 million pointings since mid-2022). Over the decade, capturing data at ever higher rates forced a systematic approach to compression and archiving; the storage estate grew to $\sim$42 PB of capacity ($\sim$31 PB in use) across seven systems on four continents by March 2026. We conclude with engineering lessons (commodity hardware over bespoke hardware, open data as a first-class requirement, commensal science as backend validation, and verification frameworks built before they are needed) and with the outlook for SKA-era commensal technosignature science.
Read the full abstract ▾
Solar and Stellar Astrophysics
High-Angular-Resolution Survey of Stars within 18 pc of the Sun: Part I
F. Carolina Rojas-Galindo, Valeri G. Orlov, Rene A. Mendez et al. (+1 more)
We present the rationale, design, methodology, and observational facilities of a high-angular-resolution imaging survey of
stars within 18~pc of the Sun. Our comprehensive sample consists of 2047
stars compiled from
Gaia eDR3 and complementary catalogs. The main goal is to observe as many
stars from this sample as possible using high-angular-resolution techniques, considering their inherent limitations, to perform astrometry of known binary systems and determine detection limits for secondary components for each observed
star. This approach may also allows us to identify previously unresolved
stellar companions. Observations were carried out using the 2.1-m
telescope at OAN-SPM in the North and the 3.58-m NTT in the South, employing high-speed cameras for speckle imaging. We obtained observations of 703
stars with V < 14 mag at OAN-SPM, and 645
stars with I < 16 mag at the NTT, of which 140
stars were observed in both hemispheres, for a total of 1208 unique
stars observed. In this paper: (1) we present the construction of the catalog of 2047
stars within 18 pc; (2) using a control sample of 70 known close binaries within 18 pc with separations 1", we show that selecting targets based on
Gaia quality parameters commonly used as binarity indicators–RUWE, ipd_frac_odd_win, and ipd_frac_multi_peak–can miss a significant fraction of binaries, justifying our unbiased, volume-limited survey; and (3) we present the results of pilot observations conducted with the 2.1 m
telescope at OAN-SPM in July 2022. A full analysis of the complete sample will be presented in of forthcoming papers.
Read the full abstract ▾
All authors F. Carolina Rojas-Galindo, Valeri G. Orlov, Rene A. Mendez, Wolfgang Brandner
Artificial Intelligence
In With the Old: Enhancing 'Classical' Document Automation with Generative AI
Marc Lauritsen and Hannes Westermann
Software-based legal assistance systems have leveraged many different forms of knowledge representation and
reasoning. This article explores how document automation services rooted in expert system style and other symbolic approaches can usefully enhance and be enhanced by current generative AI approaches. We discuss the possible benefits and challenges, and report on preliminary experiments in using large
language models to identify and fix issues in texts written by laypeople.
Read the full abstract ▾
Algebraic Geometry
Potential density of rational points on sextic double solids
Ivan Cheltsov and Yuri Tschinkel
We provide examples of smooth sextic double solids with potentially dense sets of rational points, over any field of characteristic zero.
Molecular Networks
IMPPAT 3.0: An updated FAIR database of phytochemicals and formulations of Indian Medicinal plants
Shanmuga Priya Baskaran, Ajaya Kumar Sahoo, Priyotosh Sil et al. (+6 more)
Ayurvedic formulations represent a rich source of traditional knowledge, encompassing distinct therapeutic approaches, medicinal ingredients, and underlying principles of drug action. However, systematic integration of this knowledge with standardized modern biomedical terminology and resources remains limited. Here, we present IMPPAT 3.0, an updated version of the Indian Medicinal Plants, Phytochemistry And Therapeutics (IMPPAT: https://cb.imsc.res.in/imppat/) database that extends its scope by incorporating curated and harmonized information on Ayurvedic formulations from authoritative sources, while expanding its coverage of medicinal plants, phytochemicals, and therapeutic use terms. IMPPAT 3.0 further enriches plant and phytochemical information with annotations on clinical trials, patents, bioactivity,
protein targets, spectral data, plant image links, and AyuCaRe reports. The compiled data is also organized as IMPPAT-KG, a knowledge graph that enables exploration of relationships among IMPPAT entities. We demonstrate the utility of the resource through a network medicine analysis of single herbal drugs (SHDs) reported for rheumatoid arthritis (RA), revealing significant proximity of their
protein targets to RA-associated genes, and pinpointing of phytochemical pairs with potentially complementary effects on RA pathogenesis. In conclusion, by integrating traditional medicinal knowledge, IMPPAT provides a FAIR-compliant ethnopharmacological platform for systematic investigation of Indian medicinal plants and Ayurvedic formulations for drug discovery applications.
Read the full abstract ▾
All authors Shanmuga Priya Baskaran, Ajaya Kumar Sahoo, Priyotosh Sil, Rahul Tiwari, Nikhil Chivukula, Sabrina Elsa Eapen, Geetha Ranganathan, Preeti Semwal, Areejit Samal
Human-Computer Interaction
MRPilot: Supervising and Intervening LLM-Based Multi-Robot Teams through Mixed Reality
Xiaoran Yang, Xun Qian, Yang Zhan et al. (+3 more)
Large
language models (LLMs) let users direct heterogeneous multi-
robot systems (MRS) through natural
language, but make task interpretation,
robot assignment, and coordination difficult to inspect and change. Based on a formative study with 12 non-expert users, we developed MRPilot, a mixed reality system organized around four stages of supervision and intervention. MRPilot represents
robot-team plans and execution states as structured commitments shared across synchronized situated and overview views. Across four stages, it helps users resolve ambiguous references (Forming), review plans before execution (Reviewing), monitor distributed execution (Following), and make
robot-level or team-level changes when problems arise (Repairing). In a within-subjects study with 20 participants in a virtual reality-simulated home, MRPilot reduced workload, increased situational awareness, transparency, trust, and perceived control compared with a conventional LLM-based conversational interface using the same LLM planner and
robot capabilities. We provide design implications for multi-scale intervention, adaptive supervision, and calibrated reliance in LLM-based MRS.
Read the full abstract ▾
All authors Xiaoran Yang, Xun Qian, Yang Zhan, Nathan Tran, Ziyi Liu, Qiao Jin
Computers and Society
Can Power Draw Constrain Covert Compute? Limits of Analogue Verification for AI Governance
Tom Kimpson, Mauricio Baker and Emlyn Graham
Frontier AI treaties or agreements on limiting computation require external verification; an external auditor must be able to confirm how much computation actually ran and that parties are adhering to the agreement. Analogue, off-chip measurements such as power draw provide an information channel for verification. It is unknown how well these analogue channels can constrain computation against an adversary who actively tries to subvert the audit. We derive a closed form for $\beta$, the largest hidden computation a power trace cannot exclude, as a fraction of the declared machine capacity. Measurements on NVIDIA A100 GPUs constrain $\beta = 1.16$ in the worst case, while
adversarial matched-energy strategies are shown to hide at least $\beta = 0.41$ of compute. Analogue power measurements alone therefore constrain compute weakly. Additional restrictions granted by the threat model, such as the ability of the verifier to re-execute the declared work at an observed operating point, let the verifier push $\beta$ down to $0.059$ in the maximally restricted case. This gives a quantitative estimate of what analogue measurements can contribute to compute verification.
Read the full abstract ▾
Machine Learning
Adapting to Changes in Agent Behavior via Finite-Depth Policy Sensitivity
Lan Shi, Daigo Shishika and Xuan Wang
Adapting a reinforcement learning policy to changes in another
agent's behavior typically requires a large amount of new interaction data. Policy sensitivity provides a first-order prediction of how a locally optimal policy changes with a behavioral parameter, but its computation requires second-order derivatives whose effects propagate across future interactions. We develop a finite-depth framework to estimate this sensitivity by approximating the policy Hessian and mixed derivative using information from a reference environment. The method features an adjustable propagation depth which determines where derivative propagation along the trajectory is truncated. We characterize the derivative contributions omitted by finite-depth propagation and derive truncation-error bounds for the approximated derivatives and resulting policy sensitivity. The bounds are nonincreasing with propagation depth and vanish at full-horizon propagation. Using a belief-driven pursuit-evasion game as a validation scenario, the proposed method generally achieves lower derivative-estimation errors as the propagation depth increases and outperforms the baseline methods in both estimation accuracy and policy adaptation. The sensitivity-based initialization improves zero-shot return over direct transfer, and also shows advantages for the subsequent fine-tuning in the target environment.
Read the full abstract ▾
Robotics
Risk-Sensitive Crowd Navigation with Adaptive Ellipsoidal Conformal Prediction
Ruihan A. Li, Ziyao Guo and Yingying Li
Safe crowd
navigation under distribution shift requires uncertainty representations that capture structured human-motion prediction errors and safety objectives that account for rare but consequential failures. Existing uncertainty-aware methods typically represent prediction errors using isotropic regions, which can be either overly conservative or poorly aligned with directional motion uncertainty. We introduce a risk-aware
navigation framework that uses anisotropic conformal ellipsoids to translate structured prediction uncertainty into an episode-level conditional value-at-risk (CVaR) signal that regulates the Lagrangian safety penalty. In particular, adaptive ellipsoidal conformal prediction (AECP) captures directional prediction errors and adaptively calibrates uncertainty regions under distribution shift, while the resulting CVaR-regulated
navigation policy is optimized using Lagrangian proximal policy optimization. We evaluate our proposed method under both in-distribution settings and out-of-distribution (OOD) settings involving shifts in pedestrian motion patterns. Compared with state-of-the-art baselines, our method maintains competitive in-distribution performance while improving success rates by 5.68-7.44 percentage points and reducing collision rates by 5.44-6.64 percentage points across OOD settings. We further deploy the trained policy without fine-tuning on a physical
robot with onboard perception and CPU-only inference, showing that the full pipeline is feasible in physical crowd
navigation.
Read the full abstract ▾
Artificial Intelligence
PsyCIDRA: A Dual-Agent Framework for Psychiatric Interviewing and Diagnostic Reasoning
Milad Mohammadi, Fatemeh Akrami Shamsabadi, Zahra Mohseni et al. (+4 more)
Large
language models show promise in clinical
reasoning, but psychiatric interviewing requires guiding an evolving conversation. Their ability to carry out this interactive assessment remains less studied. We present PsyCIDRA, a dual-
agent framework linking free-form psychiatric interviewing with diagnostic
reasoning for expert review. Its interviewer
agent uses tools to maintain working notes, load expert-written skills, and retrieve ICD-11 references to guide inquiry. Its diagnostic
reasoning agent then receives the completed interview transcript and reports hypotheses alongside supporting, conflicting, and missing evidence, withholding a final hypothesis when none is sufficiently supported. Using patient profiles generated with PsyCPG, we first evaluate PsyCIDRA in simulation. Across four models on 53 evaluation cases, it achieves higher diagnostic agreement than direct prompting. On 81 held-out simulated cases, rank-1 accuracy is 60.5% versus 51.9%. In a blinded study of 101 human participants in separate arms, PsyCIDRA agrees with psychologists on whether to propose a diagnostic hypothesis in 79.6% of cases, compared with 65.4% for direct prompting. Together, these findings support the potential of LLM
agents to assist psychiatric assessment through free-form dialogue. By examining diagnostic
reasoning, interview quality, and safety together, this study contributes to understanding the capabilities and limitations of psychiatric interview
agents.
Read the full abstract ▾
All authors Milad Mohammadi, Fatemeh Akrami Shamsabadi, Zahra Mohseni, Amirhossein Safdarian, Malekfarhad Malek, Hadi Moradi, Hesham Faili
Robotics
SURGE: Sonar-fUsed Reconstruction and localization via image-gated Graph Estimation
Mohammed Ibrahim M, Vallabh Deogaonkar, Trung Dong et al. (+3 more)
Remotely operated vehicles (ROVs) are widely used to explore and inspect
underwater environments such as caves, shipwrecks, and submerged infrastructure. These missions require accurate 3D understanding of the surrounding environment, which depends on both reliable vehicle localization and metric scene reconstruction. However, external positioning is often unavailable
underwater, requiring small ROVs to rely primarily on onboard perception. Optic
vision provides rich visual and
geometric information but suffers from scale ambi- guity and trajectory drift, whereas 2D imaging sonar provides metric range but incomplete 3D geometry. Existing
underwater reconstruction approaches typically address these limitations separately or assume known sensor poses, leaving localization and reconstruction disconnected. We present SURGE, a camera sonar framework that jointly estimates the ROV trajectory and target location by integrating visual and acoustic observations within a factor graph, then uses the recovered metric poses for sonar Gaussian splatting. Experiments on real
underwater RGB sonar observations show that SURGE substantially improves localization consistency over conventional
vision based pose estimation and produces a more compact, natively metric reconstruction than RGB Gaussian splatting baselines.
Read the full abstract ▾
All authors Mohammed Ibrahim M, Vallabh Deogaonkar, Trung Dong, Jane Shin, Abhilash Somayajula, Xiaomin Lin
Number Theory
Gaps theorems for linear forms with cubic coefficients
Alan Haynes
Let $1,\alpha_1,\alpha_2$ be a basis for a cubic number field $K\subset\mathbb{R}$, and for $\tau_1,\tau_2\ge 1$ let $G(\mathbf{\alpha},\mathbf{\tau})$ denote the number of distinct gaps between the fractional parts of the numbers $m_1\alpha_1+m_2\alpha_2$, with $m_1,m_2\in\mathbb{Z}$, $0\le m_1<\tau_1$ and $0\le m_2<\tau_2$. We show that $G(\mathbf{\alpha},\mathbf{\tau})$ is unbounded as $\mathbf{\tau}$ varies. When $K$ is totally real this is deduced from a density
theorem of Shapira for orbits of the diagonal group on the space of
lattices. When $K$ has a complex
embedding we give an explicit construction, which also shows that there are constants $c,\kappa>0$ for which $G(\mathbf{\alpha},\mathbf{\tau})\ge c(\log\max\{\tau_1,\tau_2\})^{\kappa}$ for infinitely many $\mathbf{\tau}\in\mathbb{N}^2$.
Read the full abstract ▾
Machine Learning
Structure, Not Belief: Correlated Thompson Sampling from LLM-Derived Covariance in Combinatorial Semi-Bandits
Vikram Kakaria, Anish Kataria and Anany Kotawala
Combinatorial Thompson sampling (CTS) draws independent posterior samples for every arm, so its exploration dynamics ignore any relation among arms. We study a minimal change to those dynamics: an LLM is queried once for a partition of the arms, the partition becomes a positive-definite correlation
matrix $\Sigma$ through an RBF kernel on cluster ranks, and the per-round posterior sample is drawn with covariance $\Sigma$ while the Beta posteriors are updated from real rewards only, so the LLM shapes how the sampler moves, not what it believes. We give a self-contained
Bayesian regret bound for the idealized Gaussian sampler whose information gain splits into a $K\log T$ term from the $K$-cluster structure and a ridge term that grows to $d\log T$: the $\sqrt{d/K}$ improvement over independent sampling is a finite-horizon transient, exact only as the within-cluster correlation tends to one. The correlated sampler reduces regret by 19% over CTS on 16 synthetic Bernoulli families at $T=2{,}500$ (6-7% at $T=25{,}000$ with data-adaptive kernels) and by 41% on the Microsoft MIND-small news
benchmark ($d=200$ real articles), while pseudo-observation warm starts give nothing. An LLM-free ablation with a simulated oracle of controlled quality shows that on unstructured instances the gain is a property of the kernel shape (a random partition, or a plain tempering of the sampling noise, reproduces it), while belief injection at matched oracle quality never helps.
Read the full abstract ▾
Artificial Intelligence
COMPASS: Finding Where Reasoning Lives in Language Models
Pratyay Dutta, Kowshik Thopalli and Vivek Narayanaswamy
Explicitly eliciting
reasoning substantially improves LLM performance. Existing approaches require a predefined characterization of
reasoning, whether through CoT
prompt design, contrastive CoT directions, or via SAE derived
reasoning features. For mathematical
reasoning with verifiable answers, we show that a much simpler signal suffices, which is the correctness of the model's own direct answer attempts. This signal yields a latent direction that elicits
reasoning. This direction is decodable within the activations of most
attention heads, but only a small subset of them can be effectively intervened. We introduce COMPASS, an inference-time steering method that identifies these heads using a logit-space attribution score and steers their activations along the correctness direction, requiring only per-head activation statistics. Across three model families and multiple math
benchmarks, COMPASS outperforms the activation-steering baselines we compare against, improves GSM8K accuracy by 16 percentage points on average, and approaches CoT accuracy with 20-70% fewer generated
tokens. Interventions transfer without re-fitting to unseen
benchmarks, and ablations show that both the correctness direction and the small set of heads carrying it are necessary, with the effect concentrated in remarkably few heads.
Read the full abstract ▾
Data Structures and Algorithms
Almost-Linear Decremental Single-Source Distance Estimates in Directed Graphs via Cut Balance
Hanqing Li
We give a deterministic reduction for maintaining simultaneous approximate single-source distance estimates in online decremental directed graphs. For positive integer weights in $[1,W]$, the
algorithm maintains an explicit array of integer $(1+\varepsilon)$ upper estimates, identifies unreachable vertices exactly, and answers numerical queries in constant time. Let $N=m+n$, $S=N+\lceil1/\varepsilon\rceil$, and assume $\log W=\operatorname{polylog}(S)$. Initialization and all updates take $O(\Delta)+(N+\Delta_{\mathrm{eff}}+\mathcal{L}/\varepsilon)S^{o(1)}$ time, where $\Delta$ counts raw updates, $\Delta_{\mathrm{eff}}=O(m(1+\log W)/\varepsilon)$ counts filtered updates, and $\mathcal{L}$ measures finite distance growth weighted by the current indegrees of the reachable subgraph. Removed edges and vertices that become unreachable incur no subsequent growth charge. Consequently, the worst-case bound is $O(\Delta)+(N/\varepsilon)S^{o(1)}$, which is almost linear for subpolynomial inverse accuracy. The reduction uses the dynamic minimum-ratio cut and exact reachability
algorithms of van den Brand et al. (FOCS 2024). A degree-weighted clipped logarithmic potential turns constant relative cut balance into accuracy at every target; a successor cut then restores strict feasibility. A distance warm start and the energy released by decreasing return coefficients yield the refined growth bound. Return mass also amplifies the accuracy of the existing change detector. The public estimates can be monotone, with $O(n+\mathcal{J}/\varepsilon)$ array writes for an unweighted finite-growth measure $\mathcal{J}\le\mathcal{L}$. Execution uses rational arithmetic. A separate reduction extends the worst-case guarantee to nonnegative integer weights. The
algorithm maintains numerical estimates and does not provide fast path reporting.
Read the full abstract ▾
Astrophysics of Galaxies
The Rogue One: A Dark Matter-Dominated Dwarf in the Trail of Dark Matter-Deficient Galaxies
Daniel Vaz, Arsen Levitskiy, Duncan Forbes et al. (+6 more)
We present the first measurement of the
stellar velocity dispersion of LEDA 4014647, a compact
dwarf galaxy spatially aligned with the NGC 1052 trail, a linear chain of dark matter-deficient
galaxies (DMDGs) proposed to have formed in a single high-speed
dwarf$-$
dwarf collision $\sim 8$ Gyr ago. Using integral-field spectroscopy obtained with the Keck
Cosmic Web Imager (KCWI), we measure a
stellar velocity dispersion of $\sigma = 15.8 \pm 2.0$ km s$^{-1}$ within the half-light radius ($R_\mathrm{e}$). We derive a dynamical mass within the 3D half-light radius of $M_\mathrm{dyn}(<r_{1/2}) = (1.5 \pm 0.4) \times 10^8\,M_\odot$, a factor of $\sim 3$ larger than the enclosed
stellar mass, implying a DM fraction of $f_\mathrm{DM} = 0.7 \pm 0.1$ at $r_{1/2}$. Full-spectrum
stellar population fitting yields an old ($t \approx 13$ Gyr) and metal-poor ($[\mathrm{M/H}] \approx -1.2$ dex)
stellar population, consistent with independent photometric estimates and predating the proposed collision epoch. LEDA 4014647 is therefore a DM-dominated system, and cannot have formed from the DM-free, shock-compressed gas that produced the proposed trail DMDGs DF2, DF4, and DF9. Its nature, however, remains an open question: while a chance-projection along the trail axis is a possible explanation, its old
stellar population, compact morphology, and DM content are also consistent with the surviving collisionless remnant of one of the progenitor
dwarfs of the
dwarf$-$
dwarf collision. Distinguishing between these two scenarios will ultimately require deeper spectroscopy to tighten the
stellar population and DM
halo constraints, and targeted $N$-body and hydrodynamical simulations tracking the post-encounter fate of the progenitors.
Read the full abstract ▾
All authors Daniel Vaz, Arsen Levitskiy, Duncan Forbes, Aaron J. Romanowsky, Jonah Gannon, Jean P. Brodie, Yimeng Tang, Kenji Bekki, Warrick J. Couch
Machine Learning
Efficient Multimodal Inference through Adaptive Acquisition and Sequential Fusion
Payal Mohapatra, Haodong Yang, Yueyuan Sui et al. (+3 more)
Multimodal systems often encode every available input, even when a subset suffices for prediction. Adaptive acquisition can reduce this cost by using predictions from incrementally fused evidence to decide which modality to encode next and when to stop. However, sequential fusion makes these predictions order-dependent, so decisions based on them may need to distinguish factorially many histories of the same acquired set. We introduce SemARC, which couples a Sequential Modality Aggregator (SeMA) with an Adaptive Runtime Controller (ARC) and uses acquired evidence to select each modality before its encoder runs. SeMA executes only selected encoder and fusion branches, updates a fixed-size state, and predicts after each acquisition without recomputing earlier branches. We supervise every acquisition prefix under randomized modality subsets and orders to encourage consistent predictions across acquisition orders. ARC combines a set-dependent marginal-utility prior with residual fitted-Q learning to select the next available modality or stop, without inspecting unacquired inputs or retaining acquisition order. Across six
multimodal classification
datasets and eleven baselines, SemARC achieves 3.2% higher macro-F1 and 61.4% lower total inference GFLOPs on average relative to each
dataset's most accurate baseline. End-to-end latency falls by 44.0% across GPU and CPU and by 47.2% on Android INT8 relative to the fastest measured baseline, on average. Under varying runtime modality missingness, SemARC still skips available modalities, matching or exceeding the best baseline macro-F1 in 21 of 24 conditions with 14.8% lower total GFLOPs on average. SemARC thus offers a practical path toward efficient
multimodal inference across heterogeneous devices.
Read the full abstract ▾
All authors Payal Mohapatra, Haodong Yang, Yueyuan Sui, Stephen Xia, Benjamin Lundell, Qi Zhu
Data Structures and Algorithms
Extending Tardos's Theorem to Separable Convex Quadratic Programming
Bin Cui, Hanqing Li and Xupeng Miao
For an integer equality
matrix $A\in\mathbb{Z}^{r\times m}$ of binary encoding length $\langle A\rangle$, Tardos's
theorem solves linear programs using $\operatorname{poly}(r,m,\langle A\rangle)$ rational arithmetic operations and comparisons, independently of the right-hand side and objective coefficients. We extend this guarantee to continuous separable convex quadratic programming over $Ax=b$, $x\ge0$: the operation count is independent of the right-hand side, linear costs, and all nonnegative quadratic weights. The
algorithm returns an exact optimal primal-dual pair or a certificate of infeasibility or unboundedness. All intermediate rational numbers have encoding lengths
polynomial in the total input length. As an application, we obtain a strongly
polynomial algorithm for continuous multicommodity flow with shared capacities and quadratic costs of aggregate arc flow, independently of demands, capacities, and cost coefficients. Objective compression and continuous-integer proximity yield a local solver returning a point close to an optimum. We relax nonnegativity on coordinates with zero optimal dual slack, minimize the largest remaining coordinate, and optimize over the relaxed coordinates. A descent LP over the recession cone provides a complementary bound.
Circuit decomposition combines these bounds into a scale ensuring that each local call reveals a new coordinate. At most $m$ calls, followed by two LPs, recover an exact optimum and its dual certificate.
Read the full abstract ▾
Computer Vision
Protective Perturbations Must Survive the Resize: Scale-Robust Image Immunization against Malicious Editing
Zhongliang Guo, Yan Lin, Yifei Qian et al. (+4 more)
While instruction-guided editors built on
diffusion transformers can turn a personal photo into a convincing forgery with a single sentence, protective perturbations aim to make such edits fail before the photo is ever shared. The threat is most acute for the photos people actually share, which have 10 megapixels or more and which current editors first downscale by a factor that the owner does not know. Existing protections are computed at one resolution or averaged over random scales, and they lose most of their effect once the photo is downscaled. They implicitly assume that the editor sees the scale for which they were optimized, or that protecting the average scale protects every scale. We propose SRIM, a protection that remains effective at every scale an editor may use, without knowing its preprocessing and at the same computational cost as standard expectation over transformation. SRIM covers the range of scales implied by the photo size with anchor scales and spends each optimization step on the scale where the protection is currently weakest. A spectral analysis shows that this worst-case protection degrades only logarithmically with the width of the range, a value that averaging over scales cannot reach. Extensive experiments on full-resolution photos and popular instruction-guided editors validate that SRIM gives the strongest protection, outperforming existing methods even with a quarter of their $\ell_\infty$ budget, remaining the strongest under input purification.
Read the full abstract ▾
All authors Zhongliang Guo, Yan Lin, Yifei Qian, Daizong Liu, Ognjen Arandjelović, Jianfeng Dong, Chun Pong Lau
Astrophysics of Galaxies
Complex Organic Molecules in Protostars with ALMA Spectral Surveys (COMPASS) III. CH$_3$OH isotopic fractionation in the low-mass protostar BHR71-IRS1
A. Coutens, F. Cruz-Sáenz de Miera, J. K. Jørgensen et al. (+26 more)
[Abridged] Methanol is a complex organic molecule detected in both ice and gas toward
star-forming regions. Due to its high abundance, its rarer isotopologues, including the deuterated ones, are also commonly detected. Our aim is to determine the column density and deuterium fractionation of methanol in the low-mass protostar BHR71-IRS1. We analyzed data from a large spectral survey of BHR71-IRS1 carried out as part of the ALMA Large Program Complex Organic Molecules in Protostars with ALMA Spectral Surveys (COMPASS). We used the CASSIS software to identify the lines of the methanol isotopologues and constrain their column densities under the assumption of local thermodynamic
equilibrium. We detected CH$_3$OH, $^{13}$CH$_3$OH, CH$_3$$^{18}$OH, CH$_3$OD, CH$_2$DOH, CHD$_2$OH, and CD$_3$OH at the continuum peak position. In addition, CH$_3$$^{17}$OH is tentatively detected, while CD$_3$OD is not detected, although a few faint lines could be present toward a position redshifted from the continuum peak. The column densities of the main isotopologue obtained from $^{13}$CH$_3$OH and CH$_3$$^{18}$OH are consistent, assuming nominal $^{12}$C/$^{13}$C and $^{16}$O/$^{18}$O ratios of 68 and 557, respectively. The CH$_2$DOH/CH$_3$OD column density ratio is equal to 7$\pm$2. The statistically corrected D/H ratio is higher for CH$_2$DOH (1.9$\pm$0.6 %) than for CH$_3$OD (0.8$\pm$0.2 %). The level of deuteration after statistical correction increases with the number of D atoms in the methyl group, reaching 23$\pm$5 % for CD$_3$OH/CH$_3$OH. These trends are similar to other low-mass protostars such as IRAS~16293–2422 and HOPS 373SW, but seem to differ from the eruptive young
star V883-Ori. Similar studies with comparable
datasets will be carried out for the other COMPASS sources to determine if factors such as environmental conditions and evolutionary states impact the deuteration of methanol.
Read the full abstract ▾
All authors A. Coutens, F. Cruz-Sáenz de Miera, J. K. Jørgensen, M. N. Drozdovskaya, J.-E. Lee, A. L. Plunkett, D. Harsono, S. Maret, A. Belloche, J. Ferrer Asensio, M. L. R. van't Hoff, J.-H. Jeong, Á. Kóspál, B. A. McGuire, P. Nazari, S. Spezzano, Z. Telkamp, Y.-L. Yang, H.-S. Yun, S. Zeng, A. Andreu, J. Bergner, C.-H. Kim, N. F. W. Ligterink, Y. Lin, S.-Y. Liu, M. Lützen, P. Marchand, M. Rao
Signal Processing
Comparative Analysis of Filter Bank Waveforms for ISAC Systems: 2D-FFT FB and AFBM
Polianna Basso, Victor Augusto Del Monego, Hyeon Seok Rou et al. (+3 more)
We present a comparative analysis of two promising filter bank multicarrier waveforms for integrated sensing and communications (
ISAC) systems operating in high-mobility environments. In particular, we consider two-dimensional FFT-precoded filter bank (2D-FFT FB) modulation and the recently-proposed affine filter bank modulation (AFBM) waveforms, which exploit different signal representations across the time-frequency, delay-Doppler and affine domains to improve robustness against Doppler effects, each resulting in distinct features. On the one hand, 2D-FFT FB improves spectral localization under high Doppler conditions, while AFBM combines chirp-based modulation with filter bank processing to achieve low peak-to-average power ratio (PAPR) and reduced out-of-band emission (OOBE). These schemes are compared in terms of OOBE, PAPR and bit-error-rate (BER), as well as the delay and Doppler cuts of the ambiguity function (AF) under deterministic and random sensing symbols. Results for orthogonal time frequency space (OTFS) and affine frequency division multiplexing (AFDM) are also included to provide additional basis of comparison. The results show the performance trade-offs between the two filter bank (FB)-based schemes, providing insights into waveform candidates for high-mobility
ISAC scenarios such as vehicular communications and future sixth generation (6G) networks.
Read the full abstract ▾
All authors Polianna Basso, Victor Augusto Del Monego, Hyeon Seok Rou, Bruno S. Chang, Giuseppe Thadeu Freitas de Abreu, Didier Le Ruyet
Representation Theory
On fusion product and N!/k-conjecture
Anton Khoroshkin and Ievgen Makedonskyi
We formulate a version of Schur–Weyl duality for the current Lie
algebra $\mathfrak{gl}_V[x,y]=\mathfrak{gl}_V\otimes\mathbb{C}[x,y]$. Under this duality, the Garsia–Haiman modules of the $N!$-
conjecture become cyclic and cocyclic $\mathfrak{gl}_V[x,y]$-modules, and we describe them as iterated fusion and cofusion products of tautological $\mathfrak{gl}_V$-modules. We show that Haiman's $N!$-
theorem for a diagram is equivalent to the coincidence of the fusion and the cofusion filtrations on the tensor product of the local Weyl modules attached to its rows, and that the fusion and cofusion products of Garsia–Haiman modules are associative. Let $\lambda$ and $\mu$ be Young diagrams obtained by removing two different corners from the same diagram. We construct an iterated fusion product of $S^2V$ with local Weyl modules, which is a quotient of the common quotient of the Garsia–Haiman modules of $\lambda$ and $\mu$, fits into short exact sequences with each of them, and has Butler's intersection
polynomial as its character. This gives a representation-theoretic proof of Butler's
conjecture. The same construction gives lower bounds for the dimensions in the $N!/k$-
conjecture.
Read the full abstract ▾
Computer Vision
ElasticFit: Fit-Aware 3D Object Insertion via VLM Reasoning and Generative Adaptation
Tzu-Hsin Hsieh and Ricardo Marroquim
Inserting objects into existing 3D scenes requires more than selecting a plausible location: the inserted object must also fit local geometry while preserving semantic intent and physical plausibility. Although recent
Vision-
Language Models (VLMs) and generative models enable semantic
reasoning and visual content creation, they offer limited 3D grounding and
geometric control when an inserted object must fit into constrained local spaces. We introduce ElasticFit, a VLM-guided framework for fit-aware object insertion centered on a novel scene-grounded representation. Given a
language instruction and rendered scene observations, ElasticFit infers structured fitting cues that specify where the object should be grounded, what volume it should occupy, how it should be oriented, and its adaptation mode (rigid placement, uniform scaling, or elastic fitting). These cues convert high-level VLM
reasoning into explicit 3D constraints that condition object generation and guide downstream
geometric fitting. ElasticFit then generates a scene-conditioned object prior, reconstructs it in 3D, and refines the mesh through mode-specific fitting while enforcing collision avoidance, contact consistency, and physical grounding. In fixed-asset baseline comparisons, ElasticFit improves spatial relation success from 50.8% to 69.7% and support success from 48.3% to 91.7% over the strongest baseline, while providing novel support for generative "make-it-fit" insertions in complex scenarios.
Read the full abstract ▾
Artificial Intelligence
Auditable Claims about AI Agents
Yue Zhao, Jiate Li, Li Li et al. (+4 more)
Organizations make claims about their AI
agents: a person approves every external email, every action is logged, an evaluation shows the
agent is safe to deploy. Article 12 of the EU AI Act requires high-risk systems to allow the automatic recording of events but does not say which records settle a given claim. The position is one sentence: to be checked, a claim about an
agent must first name its policy, its scope, the records that would settle it, and who writes them. Adapting the preconditions of an assurance engagement, we call a claim auditable when these elements and a decision rule are fixed before any verdict and the records are obtainable. This extends the Policy Checkability dimension of our Auditable
Agents framework from single actions to claims.
Agents add three conditions: coverage by an independent record, authorization bound to each action's arguments, and completeness beyond integrity. Under an explicit model, we prove that support is impossible without each wherever its hypotheses hold. A claim-check table applies the method to six common claims, anchored in current NIST, IETF, and OWASP drafts. A worked case follows one claim through five evidence states. We close with a practice box and steps for operators, buyers, auditors, and standard setters.
Read the full abstract ▾
All authors Yue Zhao, Jiate Li, Li Li, Yi Nian, Jinbo Liu, Xiaolin Zhou, Xiyang Hu
Machine Learning
Interpretable Hypergraph Learning via Neural Additive Models
Shihan Feng, Xin Zheng, Shiyi Yang et al. (+3 more)
Hypergraphs offer a natural framework for modeling networked data, where dependencies among entities are governed by higher-order interactions. While hypergraph learning methods such as hypergraph neural networks have demonstrated remarkable predictive performance, most existing approaches rely on black-box message-passing architectures, making it difficult to disentangle the contributions of node attributes and higher-order structural information. To address this challenge, we introduce the hypergraph neural additive network (HGNAN), an inherently interpretable framework for learning on hypergraph-structured data. HGNAN extends classical neural additive models to higher-order relational data by integrating feature-wise nonlinear decomposition with hypergraph-aware structural aggregation, enabling transparent prediction for both node- and hyperedge-level tasks. Extensive experiments on
benchmark datasets demonstrate that HGNAN achieves performance comparable with state-of-the-art hypergraph learning methods while providing intrinsic and meaningful interpretability.
Read the full abstract ▾
All authors Shihan Feng, Xin Zheng, Shiyi Yang, Ren Wang, Chudi Zhong, Can Chen
Machine Learning
AlignQuant: Tile-Aligned Mixed-Precision Quantization for Efficient LLM Generation
Hanzhi Zhang, Qiao Zhang, Qinglei Cao et al. (+4 more)
Fine-grained mixed-precision quantization promises efficient large
language model inference, but local precision choices can conflict with regular GPU storage and computation units. This precision-boundary mismatch limits the translation of compression into practical acceleration. We introduce AlignQuant, a post-training quantization method that uses GPU-compatible two-dimensional weight tiles as the common unit of precision allocation, compact storage, and execution. This shared partition lets precision follow sensitivity within output channels. Joint prefill/decode calibration scores precision reductions using projection-output perturbations weighted by
language-model loss gradients under quantized activations. Phase-normalized scores prioritize higher precision for tiles important to either phase under a model-wide weight-storage budget. Each tile stores one selected representation, while phase-specialized kernels reuse the packed model and expand lower-bit weights for INT8 computation with 8-bit activations. Across four LLMs spanning 3B to 14B parameters, AlignQuant achieves up to $2.50\times$ generation speedup over BF16 while preserving model quality. Evaluations further cover three GPUs and contexts up to 64K
tokens. These results show that local precision flexibility and regular GPU execution can coexist through a shared tile unit. The implementation is available at https://github.com/HanzhiZhang-Ulrica/AlignQuant.
Read the full abstract ▾
All authors Hanzhi Zhang, Qiao Zhang, Qinglei Cao, Heng Fan, Yan Huang, Kewei Sha, Yunhe Feng
Robotics
Dynamics Modeling of a Multi-UAV Slung Load System Using a Discrete-Link Cable Approach
Harvey Merton and Ian W. Hunter
A common assumption to simplify the problem of controlling a multi-
UAV slung load system (MUSLS) is that the flexible cables can be modeled as massless rigid rods. In this work, we propose an alternative Euler-Newton derived dynamical model which uses a series of rigid links to model the flexible cables. The model is specifically designed to allow efficient simulation using Featherstone's articulated body
algorithm. We perform real-world validation of this model on gentle, aggressive, and tension-engagement maneuvers and run a parameter sweep to determine the number of links, joint damping, and joint friction to achieve the greatest model fidelity. The model closely matches real-world flight data with mean load translation errors below 132 mm (5.5% of the cable length) and orientation errors below 11.4 degrees. We make the real-world flight data publicly available for the development of future cable models.
Read the full abstract ▾
Computational Complexity
Cores Characterize the One-Pass Streaming Complexity of CSPs
Joshua Brakensiek, Aaron Putterman, Amatya Sharma et al. (+1 more)
We study the one-pass streaming complexity of CSPs over a fixed finite relation $R$ under three natural objectives: $\textsf{SAT}(R)$, deciding whether all constraints can be satisfied; $\textsf{Min}$-$\textsf{CSP}(R)$, approximately minimizing the number of unsatisfied constraints; and $\textsf{Exact-CSP}(R)$, exactly computing the maximum number of satisfied constraints. Sharma and Velusamy (ESA 2026) characterized the streaming complexity of satisfiability for CSPs with literals using the non-redundancy parameter $\textsf{NRD}_n(R)$, which roughly measures the largest instance in which every constraint is independently necessary. For the most general setting without literals, they obtained the corresponding characterization for Boolean relations and showed obstacles to extending their techniques to larger domains. Kol, Paramonov, Saxena, and Yu (ITCS 2023) similarly characterized the streaming complexity of $\textsf{Exact-CSP}(R)$ for Boolean CSPs with literals in terms of the degree deg$(R)$ of the relation when written as a
polynomial, while without literals, the corresponding result was known only for $\textsf{Max-Cut}$. For all three of the objectives we study, we give tight characterizations for unweighted CSP instances over arbitrary finite domains. The streaming
algorithms we provide are deterministic, while the corresponding bounds are tight up to polylogarithmic factors, even against randomized
algorithms. The central idea in all three results is a reduction of $R$ to its core, a canonical subrelation of $R$ which admits gadgets that allow for the hard-pinning (or fixing) of variables.
Read the full abstract ▾
All authors Joshua Brakensiek, Aaron Putterman, Amatya Sharma, Santhoshini Velusamy