Peer Revenue Play credits. Real papers.

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science

cs Watch Computer Science

Friday 2 October

Cryptography and Security

From Requirements to Attack Trees: Grounded LLM Agents for Design-Time Security Review

Akash Iyer, Taha Demirkan, Keerthi Koneru et al. (+3 more)

Design-level security weaknesses can arise from requirements, trust assumptions, missing controls, and data flows before implementation begins. Existing security practices often identify these issues after code is written. We present a multi-agent LLM framework for design-time security analysis from product requirement documents and architecture diagrams. The proposed framework parses architecture diagrams into graph representations, generates misuse and failure cases, constructs attack trees, checks governance and compliance gaps, recommends mitigations, assigns enterprise security-domain tags, and produces a candidate revised architecture recommendation for expert review. The framework does not retrieve from Common Weakness Enumeration (CWE) databases at inference time. Instead, it analyzes system behavior, trust boundaries, component interactions, and data-flow assumptions. Misuse cases act as intermediate representations that link findings to system components and attack paths, while a validation and refinement loop filters unsupported findings and improves grounding, traceability, and actionability. We evaluate the framework on a Microsoft reference-labeled threat-modeling example, labeled synthetic PRD–architecture pairs, and two open-ended systems: Berty and Gas Town. The reference-labeled case supports threat-recovery and actionability analysis, while the open-ended cases evaluate validity, noise, traceability, actionability, redundancy, and attack-tree quality. Results show that architecture-informed, misuse-driven reasoning improves review quality compared with single-shot and ablation baselines. Keywords: LLM Multi-Agent Systems, Design-Time Security, Threat Modeling, Vulnerability Discovery, Architecture Diagrams, Security Analysis, Misuse Case Derivation, Attack Trees, Iterative Reasoning, Security Governance.
Read the full abstract

All authors Akash Iyer, Taha Demirkan, Keerthi Koneru, Aaryan Siddharthan, Sheethal Kumar, Ramesh Radhakrishnan

Cryptography and Security

Control OSWorld: An AI Control Environment for GUI Computer Use Agents

Maria Sanchez del Rio and Mikhail Terekhov

AI agents that operate a computer through its graphical user interface (GUI) are being widely deployed. AI control studies how to prevent an AI system from causing harm even if it is misaligned and actively trying to do so. Most control research to date has focused on coding agents, leaving computer use largely unexplored. We introduce Control OSWorld, a control evaluation that pairs 318 tasks from OSWorld with 81 harmful side tasks (e.g., exfiltrating a private file) that an agent must complete without being caught. We use Control OSWorld to create and study control monitors that detect malicious agents interacting with a GUI. We find that a weaker monitor can reliably distinguish honest from malicious trajectories produced by a more capable agent when it sees the full trajectory (97% recall at 3% false positive rate). However, when the monitor has to score each step before it is executed, recall drops at low false positive rates because each action is judged with less context. Monitor performance also depends on what the monitor can see: access to the agent's visible text is critical, while screenshots provide little additional value.
Read the full abstract

Computer Vision

Less Decoder is More Encoder: Geometric Representation Learning from Novel View Synthesis

Keerthi Kaashyap, Dennis Anthony, Akshay Krishnan et al. (+5 more)

This paper examines the role of Novel View Synthesis (NVS) in geometric representation learning. In principle, NVS should reason about 3D scene structure, thereby enabling transferable multi-view geometric representations. Yet, existing encoder-based NVS methods yield poor representations. This is not because of a lack of supervisory signal, but rather due to inconspicuous architectural choices: spatially expressive decoders that dilute representational capabilities of the scene encoder, and low-level pixel-space targets that hinder feature learning. We present SNAP, a self-supervised encoder-decoder transformer that addresses both through a pose-conditioned local decoder and a latent-space reconstruction objective. SNAP is task agnostic, and we show that it is competitive with special-purpose geometry-supervised methods. SNAP also performs competitively against self-supervised representations across five tasks: visual localization, pose estimation, point correspondence, depth estimation, and robot manipulation. Remarkably, SNAP's patch features exhibit emergent viewpoint invariance that approaches heavily supervised models despite lower compute and data budgets. Under camera shifts where standard 2D representations collapse, SNAP degrades more gracefully, revealing that restricting decoder expressivity actively prevents the suppression of transferable geometric structure. https://snap-nvs.github.io
Read the full abstract

All authors Keerthi Kaashyap, Dennis Anthony, Akshay Krishnan, Nhi Ngoc Nguyen, Jeremy Collins, James Hays, Shreyas Kousik, Animesh Garg

Computer Vision

MoSE3: Learning World-Space SE(3) at Every Pixel

Jiahuan Cheng, Zhiyi Li, Tian Xia et al. (+3 more)

Dense 3D point tracking has been a prominent paradigm for modeling motion in dynamic scenes, but a point track is just a 3-DoF translation curve per pixel: it captures where pixels go, not the rotation of the underlying part, nor which pixels move together as one body. We propose MoSE3, the first feed-forward model that predicts dense SE(3) motion from monocular RGB video, producing full 6-DoF rigid transforms at every pixel in world space. Per-pixel SE(3) motion offers a richer view of how a scene moves: rotation, translation, and grouping all at once. Directly predicting SE(3) is challenging: rotations lie on a curved manifold that is ill-suited to Euclidean regression, and annotations for SE(3) are particularly difficult to acquire. To address these challenges, MoSE3 predicts per-pixel SE(3) through two jointly learned intermediates, 3D point tracks and rigidity embeddings, and recovers SE(3) by differentiably fitting transforms within each soft rigid cluster, enabling end-to-end prediction and supervision. To close the data gap, we introduce Art-Kubric, a large-scale synthetic dataset with dense SE(3) and rigidity labels for articulated objects with rich physical interactions. MoSE3 achieves state-of-the-art SE(3) estimation at pixel, part, and object levels on both rigid and articulated benchmarks, and state-of-the-art average 3D point tracking accuracy across three datasets, while showing strong generalization to real-world videos despite being trained solely on synthetic motion data.
Read the full abstract

All authors Jiahuan Cheng, Zhiyi Li, Tian Xia, Ruojin Cai, Yilun Du, Qianqian Wang

Computer Vision

4DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes

Ruihong Shen, Žiga Kovačič, Peter Kulits et al. (+6 more)

We introduce 4DCodeBench, a benchmark for 4D inverse graphics through code generation, in which agents reconstruct dynamic scenes from video as executable graphics programs. To accomplish this, agents must translate visual observations into compact representations of scene structure and dynamics, by implementing abstractions such as physical simulations to reproduce complex behavior. To evaluate this capability, we curate a set of real-world videos and construct synthetic scenes spanning diverse physical phenomena, including deformation, fluid flow, and fracture. We perform extensive benchmarking of frontier models, finding that strong static reconstruction capabilities do not yet translate into reliable reconstruction of complex dynamics. 4DCodeBench provides a testbed for tracking progress toward agents that can interpret the dynamics of the world through code. Our benchmark is available at https://github.com/4DCodeBench/4DCodeBench
Read the full abstract

All authors Ruihong Shen, Žiga Kovačič, Peter Kulits, Xingrui Wang, Zizhang Li, Joshua B. Tenenbaum, Alan Yuille, Jieneng Chen, Jiajun Wu

Machine Learning

What Should World Models Forget? Stratified Retention for Continual Adaptation

Nishit Anand, Ramani Duraiswami and Dinesh Manocha

Continual learning treats degradation on previously seen data as evidence of failure, a convention inherited from settings with a stationary prediction target, where a correct label remains correct indefinitely. World models do not satisfy this condition. Their prediction target is the environment, which changes, so knowledge that was accurate when acquired may later become false, and discarding it is required behavior rather than a defect. Non-stationary ground truth is well studied in the concept drift literature and in the temporal factuality of language models, but has not been formulated for world models, which are distinctive in that they also encode knowledge that must never be revised. We argue that continual world models require retention stratified by invariance timescale, separating invariants such as physics and object permanence, which must never be revised, from instance-level facts that should be revised as soon as the environment changes. Standard forgetting metrics cannot distinguish a world model that has correctly revised outdated knowledge from one that has suffered catastrophic forgetting, and consequently rank a frozen model highest, while existing physical-reasoning benchmarks evaluate only frozen checkpoints. We propose differential retention, which reports invariant regression testing across the adaptation stream jointly with revision latency, without aggregation.
Read the full abstract

Machine Learning

RNADyn: A Benchmark for Generating and Understanding RNA Dynamics

Yiming Huang, Lennart Bastian, Hanqun Cao et al. (+2 more)

Ribonucleic acid (RNA) functions through conformational changes that are not fully captured by static structures. However, large-scale standardized RNA dynamics data remain limited, and existing approaches typically treat trajectory generation and dynamics understanding as separate objectives. Here, we introduce RNADynBench, a standardized RNA molecular dynamics (MD) benchmark with 2585 quality-controlled 100-ns all-atom trajectories and leakage-controlled splits. Building on RNADynBench, we develop RNADynNet, a unified model for RNA dynamics learning that uses a shared backbone for both trajectory generation and dynamics fingerprint extraction from a single conformer. It combines coordinate denoising, single-frame-to-trajectory alignment, and physical grounding to connect all-atom trajectory generation with dynamics representation learning. Physical grounding improves both generated dynamics and the physical information recoverable from these fingerprints. Across both test sets, including the high-flexibility challenge set, the generated trajectories achieve RMSF correlations of 0.875 and 0.766, while single-conformer predictions show comparable agreement with MD-derived dynamics. RNADynBench and RNADynNet together establish a benchmark and unified modeling framework for generating and understanding RNA dynamics.
Read the full abstract

All authors Yiming Huang, Lennart Bastian, Hanqun Cao, Luis Vollmers, Tolga Birdal

Robotics

EyeRobot 2.0: Active Gaze for Precise Manipulation without Wrist Cameras

Kush Hari, Justin Kerr, Nidhya Shivakumar et al. (+7 more)

Inspired by human vision, we introduce a framework using active gaze to enable fine-grained bimanual manipulation with only a single stereo camera. EyeRobot 2.0 physically attends to a 3D fixation point in the scene by swiveling two eye viewpoints to center their gaze on it. The resulting images are processed foveally by allocating more visual tokens to the image centers, focusing computation on task-relevant features. Such Active Visual Fixation (AVF) requires carefully coordinated gaze during task execution, which we accomplish hierarchically by first training a low-level gaze servoing policy conditioned on a goal object, then training a target selector which emits fixation goals based on task progress. Both modules are trained with RL on real-world data: the first is trained with a dense geometric reward and the second co-trains with the BC gripper policy which allows it to discover fixation sequences that can resemble a human's fixation sequence while performing the task. EyeRobot 2.0 further takes advantage of fixation by canonicalizing gripper information into a fixation-relative SE(3) frame, which compacts the size of the action distribution to learn. We collect teleoperation data for 7 real-world and 6 simulated tasks, and conduct over 1000 physical and 1800 simulated robot trials comparing EyeRobot 2.0 against passive stereo and ego + wrist camera policies trained on the same data. Removing wrist cameras is costly for standard policies: with only passive stereo, real-world success drops from 52% to 27%. EyeRobot 2.0 closes this gap with only stereo, outperforming passive stereo by 40% in real and 20% in sim. It matches ego + wrist policies when their wrist views are clear (69% vs. 64%), and more than doubles their success when grasped objects occlude the wrist cameras (48% vs. 22%)
Read the full abstract

All authors Kush Hari, Justin Kerr, Nidhya Shivakumar, Samarth Mahapatra, Carmelo Sferrazza, Jiahui Lei, Jitendra Malik, C. Karen Liu, Ken Goldberg, Angjoo Kanazawa

Machine Learning · Cross-listed from math.OC

From Mixing to Tearing: Graph Decomposition in Decentralized Optimization via Message Passing

Kuangyu Ding and Gesualdo Scutari

We study decentralized minimization of sums of smooth strongly convex functions, one per agent, with communication restricted to neighbors in a graph. Existing decentralized algorithms typically emulate a centralized method; the network serves only to exchange information, from which agents approximate the global quantities that the method needs. This paper breaks with this paradigm. We introduce a graph decomposition framework that uses the network to design the method, not merely execute it. It jointly determines how agreement is imposed, which variables are optimized jointly (blocks), and which connected subgraphs host the agents solving each block. The convergence analysis quantifies the trade-offs among these choices. GATE (Graph-Tearing message passing) instantiates the framework by assigning one dual variable per edge and partitioning the edges into trees. Agents interleave edge updates with local message passing recursions that summarize optimization within each tree (block). Its surrogate variant, GATE-S, uses tractable local models and compact messages to reduce computation and communication. We establish linear convergence and show that the topology-aware design acts as a preconditioner: the rate depends jointly on topology and function geometry through the coupling between subproblems defined on the selected subgraphs, whereas consensus-based optimization methods pay the worst case of each separately, the centralized condition number times the inverse spectral gap. On tree-dominant graphs, convergence is provably faster: the rate scales with the tree diameter, linearly in the number of agents on rings and barbells against quadratically for non-accelerated consensus-optimization methods. Experiments support the predicted scaling and savings in iterations and communication.
Read the full abstract

Information Theory · Cross-listed from quant-ph

Quantum estimation, channel orders, and private capacity

Christoph Hirche

Recent examples have shown that zero private capacity need not imply antidegradability and that two channels with zero private capacity can nevertheless transmit private information together. Existing entropic channel orders compare what a receiver and its environment can learn and thereby bound capacities. We connect these orders to the recent constructions through binary estimation, whose minimum mean-square error is governed by measured $\chi^2$ divergence. A new integral representation shows how measured $\chi^2$ on a qubit extension recovers quantum $\chi^2$. It lets us pass from complete measured-$\chi^2$ ordering to complete quantum-$\chi^2$, relative-entropy, and less-noisy ordering. Zhu and Wang used a signed lift to show that their qutrit channel has zero private capacity. We show that Hermitian-smoothed measured-$\chi^2$ ordering characterizes when such lifts exist, even with a quantum reference. Environmental dominance in binary estimation at every blocklength yields a finite-code reliability–secrecy bound. These results explain why complete comparison prevents activation with antidegradable helpers whereas regularized comparison alone does not. Building on that qutrit example, we establish this stability for a range of noisy Werner–Holevo channels, determine sharp private-capacity and antidegradability thresholds, and compute exact complementary capacities in a nondegradable range. By contrast, we extend Pauli half-erasure activation to all $1/2\le p<1$ and establish the same range for a new four-level family. Reference-assisted measured-$\chi^2$ witnesses show why these activating constructions lack complete comparison.
Read the full abstract

Computational Complexity · Cross-listed from quant-ph

Unitary complexity in polynomial space

William Kretschmer and Ewin Tang

We show that if quantum commitments exist, then either there is no polynomial-time solution to the unitary synthesis problem, or $\mathsf{BPP} \neq \mathsf{NEXP}$. Thus, showing unconditionally that quantum commitments exist would require answering at least one of two longstanding open questions in complexity theory. We prove our main result as a consequence of a more general lemma, which shows that every unitary in $\mathsf{unitaryPSPACE}$ either cannot be synthesized efficiently relative to any classical oracle, or can be synthesized efficiently with an oracle for $\mathsf{NEXP}$ search problems. Our lemma has other noteworthy consequences, including that certain oracle separations involving $\mathsf{unitaryPSPACE}$ would imply breakthrough classical lower bounds such as $\mathsf{NC} \neq \mathsf{NP}$. Along the way, we propose new definitions for the unitary complexity classes $\mathsf{unitaryP}$ and $\mathsf{unitaryPSPACE}$. Our changes address the biggest conceptual issues with definitions suggested in prior work, and lead to elegant proofs. We study both implementations that erase garbage and implementations that allow it, because we cannot rule out the possibility that the two definitions differ. Nevertheless, we show that both definitions can be viewed as special cases of each other. We also showcase many other ways in which our definitions are robust. For example, we show that $\mathsf{unitaryPSPACE}$ has an equivalent characterization as the set of unitary transformations whose entries can be computed to arbitrary precision in polynomial space. Consequently, we deduce that $\mathsf{unitaryPSPACE}$ can generically erase garbage, a result that provably fails relative to unitary oracles.
Read the full abstract

Information Theory · Cross-listed from math.CO

Non-isomorphic graphs have distinct vertex-Ramsey classes

Maria Axenovich and Patrick Schmitteckert

For a graph $H$, its $k$-colour vertex Ramsey class is the set of all graphs $G$ such that any colouring of the vertices of $G$ in $k$ colours results in a monochromatic (induced) copy of $H$. We prove that for any $k$, Ramsey classes of any non-isomorphic graphs are distinct.

Machine Learning

LESSER: Post-Training Data Selection with Output-Layer Gradients

Lyuxin David Zhang, Eric Wong, Surbhi Goel et al. (+1 more)

The choice of post-training data for large language models substantially affects downstream performance. Gradient-based data selection is a popular approach that ranks training data by how well their gradients align with those of a small validation set. However, ranking with full-parameter gradients requires an expensive backward pass on every sample, making computation intractable for large candidate pools. This raises a natural question: can we approximate full-gradient features at a fraction of the cost? Conveniently, we find that output-layer gradients suffice for effective data selection, yet require only the cheaper forward pass. We implement this as LESSER, a drop-in wrapper for selection methods that reduces the feature-extraction FLOP cost by $9.7\times$ for SFT and $3.0\times$ for RL benchmarks, while tracking full-gradient performance on downstream tasks. Empirically, we find that even when output-layer and full gradients rank individual samples differently, they select batches with aligned gradients.
Read the full abstract

All authors Lyuxin David Zhang, Eric Wong, Surbhi Goel, Anton Xue

Computer Vision

Decoding the Functional Roles of Register and High-Norm Patch Tokens in Vision Transformers

Neel Varma, Andrew Rufail, Dipika Khullar et al. (+1 more)

Self-supervised Vision Transformers (ViTs), such as DINOv2, learn rich visual representations, but the functions of their internal tokens remain poorly understood. Recent architectures introduce dedicated register tokens to reduce high-norm out- lier patch tokens that emerge in background re- gions, yet the semantic and functional roles of both token types have not been fully established. In this paper, we analyze these roles by training sparse autoencoders (SAEs) on register-token and outlier-token activations in DINOv2. Using an automated interpretability pipeline, UMAP clus- tering, and CLIP-space cross-checks, we find that register-token features are more strongly associ- ated with high-level semantic concepts. Outlier- token features, by contrast, are more often associ- ated with lower-level structural, background, and texture-dominant patterns. Causal ablations fur- ther reveal a substantial functional asymmetry: disrupting top-activating register-derived features produces a 48.17% drop in representation cosine similarity, whereas disrupting outlier-derived fea- tures produces only a 0.31% drop. Together, our results provide evidence for token specialization in self-supervised ViTs.
Read the full abstract

All authors Neel Varma, Andrew Rufail, Dipika Khullar, Vasu Sharma

Computation and Language

Language Models that Play Chess and Explain Their Moves

Adithya Bhaskar, Jeffrey Cheng and Danqi Chen

Modern chess engines are silent experts: they play at a superhuman level, but do not offer explanations for their play. On the other hand, language models (LMs) can generate plausible-sounding explanations, but their weak playing strength limits the utility of their explanations. We introduce Queen, a 4B-parameter chess-language model that can explain its moves and plans while playing at the level of a typical Grandmaster. Our novel framework enables domain-specific reasoning through complementary components: an encoder-decoder architecture and an iterative distillation algorithm. This architecture integrates a silent expert chess encoder with an instruction-tuned LM through cross-attention, which we train via a question-answering curriculum to extract chess concepts from the encoder's representations. Building on this domain-adapted model, we iteratively improve its explanations with a natural-language analog of the Bellman update: the model analyzes the positions after its top candidate moves and consolidates them into an explanation of the current position, which is then distilled back into the model. Over seven iterations, our model gains over 900 Elo points (1782 to 2697), substantially surpassing all frontier models on both playing strength and puzzle accuracy, despite containing three orders of magnitude fewer parameters. Furthermore, LM-based evaluations show that our explanations are fluent and approach GPT-5.6-Sol (high) in coherence. The generality of our architecture and training procedure suggests a recipe for applying language models to domains where silent expert encoders are available, like games, robotics, and computer use.
Read the full abstract

Artificial Intelligence

Transcriptome-informed multi-modal AI for predicting neoadjuvant therapy response from breast cancer biopsies

Jungkyu Park, Dhruva Biswas, Joseph Cappadona et al. (+22 more)

Scarcity of labeled data limits development of deep learning biomarkers in oncology. We develop a two-stage AI model predicting pathological complete response (pCR) to neoadjuvant therapy in breast cancer. The first stage learns the transcriptome from histopathology using 8,742 patients across 32 cancer types, corroborated by pathologist review and spatial agreement with measured expression. This simplifies the second stage to predicting pCR from inferred expression and clinical variables. Developed using 1,080 patients (five cohorts) and evaluated in 1,412 patients (nine cohorts), the model achieves a pooled AUROC of 0.79 (95% CI, 0.73-0.85), discriminating responders within molecular subtypes. It outperforms histopathological biomarkers, remaining stable across intratumoral sampling and with minimal biopsy tissue. Ablations show transcriptome-wide inference improves discrimination over clinical variables alone or one-stage pathology models, and robustness by avoiding genomic assays' gene selection constraints. These results indicate that biologically informed compression may generalize to data-sparse applications in precision oncology.
Read the full abstract

All authors Jungkyu Park, Dhruva Biswas, Joseph Cappadona, Cerise Tang, Ken G. Zeng, Bartosz Machura, Chuwen Liu, Paolo Tarantino, Coral Omene, Francisco J. Esteva, Rohit Bhargava, Marcin Braun, Kamila Paździerz, Jakub Czerwiński, Hanna Romańska-Knight, Albert Grinshpun, Bareket Daniel, Michele Buchinger, Frederick Howard, Piotr Wysocki, Brie Chun, Freya Schnabel, Rich Caruana, Jan Witowski, Krzysztof J. Geras

Computer Vision

FlowHMR: Physically Plausible Motion Capture from Video

Zhanke Wang, Chengfeng Zhao, Qing Shuai et al. (+8 more)

We present FlowHMR, a framework for recovering physically plausible global 3D human motion from monocular video. Previous learning-based methods typically regress human motion directly from video and train the network with geometric supervision. However, recovering human motion from monocular video is inherently ambiguous in depth, and direct regression tends to collapse toward an averaged solution. Moreover, the recovered motions are not guaranteed to be physically plausible, so physics-based tracking of them often fails. To address these challenges, we formulate video motion capture as a video-conditioned motion generation problem and first pretrain a flow matching model for this task. Given an input video, the pretrained model generates diverse motion candidates, but not all of them are faithful to the video or physically trackable. We therefore post-train the model using Group Relative Policy Optimization (GRPO) with two rewards. A fidelity reward encourages consistency with the input video. A tracking reward favors motions that a physics-based controller can track successfully. Together, these rewards shift the model's output preference, so the post-trained model stays faithful to the input video while producing more physically plausible motion. We further introduce Wild-4K, a large and diverse dataset of about 4K internet videos, for evaluating human motion recovery in the wild. Qualitative and quantitative experiments on Wild-4K show that our method outperforms state-of-the-art methods in overall motion fidelity and achieves a physical tracking success rate of 82.47%, compared with 62.82% for the strongest baseline, GVHMR.
Read the full abstract

All authors Zhanke Wang, Chengfeng Zhao, Qing Shuai, Jingzhong Lin, Heng Li, Zeyu Ling, Yuxin Wen, Jing Li, Di Kang, Chunchao Guo, Linchao Bao

Computer Vision

SigLIP2 for aerial fire risk classification

Yunus Serhat B{\i}çakç{\i}

We examine the transfer of a pretrained SigLIP2 image encoder to seven class fire risk classification from aerial imagery. We introduce a reproducible partition of the public FireRisk training mirror and an implementation that records data provenance, preprocessing and model selection. Two initial runs compare a frozen encoder probe with full model adaptation. On the validation partition, full adaptation reaches 63.05% accuracy and 58.94% macro F1, compared with 55.95% and 50.19% for the probe. Both runs use one training seed and select their checkpoint on the same validation partition. These development results support further evaluation of SigLIP2 but do not establish performance on an independent test set or unseen regions. The accompanying code provides a common framework for repeated experiments and comparisons with additional visual encoders.
Read the full abstract

Systems and Control

Risk-Aware Input-Constrained Safe Intercept Guidance Against Multiple Moving Defenders

Praveen Kumar Ranjan, Abhinav Sinha, Yongcan Cao et al. (+2 more)

This paper develops a risk-aware guidance law for an attacker to intercept a stationary target in the presence of multiple moving defenders while respecting the control input limits. We represent defender threats via engagement zones (EZs) (regions of state-space from which attacker interception is feasible) and employ the dynamic maneuvering cue (DMC) (minimum heading correction to exit EZs) as a deterministic measure of geometric risk. Safety is enforced through a prescribed bound on the DMC to enable controlled EZ penetration subject to a specified risk tolerance. For multiple defenders, the corresponding safety constraints are combined through a smooth-minimum aggregation. The proposed guidance strategy drives the attacker toward the target when the engagement remains safe and transitions to an avoidance maneuver as the prescribed safety boundary is approached. The resulting online optimization-free guidance law directly bounds the applied lateral acceleration and initiates a bounded preemptive maneuver before corrective action is required. Closed-loop analysis establishes preservation of the prescribed risk constraints under pointwise bounded-input feasibility and finite-time target interception under a sustained target-accessibility condition. Numerical studies validate the proposed strategy and illustrate the tradeoff between allowable geometric risk and interception performance.
Read the full abstract

All authors Praveen Kumar Ranjan, Abhinav Sinha, Yongcan Cao, Alexander Von Moll, Isaac E. Weintraub

Machine Learning

Simulation-Free Learning of Population Dynamics with Wasserstein Lagrangian Residuals

Fedor Sergeev, Markus Heinonen, Daniel Waxman et al. (+4 more)

The dynamics of cells, organisms, and fluids are often modeled as probability distributions evolving over time. Reconstructing and extrapolating this evolution from unpaired snapshots requires assumptions about the underlying process. Wasserstein gradient flows are a common choice, but they cannot describe conservative or periodic dynamics. Lagrangian mechanics in Wasserstein space covers both, but existing methods for learning it are simulation-based: they run a numerical solver at every training step, which makes training expensive. We propose Double-Stitch, a simulation-free method that learns these mechanics by penalizing the residual of the equation of motion along a learned population path. We derive this equation from a Clebsch variational principle that does not require gradient velocities, and show that the residual vanishes exactly when the equation holds. We test Double-Stitch on synthetic, single-cell and ocean vortex datasets and find that it matches or outperforms gradient-flow methods and simulation-based WLM on most tasks, while training $4$-$14$ times faster than WLM. We provide a JAX implementation of Double-Stitch at https://github.com/BasisResearch/stitching.
Read the full abstract

All authors Fedor Sergeev, Markus Heinonen, Daniel Waxman, Tim Cooijmans, Ricardo Baptista, Dmitry Batenkov, Eli Bingham

Neural and Evolutionary Computing

FrugalEvo: Towards Cost-Aware LLM-Guided Program Evolution

Hui Chen, Xuan Qi, James Xu Zhao et al. (+5 more)

LLM-guided evolutionary methods, such as AlphaEvolve, have emerged as powerful approaches for challenging computational optimization problems, such as circle packing. However, prior work typically optimizes performance gain over a fixed number of iterations. We argue that practical optimization should maximize gain per unit cost. To this end, we propose FrugalEvo, a cost-aware evolutionary framework where a stronger, higher-cost LLM explores solution strategies, and a cheaper LLM implements them and iteratively refines the resulting code. We also design a cache-efficient evolution process, where our harness and prompts maximize the sharing of prefixes across different evolution steps, to improve cache reuse. To measure solution quality throughout a fixed cost budget, we introduce Budget-Aware Area Under the Curve (BA-AUC), defined as the area under the best-so-far evaluation score curve over cumulative LLM cost, up to the budget. Across 10 mathematical and systems optimization tasks, FrugalEvo matches or surpasses state-of-the-art baselines, including OpenEvolve, ShinkaEvolve, AdaEvolve, and EvoX, in final solution quality and achieves higher BA-AUC on 9 tasks. It also achieves higher average performance than these baselines on 10 algorithmic optimization tasks from ALE-Bench-Lite. Notably, on circle packing, FrugalEvo achieves new state-of-the-art performance with GPT-5.6 Terra and Luna for only 1.68 USD and with GLM-5.3 and its Flash variant for only 0.55 USD, matching or surpassing all baselines, including multi-agent methods such as CORAL and SwarmResearch, which cost approximately 50 USD on average.
Read the full abstract

All authors Hui Chen, Xuan Qi, James Xu Zhao, Zhaopeng Feng, Shilong Liu, Kuang Xu, Pang Wei Koh, Bryan Hooi

Information Theory · Cross-listed from quant-ph

Efficient capacity-achieving entanglement generation with application to pure-loss Bosonic channels

Avijit Mandal, Christophe Piveteau, Henry D. Pfister et al. (+1 more)

While the ultimate limits on the rate of quantum communication over noisy channels are well-established, very few efficient coding schemes achieving these limits are known. This contrasts sharply with transmitting classical data over classical channels, where polar codes and low-density parity-check codes both efficiently achieve the classical capacity of any noisy channel. In this work we construct an efficient entanglement generation scheme which achieves the coherent information for a broad class of channels. For degradable channels in the class, which includes truncated versions of the pure loss Bosonic channel, the resulting scheme achieves the quantum capacity. The construction makes use of polar codes for two kinds of classical-input, quantum-output (CQ) channels: those with commuting outputs and those whose outputs are heralded mixtures of pure states. The former case is amenable to decoding by classical polar decoding algorithms, the latter by the belief propagation with quantum messages (BPQM) algorithm. To our knowledge, this construction is the first explicit and efficiently decodable protocol that achieves the energy-constrained quantum capacity of the pure-loss Bosonic channel.
Read the full abstract

All authors Avijit Mandal, Christophe Piveteau, Henry D. Pfister, Joseph M. Renes

Data Structures and Algorithms · Cross-listed from quant-ph

Quantum Simulation on Riemannian Manifolds

Dylan Herman, Jacob Watkins, Guneykan Ozgul et al. (+4 more)

We investigate algorithms for the quantum simulation of the Schrödinger equation on a Riemannian manifold, where the kinetic operator is defined by the Laplace–Beltrami operator corresponding to the metric. Our first algorithms are based on a global spectral method based on the identification of an efficient transform to the eigenbasis of the Laplace–Beltrami operator. We use this method to provide explicit, efficient, quantum simulation algorithms for the Riemannian Schrödinger equation on tori and spheres with their standard metrics, simplices with the Wright–Fisher metric, truncated positive orthants and their invertible affine images with the log-barrier Hessian metric, and $\ell_p$ balls with a metric induced by the Duffy map. Our second algorithm is based on a coherent simulation of local spectral methods on multiple charts, and is in principle applicable to any compact manifold. We first analyze this algorithm in the continuum and derive conditions under which a polynomial spectral cutoff suffices. We also provide a discretization analysis of a polynomial spectral cutoff for tensor-products of constant-dimensional manifolds. Finally, we consider applications of these methods to optimization and physical simulation. For optimization, we provide results including a generalization and convergence analysis of Quantum Hamiltonian Descent for geodesically convex functions that leads to explicit algorithms on the sphere and simplex, and a Riemannian generalization of the Real-Space Adiabatic Algorithm. For physical simulation, we show that our algorithms can simulate certain spatially discretized field theories, including a variant of the nonlinear sigma model.
Read the full abstract

All authors Dylan Herman, Jacob Watkins, Guneykan Ozgul, Jiayu Shen, Brandon Augustino, Junhyung Lyle Kim, Shouvanik Chakrabarti

Machine Learning

Planning to Learn

Ian Osband

Policy-gradient methods are central to modern reinforcement learning, including LLM post-training. When they struggle, the usual suspects are exploration, credit assignment and action-sampling noise. Classification has none of them. A classifier is a policy whose expected reward, its expected accuracy, is the probability it assigns to the correct label, and because that label is known, the policy gradient is exact and smooth. Yet exact policy gradient loses to cross-entropy, even on expected accuracy. The exact gradient is myopic: it values an update only by what it buys now, but each update also sets where the next one starts, so an update's value depends on how much learning remains. Viewed this way, cross-entropy is patient accuracy, the total error an example would pay if its log-odds rose at unit speed forever, while exact policy gradient is the zero-horizon limit. Truncating this total at the learning that remains yields the horizon loss, a one-line change that moves from cross-entropy toward exact policy gradient as training runs out. In a simple allocation model, it provably escapes the trap that catches each endpoint. On MNIST and on ImageNet with ResNet-50, ResNet-101 and ViT-S/16, the horizon loss improves top-1 accuracy over cross-entropy at a flat learning rate, and the gain grows with label noise.
Read the full abstract

Numerical Analysis · Cross-listed from math.ST

Bayesian Operator Learning: Posterior Existence and Convergence of Point Estimates for Gaussian Priors

Niklas Reinhardt and Jakob Zech

We develop a Bayesian framework for learning nonlinear operators between infinite-dimensional spaces. Given a map $g_0:\mathcal{X}\to\mathcal{Y}$ between separable Hilbert spaces, we study the recovery of $g_0$ from $n\in\mathbb{N}$ noisy input-output pairs $(\boldsymbol{X},\boldsymbol{Z})=(X_i,Z_i)_{i=1}^n$ with $Z_i= g_0 (X_i ) + E_i$. Here the $X_i\in\mathcal{X}$ are randomly drawn 'design' points in a compact subset of $\mathcal X$, and the $E_i$ are assumed to be i.i.d. draws from a Gaussian white noise process indexed by $\mathcal{Y}$. For any 'operator-valued' prior $\mathbb{P}_G$ supported on the space of continuous operators, we show existence of the posterior $\mathbb P_{G|(\boldsymbol{X},\boldsymbol{Z})}$ as a regular conditional distribution, and provide a characterization of its Radon-Nikodym derivative. For Gaussian priors, we establish algebraic (in the sample size $n$) convergence rates for the posterior mean towards the ground truth; this corresponds to a ridge regularized kernel estimator. Moreover, we show that the posterior mean is minimax optimal (up to logarithmic factors) over hyperrectangles when the smoothness of the prior matches that of the ground truth. To illustrate the applicability of our analysis, we derive explicit learning rates for the Darcy flow solution operator.
Read the full abstract

Machine Learning

Pivot-SD: Efficient Self-Distillation for Masked Diffusion Language Models

Seo Hyun Kim, Sunwoo Hong, Younwoo Choi et al. (+3 more)

Masked diffusion language models (dLMs) offer a promising parallel alternative to autoregressive models for complex reasoning. However, they face a distinct credit-assignment challenge, since a few commitments during denoising sharply reduce the uncertainty over the remaining masked positions and shape much of the response. Most post-training recipes for dLMs do not use this signal to decide which tokens to train on: they typically train on the final text or assign rewards to whole denoising steps, rather than selecting the individual commitments that shape the response. We introduce Pivot-SD, an efficient offline self-distillation framework that supervises only these high-impact commitments (pivots). Pivot-SD selects pivots using an information-gain metric measuring uncertainty reduction over the remaining masked positions. Pivots from successful trajectories are trained with cross-entropy, and pivots from failed trajectories with targeted unlikelihood, leaving the rest of the failed trajectory untouched. Using only 200 questions and four rollouts each, Pivot-SD improves LLaDA-8B-Instruct over full-sequence SFT and budget-matched diffusion RL baselines across math and code benchmarks.
Read the full abstract

All authors Seo Hyun Kim, Sunwoo Hong, Younwoo Choi, Chen-Hao Chao, Se-Young Yun, Rahul G. Krishnan

Computer Vision

ProAR: Learning Prospective Reasoning with Autoregressive Video Models

Linghui Shen, Tinghui Zhu, Sheng Zhang et al. (+1 more)

Autoregressive (AR) video models excel at causal generation, but their reliance on next-chunk prediction confines them to a short-sighted, reactive paradigm. This limitation is particularly consequential for reasoning-oriented generation, where achieving a target outcome through valid intermediate states matters more than local visual plausibility. To address this challenge, we propose Learning Prospective Reasoning with Autoregressive Video Models (ProAR), a novel framework that transforms autoregressive video generation into a goal-oriented reasoning process. ProAR introduces two key components: (1) To anchor generation to the long-range outcome, we integrate goal-frame prediction into the autoregressive loop via an asymmetric attention mask, enabling the predicted goal frame to guide the generation of intermediate states without being disrupted by them. (2) To guide short-range transitions, we introduce future representation self-alignment to encourage current hidden states to anticipate upcoming temporal dynamics. By leveraging teacher-forcing in AR training, we extract clean future representations in a single forward pass and align current representations with them using a lightweight, training-only predictor. Together, these two mechanisms seamlessly combine explicit, sparse target supervision with implicit, dense step-wise guidance, promoting coherent, goal-directed reasoning progress with modest computational cost. Experiments show that ProAR's complementary components consistently improve performance across diverse visual reasoning benchmarks. The framework proves highly training-efficient, surpassing fully trained standard AR baselines using only 25% of the training steps. This paradigm also demonstrates promising applicability to embodied reasoning tasks.
Read the full abstract

All authors Linghui Shen, Tinghui Zhu, Sheng Zhang, Muhao Chen

Machine Learning

Forecasting from Counterfactual Simulator Rollouts: A Sim2Real Evaluation

Angel Wang, Dominique Perrault-Joncas, Alvaro Maggiar et al. (+2 more)

Deploying a new decision policy creates a cold-start problem for prediction models whose targets depend on the policy's actions: historical observations reflect earlier policies, while real observations under the new policy are not yet available. Simulation offers a way to address this gap by rolling out the target policy across counterfactual scenarios and using the resulting trajectories to learn how the system responds to those controls. The simulation-to-reality (Sim2Real) transfer of this simulator-trained model can then be backtested by evaluating it against real observations from past deployments. Using two real-world inventory-control deployments, we evaluate this process from three angles: simulator fidelity, zero-shot transfer to real behavior, and adaptation as real target-policy observations accumulate. The simulator-trained forecaster achieves lower point-estimate mean absolute percentage error (MAPE) than the same architecture trained on historical real data, reducing MAPE by 1.2-3.1 percentage points in Study 1 and 12.5-18.7 points in Study 2. After deployment, lightweight calibration using early real observations further reduces error by up to 2.5 percentage points. These results provide empirical evidence that simulator-generated counterfactual data can support cold-start forecasting under a new policy, and the resulting model can be further refined as real deployment data become available.
Read the full abstract

All authors Angel Wang, Dominique Perrault-Joncas, Alvaro Maggiar, Dean Foster, Carson Eisenach

Game Theory

Single-Sample Prophet Inequalities: A Combinatorial to Single-Item Reduction

Shuchi Chawla and Trung Dang

We study single-sample prophet inequalities for online combinatorial allocation. Our main contribution is a general reduction from combinatorial to single-item prophet inequalities for valuation classes admitting suitable supporting prices. The reduction uses a free-disposal value to separate buyer-side combinatorial constraints from item-side supply constraints, yielding a modular framework that applies in the stronger Game of Googol model. This framework yields a $\frac{1}{6\sqrt{3}}\approx\frac{1}{10.4}$-competitive single-sample prophet inequality and a $(\beta_{k-1}/4)$-competitive $k$-sample prophet inequality for XOS valuations, where $\beta_k$ is the competitive ratio of a $k$-sample single-item prophet inequality, improving upon the work of [DKL+24]. Both results extend directly to divisible resources with capped-XOS valuations. Along the way, we obtain new results for online free disposal and an optimal single-sample prophet inequality for fractional knapsack in the Game of Googol model.
Read the full abstract

Sound

Revisiting Input Time-frequency Representations in Multi-pitch Estimation for Vocal Ensembles

Junyoung Koh and Hao-Wen Dong

Multi-pitch estimation in vocal ensembles is challenging because singers occupy overlapping pitch ranges and often sing at closely spaced fundamental frequencies, causing their harmonics to overlap in time-frequency representations. Existing models commonly use harmonic constant-Q transform (HCQT)-based representations to provide frequency-adaptive resolution, at the cost of expensive feature extraction when training mixtures are generated on the fly. We revisit this design and compare HCQT with a linear short-time Fourier transform (STFT), whose frequency bins are directly provided as model inputs. Despite its fixed frequency resolution and the absence of a pitch-aligned input grid, the linear STFT outperforms HCQT while substantially reducing feature-extraction cost. Further analysis shows that a longer analysis window or broader spectral coverage provides no additional improvement, while restricting the input to the predicted pitch range reduces the advantage of the linear STFT. These results suggest that finer frequency resolution does not necessarily improve vocal-ensemble MPE, and that shorter analysis windows can be more effective for time-varying vocal pitches.
Read the full abstract