Cryptography and Security
Residual Community Prototypes Under-Reject Held-Out Malware Families in FCG-MFD
Junru Zhu, Yixin Yang, Xiaoqing Ding et al. (+1 more)
Open-set malware-family recognition must classify known families while rejecting families absent from training. We test whether Louvain-community summaries add rejection information beyond a graph neural network
embedding and dimension-matched generic
topology. The study uses a deduplicated, conflict-audited FCG-MFD corpus, five held-out families, and three optimization seeds. Community features are residualized against generic
topology using known-family training data before nearest-prototype scoring. Residual community does not produce stable held-out-family rejection. Ranking effects reverse across families, the false-positive rate at 95 percent unknown recall worsens for every held-out family, and a validation-fitted threshold rejects only 4.48 percent of unknown samples. Accepted-known macro F1 improves in every family, but with five independent family units the exact two-sided sign-flip p-value is 0.0625, the smallest attainable value. The score remains associated with graph scale, while simple classifier uncertainty performs better on ranking, high-recall rejection, and OSCR. In this GIN/FCG-MFD setting, community-enriched prototypes change known-class geometry without creating a stable unknown margin. Graph open-set evaluations should pair structural features with matched
topology controls, operational thresholds, and held-out-family analysis.
Read the full abstract ▾
All authors Junru Zhu, Yixin Yang, Xiaoqing Ding, Ruoyu Qi
Machine Learning
LoRA-generating hypernetworks for efficient on-device LLM generative personalization
Sean Augenstein, Li Ding, Jihwan Lee et al. (+2 more)
On-device large
language models (`LLMs'), e.g. running on mobile phones, are ripe for improvement via personalization. The limited compute resources of mobile devices impose limits on model scale and thus model quality, making any realizable quality gains highly impactful. At the same time, their personal nature (i.e., the close coupling to a particular user) means that a given on-device LLM tends to be used in similar, predictable patterns over the course of time. This paper presents a novel method for personalizing on-device LLMs. It trains a hypernetwork to map a user's context
tokens to a low-rank adaptation (`LoRA') well-suited to that user. Once the trained common artifacts are deployed to users' devices, each user uses the hypernetwork to synthesize (entirely on device) a personalized LoRA. This approach blends the benefits while avoiding the drawbacks of two existing approaches to LLM customization: in-context learning (`ICL') and parameter-efficient fine-tuning (`PEFT'). Like ICL (and unlike PEFT), the on-device phase of our approach is computationally feasible, requiring only forward passes through neural networks. Like PEFT (and unlike ICL), our approach modifies the `target' base LLM via weights (the LoRA), avoiding negative consequences (e.g. increased latency) associated with extending the input sequence. Our approach is particularly well-suited to the mobile device regime. Apart from the on-device compute and latency benefits mentioned, it also requires minimal additional storage, as internally its architecture partly leverages the same LLM weights as belong to the target LLM to be personalized. We demonstrate the benefits of LoRA-generating hypernetworks on several representative personalization
datasets, comparing against baselines like ICL and PEFT. Of note, our personalization experiments focus on more challenging and less studied long-form text generation tasks.
Read the full abstract ▾
All authors Sean Augenstein, Li Ding, Jihwan Lee, Keith Rush, Andrey Zhmoginov
Robotics
DexTacWAM: A Visuo-Tactile World-Action Model for Dexterous Manipulation
Haoran Yuan, Zekai Wang, Boning Shao et al. (+4 more)
Dexterous manipulation depends on contact dynamics that are often only partially observable from
vision. Recent World-Action Models (WAMs) couple predictive
video world modeling with action generation, but remain largely
vision-centric and therefore cannot directly model these contact dynamics. We present DexTacWAM, a visuo-tactile WAM that encodes each fingertip independently, aggregates the resulting features through a finger- and pose-aware tactile compressor, and injects the tactile latent into a
video diffusion world model for joint visuo-tactile world modeling. Across six contact-rich dexterous manipulation tasks on a 22-DoF bimanual platform, DexTacWAM achieves the highest score on every task, averaging 70.6 versus 38.0 for the strongest baseline. Ablations attribute the gain to modeling contact
evolution as part of the predicted world state rather than tactile conditioning alone: removing tactile world modeling reduces the four-task mean from 74.7 to 26.6 while keeping the same tactile features and action expert. After four hours of tactile-encoder adaptation with a frozen pretrained
vision VAE, our continual
vision-to-touch learning extends the pretrained
video model to touch using roughly 100 demonstrations per task without tactile midtraining, while retaining visual prediction quality within 0.5 dB of
vision-only counterparts. The compressor retains 89.4% of pre-fusion contact recall while enabling 2.26x faster training and 1.29x faster inference. Together, these results show that pretrained
video priors can be extended to distributed multi-finger contact dynamics in a data- and compute-efficient manner.
Read the full abstract ▾
All authors Haoran Yuan, Zekai Wang, Boning Shao, Haoran Lu, Trevor Darrell, Ismini Lourentzou, Wei Zhan
Artificial Intelligence
Harness-Zero: Harness Distillation via Agent-as-Harness
Haoran Ye, Yuxing Lu, Haonan Dong et al. (+2 more)
Agent harnesses, the external systems that mediate model-environment interaction, can substantially improve
agent performance, but their gains remain tied to the harness at deployment. Because the best harness varies across domains, instances, and models, a general-purpose
agent must either settle for a suboptimal shared harness or route among an ever-growing set of specialized ones. We therefore study
agent harness
distillation: using a domain- or instance-optimized harness as training-time guidance and transferring the behaviors it induces into model weights, so that its gains survive under a single fixed target harness. The challenge is that the two harnesses differ in action space and available information, so guidance from the optimized harness cannot serve directly as supervision for the target one. We introduce Harness-Zero, which enables harness
distillation through
agent-as-harness. Guided by the optimized harness, a harnessing
agent corrects student responses before execution in the target harness's action space, turning harness guidance into training demonstrations. Fine-tuning on the resulting trajectories internalizes harness-induced behavior into the model, so the specialized harness can be removed at deployment. Our experiments spanning knowledge work, tool use, and science domains show that: (1) For frontier LLMs using the same evolved harness,
agent-as-harness outperforms code-as-harness. (2) With the specialized harness removed at deployment, Harness-Zero improves the base model's macro-average task success from 23.3% to 44.3%, even exceeding the 41.7% it reaches with that harness still attached. (3) Harness-Zero recovers harness-induced behaviors absent from the base model, with 82.3% average recovery across 28 patterns in the three domains.
Read the full abstract ▾
All authors Haoran Ye, Yuxing Lu, Haonan Dong, Zhaochen Su, Guojie Song
Machine Learning
RRSI: Regularized Recursive Self-Improvement of Agent Harnesses
Peng Xia, Rujun Han, Zifeng Wang et al. (+11 more)
An LLM
agent's capability is largely magnified by its harness, namely the
prompts, control flow, tooling,
memory, and context management surrounding the frozen backbone model. Recent methods increasingly automate this process by iteratively proposing and selecting component-wise edits of an
agent harness, practically establishing a form of recursive self-improvement (RSI) at the
agent-system level. However, such recursive
evolution may overfit by memorizing the training tasks, showing large in-distribution gains that shrink or even vanish on out-of-distribution
benchmarks. We introduce Regularized Recursive Self-Improvement of
Agent Harnesses (RRSI), which incorporates the principles of regularizations into harness self-improvement by constraining the
evolution candidate proposal and selection. The proposer operates with a temporally annealed budget, limiting how many edits a candidate can bundle, and it encourages unexplored trajectories based on
evolution history. The selector is equipped with a critic and a pruner: the critic screens
benchmark-specific proposals, while the pruner, removes changes that are too small, too expensive, or no longer useful. Together these constraints favor reusable
agent mechanisms over
benchmark-specific ones or even noises. Across eight
benchmarks spanning coding, agentic workspace and engineering design tasks, RRSI gains up to 6.0 points on the split it evolves against and up to 4.3 points on the five out-of-distribution
benchmarks, while producing a harness that runs on 30% fewer policy
tokens than the unregularized
evolution. Code is available at https://github.com/google-research/rrsi and project page is https://regularized-rsi.com/.
Read the full abstract ▾
All authors Peng Xia, Rujun Han, Zifeng Wang, Yanfei Chen, Yufan Zhuang, Yoonho Lee, Chengsong Huang, Han Yu, Zhongying CuiZhu, Yifei Ming, Huaxiu Yao, Burak Gokturk, Tomas Pfister, Chen-Yu Lee
Computation and Language
DolphinBench: Mapping the Pareto Frontier of Agent Memory
Soumil Rathi, Deshraj Yadav and Taranjeet Singh
Agents today often take real-world actions that depend on long-term
memory and context recall over time. However, most current
memory benchmarks are built for a conversational question-answer format, where the question itself signals that some fact must be retrieved, and often which one. Moreover,
benchmarks rarely require anything beyond accuracy from submissions, allowing
memory systems to make unreasonable cost/time tradeoffs to achieve higher scores. We present DolphinBench, a
benchmark that evaluates
memory directly through an
agent's task completion. DolphinBench includes three knowledge-work personas with roughly 500k
tokens of user messages per persona and evaluates
agents on tasks that depend on information from that history. We verify all 200 tasks per persona by running an
agent with and without the relevant history, requiring success with it and failure without it. Finally, we require all evaluations to report total cost and latency alongside accuracy, which enables us to evaluate
agent memory systems holistically. No existing
memory benchmark combines all three. The
dataset and evaluation code are available at https://dolphinbench.ai.
Read the full abstract ▾
Machine Learning
Rare Event Estimation via Iterative Unalignment
Hanming Yang, Daksh Mittal, Jing Dong et al. (+1 more)
As
agents are deployed with increased autonomy, even extremely rare events along their
stochastic output trajectories can occur and prove catastrophic. Safe deployment therefore does not depend on whether these events can occur, but on how often they might. We study the problem of estimating the probability of rare events that arise from
stochastic variation in the
agent's own actions. Estimating this type of risk requires searching over the combinatorially vast space of trajectories. Naive Monte Carlo is computationally prohibitive in this regime, and constructing effective importance sampling (IS) proposals requires coordinated changes to a context-dependent chain of conditional distributions. We develop a new IS method that perturbs the original model's weights to construct the proposal. The proposal is itself a differentiably parameterized
language model, enabling gradient-based search over weight space. We formulate an objective that combines a differentiable surrogate for event amplification and an adaptive regularization scheme that dynamically balances amplification against
estimator stability. We evaluate our approach on $\sim$120M and $\sim$2.6B models across three event families spanning 300+ rare events as rare as $10^{-9}$, with reference probabilities computed with $<10\%$ relative standard error. In our most verifiable settings, we observe that our IS
estimator achieves over $800\times$ compute-weighted efficiency gains over naive Monte Carlo for events with probabilities lower than $10^{-7}$. Our implementation is available at https://github.com/namkoong-lab/iterative-unalignment.
Read the full abstract ▾
All authors Hanming Yang, Daksh Mittal, Jing Dong, Hongseok Namkoong
Artificial Intelligence
Emergent Collusion in Long-Horizon LLM Agent Interaction
Xinrui Shi, Yanzhe Zhang and Diyi Yang
LLM
agents are increasingly deployed in collaborative settings, yet long-term interaction may give rise to undesirable coordination. We study the emergence of collusion in a long-horizon multi-
agent environment: two
agents repeatedly complete individual tasks, share task logs, verify each other's work, and receive rewards. We introduce realistic constraints under which higher reward is attainable only by violating the verification protocol, and find that
agents increasingly deviate from the protocol over repeated interactions. Collusion emerges in 94% of trajectories across 10 models, and more capable models within the same family reach it earlier. Controlled peer interventions show that collusion is shaped by peer behavior, while ablations reveal additional effects of the verification feedback
agents receive, their interaction history, and the reward structure. In particular, restricting the amount and scope of interaction history available to
agents reduces collusion. Overall, our findings show that long-horizon interaction can reshape how
agents coordinate in ways that create safety risks.
Read the full abstract ▾
Systems and Control
Efficient physiological control of an integrated system architecture for continuous-flow ventricular assist devices: in-silico study
Bruno J. Santos and Idagene A. Cestari
This study presents the development and in silico evaluation of an Integrated System Architecture (ISA) for the physiological control of continuous-flow ventricular assist devices (VADs). The system employs an automatic controller based on pressure measurements at the VAD inflow cannula to estimate heart rate and ventricular filling pressure, enabling dynamic speed adjustments that optimize VAD-patient interaction. The evaluation encompassed 27 simulation scenarios assessing four aspects: operating speed regulation, responsiveness to variable demand, adverse event mitigation, and physiological impact. The controller continuously adapted to preload, afterload, and heart rate, accommodating flow demands with speed adjustments ranging from -10% (-600 rpm) to +43% (+2,600 rpm) relative to the baseline (6,000 rpm). Furthermore, dynamic regulation eliminated ventricular suction and backflow events, which were previously observed in 12 of the 27 uncontrolled scenarios. Hemodynamic and metabolic outcomes demonstrated improved left ventricular ejection fraction (+6.23% to +62.31%), reduced ejection work (-1,658.64 to -206.37 mmHg*mL), decreased pressure-volume loop area (-9,485.17 to -1,056.05 mmHg*mL), and reduced myocardial oxygen consumption (-20.5 to -1.14 mL/min). Concurrently, total oxygen delivery increased (+56.9 to +626.23 mL/min) along with cardiac power (+100 to +3,070 mW). These findings demonstrate that the ISA successfully maintains physiological regulation and mitigates adverse events, establishing a solid foundation for future in vitro validation.
Read the full abstract ▾
Computation and Language
Jev for Scientific Decisions: Evaluating Semantic Choices and Their Consequences
Boyuan Deng, Shuyi Fan, Hongyang Zhang et al. (+1 more)
Scientific workflows often require choosing among known relations before a deterministic calculation can proceed. Whether observations share a culture, treatment or reference standard can change the scientific meaning of the resulting count or comparison. Once the evidence is prepared and the calculation is written as code, this choice reduces to one semantic judgment among listed candidates. We evaluate Jev on this step, using a harness that follows its documented guidance. The study compares twelve model configurations on twenty Choices in ten scientific cases built from published sources, each repeated five times. We measure semantic selections, downstream outputs and final claim labels separately. Jev tied with five other configurations at complete semantic correctness and achieved the lowest observed median latency and known mean cost among successful responses. On one question, whether samples shared a culture, three comparison models made seven wrong selections that changed downstream counts while preserving the correct final label. These results support using Jev to select relations when the evidence and candidates are prepared in advance, and show that evaluating it requires checking the relations and quantities that a workflow will reuse.
Read the full abstract ▾
All authors Boyuan Deng, Shuyi Fan, Hongyang Zhang, Xinhong Xie
Multiagent Systems
Perception-Aware Communication Middleware for Distributed Visual Perception in UAV Swarms
Manveen Kaur, Kevin Loi, Ifunanya Okafor et al. (+2 more)
Unmanned Aerial Vehicle (
UAV) swarms increasingly support safety-critical applications that rely on distributed visual perception. Meeting the low-latency requirements of these applications can require perception models to execute within the swarm on inference-capable
UAVs, creating a need for efficient
UAV-to-
UAV transport of high-bandwidth perception data. However, the Quality-of-Service (QoS) requirements of perception differ from conventional packet-level QoS; successful delivery of individual packets does not ensure that a complete, timely, and usable image is available for inference. We present a novel perception-aware communication middleware that treats complete perception-data samples as the communication objects for which QoS must be satisfied. The middleware extends a lightweight UDP broker-based publish-subscribe architecture with perception-specific services, including image fragmentation and reconstruction, concurrent packet transmission, priority-aware scheduling, and image quality assessment. The middleware is evaluated on a heterogeneous hardware testbed emulating a
UAV swarm using YOLOv8n object detection. Experimental results demonstrate low end-to-end application latency, substantially higher throughput than a lightweight UDP broker, effective prioritization of perception traffic under increasing background load, and mitigation of object-detection degradation through middleware-level image quality assessment. This work provides an initial framework for integrating AI-specific data handling into communication middleware to support emerging distributed AI applications in multi-
agent mobile cyber-physical systems.
Read the full abstract ▾
All authors Manveen Kaur, Kevin Loi, Ifunanya Okafor, Daniel Ng, Joseph Lucey-Renteria
Human-Computer Interaction
Generative Tutorial: Towards Live Contextualized Visual Instructions for Physical Tasks
Muzhe Wu, Zuchen Li, Xu Wang et al. (+1 more)
Visual instructions for physical tasks are typically authored in one context and followed in another, requiring users to translate demonstrated tools, materials, and spatial relationships into their own environment. We introduce Generative Tutorial, a conceptual framework for live visual instruction that depicts intended outcomes and actions within the user's environment and task flow. A formative evaluation of state-of-the-art image and
video generation identifies failures and potential benefits across 15 physical tasks. Drawing on these findings, we build an augmented-reality prototype system that proactively generates goal images and demonstration
videos using observed workspace context and predicted visual outcomes of preceding actions. A 24-participant lab study found higher task performance quality, greater perceived workspace correspondence, and shorter step-confirmation intervals with the system than with pre-authored guidance. Qualitative findings highlighted how contextual resemblance shapes trust, how generation errors affect interpretation, and how guidance delivery should adapt to users' needs, informing future designs.
Read the full abstract ▾
All authors Muzhe Wu, Zuchen Li, Xu Wang, Anhong Guo
Machine Learning · Cross-listed from stat.ML
JAREX: An Acquisition Function for Multi-Objective Algorithmic Process Characterization
Xinyang Li, Kevin Stone and Ajit Vikram
Pharmaceutical process characterization is central to Quality by Design because it defines how variations in process parameters affect the ability to meet product quality specifications, thereby supporting proven acceptable ranges and robust manufacturing. In practice, however, characterization still relies largely on factorial design of experiments (DOE) approaches, which are inefficient for resolving multivariate pass/fail boundaries in higher-dimensional spaces. While
Bayesian optimization has transformed process optimization, adaptive methods for multi-objective process characterization remain lacking. Here, we introduce JAREX (Joint Acceptable Region EXploration), a
Bayesian active-learning acquisition function for multi-objective process characterization. JAREX formulates characterization as a joint boundary-learning problem and adaptively selects experiments to recover the joint pass region defined by simultaneous satisfaction of threshold criteria across multiple objectives. JAREX combines an optimistic joint-feasibility mask with a multi-objective extension of randomized straddle, focusing sampling on the joint edge of failure. Our
benchmark study suggests that JAREX provides more accurate and sample-efficient recovery of the joint pass region than factorial DOE, space-filling designs, and greedy objective-wise strategies over the full experimental budget range. For batched experimentation, it reduces the number of iterative process characterization experiments by more than half while preserving high accuracy for the boundary-identification task. Implemented in the open-source obsidian package, JAREX provides a modular framework for adaptive, data-efficient multi-objective algorithmic process characterization, supporting sample-efficient range finding in high-dimensional spaces.
Read the full abstract ▾
Robotics
Learning to Drive on Mars: Visual Multimodal Traversability Estimation for Off-World Navigation
Darren Chiu, Cole Wilson, Andrei Tumbar et al. (+2 more)
Autonomous
navigation on Mars requires vehicles to distinguish between traversable terrains across diverse and visually challenging environments. However, progress in learning-based
navigation for off-world environments has been limited by the lack of large-scale
datasets. Since landing in Jezero Crater, the Mars 2020 Perseverance rover has traversed terrain ranging from sandy dunes, rocky patches, and flat bedrocks. As a result, this paper presents a
dataset spanning 500 sols and 45km of trajectories driven by both human operators and the onboard planner, ENav. Our
dataset contains grayscale stereo image pairs, poses, accelerometer readings, rocker-bogie angles, and estimates of tilt and wheel slip. Building on this
dataset, we introduce an uncertainty-aware traversability-estimation framework that learns terrain representations from
multimodal driving experience. We compare our proposed method against existing approaches on the Mars 2020
dataset and show that our method achieves an AUROC of 0.874 and an F1 score of 0.758, outperforming the strongest baseline by 0.058 and 0.156, respectively, while also achieving the highest average precision and recall. Finally, we show that the visual representations can be integrated into path planners, such as ENav, on a physical rover test bed.
Videos, code, and the M2020
dataset will be available at https://darren-chiu.github.io/learning-to-drive-on-mars.
Read the full abstract ▾
All authors Darren Chiu, Cole Wilson, Andrei Tumbar, Gaurav S. Sukhatme, Steven Myint
Machine Learning
Learning Physics from an Imperfect Ancestor
S. Mohammad Mousavi, Teeratorn Kadeethum, Nikolaos Bouklas et al. (+1 more)
Neural operators evaluate parametric partial differential equations cheaply but degrade sharply outside their training distribution. Physics-informed neural networks avoid dependence on labeled data, yet their optimization can be basin-fragile: when the governing residual admits multiple solutions, a PINN trained from scratch may converge to a physically incorrect state despite achieving a small residual. We show that these failure modes can be addressed jointly: an imperfect NO provides the structural prior needed to place a PINN in the correct solution basin, while the PDE residual refines the solution beyond the operator's accuracy. We introduce a three-stage framework that freezes the spatial basis of a physics-informed NO, extrapolates its solution branch to an out-of-distribution parameter using a
polynomial continuation prior, and distills the resulting field into a fresh PINN. The NO need not be accurate at the target; it transfers solution-branch information, while PDE residual minimization in the PINN governs convergence. We evaluate the framework on three nonlinear PDEs: 1D viscous Burgers, 2D steady Allen-Cahn near a pitchfork bifurcation, and 2D steady lid-driven cavity flow. For Allen-Cahn, where the trivial solution satisfies the PDE residual exactly, a standard PINN collapses to the trivial zero branch, whereas
distillation from the crude extrapolated operator recovers the non-trivial branch that matches the finite-difference reference. For the lid-driven cavity, extrapolating to a Reynolds number of Re = 3200 accelerates convergence to the correct physical state, achieving competitive accuracy using fewer parameters and optimization steps than recent literature baselines. These results establish a simple principle: an NO need not accurately predict the solution to be useful; it only needs to identify the correct basin from which PINN optimization can recover it.
Read the full abstract ▾
All authors S. Mohammad Mousavi, Teeratorn Kadeethum, Nikolaos Bouklas, Somdatta Goswami
Data Structures and Algorithms
Approximating Prize-Collecting TSP below 1.556
Hong Li
The prize-collecting traveling salesperson problem is a variant of the metric traveling salesperson problem in which vertices may be left unvisited by paying their associated penalties. The objective is to minimize the length of the tour plus the total penalty of the unvisited vertices. Blauth, Klein, and Nägele gave the previously best-known LP-relative $1.599$-approximation. Their
algorithm constructs tours by applying a splitting-off preprocessing to an LP solution, decomposing the resulting solution into trees,
pruning them, and performing parity correction. We improve the LP-relative approximation ratio to $1.55576$. Our main contribution is a new bound on the cost of parity correction that exploits parity information revealed by further
pruning in the analysis. This bound makes the splitting-off preprocessing unnecessary, so the improvement is achieved by a simpler version of their
algorithm. The stated factor follows from a numerical parameter search with exact verification, while an elementary analysis already yields an LP-relative $1.56$-approximation.
Read the full abstract ▾
Numerical Analysis
A Contour Method for Multiparameter Eigenvalue Problems
Emil Graf and Alex Townsend
Multiparameter
eigenvalue problems arise in boundary value problems, stability analysis, and delay-differential equations. Despite their importance, existing methods either require solving extremely large global problems or rely on local iterative techniques that only recover a few
eigenvalues at a time. In this work we develop the first contour method for analytic multiparameter
eigenvalue problems. The key theoretical ingredient is a new residue formula for multivariate
matrix-valued analytic functions, extending Beyn's Keldysh-based residue
theorem for meromorphic operator functions to several complex variables. Using this, we derive a multidimensional analogue of Beyn's contour method that computes all the
eigenvalues of a multiparameter
eigenvalue problem contained in a prescribed region of $\mathbb{C}^d$. The resulting
algorithm targets
eigenvalues in a region without constructing preposterously large
matrices and is embarrassingly parallelizable. Numerical experiments demonstrate that we can now successfully solve large multiparameter problems arising in applications where existing approaches struggle.
Read the full abstract ▾
Machine Learning
Exactness at Inference: A Representational Criterion for Out-of-Distribution Generalization
Filipe Marinho Rocha, Inês Dutra, Vítor Santos Costa et al. (+1 more)
A model generalizes outside its training distribution only when it computes a representation structurally equivalent to the generating mechanism, not an approximation fitted to it. Such equivalence is necessary for exactness in and out of distribution, and extrapolation is governed by this exactness at inference, whatever its realization. Tensor Logic shows this: a zero-temperature contraction is equivalent to discrete logic, deducing in place with no artefact extracted, its tensors Boolean, its
embeddings orthonormal, only its arithmetic continuous. Lacking infinite recursion it reaches Datalog, not Prolog, and though exact over closed domains it needs external
memory to bind a novel entity. The criterion needs neither a discrete representation nor an extracted expression, and constrains inference, not training: an exact marginal in $[0,1]$ passes, a Neural Network thresholded to a hard label does not. Logic Tensor Networks fail it, while differentiable ILP and Tensor Logic at $T=0$ pass. Piecewise-affine extrapolation divergence and an inability to bind novel entities are two faces of a shortfall in exact representability. For hybrid architectures, a propagation rule follows: the output inherits the bounds of every fitted
estimator on its path, explaining which axes fail in equivariant models and the ARC-AGI induction/transduction split. Only an exact hypothesis class certifies what the training data leave underdetermined: on a law-derived partition it finds the $56.3\%$ of distant queries that are answerable, which ensembles meet with false confidence and distance metrics rank backwards. Common inductive biases, from
symmetries to
memory, reach exactness only because humans inject them, an argument for inducing exact representations rather than fitting surrogates whose residuals, even at the arithmetic floor in training, diverge outside the data and compound under composition.
Read the full abstract ▾
All authors Filipe Marinho Rocha, Inês Dutra, Vítor Santos Costa, Luís Paulo Reis
Computer Vision
Anatomy-Decomposed Chest Computed Tomography (CT) Projections as Scalable Supervision for Bone Suppression in Chest Radiographs
Mrunmay Angaitkar, Piyush Kumar, Aarjav Satia et al. (+4 more)
Bone overlap can obscure abnormalities in chest radiographs, while scarce paired training data limit supervised bone suppression. We address this challenge with a digitally reconstructed radiograph (DRR) framework that converts chest computed
tomography (CT) into paired supervision for component suppression. A novel bone
segmentation algorithm enables CT decomposition into bone, non-lung soft-tissue, and lung components, which are projected separately. Their weighted combination yields synthetic radiographs with pixel-registered component images that sum exactly to the full DRR. Models trained on these data suppress bone or lung components by predicting the target component and recovering the remainder by subtraction, transferring to real radiographs without real paired training data. As an extension, their outputs on real radiographs provide target domains for unpaired, component-wise DRR translation, reducing the appearance gap while retaining anatomical details. Across multiple public
datasets, downstream detection experiments demonstrate the utility of bone suppression, with gains concentrated on abnormalities with substantial bone overlap. Compared with open-source DRR engines applied to the same CTs, our unmodified DRRs achieve comparable realism and preservation of label-relevant anatomy, while translated DRRs achieve the best Fréchet inception distance (FID), lung-field sharpness, and agreement with source-CT anatomy among the evaluated methods. Models and inference code: https://huggingface.co/qureaiorg/bone-suppression ; Translated projections: https://huggingface.co/
datasets/qureaiorg/ct2xr-projections.
Read the full abstract ▾
All authors Mrunmay Angaitkar, Piyush Kumar, Aarjav Satia, Pranav Rao, Ashish Mittal, Manoj Tadepalli, Preetham Putha
Data Structures and Algorithms
The Facility Advantage in the One-Round Discrete Voronoi Game on a Line
Tamal Maharaj
In the one-round discrete Voronoi game a multiset $V$ of $n$ voters on a line is given; player P places $k$ facilities, player Q then places $\ell$, and each voter is won by the nearer facility, ties going to P. P wins if it keeps at least $n/2$ voters. In the vocabulary of competitive location this is the absolute $(\ell|k)$-centroid problem on a path with unit demands, and the responder's problem is the $(\ell|X_k)$-medianoid, whose closed form on a path – the sum of the $\ell$ largest of at most $2k$ explicit marginals – is due to Spoerhase and Wirth. We record this structure, with complete proofs, and draw two consequences that we believe are new. First, we compute the value of the game against a single responding facility, $\Gamma_{k,1}(V)$, together with an optimal strategy for P, in $O(n\log n)$ time for arbitrary positive real demands and every $k$. This improves the $O(kn\log^2 n)$ bound of Lazar and Tamir for the absolute $(1|k)$-centroid on a path. Second, we study the facility advantage $k^*(\ell)$, the least $k$ for which P wins every instance against $\ell$ facilities. We prove $k^*(\ell)\le 2\ell-1$, exhibit instances proving $k^*(\ell)\ge\ell+1$ for $2\le\ell\le6$ (an exact, computer-assisted proof resting on a half-integer discretisation), determine $k^*(1)=1$ and $k^*(2)=3$, and show that on uniform instances $k=\ell$ already suffices, so the extremal instances are weighted and Q wins them by a single voter. We
conjecture $k^*(\ell)=\ell+1$ for all $\ell\ge2$.
Read the full abstract ▾
Human-Computer Interaction
Whose Facts Count? A Culturally Responsive Audit of LLM Evaluation Benchmarks
Fatima Tuz Zahra, Md. Sajeebul Islam Sk. and Rachel Chung
LLM
benchmarks function as evaluation instruments, informing decisions that affect education, labor, and public services worldwide. Drawing on Hood, Kirkhart, and Hopson's culturally responsive evaluation (CRE) frameworks, this paper applies a six-dimension CR rubric to audit OpenAI's SimpleQA (N = 4,326 items) and the LMSYS Chatbot Arena (N = 600 conversations). Every SimpleQA question requires English-
language archival verification as its evidentiary basis. A single rater's preoccupation with Colombian founding dates accounts for 2.70% of items, inflating the appearance of Global South coverage. English-
language prompts constitute 76.3% of Arena conversations, against an International Telecommunication Union (ITU)-estimated 25.9% share of global internet users. A 50-item counter-
benchmark scored a mean CR deficit nearly three times lower than SimpleQA (Cohen's d = 1.01). The paper proposes a practical CR evaluation framework. These are structural validity failures, not incidental measurement problems, with direct consequences for communities whose knowledge traditions these instruments were not built to see.
Read the full abstract ▾
Computation and Language
Linguistic Features for Interpretable Textual Entailment
David Torres-Moreno, Jorge Hermosillo-Valadez and Asela Reig-Alamillo
Despite the success of neural models in natural
language processing, their black-box nature limits interpretability and conceals the linguistic phenomena underlying their predictions. We present SLITE, an explainable hybrid model for Recognizing Textual Entailment that integrates two complementary layers of semantic analysis: a structural-relational layer, based on semantic compatibility and incompatibility between compositional entities, and a distributional-informational layer, based on structured patterns of information change between
embedding-based representations of the premise and the hypothesis. We propose 17 features that combine entity-level semantic relations, polarity-sensitive lexical matching, and
alignment measures over semantic sub-representations of the similarity
matrix, including measures based on
entropy and transfer
entropy. A logistic regression trained on these features achieves an accuracy of 83% on three-class SICK and 96% on SICK-CE, outperforming IsoLex by 4 percentage points and falling within 2 percentage points of RoBERTa with a fraction of its computational complexity. Ablation studies and SHAP analysis confirm that structural-relational features are the primary drivers of classification, while distributional-informational features provide essential complementary contributions, particularly for detecting neutrality and contradiction. Our results demonstrate that further exploration of hybrid approaches is a viable and scientifically productive alternative to massive neural architectures, and we hope they will strengthen the dialogue between linguistic theory and computational modeling of inference
Read the full abstract ▾
Data Structures and Algorithms
A Proof of the Most Informative Boolean Function Conjecture
Zijie Chen, Amin Gohari, Adel Javanmard et al. (+4 more)
Let $X$ be uniform on $\{-1,1\}^n$, let $Y$ be obtained by passing its coordinates independently through a binary symmetric channel with crossover probability $p$, and let $g:\{-1,1\}^n\to\{0,1\}$ be a Boolean function. We give a computer-assisted proof of the Courtade–Kumar
conjecture $I(g(X);Y)\le1-H_2(p)$, where $H_2$ is binary
entropy, with equality attained by dictator functions. The present work builds on the differential-equation method, itself a limiting form of the auxiliary-receiver approach in network information theory using a continuum of degraded receivers. The proof proceeds from a local inequality to a dimension-independent bound on
entropy production. Differentiation along the Boolean noise
semigroup expresses
entropy production as an average of edge costs. The key estimate is therefore an unrestricted Bellman inequality with two mean constraints and two
entropy constraints, allowing arbitrary couplings of the edge variables. This paper and its supplement provide the proofs and computational verification records. The document is lengthy because it is designed to be entirely self-contained, deriving all proofs from first principles and reproducing the proofs of cited results. We also give a self-contained expository note explaining the reduction to a low-dimensional inequality and the ideas behind the key lower bounds. The entire proof, including all numerical certificates, has been formally verified in Lean end-to-end, and is available online.
Read the full abstract ▾
All authors Zijie Chen, Amin Gohari, Adel Javanmard, Honghao Lin, Vahab Mirrokni, Chandra Nair, David P. Woodruff
Machine Learning · Cross-listed from math.ST
Conformalized Quantile Regression and Minimax Limits of Fixed-Score Calibration under Known Covariate Shift
Rustam Isaev, Anton Conrad, Denis Belomestny et al. (+2 more)
In this paper, we study nonasymptotic $L^p$ error bounds for interval length and conditional coverage in split conformalized
quantile regression (CQR). Our bounds rely on local regularity conditions and accuracy guarantees for the estimated
quantiles. We further instantiate our bounds for
quantile regression with sparse ReLU neural networks. We also consider
covariate shift, where the calibration and test
covariates have different distributions, and derive nonasymptotic bounds for this setting. We obtain matching minimax upper and lower bounds in expectation for two constructed fixed-score calibration
benchmarks under known
covariate shift. The bounds match for every $p\in[1,\infty]$ in the scalar problem and for finite $p$ in the $K$-threshold problem; for the latter, a high-probability minimax lower bound holds for every $p\in[1,\infty]$.
Read the full abstract ▾
All authors Rustam Isaev, Anton Conrad, Denis Belomestny, Eric Moulines, Sergey Samsonov
Software Engineering
Trajectory-Aware Benchmark Subset Selection for Cost-Efficient Software Engineering Agent Regression Testing
Mahmoud Ayyad, Zehao Wang, Jiho Shin et al. (+2 more)
Autonomous software engineering
agents (SWE-
agents) automate coding tasks. Each
agent update may require re-running the full
benchmark to detect regressions and improvements, at a cost of hundreds of millions of LLM
tokens per run, which makes evaluation a bottleneck. One solution is to evaluate only a subset of
benchmark instances. Yet, simple approaches, such as random sampling or stratified random sampling based on past pass/fail outcomes, risk producing high variance and unrepresentative subsets. We turn to
agent trajectories, the step-by-step record of the actions an
agent took. We propose a trajectory-aware subset selection approach that replaces random sampling with deterministic selection based on trajectory
embeddings. We first group test set instances by their test outcome in a recent full test run to preserve the historical pass/fail rate, then select the subset using the trajectory's
embedding space. We evaluate 76 subset selection configurations, including random sampling,
embedding-based selection, clustering-based selection, and hybrid shortlist-then-subsample strategies, across three regression scenarios: same-configuration reruns, model and configuration changes, and
agent framework changes. Our best trajectory-aware method is the one selecting
benchmark instances closest to the centroid of each outcome group in the
embedding space. It achieves the lowest estimation error among all methods we evaluate. For instance, when evaluating a given
agent version on a selected subset of 5% or 10% of the test instances, our approach reduces the average estimation error by 3–11% and the worst-case error by 4–11% relative to the typical draw and 38–46% relative to the 95th-percentile draw of the strongest baseline. Our results show that a 10% trajectory-aware subset keeps the median estimation error below 5% while cutting
token cost by roughly 90%.
Read the full abstract ▾
All authors Mahmoud Ayyad, Zehao Wang, Jiho Shin, Ying Zou, Bram Adams
Artificial Intelligence
Et Tu, Brute? Economic Misalignment in Personal AI Agents
Aman Priyanshu, Supriti Vijay, Brian Jabarian et al. (+1 more)
Personal AI
agents make recommendations and take actions on people's behalf in high-stakes economic contexts, e.g., buying a flight, choosing health insurance, or selecting a graduate program. The
agent is given access to the user's personal context, e.g., their email inbox and a structured profile of personal attributes, with the intention of making an optimal, personalized decision for the user. We show that by simply providing this personal context, the
agent steers recommendations based on inferred wealth, without being explicitly instructed to do so. In a suite of 325K experiments on 13
agents across three types of economic decisions (flights, health insurance, and graduate programs), we find that 8 models systematically choose more expensive options for wealthier users when requests are identical. This steering continues even when it directly goes against the user's stated objective: when explicitly instructed to find the cheapest option, some
agents still act on the wealth profile they have inferred. It also occurs when wealth is inferred from ambient data, such as emails unrelated to the task. And it persists under
privacy controls that block specific attributes: blocking financial attributes largely removes the disparity, but blocking other attributes leaves it unchanged and can increase it by up to 40% for insurance, as
agents rely on the remaining signals to infer wealth. Larger and more capable models are no better; Claude Opus 4.8 shows the largest effect. We term this misalignment "
adversarial delegation", in which the very conditions that make a personal AI
agent useful - access to personal information - enable it to act against the user's interests.
Read the full abstract ▾
All authors Aman Priyanshu, Supriti Vijay, Brian Jabarian, Niloofar Mireshghallah
Logic in Computer Science
A decision procedure for intuitionistic modal logic IS4 (and IK4)
Marianna Girlando, Roman Kuznets, Sonia Marin et al. (+1 more)
In this paper, we show that the two intuitionistic modal logics IS4 and IK4 are decidable. We provide a constructive decision procedure, that, given a formula, produces either a proof showing the formula to be valid or a finite countermodel falsifying the formula, thus also proving the finite model property for both logics. The main ingredient of our strategy is the introduction of (possibly unsound) loop rules, which encode repeating behaviour in proof search. This paper fixes a previous mistake in our LICS'23 contribution.
Read the full abstract ▾
All authors Marianna Girlando, Roman Kuznets, Sonia Marin, Lutz Straßburger
Artificial Intelligence
BackTrend: Evaluating Scientific Weak-Signal Prediction via Backward Reconstruction
Xiao Zhou, Yilun Zhao, Owen Jiang et al. (+4 more)
Scientific weak signals are early, low-visibility research directions that later become central to mature scientific topics, yet existing resources such as trend tracking, citation
forecasting, and foresight reports rarely provide validated reference sets that link concrete early precursors to later paradigms. We introduce BackTrend, a retrospective
benchmark in which, given a mature target topic and a temporal evidence constraint, systems must recover two types of precursors: problem-space signals, underrecognized research problems, and solution-space signals, emerging methods for known problems. BackTrend contains 25 mature target topics in artificial intelligence and machine learning and 66 human-validated weak signals, reconstructed from large-scale literature by grounding each candidate in its 2019-2024 publication-frequency trajectory. We evaluate frontier LLMs, RAG systems, and agentic research systems using semantic matching and coverage-based metrics. Current systems often generate plausible but misaligned precursors, exhibiting topic drift, granularity mismatch, near-miss matching, and incomplete coverage; the strongest system achieves only 10.1% F1, while Coverage10 reaches at most 18.5% of the reference signals. Our budget analyses show that additional
retrieval and web-search evidence can improve performance up to a moderate budget, but does not by itself close the substantial performance gap.
Read the full abstract ▾
All authors Xiao Zhou, Yilun Zhao, Owen Jiang, Tiansheng Hu, Cai Xu, Manasi Patwardhan, Arman Cohan
Computer Vision
Yongsheng Yu, Wei Xiong, Yichen Sheng et al. (+2 more)
Recent advances in pixel-space
diffusion models have narrowed the image quality gap with latent-space
diffusion, but still converge more slowly and lag behind in final image quality. We argue that a key reason is the lack of an explicit representation prior: unlike latent
diffusion, which usually denoises in a compact and structured latent space, pixel
diffusion needs to learn denoising-friendly representations and pixel generation simultaneously from raw RGB space. To address this problem, we propose PixelDiT2, an end-to-end pixel-space
diffusion model designed to decouple representation learning from pixel generation without introducing an autoencoder or latent reconstruction bottleneck. We propose representation grounding that uses a frozen pretrained
vision foundation model to provide explicit per-patch representation guidance throughout denoising, allowing the pixel
diffusion transformer to focus more on pixel generation. On ImageNet-256x256, PixelDiT2 achieves an FID of 1.46 after 600 epochs; at 512x512 resolution, PixelDiT2 achieves an FID of 1.48 after 680 epochs. Project page: https://pixeldit.github.io/pixeldit2/
Read the full abstract ▾
All authors Yongsheng Yu, Wei Xiong, Yichen Sheng, Shiqiu Liu, Jiebo Luo
Computation and Language
SocioVerse2: A Longitudinal Dynamic Social Simulation Framework under a Human-AI Co-evolutionary Paradigm
Xinnong Zhang, Jiayu Lin, Jia Wang et al. (+19 more)
Social simulation offers the social sciences an experimental instrument that the real world cannot supply, and generative
agents have transformed it by acting as silicon samples that unite
agent-based modeling with real behavioral data. Existing platforms verify collective behavior, align simulated populations with real societies in cross-sections, and employ autonomous
agents for the research process. However, two social science requirements remain without systematic support: intervention in the content of a simulation and the researcher's control over the process that produces it. We present SocioVerse2, which extends SocioVerse 1.0 into a human-AI co-evolutionary paradigm built from two loops and one infrastructure. The longitudinal simulation loop simulates the target population with evolving environments and forks counterfactual branches via interventions. The controllable research loop takes the study itself as an editable state and updates state versions via controllable editing. The social science agentic infrastructure carries both loops through composable skills with researcher checkpoints, a population service over five persona pools, and an environment service over 21 real-world signal sources with point-in-time guarantees. We validate SocioVerse2 across three case families and seven case studies, from reproducing canonical
agent-based models to modeling policy processes on real records and nowcasting macro-economic indices beyond the response model's knowledge cutoff. With the human-AI co-evolutionary paradigm, these cases go beyond system demonstrations to become substantive studies that investigate frontier questions in their respective disciplines. Code, data services, and a workbench are released as open-source resources.
Read the full abstract ▾
All authors Xinnong Zhang, Jiayu Lin, Jia Wang, Yixu Huang, Xinyi Mou, Yingqian Wu, Jingcong Liang, Shijun Lei, Jianing Shi, Guanying Li, Siyuan Wang, Hanjia Lyu, Zhenfei Yin, Yunlu Yin, Siming Chen, Yulan He, Jiebo Luo, Xuanjing Huang, Liyin Jin, Baohua Zhou, Hanqi Yan, Zhongyu Wei