Machine Learning
TRACER: Trace-Regularized Training Against Indirect Prompt Injection
Kshitij Mishra, Salem Lahlou and Nils Lukas
Indirect
prompt injection uses untrusted retrieved content, tool outputs, or
agent messages to override an LLM's intended behavior. We show that defense robustness is channel-conditioned: the same attack succeeds 18% of the time as a follow-up message but 53% when placed in retrieved context. We propose TRACER (Trace-Regularized
Adversarial Channel Exposure with Reward-shaping), a channel-aware
adversarial training method that samples presentation wrappers and combines an answer-anchored, evidence-gated reward with ATRC, which aligns attacked
reasoning with clean evidence when an injection is invalid. On GSM8K with Qwen2.5-3B-Instruct, TRACER reduces RAG-framed ASR from 65.5% to 6.1% while preserving 78-82% clean accuracy. Joint RAG+tool training achieves 13.9% average ASR across framings at 3B scale, while a single epoch at 7B reaches 9.4%. These results demonstrate that robust defenses must explicitly train and evaluate across deployment channels.
Read the full abstract ▾
Artificial Intelligence
Plant Memory: Technical Language Processing and a Verified Maintenance Ontology for Agent-Accessible Failure Knowledge from SAP PM Work Orders
Akash Raj
Maintenance work orders are the largest written record of how industrial equipment fails, yet in most plants they are close to unusable for analysis. Short texts are abbreviated and misspelt, asset identity is buried in free text, work-type labels contradict the work described, and the fields that matter most for reliability (symptom, root cause, action taken) are usually empty. As a result, diagnostic knowledge stays with senior technicians and leaves when they do. We present Plant
Memory, a system that applies technical
language processing (TLP) to SAP Plant Maintenance (PM) exports and builds an ISO 14224-aligned maintenance ontology in which every extracted statement is a reified fact carrying a confidence score, the evidence it was read from, and a verification state. Extraction is rule-first, with an optional large
language model (LLM) acting as a second reader whose disagreements raise a fact's review priority rather than overwrite it. Technicians verify facts through a review queue, answer targeted knowledge-gap questions where failures repeat without a recorded cause, and approve or reject ontology drift proposals when new terms appear. The resulting graph is served to people through a web application and to AI
agents through a Model Context Protocol (MCP) server, so both query the same verified knowledge and every answer cites the work orders behind it. On a synthetic 12-month export of 400 work orders from a parboiled-rice plant, rule-based extraction reaches 96.2% component accuracy, 88.9% failure-mode accuracy and 100% root-cause precision at 62% coverage; on 28 diagnostic questions, ranked root causes from the ontology are correct at top-1 in 82.1% of cases against 53.6% for the raw SAP root-cause column.
Read the full abstract ▾
Machine Learning
Imagining Goals with Geometric Horizon Models for Policy Generalization
Daniel Lawson, Dhruv Sreenivas, Adriana Hugessen et al. (+2 more)
Training from offline data has allowed for substantial progress in domains such as robotics, leading to general-purpose policies that can be easily applied zero-shot or efficiently finetuned for downstream tasks. However, these policies can still have poor generalization, both due to the choice of modeling objective and from learning from a static
dataset. In this work, we focus on the challenging task of zero-shot goal generalization, where a policy is evaluated on unseen tasks that require combining its existing knowledge (compositional generalization). An avenue for improving a policy's generalization is by generating new experience with world models; however, such generation has proven difficult for longer horizons. Thus, to alleviate this issue, we propose TD-Aug, which samples from a
geometric horizon model and allows for directly imagining novel outcomes that can be achieved by composing existing knowledge. We demonstrate that training on these future outcomes as goals for goal-conditioned BC policies significantly improves generalization in stitching-based OGBench tasks.
Read the full abstract ▾
All authors Daniel Lawson, Dhruv Sreenivas, Adriana Hugessen, Khimya Khetarpal, Glen Berseth
Multiagent Systems
CLASHarness: Benchmarking Multi-Agent Conflict in Computer Use via a Controllable and Verifiable Generation Pipeline
Yuxiang Lai, Jike Zhong, Chengzhi Liu et al. (+6 more)
Vision-
language models (VLMs) are increasingly deployed in multi-
agent systems to automate complex computer-use workflows, yet existing
benchmarks mostly assume consistent, cooperative environments. In contrast, real-world collaboration rarely runs on consistent information: peer or sub-
agents frequently report outdated states, issue contradictory instructions, or compete over shared permissions and files, forcing
agents to check others' outputs and verify ground truth in the environment. Evaluating such conflict resolution remains challenging: manual authoring cannot scale across complex systems, while unconstrained LLM generation produces narrative drift, answer leakage, and unsatisfiable rubrics. We introduce CLASHarness (Conflict-Loaded
Agent Scenario Harness), a controllable framework for generating verifiable multi-
agent conflicts in computer use, with a
benchmark of 600 multi-round tasks. By combining hierarchical scenario planning with an eight-step verified micro-pipeline, CLASHarness pre-commits decisive visual facts before rendering and compiles hybrid code and semantic graders directly from executed reference trajectories, guaranteeing every task is solvable by construction. Evaluating 15 frontier models on CLASHarness reveals three core bottlenecks. First, when sub-
agent outputs conflict with the environment, weaker models blindly follow misleading information, whereas stronger models inspect visual evidence to verify ground truth. Second, resolving conflicts is much harder than finding them: while
agents can spot inconsistencies, actively fixing system state drops task success significantly. Third, coordination protocols remain a universal bottleneck: even frontier models fail over 58% of closing actions, often forgetting to release shared locks or hand off tasks. CLASHarness provides a scalable, verifiable foundation for building reliable multi-
agent systems.
Read the full abstract ▾
All authors Yuxiang Lai, Jike Zhong, Chengzhi Liu, Ming Li, Haonan Wang, Xiaofeng Yang, Liang Zhao, Youbao Tang, Ruixi Fan
Multimedia
AdaFrame: Hierarchical Multimodal Deduplication with Adaptive Information Budgeting for Cost-Efficient Video Advertisement Analysis
Abdul Basit Tonmoy, Arman Luthra, Guang Lin et al. (+1 more)
Uniform frame sampling for
vision-
language model (VLM)-based
video analysis often floods
multimodal backbones with redundant content, while existing keyframe selection methods are typically optimized for human viewing rather than downstream extraction accuracy. We propose AdaFrame, a content-adaptive preprocessing cascade that reduces visual redundancy without sacrificing extraction fidelity. Three progressively finer filters, perceptual hashing, learned perceptual image patch similarity (LPIPS), and CLIP-based semantic clustering, efficiently eliminate redundant frames before costly cross-modal inference. Per-
video frame budgets are determined using Intrinsic Semantic Dimensionality (ISD), which estimates each
video's semantic complexity through singular value decomposition of its frame
embeddings. Experiments on 500
video advertisements from the Pitt Ads
Dataset show that AdaFrame reduces the frame count by 48 percent and VLM inference cost by 75 percent compared with uniform sampling, while achieving 86.0 percent topic accuracy, an improvement of 1.6 percentage points, and 79.4 percent sentiment accuracy, an improvement of 7.5 percentage points.
Read the full abstract ▾
All authors Abdul Basit Tonmoy, Arman Luthra, Guang Lin, Qixin Deng
Systems and Control
Measurements and Analysis of Distortion in Inertial Force Exciters for Flat-Panel Loudspeakers
Stephen F. Roessner and Michael C. Heilemann
Flat-panel loudspeakers are typically driven by dynamic exciters that employ a voice coil coupled to a reaction mass to exert force on the panel. Unlike conventional loudspeakers, where the cone is relatively light weight, heavy panels may require significant exertion from the driver to achieve sound pressure levels required of consumer grade loudspeakers. Overexertion can cause harmonic distortion and reduced sound quality, especially in drivers where the voice coil is not centered in the
magnetic field. There are many different exciters available commercially with different power ratings and price points. The frequency response, linearity, total-harmonic distortion (THD), intermodulation distortion (IMD), and force vs. displacement were measured for three types of exciters to determine the consistency of manufacturing and use in panel loudspeakers. These exciters were found to have high variability in all metrics among units of the same type. Distortion metrics such as IMD may be reduced by running impedance sweeps to match exciters with similar response characteristics in multi-actuator panels.
Read the full abstract ▾
Machine Learning
PairIT: Autoregressive Transformers for Low-Data Molecule Optimization
Hannah Lawrence, Bodhi P. Vani, Ji Won Park et al. (+5 more)
Generating novel molecules with desired properties is a central challenge in drug discovery. Although foundational work focused on de novo generation, practical use cases require a more complex setting: conditioning on an initial seed molecule, optimizing multiple properties, and operating in data-sparse regimes. We introduce PairIT, a flexible training framework for autoregressive
transformers over SMILES sequences that enables seeded generation by learning from pairs of structurally similar molecules. By leveraging matched pairs, the model learns to generate local, chemically meaningful edits that improve a property of the seed molecule.
Prompt tokens extend this framework by specifying the target property, desired direction, and approximate magnitude of change. Multiple
prompt tokens can be concatenated to enable multi-property optimization at inference time. For properties where pair supervision alone is insufficient, reinforcement learning post-training can further improve optimization, providing a tunable trade-off between proximity to the seed and the optimization objective. PairIT naturally supports pretraining on a large
dataset and fine-tuning on a smaller
dataset, which is critical for performance in data-sparse regimes. Surprisingly, we observe diminishing returns to the scale of the pretraining
dataset. We demonstrate empirically on MoleculeNet and Therapeutics Data Commons
datasets that, with appropriate paired-data curation, a standard
transformer model of modest size (68M parameters) can achieve robust seeded molecular optimization in low-data regimes.
Read the full abstract ▾
All authors Hannah Lawrence, Bodhi P. Vani, Ji Won Park, Natasa Tagasovska, Samuel Don Stanton, Andrew Martin Watkins, Michael Maser, Ewa M. Nowara
Robotics
Learning in Orbit: Onboard Training and Closed-Loop Attitude Control with a Thermal Segmentation Model on a Spacecraft
Elena Sorina Lupu, Hannah Grauer, Phaedrus Leeds et al. (+9 more)
Deep space missions increasingly require spacecraft capable of autonomously operating in environments with communication delays and bandwidth limitations. A key enabler of such autonomy is the ability to run learning-based
algorithms directly onboard. In this work, we present a flight deployment on a 6U CubeSat that demonstrates (1) onboard training and inference of a thermal segmentation model on an NVIDIA Jetson TX2 NX GPU in space and (2) closed-loop attitude control using the segmentation model on a real-time, thermal image feed to track the Moon. In addition to this demonstration, we implement ROS 2 Foxy as a data transport middleware and integrate an open-source file system that provides strong data integrity guarantees and self-healing features. Over the course of approximately one year, we performed 12 experiments on the spacecraft, advancing the state of the art in autonomous spacecraft systems by showing how modern learning-based pipelines, commercially available hardware, and open-source software can operate reliably under the compute and environmental constraints of Low Earth Orbit (LEO).
Read the full abstract ▾
All authors Elena Sorina Lupu, Hannah Grauer, Phaedrus Leeds, Nikhil Ranganathan, Connor Lee, Sulekha Kishore, Cailyn Smith, Shon Cortes, Brian Hardy, Benjamen Bycroft, Darren W. Rowen, Soon-Jo Chung
Machine Learning
Woosang Lim, Haneul Yoo, Vincent-Daniel Yun et al. (+1 more)
Structured
pruning reduces LLM inference costs by removing model components to produce smaller dense models. However, existing methods can cause
reasoning performance to collapse on long-form
reasoning tasks such as AIME. We propose LayerTrim, a training-free structured
pruning method that identifies redundant decoder layers and selectively trims their MLP features while preserving
attention and decoder depth. LayerTrim is the first training-free structured
pruning method designed to preserve long-form
reasoning without gradients or recovery training. Across three
reasoning language models and five
benchmarks, LayerTrim outperforms existing structured
pruning methods in most evaluated settings, improving average accuracy by up to 21.4 percentage points over RESP. On Qwen3-14B, LayerTrim achieves 1.24$\times$ faster prefill and 19.7% lower peak GPU
memory than the dense model, while better preserving
reasoning ability. It also achieves the shortest average generation length among evaluated pruned models, while retaining the highest average accuracy. These results demonstrate that LayerTrim improves
reasoning efficiency through both structural compression and reduced
token generation.
Read the full abstract ▾
All authors Woosang Lim, Haneul Yoo, Vincent-Daniel Yun, Sungjoo Yoo
Computer Vision · Cross-listed from eess.IV
DoReMe: Dual optimization of Reconstruction and Motion estimation for self-navigated free-breathing abdominal MRI using Gaussian Splatting
Majd Helo, Dominik Nickel and Thomas Kuestner
Purpose: Free-breathing abdominal MRI is limited by respiratory motion, which introduces image artifacts and k-space inconsistencies. Existing reconstruction approaches often depend on pre-estimated motion fields or external respiratory surrogate signals. We propose a coupled reconstruction-motion estimation
algorithm for self-navigated free-breathing acquisition, in which motion is represented by compact Gaussian primitives and jointly refined with the image estimates during iterative reconstruction. Methods: An iterative reconstruction that alternates between data consistency updates and motion modelling was proposed. Respiratory motion was represented using Gaussian primitives. A Gaussian splatting was integrated into the reconstruction
algorithm. The method was evaluated on self-navigated free-breathing Cartesian gradient-echo (GRE) acquisition in four healthy volunteers, including retrospective scan shortening experiments, and was compared with regularized compressed sensing (CS) reconstruction. Results: Respiratory motion states were reconstructed in approximately 1.5 min. Compared with CS, the proposed method improved visual image quality, particularly in coronal liver views, and better preserved anatomical structures in retrospectively shortened acquisitions. These findings provide proof of concept for the proposed method. Conclusion: The proposed coupled reconstruction-motion estimation
algorithm improved visual image quality compared with CS alone. Gaussian primitives provided a compact and sufficiently flexible representation of nonrigid respiratory motion with practical runtime, supporting further scanner integration and validation in larger cohorts.
Read the full abstract ▾
Computation and Language
DecisionRobust: Benchmarking Robustness for JEV Style Decision Models Across Text and Vision
Yifan Lan, Zhongye Liu, Yurui Chang et al. (+4 more)
Emerging decision models such as JEV provide typed interfaces that map task instructions and observations directly to choices, judgments, and scores. As these models are increasingly used for automated decision-making, understanding their reliability under
adversarial manipulation becomes critical. We introduce DecisionRobust, a
benchmark for systematically evaluating the robustness of decision models across textual and visual inputs. Our
benchmark covers practical decision-making scenarios and a diverse suite of attacks, including semantics-preserving text perturbations, image perturbations, and
prompt injection in both modalities. We curate evaluation sets through external validity checks and cross-model candidate selection. We evaluate 30 model configurations on text tasks and 17 on
vision tasks, including 24 and 12 held-out models, respectively, that are excluded from candidate selection. Our experiments reveal several key findings. First, attacks expose vulnerabilities beyond the models used for construction and selection, although optimized image perturbations transfer weakly to many targets even with multiple surrogates. Second, relative model robustness varies across tasks and attack types, and resistance to input perturbations does not necessarily imply resistance to
prompt injection. Third, label-consistency checks substantially reduce measured attack success across text and image settings, highlighting the importance of validating apparent failures. The
benchmark is available at https://yifan-lan.github.io/DecisionRobust/.
Read the full abstract ▾
All authors Yifan Lan, Zhongye Liu, Yurui Chang, Hanyu Wang, Yongkang Du, Lu Lin, Jinghui Chen
Machine Learning
Genesis Steering: Better Activation Steering Through Training Data
Tora Bodin, Eric Aubinais, Ilaria Torre et al. (+1 more)
Activation steering controls large
language models at inference time, but its effectiveness depends on the choice of reference data. We introduce genesis steering, which derives a genesis vector from contrastive examples in the model's own fine-tuning data. When these data are unavailable, we draw on the membership inference literature to identify likely training examples and construct a proxy
dataset. We establish two theoretical results on optimal displacement to the decision boundary and reduced proxy-estimation bias. We evaluate genesis steering and membership-based proxy construction on Tülu-3-8B, whose fine-tuning data are publicly available, and Llama-3.1-8B-Instruct as a control. We find that safety data from Tülu-3-8B's training mixture yield stronger steering than external
datasets on both models. On Tülu-3-8B, membership scores largely agree in identifying training examples, and vectors built from top-ranked examples achieve competitive performance against random subsets of the same size. In contrast, the results on Llama-3.1-8B-Instruct hint that a MIA method will only have a positive effect if the mean direction shift with MIA-filtered in-distribution data is much less severe than the direction shift with OoD data.
Read the full abstract ▾
All authors Tora Bodin, Eric Aubinais, Ilaria Torre, Chih-Hong Cheng
Computation and Language
From Copying to Composition: How Language Models Develop In-Context Learning
Minglai Yang, Xinyu Guo, Renxiong Wang et al. (+3 more)
In-context learning (ICL) allows
language models to adapt their behavior from instructions and demonstrations in a
prompt, but accuracy alone does not reveal how contextual information controls their predictions. We study the acquisition and trainability of ICL with a controlled diagnostic that separates copying a nearby demonstration from integrating information across the
prompt. Across 17 models, about a third prefer the copied answer, a few are undecided, and the rest prefer the rule-consistent answer, which goes with higher accuracy and with control by the requested value rather than the closest conflicting example. Checkpoint analyses show that models begin prioritizing task-relevant
prompt tokens over conflicting examples long before their accuracy improves beyond chance level. In matched training experiments, synthetic documents that define endings and then query them shift models toward compositional responses on the controlled diagnostic, whereas fine-tuning on definition exercises built from rewritten real documents improves accuracy when
prompts reassign label meanings. The results suggest that ICL is not acquired as a single, uniform capability. Instead,
prompt control, answer preference, construction without candidates, and transfer can develop along distinct trajectories.
Read the full abstract ▾
All authors Minglai Yang, Xinyu Guo, Renxiong Wang, Sunjie Hou, Daniel Yue Zhang, Yunzhong He
Computer Vision
Towards a Data-Centric Understanding of Spatial Reasoning in Multimodal Large Language Models
Mahdieh Mallahnezhad, Masoud Jafaripour, Mohamadali Tofigh et al. (+2 more)
Multimodal Large
Language Models (MLLMs) have been widely applied in embodied
agents and robotics for
vision tasks. However, MLLMs suffer from limitations in spatial
reasoning and perception. Post-training techniques have shown promise for improving these capabilities; yet, there are limited data-driven surveys of such approaches. In this survey, we consider approaches to fine-tuning pretrained MLLMs for spatial
reasoning tasks, ranging from supervised to reinforcement learning, with an emphasis on the
datasets used. We investigate themes of
dataset construction, data modality and annotation, and evaluation of the resulting models. Based on these themes, we categorize research into three groups:
dataset design,
dataset construction and evaluation. We find four main methods for constructing fixed spatial annotations: rules and templates, LLM prompting, procedural generation, and human-in-the-loop. We also observe substantial variation in evaluation approaches, including different scoring methods, tolerance metrics, and
benchmark types. Finally, we identify opportunities for future research in unified dynamic annotation, efficient spatial
reasoning, standardization of evaluation, expanded spatial range, and human-centered spatial interactions.
Read the full abstract ▾
All authors Mahdieh Mallahnezhad, Masoud Jafaripour, Mohamadali Tofigh, Sheila Schoepp, Osmar R. Zaiane
Machine Learning · Cross-listed from stat.ML
Neural Supervised Clustering for Learning Individualized Treatment Rules with Many Treatments
Daixi Huang, Yixin Yuan, Yifan Dai et al. (+1 more)
Learning an individualized treatment rule (ITR) with many treatments requires estimating treatment-specific effects from limited observations per arm. Treatments with similar conditional responses can share information, but linear contrast models may miss nonlinear heterogeneity. We propose nonlinear supervised clustering fusion (NSCF), a neural Q-learning framework with a shared nonlinear
covariate representation and low-dimensional treatment
embeddings. Pairwise fusion groups treatments with similar learned contrasts, yielding an ITR and an interpretable partition. An alternating
algorithm combines neural training,
embedding fusion, validation-based partition selection, and unpenalized grouped refitting. NSCF lowers regret relative to a strong neural reference in nonlinear exact-sharing simulations; perturbations characterize the limits of hard sharing. In a melanoma xenograft application, NSCF improves average policy value over the neural reference. These results support nonlinear representation learning with supervised treatment fusion when treatment effects exhibit shared structure.
Read the full abstract ▾
All authors Daixi Huang, Yixin Yuan, Yifan Dai, Yufeng Liu
Machine Learning
Contextual Credit Policy Optimization
Huiwen Han, Ziyao Zeng, Zihao Zhu et al. (+6 more)
Group-based reinforcement learning enables large
language model
agents to learn from sparse outcome rewards in long-horizon tasks. Recent methods derive step-level credit by comparing observation-matched experiences across trajectories. However, identical observations can occur in different contexts, and matched peers are not equally informative for a given decision. Moreover, favorable terminal outcomes can obscure redundant actions or detours within successful trajectories. To address these two challenges, we propose Contextual Credit Policy Optimization (CCPO). For the first, CCPO weights observation-matched peers from other trajectories by contextual similarity, computed from frozen LLM representations and accumulated trajectory statistics, allowing peers from similar contexts to contribute more to a step's baseline. For the second, CCPO pairs historical credit, which compares the realized return against the weighted peer baseline, with future credit, which measures the change in contextual outcome value over a short realized continuation. A step is thus credited for the progress it makes, not only for its trajectory's eventual outcome. Both credits are computed in hindsight from rollouts already collected for training, enabling CCPO to address these challenges without an auxiliary value critic. Across two Qwen2.5-Instruct backbones (1.5B and 7B), CCPO achieves up to 97.4% success on ALFWorld and 79.4% on WebShop and outperforms GRPO by up to 21.6 and 18.5 points. Ablations show that contextual weighting outperforms uniform weighting, and that historical and future credit serve as complementary learning signals.
Read the full abstract ▾
All authors Huiwen Han, Ziyao Zeng, Zihao Zhu, Sisong Bei, Hao Wang, Hongyu Xu, Yan Han, Degui Zhi, Zhiwen Fan
Computer Vision
The Gap Is in the Geometry: A Convergent Meta-Analysis of Multi-Facet Aerial and Remote Sensing Video Understanding
Georgios Angelidis, Aggelos Psiris, Maria Vakalopoulou et al. (+3 more)
Aerial and remote sensing
video is increasingly evaluated like web
video, by posing multiple-choice questions to
multimodal large
language models (MLLMs) over sampled frames and reporting accuracy. This paper argues that this recipe measures the wrong aspect, and supports the claim with a convergent meta-analysis of a broad set of published results, organized in four evidence tiers, in which a claim becomes a position only when collected evidence agrees. Parameter scale exhibits a median of +3.4 accuracy points per tenfold increase on aerial
benchmarks, far below a human gap of at least 19 points, whereas acquisition conditions control perception, as 315 of 318 evaluations in 19 within-paper contrasts lose accuracy when conditions such as altitude, view, object size or time horizon become harder. No aerial
benchmark in the corpus combines
video input with per-task human and random baselines, competence collapses from answering to acting in closed-loop navigation, and the same MLLMs score higher on the aerial
benchmark than on ground spatial ones, but lower on studies that test cross-view geometry. From these findings the current study derives five falsifiable principles and proposes the AVU-Card, a reporting card for aerial
video benchmarks
Read the full abstract ▾
All authors Georgios Angelidis, Aggelos Psiris, Maria Vakalopoulou, Georgios Th. Papadopoulos, Giorgos Sfikas, Iraklis Varlamis
Artificial Intelligence
GroundGUI: GUI Grounding by High-Quality Data and Distillation-to-Reinforcement Learning
Qingsong Xie, Jiahao Tian, Jiacheng Tang et al. (+5 more)
Constructing robust GUI
agents relies on
multimodal visual grounding: the ability to precisely map natural
language intents to actionable on-screen components. Despite abundant desktop, web, and mobile
benchmarks, high-fidelity resources tailored for diverse environments are surprisingly scarce. To bridge this gap, we introduce the Screen Referring Grounding
Dataset (ScreenRef), a comprehensive GUI grounding
dataset consisting of GUI screenshots paired with natural
language referring expressions and box or point annotations. Spanning desktop, web, and mobile domains, ScreenRef comprises 586K screenshots and over 633K referring expression instances, covering tasks such as text recognition, visual matching, spatial understanding, and refusal scenarios. To boost the model's grounding performance, we propose the
Distillation-to-Reinforcement Learning (D2RL) method to address the limited generalization of supervised fine-tuning and the sparse reward problem in reinforcement learning. Utilizing ScreenRef, we train Qwen3-VL-8B-Instruct via sequential SFT and D2RL training, yielding GroundGUI-8B. GroundGUI-8B achieves 95.2% on ScreenSpot-V2, 63.9% on ScreenSpot-Pro, 65.4% on OSWorld-G, 86.8% on MMBench-GUI L2, and 38.3% on UI-
Vision. Among 8B-scale models, it produces substantial gains over models trained on open-source
datasets, with performance comparable or even superior to models trained on closed-source data. Code, models, and
datasets are available at https://github.com/PrentisAI/GroundGUI.
Read the full abstract ▾
All authors Qingsong Xie, Jiahao Tian, Jiacheng Tang, Zhifeng Li, Madalina Ciobanu, Navan Preet Singh, Qingqing Mao, Ritankar Das
Game Theory
Maximin share allocations for two types of items
Yu Chen, Kai Jie Wong and Xiaorui Zhang
We study the fair allocation of indivisible items among $n$
agents with additive valuations (or costs) using the
fairness notion of maximin share (MMS). Since MMS allocations do not always exist when $n > 2$, one direction in the literature has been to identify special classes of instances in which exact MMS allocations can be guaranteed. We show that, when items can be divided into two types of chores, MMS allocations always exist and can be computed in
polynomial time using a novel
geometric approach inspired by prior work in job scheduling. We further discuss how our technique extends to instances with two types of goods, as well as mixed instances consisting of one type of objective good and one type of objective chore.
Read the full abstract ▾
Systems and Control
Global Parameter Identification and Uncertainty Quantification of reduced-order ADM1 using Maximum Likelihood Estimation and Bayesian Inference
Simon Hellmann, Leander Lerch, Terrance Wilms et al. (+6 more)
Anaerobic digestion (AD) models can be challenging to calibrate against real data due to limited practical identifiability, data scarcity, and model complexity. Weighted least squares objective functions and gradient-based solvers using finite differences are often used in literature, but result in suboptimal parameter estimates and large uncertainty bands. This paper identifies the parameters of a reduced-order ADM1 by comparing the frameworks of maximum likelihood estimation (MLE) and
Bayesian inference (BI), and quantifies uncertainties of parameters and outputs. Multirate experimental data are taken from a lab-scale AD reactor fed with agricultural substrates and operated at organic loading rates of 3$\,$g VS $\mathrm{m^{-3}d^{-1}}$. Global optima are found via global and gradient-based local search
algorithms using forward sensitivities. Enhanced scatter search provides the best global search results. These are refined by the Gauss-Newton
algorithm as the best local search, which delivers $R^2$ values of 0.95 for acetic acid and 0.77 for biogas production. BI yields substantially narrower uncertainty bands than MLE and avoids the need for a global search by incorporating prior knowledge about parameter distributions. The search space is captured efficiently by log10 scaling of parameters. Algorithmic details on its implications are provided. Despite a high-resolution lab-scale
dataset, the ADM1-specific inhibition parameter $K_\mathrm{I,nh3}$ is practically not identifiable with MLE, and shows a low output sensitivity, whereas a parameter for the effective ion concentration shows superb practical identifiabilty at high confidence with both MLE and BI. The present work lays a scalable base for calibration of nonlinear AD models by providing reliable simulations. It thus advances model-based monitoring and control applications of multirate processes such as agricultural AD plants.
Read the full abstract ▾
All authors Simon Hellmann, Leander Lerch, Terrance Wilms, Moritz Reumschüssel, Alberto Meola, Félix Delory, Steffi Knorn, Stefan Streif, Sören Weinrich
Robotics
Benchmarking 3D Reconstruction for Under-Ice Robotic Perception in Arctic Environments
Klára Orbán, Ashwin Nedungadi, Ana-Ştefania Kogălniceanu et al. (+5 more)
As the Arctic transitions toward a seasonally ice-free state, capturing the complex morphology of submerged sea ice is crucial for advancing models of ocean-ice-atmosphere heat exchange and monitoring under-ice habitats. Currently, sub-surface ice mapping is predominantly achieved through acoustic sensors such as multibeam sonar. While sonar provides robust large-scale geometry, it lacks spectral and high-resolution textural information required to record fine morphological features - a critical limitation in under-ice environments, where sparse visual features and degraded sensing conditions challenge the capture of detailed structural and optical surface properties. We present a
benchmark for
vision-based under-ice 3D reconstruction using real-world data from the MOSAiC expedition and synthetic data generated in an Unreal Engine-based underwater robotics simulator. The
benchmark evaluates Structure-From-Motion (SfM) and monocular depth estimation, with quantitative comparison enabled through cross-modal registration to upward-looking multibeam sonar.
Read the full abstract ▾
All authors Klára Orbán, Ashwin Nedungadi, Ana-Ştefania Kogălniceanu, Bianca-Marcela Sava, Bastian Cieply, Raul-Alexandru Simon, Kuderna-Iulian Benţa, Stefan Lüdtke
Computation and Language
Similar Models, Broken Odds: Where Luce's Axiom Fails in Chatbot Arena
Soovadeep Bakshi, Apurba Bose, Aishwarya Bose et al. (+1 more)
Chatbot Arena ranks
language models with the Bradley-Terry model, which gives each model one score and so assumes Luce's choice axiom. Choice theory predicts where this fails: near-copies are told apart more decisively than their scores imply. On 1.8 million Arena votes, votes between versions of one model are 1.37 times as decisive as Bradley-Terry predicts, between sizes of one generation 1.26 times and between models of one lab 1.12 times; a release a year later gives consistent multipliers, and the effect survives alternative tie treatments,
prompt subsets and topics, and timing checks. How alike two models' answers are worded and formatted tracks the effect. A correction with four to six parameters predicts held-out votes better than Bradley-Terry and than models with hundreds of parameters, mostly by modelling ties; frozen and carried to new releases in a test fixed in advance, its gains are concentrated in ties, and better head-to-head odds are not established. The leaderboard order barely moves. With
language-model judges and three-answer menus, a near-copy takes votes mostly from its twin when choices are pooled over
prompts (log-odds shift +0.10, 95% interval 0.05 to 0.16); within a
prompt the shift is smaller and clear for two of four judges.
Read the full abstract ▾
All authors Soovadeep Bakshi, Apurba Bose, Aishwarya Bose, Sandip Nandi
Data Structures and Algorithms · Cross-listed from math.CO
Finding non-bisimplicial and triad-free minimal separators
Maria Chudnovsky and Ilya Maier
A $u\hbox{-}v$ separator in $G$ is a set $S\subseteq V(G)\setminus\{u,v\}$ such that there is no $u\hbox{-}v$ path in $G\setminus S$. A minimal separator in $G$ is a set $S$ such that for some $u,v\in V(G)\setminus S$, $S$ is a $u\hbox{-}v$ separator in $G$ but no proper subset of $S$ is. A set $S$ is bisimplicial if it is the union of at most two cliques. Recognizing graphs in which every minimal separator is the union of at most $k$ cliques is
polynomial-time solvable for $k=1$ and NP-hard for every fixed $k\geq 3$. We settle the remaining case $k=2$ by giving a
polynomial-time
algorithm to decide whether every minimal separator in a graph is bisimplicial. A set $S$ is triad-free if its independence number $\alpha(S)$ is at most two. Given a graph $G$ and two vertices $u,v$, the problem of finding a $u\hbox{-}v$ separator $S$ with $\alpha(S)\leq k$ had the same complexity gap: it was known to be
polynomial-time solvable for $k=1$ and NP-hard for every fixed $k\geq 3$. We resolve the remaining case $k=2$ by giving a
polynomial-time
algorithm that finds a triad-free $u\hbox{-}v$ separator or determines that none exists.
Read the full abstract ▾
Numerical Analysis
Neural Spline Flow Diffeomorphisms for Pullback Finite Element Methods on Complex Domains
Ioannis Kalogeris, Anaksagoras Spitas, Konstantinos Atzarakis et al. (+2 more)
We propose a method for solving partial differential equations on complex domains by learning smooth, invertible mappings from a fixed reference domain using Neural Spline Flows (NSFs). Monotone rational-quadratic spline coupling layers ensure a strictly positive Jacobian determinant by construction, eliminating the need for Jacobian-sign penalties. A diffeomorphic pullback transfers the weak form of the PDE to the reference domain, enabling finite element analysis on reusable structured meshes. To generalize across shapes, a shared NSF is conditioned on low-dimensional latent codes learned through an auto-decoder framework; a subsequent encoder predicts these codes for unseen geometries in a single forward pass. For a given learned map, the pullback preserves the mathematical structure of the PDE and is exactly equivalent to solving on the domain represented by that map. Because the learned domain generally approximates the target geometry,
geometric mapping error remains distinct from finite element discretization and quadrature errors. Numerical
benchmarks show that sufficiently accurate learned mappings yield reliable finite element solutions. By avoiding repeated generation of unstructured meshes, the method addresses a bottleneck in simulation workflows. The fixed reference mesh also creates opportunities for efficient assembly,
memory-aligned data access, and precomputed quadrature. The resulting framework assigns
geometric complexity to the neural network while retaining conventional finite element discretization and convergence properties on the learned domain, with overall accuracy also governed by
geometric fidelity.
Read the full abstract ▾
All authors Ioannis Kalogeris, Anaksagoras Spitas, Konstantinos Atzarakis, George Stavroulakis, Vissarion Papadopoulos
Graphics
DiffGIPC: Differentiable Mixed-Coordinate Contact Dynamics on GPU
Kemeng Huang, Bowen Ren, Xinyu Lu et al. (+2 more)
Contact-rich inverse problems require efficient gradients and reliable enforcement of non-penetration. Existing differentiable methods provide fast simulation and rigid-deformable coupling, but contact treatments based on penalties or velocity-level constraints can permit penetration or positional drift. Incremental Potential Contact (IPC) maintains non-penetration through
geometric barriers and {continuous collision detection (CCD)}. However, repeated forward and backward evaluations remain costly in full-space finite-element (FEM) implementations, particularly when nearly rigid components retain many vertex {degrees of freedom (DoFs)}. We present DiffGIPC, a GPU-accelerated differentiable IPC framework for optimizing interacting deformable and nearly rigid bodies. Our affine-body derivatives enable {rest-shape} design, initial-state optimization, and articulated control while retaining only twelve motion DoFs per affine body. These gradients account for how changes in geometry, placement, and actuation affect other objects through collision and friction. We preserve these interactions in one coupled FEM-affine adjoint system per frame, reducing the backward-system size without discarding the dependencies that drive the inverse problem. GPU-optimized backward computation further reduces the cost of repeated gradient evaluations. A reusable PyTorch interface connects supported physical parameters to user-defined parameter maps and losses across design, identification, motion, placement, and articulated control. Experiments demonstrate peak speedups over DiffIPC of approximately 150.0x with full-space FEM and 4133.3x with affine bodies for combined forward simulation and backward differentiation.
Read the full abstract ▾
All authors Kemeng Huang, Bowen Ren, Xinyu Lu, Minchen Li, Taku komura
Robotics
DexMimic: A Generalist Dexterous Hand-Object Tracking Policy via Value-Guided Reset Allocation
Zhexi Luo, Zhixuan Xu, Rui Yang et al. (+3 more)
Achieving human-like dexterous manipulation remains a central challenge in robotics. Learning from human hand-object interaction (HOI)
datasets offers a promising pathway to diverse dexterous skills, yet existing physics-based approaches train specialist policies for individual trajectories, thereby limiting skill reuse at scale. We introduce DexMimic, a generalist dexterous hand-object tracking policy jointly trained across diverse HOI trajectories. Efficient joint training requires allocating each rollout to both an undertrained phase and a starting state that supports continued tracking. DexMimic realizes this insight through Value-Guided Reset Allocation, which adapts the initialization distribution online to prioritize difficult phases and select reset states with higher expected tracking returns. We further introduce a
benchmark spanning training, fine-tuning, and generalization. Experiments show improved tracking success and training efficiency, faster fine-tuning, and the potential for zero-shot generalization to unseen trajectories and objects; larger training sets further improve efficiency and generalization. Finally, we validate DexMimic on a real-world dexterous manipulation platform.
Read the full abstract ▾
All authors Zhexi Luo, Zhixuan Xu, Rui Yang, Zeyu Xiao, Yiwen Hou, Lin Shao
Computational Engineering
Linguistic Passiveness in Earnings Calls and Stock Returns
Lynn Tao, Yuntao Wu, Charles Martineau et al. (+2 more)
We study linguistic passiveness as the fraction of passive-voice sentences in earnings conference call Q&A sessions and show it is informative for equity
markets. Using 105,642 U.S. calls from 2008 to 2024, passiveness is negatively associated with announcement-day returns among positive-surprise firms: returns fall from 4.38% to 2.74% across passiveness quintiles. This announcement-day discount fully reverses over the subsequent quarter, indicating a temporary mispricing when news is good. For negative-surprise firms, passiveness has no announcement-day effect but predicts negative long-run returns, consistent with investor under-
attention when salient bad news dominates. Passiveness remains informative after controlling for sentiment and standard readability proxies, suggesting that linguistic passiveness captures a distinct yet important dimension of managerial communication.
Read the full abstract ▾
All authors Lynn Tao, Yuntao Wu, Charles Martineau, Vincent Grégoire, Andreas Veneris
Machine Learning
Beyond Aggregate Accuracy: Item-Level Transitions in Prompt Optimization
Chinmoy Mitra and Tarek Mahmud
Automatic
prompt optimization (APO) uses feedback from model responses to improve
prompts automatically. However, its effectiveness is usually measured through overall scores, which do not reveal which questions become correct, which previously correct answers become wrong, or whether improvements extend to unseen questions. We introduce Reflective Feedback-Driven
Prompt Optimization (RFDPO), a tool that tracks recoveries (incorrect to correct), regressions (correct to incorrect), and churn (all changed outcomes). RFDPO uses this feedback to guide subsequent revisions and records
prompt changes throughout optimization. We evaluate RFDPO across five
benchmarks covering law, knowledge, instruction following, mathematics, and
privacy, using GPT-5 as the optimizer and GPT-4o-mini and GPT-4.1 Mini as solvers. Our results show that overall accuracy can hide substantial changes: in five of nine configurations, churn was at least five times the absolute net change, and a single-item net change concealed up to 17 changed outcomes. Average validation gains were 7.9 percentage points, compared with 5.2 points on held-out tests. In a controlled ablation on LegalBench-Hearsay, item-level feedback reduced churn by 40% ($p=0.024$) while maintaining similar net gains. These findings motivate reporting recovery, regression, churn, and performance on unseen data alongside overall accuracy.
Read the full abstract ▾
Robotics
Receding-Horizon Next-Best-View Planning for Highly Occluded Target Perception
Ayse Gul Yildiz and Rekha Raja
Robotic systems that must acquire information about a specific target often face severe occlusion from sur- rounding structures or from the target itself, such that a single camera viewpoint provides only partial information. Active perception must therefore select viewpoints that progressively reveal unobserved regions. However, conventional local next- best-view (NBV) methods typically select viewpoints according to their immediate utility, which can overlook views that provide limited information initially but enable more informative obser- vations from subsequent viewpoints. We formulated local target perception as a short-horizon sequential view-planning problem and proposed a Receding-Horizon Next-Best-View (RH-NBV) planner that evaluates candidate sequences of future viewpoints rather than isolated views. RH-NBV is evaluated on a UR5e manipulator with an eye-in-hand RGB-D camera in simulation as well as on physical
robot against a gradient-based NBV planner, and random search, using a coffee mug and Stanford bunny under controlled occlusion and a tomato plant with natural self-occlusion. Under heavy occlusion, RH-NBV achieves substantially higher target information recovery, reaching 63.8% ROI coverage versus 34.2% and 85.5% occluded-surface recall versus 7.4% for the single-step NBV baselines on the most occluded mug configuration. A controlled horizon ablation shows that this improvement arises from multi-step
reasoning rather than additional computation. RH-NBV provides the greatest benefit for strongly occluded targets, while myopic NBV remains competitive and substantially cheaper when visibility is less constrained.
Read the full abstract ▾
Machine Learning
Backpropagating Verifier Rewards Through Continuous Flow Language Models
Xu Han, Jiajing Hu and Li-Ping Liu
Reinforcement learning (RL) has substantially improved the
reasoning of autoregressive and discrete-
diffusion language models.
Language models that generate continuous
token embeddings are emerging as a strong alternative, but RL post-training for them remains understudied. We propose \method{}, a post-training framework for continuous flow
language models. Such a model denoises
token embeddings over multiple steps and decodes them into discrete
tokens only at the last step. To obtain pathwise gradients, which backpropagate through continuous actions and have much lower variance than REINFORCE, we introduce a critic that estimates the value of intermediate
token embeddings, bypassing the non-differentiable decoding step. The critic must also keep track of the value function as the policy changes; to this end, we design a critic that predicts a value from every
token representation and improves policy optimization. Across four
reasoning tasks, \method{} reliably improves a continuous flow
language model through RL post-training and outperforms baseline methods of the same type.
Read the full abstract ▾