Face
-
Characterising divergence between heuristic and language-model ratings of mobile user interface quality
2026-11-09 21:15:50Md Rejaul Korim Sadi, Golam Mostofa Naeem, Toufiqur Rahman Tasin, Syed Mostofa Moosa, Mahmudul Hasan Emon, Mahmudur Rashid, Ferdus AhmedAbstract
Automated assessment of mobile user interface quality is attractive because manual review does not scale, and large language models are increasingly proposed for the task. Whether their ratings correspond to those produced by established rule-based heuristics has not been characterised at scale. We construct a 15,000-screen corpus from the RICO dataset using six documented filters, score every screen with a literature-grounded heuristic scorer, and collect ratings from three open-weight language models across two input representations, yielding 270,000 ratings. We report linearly weighted Cohen's kappa with bootstrap confidence intervals, offset-corrected kappa, intraclass correlation, and Bland-Altman limits of agreement, together with a chance baseline for the tolerance-band agreement rule. Agreement between the two rating sources is consistently weak: raw kappa falls below 0.15 in seventeen of eighteen model-representation-dimension cells. However, fifteen of eighteen cells are statistically distinguishable from zero, and correcting for a constant offset raises five cells above 0.15, so the divergence is better described as a combination of systematic bias and weak covariation than as absence of relationship. Model ratings track structural properties of the interface, but substantially less strongly than the heuristic does, and more strongly from an untruncated structural element list than from a screenshot. We further show that dimensions elicited in a single generated response are correlated by construction, reaching rho = 0.97 in one condition, which constrains what such designs can measure. We report these results as a characterisation of divergence between two automated raters rather than as evidence that either is correct, and we set out the validation a stronger claim would require.
Abstract (translated)
URL
https://arxiv.org/abs/2609.05423
PDF
-
Incorporating World Models in Decision Making for Next Best View Selection in Active Sensing
2026-11-09 20:56:59Nikita Sarawgi, Omey M. Manyar, Satyandra K. GuptaAbstract
Efficient robotic 3D reconstruction requires selecting views that contribute new surface measurements with few physical captures. Pretrained world models can guide this choice, but a predicted surface may not produce valid depth measurements under the operating conditions of the deployed sensor. We present a deployment adaptation methodology for next-best-view selection that learns a sensor-return adapter from limited local calibration data while keeping the pretrained predictor fixed. The adapter estimates measurement dropout over each predicted surface, allowing the selection method to favor views likely to fill gaps in the measured reconstruction. In a real-robot experiment with a structured-light sensor, the adapted method achieves higher measured surface coverage with 60% fewer captures than nominal selection. The adapted method recovers a surface region that the nominal method repeatedly targets but fails to measure. These results suggest that robots can reuse pretrained predictive models while adapting their decisions to local operating conditions in data-scarce environments.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13229
PDF
-
An Integrated Open-Source Stack for Vision-Based Autonomous Navigation of Wheeled Rovers
2026-11-09 20:38:25Iaroslav Kolomiets, Iaroslav Sheipak, Mikhail Reppo, Vsevolod Egorov, Viktor Chertopolokhov, Isaac ChairezAbstract
Vision-based rover autonomy requires integrating perception, localization, planning and platform-specific control under limited sensing and computing resources. We present an open-source ROS 2 stack for following directional arrows, reaching a terminal cone and returning autonomously to the start. It connects YOLOv8n detection and geometric direction, range and bearing estimation with RGB-D SLAM, wheel-inertial state estimation, kinematics-aware planning, behavior-tree mission management and STM32 actuation. Standard interfaces separate reusable autonomy from the hardware layer; a proportional path-following plugin supports low-speed rover motion. Public resources include software, configuration, a labeled dataset, trained weights and evaluation logs. On 478 held-out images, the detector achieves mAP@0.5 of 0.720 under the Ultralytics evaluator and outperforms a classical OpenCV baseline under a shared evaluation protocol. The reported perception latency is 25 ms on a Jetson Orin NX. Three missions, one indoor and two outdoor, demonstrate marker-guided navigation and autonomous return without operator motion commands or reported collisions. Field results document integration failures and corrective choices; repeated instrumented trials remain necessary to quantify physical navigation errors and reliability.
Abstract (translated)
URL
https://arxiv.org/abs/2611.08100
PDF
-
Structured Kernel Surrogate Models for Multimodal Attribution
2026-11-09 20:21:39Ziniu Zhang, Zhenshuo Zhang, Jianglin Lu, Ruoxuan Xiong, Yun Fu, Hongyang R. ZhangAbstract
We study the problem of cross-sample modality attribution, which involves measuring how one modality in one sample affects the learning outcome in other multimodal samples. This problem is crucial in a multimodal system because a data modality (such as a text description) may be redundant for one sample (a self-explanatory image), but the same data modality would otherwise be uniquely informative for another sample, or informative when combined with other modalities. Prior work focuses on influence estimation at the level of one sample, and it remains an open question how one should capture the interactions across both samples and modalities. To capture scenarios like the above, we propose structured kernel surrogate models, which are surrogate mappings from both samples and modalities to the prediction outcome when they are trained together. We design an algorithm, SKS, which applies kernel ridge regression with a structured, compositional kernel on the selection states of individual samples and modalities. Specifically, the kernel function multiplies kernel-based similarity scores between every pair of data modalities for one sample and a pair of two samples. Additionally, we design a gradient-based estimation algorithm to efficiently estimate the structured kernel surrogate model. We evaluate our approach on two multimodal benchmarks, spanning a range of data modalities including satellite images, road networks, text, audio, and tabular data. We find that SKS achieves $57.8$% higher correlation with the true prediction outcomes than existing methods. In downstream data selection, SKS improves the average accuracy by $1.93$% over baselines. Models with data selected by SKS have lower Hessian traces, indicating a flatter loss surface. Using SKS to select satellite images identifies road segments, where accident scenes commonly occur, as opposed to background images.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13198
PDF
-
From Process Models to Composable Agentic Workflows: Combining BPMN, Agents and Enterprise Knowledge
2026-11-09 20:18:32Christian Fillies, Jan Fillies, Frauke Weichhardt, Gay Anne Wood-AlbrechtAbstract
LLM-based agents can reason, use tools and collaborate. However, coordinating increasingly complex agentic applications becomes difficult to understand, monitor and improve. Decisions distributed across prompts, tool calls and application logic make workflows implicit. We introduce **Recursive Capability Composition**, enabling agents to execute business processes and expose them as reusable Agentic Tools. This paper presents a BPMN-based approach to Agentic Workflows, combining explicit orchestration with autonomous reasoning. SemTalk BPMN models are transformed into executable workflows using a LangGraph/Pregel runtime. Agentic Tasks introduce LLM reasoning at selected activities, while conventional BPMN controls process flows, deterministic decisions, system interactions and human approvals. Agentic Participants provide reusable interfaces for agent behavior or other executable processes. BPMN orchestration makes multi-agent systems more understandable and manageable. Explicit process models provide developers and operators with a shared view of workflow structures and execution progress, facilitating debugging, monitoring and optimization. Enterprise agents also need organization-specific context. Process Models and Knowledge Graphs describe activities, participants, information objects, decisions and relationships between processes. They provide structured knowledge of how an organization operates, supporting informed agent decisions and actions. Our contributions are threefold: 1. **Model-Driven Execution:** Transforming BPMN models into executable Agentic Workflows. 2. **Recursive Capability Composition:** Exposing agents and executable business processes as reusable tools for other agents. 3. **Enterprise Context:** Using Process Models and Ontologies to provide organization-specific knowledge for agent reasoning.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13196
PDF
-
Comparative Evaluation of Deep Learning Models for Geographic Atrophy Segmentation in En Face OCT Images
2026-11-09 20:12:13Utkarsh Doshi, Adarsh Gadari, Sharat Chandra Vupparaboina, Joseph DeCicco, Giulia Gregori, Nicola Valsecchi, Nasiq Hasan, Elham Sadeghi, Jos\`e-Alain Sahel, Jay Chhablani, Kiran Kumar Vupparaboina, Sandeep Chandra BollepalliAbstract
Background: Geographic atrophy (GA) is an advanced form of age-related macular degeneration (AMD). It causes irreversible vision loss due to progressive degeneration of the retinal pigment epithelium (RPE) and photoreceptors. Accurate segmentation of GA in en-face image is crucial for early diagnosis, monitoring disease progression, and developing personalized treatment strategies. However, existing deep learning approaches are typically evaluated using single architectures and single-device datasets, limiting insight into relative performance and cross-device robustness. Methods: We trained and systematically compared five deep learning architectures for GA segmentation: Nested U-Net, ResU-Net, nnUnet, Swin-Unet and MedSegDiff model, together with a thresholding based classical baseline. The models were trained on a dataset of en-face OCT images derived from 269 OCT volumes from two different devices, following a three-step preprocessing technique involving normalization and inpainting to enhance the quality of the en-face images. Results: On the fixed held-out validation set comprising OCT scans from both Cirrus (R) (Carl Zeiss Meditec, Inc., USA) and Spectralis (R) (Heidelberg Engineering, Germany) devices, nnUnet achieved the highest mean Dice similarity coefficient (DSC) of 0.8882 +/- 0.0033. The other models yielded the following Dice scores: Nested U-Net (0.7932 +/- 0.0423), ResU-Net (0.8453 +/- 0.0074), Swin-Unet (0.6886 +/- 0.0294), and Diffusion model (0.7959 +/- 0.0242). Conclusions: nnUnet framework, demonstrated most reliable performance for GA segmentation in en-face OCT under limited data conditions. It offers the best balance of accuracy, stability, and efficiency for GA quantification.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13191
PDF
-
One-Sided Expert-Parallel All-to-All for Mixture-of-Experts Inference over NVLink
2026-11-09 20:06:38Bo Li, Chulian Zhang, Or Biri, Anthony Chang, Anton Korzh, Noam Duvdevani, XingFei Xi, Daniel Stokes, Zhenhuan Chen, Ludwig Schneider, Artem Y. Polyakov, Julien Demouth, Chandler ZhouAbstract
Expert parallelism (EP) shards the experts of a Mixture-of-Experts (MoE) layer across GPUs, so every MoE layer requires two all-to-all communications, namely dispatch and combine. Compared with training, inference processes relatively few tokens per GPU at a time, and at small batch sizes fixed costs that do not grow with the number of tokens, rather than data movement, dominate the latency. We present NVLinkOneSided, a one-sided EP all-to-all for GPUs within a single NVLink domain. Each source rank pushes its tokens, without first exchanging metadata, into rank-major buffers on the target GPUs, and the grouped GEMMs read them in place instead of from a per-expert copy. We provide two protocols for the synchronization that the communication requires, namely Fence and Sentinel, for high-throughput and low-latency scenarios respectively. On Blackwell GPUs, NVLinkOneSided completes dispatch and combine 1.2-3.0$\times$ faster than DeepEP, with the largest speedups at small batch sizes. The resulting MoE layer is up to 2.4$\times$ faster than DeepEP with DeepGEMM. It even outperforms the fused DeepGEMM MegaMoE at up to 128 tokens per GPU, making it still competitive for decoding. We expose NVLinkOneSided through a modular interface, so that it is agnostic to the activation quantization format, decoupled from the MoE compute backend and easy to integrate into inference frameworks.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13188
PDF
-
AgentScript-Eval: Benchmarking LLMs and Agents for Code Generation in an Enterprise DSL
2026-11-09 20:04:32Dipin Khati, Shubham Mehrotra, Bin Bi, Zhou Yu, Denys Poshyvanyk, James Zhu, Sitaram Asur, Phil L. MuiAbstract
Domain-specific languages (DSLs) are widely used in enterprise software, giving a compact interface to complex tasks, from data access to infrastructure automation. Platforms increasingly extend them to agents, where a developer declares the topics, permitted actions, and guardrails of an agent rather than writing general-purpose code. Large language models (LLMs) write general-purpose code well, but that ability has been measured almost entirely on languages abundant in public pretraining data, and enterprise DSLs are neither abundant nor public. We introduce AgentScript-Eval, an execution-graded benchmark of 100 real tasks for AgentScript, the declarative DSL that Salesforce uses in Agentforce to build conversational agents. Tasks span authoring an agent from a specification, debugging a broken definition, and optimizing a working one. Evaluating five models zero-shot, we find that the regime is hard: the best model reaches only 25.0% pass@3, and every model scores 0% on authoring from scratch. We further find that model scale and price are weak predictors of success -- a 31B open-weight model attains the highest compilation rate of any model tested (48.0%) and matches the strongest frontier model on partial-credit accuracy at the lowest token cost. Adding an agentic compile-and-edit loop is the single largest lever, roughly doubling partial-credit accuracy. Beyond that gain, the wording of domain guidance matters more than its packaging. The same skill pack scores 28% as plain documentation but only 14% as a live plugin. Rewriting one skill inside that plugin then raises it to 37%, our best result, with catalog and tooling untouched. Larger models did not reliably outperform smaller ones; what mattered was the harness surrounding the model and the guidance supplied to it.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13183
PDF
-
GroundCascade: Selective Second Opinions for GUI Grounding
Abstract
Graphical user interface (GUI) grounding maps a screenshot and a natural-language instruction to the screen location where an agent should act. Zoomed views can reveal small targets but may lose the context needed to identify them. We introduce GroundCascade, a training-free controller that uses agreement between a grounder's full-screen and zoomed predictions to decide when to consult a complementary model. It selects between zoomed predictions while preserving corroborated full-screen locations. An optional Finalizer predicts from an unmarked joint crop when disagreement remains (Full); omitting it yields the two-stage Selective variant. GroundCascade reaches 85.33% on ScreenSpot-Pro with Indeed-UI-32B/8B/32B and 88.43% on the visible-target OSWorld-G-Refined subset with Qwen3.6-27B/3.8-27B/3.8-27B, gains of 2.66 and 2.35 percentage points over the stronger standalone two-pass grounder. On UI-Vision, GroundCascade reaches 72.20% category-balanced accuracy, with Selective slightly higher at 72.28%. Across these three evaluations, GroundCascade in Full mode uses 2.42-2.73 calls per request, 31-39% fewer than unconditionally acquiring both models' two-pass predictions. At matched second-model call budgets, selective acquisition gains 1.52-2.56 points over standalone Two-pass, compared with 0.22-0.69 points from stratified random acquisition. GroundCascade leads the official ScreenSpot-Pro leaderboard and exceeds reported GUI-specialist comparisons on OSWorld-G-Refined and UI-Vision, subject to differences in external evaluation protocols.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13177
PDF
-
Autonomous Optimization of Numerical Algorithms by an AI Agent: Application to Atomistic Simulation
2026-11-09 19:23:39Jeheon WooAbstract
Coding agents built on large language models, run in automated improvement loops, can discover more efficient algorithms. We present AIOA, a framework that brings this approach to the numerical algorithms of atomistic simulation: an agent improves an algorithm against a pre-specified metric in a loop guarded by verifiers it cannot alter. Applied to ASE, a widely used atomistic simulation library, AIOA targets two facets of an algorithm: its implementation, rewritten to run faster with unchanged results, and the method itself, redesigned to converge with fewer force evaluations. Agents made six kernels 22-24 times faster on average in Python with NumPy and SciPy. On unseen problems, optimizers from the best configuration needed 3.1-3.4 times fewer force evaluations than L-BFGS for structure relaxation and 4.6-17 times fewer than standard climbing-image nudged elastic band calculations for reaction paths. The agents' optimizers also contain two algorithmic components we did not find in the literature.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13143
PDF
-
Building World Models from Intrinsic Motivation
2026-11-09 19:02:32Reece Keller, Declan Kutscher, Xaq Pitkow, Aran NayebiAbstract
In the absence of extrinsic rewards or task supervision, human behavior is guided by intrinsic motivation---neural signals that drive curiosity, creativity, play, and other essential facets of intelligence. Intrinsic motivation plays an important developmental role in building robust world models that enable generalization and adaptation. Yet existing studies leave open how a broad range of intrinsic motivations interacts with world-model representation learning to support downstream control. This limits our understanding of which intrinsically collected experiences build reusable models. To address these gaps, we integrate 24 intrinsic objectives, including established methods and explicit variants spanning curiosity, entropy, and competency, into a common model-based reinforcement learning framework. We evaluate the world models they build through zero-shot, few-shot, and multi-task control in locomotion, manipulation, and open-ended gaming environments, using three representation-learning strategies: observation reconstruction, latent prediction, and redundancy reduction. Curiosity-driven exploration with observation reconstruction yields the strongest aggregate family profile, although the best individual pairing depends on the experiment. In compositional vision-based tasks, intrinsic motivation derived from both episodic and lifelong novelty---providing a complementary memory to the world model's generic recurrent state---achieves the best zero-shot transfer and few-shot adaptation. These findings motivate designing intrinsic motivation and representation learning jointly. Our results demonstrate world models as a powerful tool for measuring the quality of intrinsically motivated experience, and positions intrinsic motivation as a key ingredient for building world models autonomously.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13113
PDF
-
Code-Grounded Agentic Explanations for Static Analysis Vulnerability Findings
2026-11-09 11:40:08Oshando Johnson, Ranjith Krishnamurthy, Rohith Kumar Shanmuganathan, Goran Piskachev, Eric BoddenAbstract
Static application security testing (SAST) tools surface vulnerabilities early and their verdicts are rule-based and auditable. Yet developers routinely dismiss findings they cannot interpret. Large language models can supply the missing explanation, but designs that also hand the model the detection give up the auditability that makes static analysis defensible. We keep detection with the analyser and give the model only the explaining. A preliminary user study with 20 participants and a workshop with 19 practitioners yielded five requirements. Guided by these we redesigned SAFE, an open-source IntelliJ IDEA plugin that explains findings from any analyser reporting in the Static Analysis Results Interchange Format. It tiers explanations by demand, ties them to the reported data flow, and replaces the single-prompt backend with an agent that must consult the repository and the rule that fired before answering. A within-subjects crossover experiment with 24 participants compared the redesign against its predecessor. Perceived usability rose from 77.3 to 85.0 on the System Usability Scale. Actionability gained most among the explanation-quality items, the aspect both earlier studies flagged as weakest, and the odds of a correct remediation were 2.6 times higher. Triage accuracy and time per finding were indistinguishable, which we read as uninformative rather than as equivalence. Trust was the one measure that did not move, and the closing interviews indicate that grounding made findings easier to understand rather than easier to believe. Participants also drew a boundary no requirement anticipated, wanting the tool to find and explain while they judge and apply.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13041
PDF
-
GTAGym: Real AAA Game Tasks Environment for Evaluation and Reinforcement Learning
2026-11-09 08:59:36Jiajun Chen, Shicheng Fang, Jiahao Lu, Yuxin Wang, Xipeng QiuAbstract
AAA games offer a rich testbed for evaluating agent perception, reasoning, and control. However, evaluating whether agents can complete tasks in AAA games is challenging and often human-annotated because task outcomes are often difficult to verify automatically, let alone applying it for Reinforcement Learning (RL). We introduce GTAGym, an environment and framework for evaluation and RL on GTA V tasks. Its evaluation benchmark, GTAVBench, derived from GTA V main-story missions, contains 103 online tasks reconstructed across nine task families, alongside 47 image-based shooting and sniping tasks using GTA V imagery. A web server provides access to the online environment and evaluation interface, supporting parallel testing through screenshots and keyboard-mouse actions with automatic engine-state outcome checks. We evaluate six frontier LLMs on GTAVBench with textual task instructions and on its GTAVBench-AGI branch, where instructions appear only in the first screenshot and a harness automatically compresses interaction history. The best configuration achieves 70.9% overall accuracy in GTAVBench-AGI, yet aerial navigation, evasion and interception remain difficult. GTAGym also provides a scalable generator that samples task parameters within user-specified ranges and option sets under fixed templates, creating batches of 3D and image-based shooting environments for RL with automatic reward and termination signals. LoRA RL of Qwen3.8-27B on generated on-foot navigation tasks improves the in-domain performance and transfers to out-of-domain task categories, and native GTA V tasks from 15% to 23%.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13028
PDF
-
G-STAR: Group-Scaled Token Capacity for Deeply Compressed Autoregressive Generation
2026-11-08 16:59:18Xu Huang, Ye Huang, Xiaotong Li, Zhengrong Yue, Jialv Zou, Minhao Jing, Haodong Li, Wenhao Yan, Yaxin Luo, Duomin Wang, Daquan ZhouAbstract
Discrete autoregressive models offer a scalable framework for image generation. However, they face a fundamental trade-off: long token sequences preserve representation quality but slow generation, while aggressive spatial compression reduces representation capacity. Based on product quantization, we show that, under a fixed nominal information budget, group size should scale quadratically with the per-axis spatial compression factor. Building on this principle, we propose GSTAR, a spatial--group co-scaling framework that enables \(32\times\) and even effective \(64\times\) compression while preserving strong reconstruction, understanding, and generation performance. Since larger groups introduce intra-group dependencies that must be modeled efficiently, we analyze their impact on inference latency and generation quality and introduce a semi-autoregressive decoder that combines parallel feature computation with lightweight causal modeling. With these designs, our highly compressed models perform competitively with leading models across five representative text-to-image benchmarks (GenEval, DPG-Bench, PRISM, LongText-Bench, and Qwen-Image-Bench). At \(1024\times1024\) resolution, our model delivers a \(20\times\) speedup over prior discrete autoregressive models, generating each image in 2.5 seconds on a single NVIDIA H200. Together, these results show that highly compressed discrete representations can enable high-quality autoregressive generation at low latency.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13004
PDF
-
Embodied Science Agents: Making Embodied Experimental Design Learnable
2026-11-07 07:52:16Yihang Che, Zhongwei Yu, Yang Li, Xingyu Lu, Hongxia Yu, Jun WangAbstract
Recent advances in large models have accelerated AI for Science toward agentic science, where AI agents autonomously conduct scientific discovery. Realising this vision requires closing the loop between computational reasoning and physical experimentation, positioning self-driving laboratories (SDLs) as critical enablers. However, existing SDLs exhibit a fundamental paradox: foundation model integration has increased linguistic sophistication while severing physical grounding. By treating models as disembodied planners that output symbolic workflows for separate robotic systems, current architectures inherently block the development of embodied experimental intuition. We argue that overcoming this paradox requires embedding \emph{learnability} along three interdependent axes: cognitive learnability (learning what to investigate), experimental learnability (learning where to search), and embodied learnability (learning how to act). Building on this view, we introduce the Embodied Science Agent (ESA), which unifies digital intelligence with physical embodiment through three synergistic components: a Digital Agent that provides cognitive and experimental learnability via memory-based reasoning and Bayesian optimisation, an Embodied Agent that provides embodied learnability via generalisable instrument control, and an Embodied Unified Interface for seamless coordination. We validated ESA in autonomous wastewater treatment experiments, navigating over 200 million possible conditions. Through 15 continuous rounds, ESA raised the final solution transmittance from 82\% to 99.7\%, corresponding to a 98.5\% reduction in residual dye concentration and near-complete decolourisation, while its learned visuomotor policies generalised across varying instrument placements, a promising step toward next-generation SDLs for autonomous scientific discovery.
Abstract (translated)
URL
https://arxiv.org/abs/2611.12958
PDF
-
Language as Trait, Politeness as Strategy: Controlled Tests of Linguistic Effects in LLM Social-Deduction Agents
2026-11-06 17:31:01Yuchen Li, Lisa Liu, Runqi Zou, Shuxuan Kuang, Qingquan Zhang, Julian TogeliusAbstract
Large language model (LLM) agents coordinate through conversation, and the same message can be phrased in simpler or more complex language, bluntly or politely. We test whether such differences change how other agents judge and act, using the LURK Werewolf framework, which separates each utterance's speech-act predicate from its natural-language realization. We rewrite only the realization, check that the game content is preserved, and replay each game day from saved checkpoints against a re-sampled control. We vary linguistic range consistently across a speaker's messages and politeness strategy per utterance. Across 30 games and 4,335 replays, neither manipulation changes the trust other agents place in the speaker, and no effect on votes or night actions survives correction for multiple comparisons; the largest uncorrected effect is that shifting range away from a neutral paraphrase changes about 4 percentage points more of the other players' votes. In natural play, 88% of face-threatening speech is bald on-record regardless of role.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09768
PDF
-
MemoryDojo: Benchmarking Poisoning Through LLM Agent Memory
2026-11-06 17:00:09David H. Yang, Blake Bullwinkel, Amanda Minnich, Mohammad Mohammadi Amiri, Giorgio SeveriAbstract
LLM agents benefit from using memory systems to improve performance on long-horizon, multi-session tasks. However, memory introduces a critical attack surface. Malicious instructions encountered in one session may be stored and propagated through memory before being retrieved and acted upon in later sessions. Because memory systems differ in how they process and retrieve information, the downstream effects of poisoning can vary significantly across systems. To quantify the effects of poisoning across different memory architectures, we introduce MemoryDojo, a benchmark for tracing the lifecycle of poisoned information through agent memory and measuring its influence on subsequent agent behavior. MemoryDojo is easily extensible, consists of 155 multi-session long-horizon trajectories covering four domains, and supports five different memory systems. Through our evaluation, we find that all memory systems are susceptible to memory poisoning, with substantial variation in downstream effects. We further propose a memory-aware poison optimization process that increases the poisoning efficacy, highlighting differences between memory architectures. We hope that MemoryDojo will support research on understanding and mitigating agentic memory risks.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09721
PDF
-
A wearable input/output interface learns personalized models of haptic perception
2026-11-06 16:50:24Wen Li, E. Magnus Adams, Zijie Xu, Jiawen Yao, Aybala Esmer, Xiaoyue Ni, Bozhi Tian, Pedro LopesAbstract
Wearable haptic interfaces deliver physical stimuli to the skin, yet perceived locations vary widely across users and diverge from actuator locations, particularly for emergent tactile-feedback techniques. We developed a wearable haptic input/output (I/O) device integrating a 36-channel electrotactile array with capacitive touch sensing, enabling stimulation and user-reported percept locations to be registered within the same body-referenced coordinate frame. In 24 participants, the device revealed electrotactile and referred-thermal perceptual maps with notable interparticipant variability. Despite this variability, both modalities retained electrode-pair-specific spatial structure across participants. Tactile and thermal percepts also showed spatial correspondence, whose strength varied across participants. These findings motivated our human-in-the-loop calibration framework, which adapts a forward-prediction strategy to individual users and generates personalized perceptual models. These models enabled inverse rendering by selecting stimulation patterns predicted to generate a target percept for a specific user. Using these models, we demonstrate personalized haptic rendering in haptic-guided robot teleoperation, visual-to-haptic sensory substitution, interpersonal haptic communication, and virtual reality (VR). Together, this platform provides a route toward adaptive haptic interfaces that measure, model, and render according to each user's perception.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09708
PDF
-
Left-Right-Consistent Iterative Stereo Matching via Cross-Injection
2026-11-06 13:29:00Manuel Knott, Diogo Luvizon, Daniel Scharstein, Elias VansteenkisteAbstract
State-of-the-art stereo matching models predominantly predict the disparity of only the left (reference) view. However, applications such as per-eye AR/VR rendering, novel view synthesis, or two-view depth fusion require disparity for both views, and need those two maps to agree. The usual workaround of running the network a second time on the horizontally flipped and swapped pair gives two independent predictions that can be inconsistent, especially on transparent surfaces, in textureless regions, and at occlusion boundaries. We introduce cross-injection (CI), a lightweight extension for iterative (refinement-based) models that can be added to any pretrained left-only iterative matcher. It couples the two passes by injecting the explicit, signed left-right inconsistency as an additional input cue at every step of the refinement stage. We empirically show that CI substantially reduces left-right disagreement on every benchmark (more than halving it on Booster for FoundationStereo), while largely preserving sharp object boundaries. Furthermore, using two state-of-the-art stereo matching models, we show that CI also reduces the single-view disparity error, making it a worthwhile extension even if only left disparity is needed.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09458
PDF
-
Mesh-Agnostic Refinement Models for Latent Space Encoding of 3D Human Body Shapes
2026-11-06 08:03:33Chaima Zouaoui, Jonathan Cerqueira, Sylvain Arguillere, Martin Bauer, Nicolas Charon, Mohamed Daoudi, Emmanuel HartmanAbstract
Parametric human body models such as the Skinned Multi-Person Linear (SMPL) model provide compact representations of human shape and pose, but their reconstructions remain affected by both errors in estimated latent parameters and limitations in the decoder's expressive capacity. We propose a framework for refining these reconstructions by exploiting the geometric discrepancy between an initial decoded surface and a target mesh, without requiring vertex correspondences between them. The framework comprises three complementary approaches. Latent-VaRefine uses varifold distance gradients to correct the estimated latent code while preserving the original parametric representation. Vertex-VaRefine processes multiscale varifold-gradient features with a DiffusionNet backbone to predict vertex displacements in a canonical pose, yielding an approximately pose-equivariant refinement pipeline. ElaOpt directly optimizes surface deformations under elastic regularization and normal direction constraints. On AMASS, Vertex-VaRefine reduces the mean vertex-to-vertex error of OmniFit reconstructions from 1.181 to 0.342 cm, a 71.0 percent reduction, while combining Latent-VaRefine with ElaOpt reduces the asymmetric Chamfer distance of ArtEq reconstructions from 1.681 to 0.717 cm, a 57.3 percent reduction. Evaluations with SMPL-H and SMPL-X demonstrate the framework's adaptability to different body models, while additional experiments on remeshed targets and raw scans assess its robustness to changes in discretization and geometry beyond the parametric model. These results highlight the complementary strengths of latent space correction, learned vertex refinement, and elastic optimization, offering different trade-offs between preserving the model parameterization and improving geometric fidelity.
Abstract (translated)
URL
https://arxiv.org/abs/2611.03285
PDF
