CS Paper Radar

Weekly top 20

2026-W34 Aug 17 – Aug 23, 2026

Ranked from 3,407 papers submitted on 7 days. Each research area gets slots in proportion to its share of this week's papers (at least one), filled by score; near-duplicates are removed. Why

Score = weighted mean ofCitations 20%Upvotes 10%Code stars 10%Venue 15%Code/data 10%Novelty 15%Momentum 15%Substance 5%how it works
1

SAC-Copula: Quality-Preserving Watermarking for Diffusion Language Models via Smooth Correlated Gumbel Fields

cs.CL cs.CRcs.LG ·2026-08-21 ·Baixin Li, Haiyun He
top venuecode/data
Abstract · 24 pages, 14 figures. Accepted to Findings of EMNLP 2026

Watermarking diffusion language models (DLMs) requires mechanisms compatible with iterative parallel unmasking rather than autoregressive decoding. Existing sampling-based watermarking methods typically inject position-wise i.i.d. perturbations, which can be poorly aligned with DLM decoding dynamics and degrade generation quality. We propose SAC-Copula, a quality-preserving watermarking method for DLMs based on smooth, locally correlated Gumbel perturbation fields constructed via a Gaussian copula. We further develop a SAC-aware detector using covariance-aware filtering and native-sample calibration. Mechanism-level analysis shows that local correlation reduces latent perturbation roughness and better matches iterative refinement dynamics. Experiments on LLaDA show that SAC-Copula achieves a favorable quality-detectability trade-off compared with existing baselines. In particular, further evaluations on Dream-7B and additional datasets show that SAC-Copula substantially improves PPL tail stability over the i.i.d. Gumbel baseline, while maintaining strong low-FPR detectability and competitive overall generation quality. Additional token-edit stress tests further assess watermark robustness under controlled synchronization drift. Code is available at https://github.com/PunkyKnife/SAC-Copula.

0.86
2

DistillPath: An Efficient 22M Distilled Pathology Encoder Approaching Large Foundation Model Performance

cs.CV ·2026-08-18 ·Ramon Kaspar, Andrey Ignatov, Valentina Boeva
publishedcode/datahot direction
Abstract · 26 pages, 5 figures. Accepted at the ECCV 2026 Workshop on Medical Foundation Models and Benchmarks (MedFM-Bench)

Many high-performing pathology tile encoders are now foundation models with hundreds of millions to over a billion parameters. Encoding and storing the thousands of tiles in each whole-slide image with such models is costly on commodity hardware, so compact encoders that retain useful downstream performance are a valuable alternative. We present DistillPath-KS16, which starts from the existing 22M kaiko ViT-S/16 encoder and improves it by distilling from released pathology encoders used as frozen teachers. The recipe reads only the teachers' final class and patch tokens and trains on 6,000 public slides, needing neither their DINO nor iBOT pretraining heads nor a billion-tile corpus, so it applies to any released encoder that exposes backbone tokens. We distill four teachers spanning 86M to 1.1B parameters into the same student. Every variant improves the kaiko baseline on all three benchmarks we use, EVA, HEST, and PLISM, and the strongest teacher is task-dependent. On the seven-task EVA mean, DistillPath-KS16-Virchow2 reaches $0.795$, within $0.015$ points of Virchow2, the top-scoring model in our evaluation, at about $29\times$ fewer parameters; it also scores above H0-mini and GPFM on this aggregate metric, though that advantage is task-concentrated rather than uniform. Because it remains a 22M ViT-S/16 with 384-dimensional features, DistillPath-KS16 runs more than $25\times$ faster than Virchow2. Code is available at https://github.com/RamonKaspar/DistillPath, and released model weights are available at https://huggingface.co/collections/RamonK/distillpath.

0.85
3

Towards Investigating Residual Hearing Loss: Quantification of Fibrosis in a Novel Cochlear OCT Dataset

cs.CV cs.AI ·2026-08-21 ·Julia Dietlmeier, Benjamin Greenberg, Wenxuan He, Teresa Wilson, Rubing Xing +8 more
top venuecode/dataunusual
Abstract · Copyright 2026 IEEE. Personal use of this material is permitted. Citation/DOI: 10.1109/TBME.2025.3537868

Objective: Cochlear implants (CIs) are bionic prostheses that restores hearing via electrical stimulation of the auditory nerve. Hybrid CIs, which use electroacoustic stimulation (EAS), combine residual low-frequency acoustic hearing with CI electrical stimulation. Intracochlear fibrosis, which forms in response to the presence of the implant, may impede residual hearing function and gradually reduce the efficacy of EAS. It is therefore a translational objective to study the formation of cochlear fibrosis in rodents, with the goal of reducing fibrotic burden and improving outcomes for CI patients. Methods: We generate and annotate a novel dataset of optical coherence tomography (OCT) images from chronically implanted guinea pigs as part of an ongoing study focused on implant induced fibrosis. Objectively assessing fibrotic burden in this model, with high resolution and repeatability, presents an obvious use case for computer vision methods. Results: We present the results of several state-of-the-art semantic segmentation models and compare their efficacy for identifying cochlear fibrosis and other relevant annotations, using a new library of manually segmented OCT images. Conclusions: We find that the best performance is achieved by using a modified version of the well-known UNET architecture (which we term 2D-OCT-UNET) that operates on the upscaled OCT input resolution. Significance: For the first time, we have successfully applied computer vision techniques to an OCT dataset of implanted cochleae with fibrosis. Using this deep learning model, the cochlear fibrotic burden calculation can be reliably carried out as we verify in our experimental section. The dataset and the project code are available at: https://github.com/juliadietlmeier/CF-OCT-segmentation

0.84
4

Benchmarking Patent Drafting from Inventor-Style Disclosures

cs.CL ·2026-08-21 ·Lekang Jiang, Wenjun Sun, Stephan Goetz
top venuebenchmarkdatasetcode/data
Abstract · Accepted to EMNLP 2026

While recent large language models (LLMs) have achieved promising results on individual patent drafting tasks, they fundamentally fail to investigate the core challenge of real-world patent drafting: generating a complete and legally coherent patent application directly from early-stage invention materials. Prior work predominantly assumes later-stage, highly structured, or already legalistic inputs. However, real patenting workflows begin with informal, de-legalized disclosures authored by inventors. To bridge the gap, we introduce Dis2Pat, a disclosure-to-patent dataset that reflects realistic patenting workflows by requiring the generation of complete patent applications directly from inventor-style, de-legalized disclosures. Given the inherent difficulty of long-form, legally constrained patent drafting and the strong privacy requirements, we further propose a strong baseline named Patent-MAF. It is a multi-agent framework for locally deployable patent drafting. Benchmark results reveal that current LLMs exhibit limitations in patent drafting, while Patent-MAF provides a strong baseline that consistently outperforms evaluated open-source models and remains competitive with large closed-source models.

0.82
5

MemGuard: Persisting Verifier Signals for LLM-Agent Memory Governance

cs.AI cs.CL ·2026-08-22 ·Haoyu Wang, Guangyuan Dong, He Liang, Zijing Zhang, Jiachen Luo +3 more
top venuebenchmarkcode/datahighly cited
Abstract · 30 pages, 7 figures

LLM agents are moving from single-prompt use to long task streams in which reusable memory becomes a core capability for terminal, software-engineering, and web tasks. Such memory is useful only when stored experience remains reliable across hundreds of interactions, but two failure modes break that assumption in practice. The first is unreliable admission: failed trajectories,accidental successes, and misleading observations enter memory because they appear relevant, then mislead later decisions. The second is memory drift: long-running banks accumulate duplicate, stale, and conflicting records that retrieval alone cannot repair. MemGuard's key distinction is to treat verifier output not as a one-shot filter, but as persistent lifecycle metadata. It converts multi-criteria score-token verification into reward, confidence, label, and uncertainty descriptors that are attached to every candidate before activation and reused during retrieval, conflict resolution, summarization, and archival. We evaluate MemGuard on Terminal-Bench 2.0, SWE-Bench Verified, WebArena, and Mind2Web across four backbones, comparing against four memory baselines plus a verifier-only control under matched runtime budgets. Averaged over five seeds, MemGuard achieves the best success metric and lowest average steps in all 16 backbone-benchmark settings, improving over ReasoningBank, the strongest prior baseline among the memory methods we evaluate, with a largest gain of 7.9 success-rate points on WebArena, 5.6 step-success-rate points on Mind2Web, and 2.4-3.5 points on terminal and software-engineering benchmarks. Code is available at https://github.com/whyyyyy123/MemGuard.

0.82
6

Dynamic SpectraFormer for Ultra-High-Definition Underwater Image Enhancement

cs.CV cs.RO ·2026-08-19 ·Zhiqiang Hu, Tao Yu, Shouren Huang, Masatoshi Ishikawa
publishedcode/data
Abstract · 8 pages, 7 figures. Published in the 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2024)

Underwater images suffer from color distortion, haze, and poor visibility due to light refraction and absorption in water. These challenges significantly impact the utilization of Autonomous Underwater Vehicles (AUVs) or marine robots. Typically, color and brightness distortions manifest at lower frequencies, while edge and texture distortions are prevalent at higher frequencies. Traditional methods struggle to concurrently rectify these mixed distortions as they primarily concentrate on the spatial domain. To address these issues, we introduce the Dynamic SpectraFormer, which enhances underwater images through a frequency domain transformer. The Dynamic SpectraFormer introduces an ultra-high-resolution sparse spectrum attention module, which could capture the long-term dependency without losing the universal approximating power. Additionally, we have developed a dynamic spectrum weight generation layer that serves as an adaptive spectrum band selector, accentuating critical frequency bands and suppressing less relevant ones. Consequently, this method significantly improves underwater image quality by addressing both high- and low-frequency distortions. Our extensive ablation studies and comparative evaluations consolidate the Dynamic SpectraFormer's efficacy across multiple underwater image enhancement benchmarks. The source code is available at https://github.com/arifence2024/DynamicSpectraFormer.git.

0.80
7

AT-ViT: Area-Targeted Multi-View Vision Transformer with Cross-Attention and Multi-Scale Patching for Plant Trait Recognition in Herbarium Images

cs.CV cs.AI ·2026-08-21 ·Amani Sedrat, Takieddine Chehhat, Youcef Sklab, Hanane Ariouat, Abderrazak Sebaa +3 more
top venue
Abstract

Automated plant traits recognition from herbarium images is essential for plant sciences, yet remains challenging because background elements (e.g., textual labels, mounting artifacts, and color charts) can introduce shortcut learning, leading models to rely on spurious non-plant cues rather than plant morphology. This bias degrades both generalization and interpretability. In this paper, we introduce AT-ViT, a dual-branch Vision Transformer that jointly encodes raw herbarium scans and their segmented-derived counterparts via a multi-scale, multi-view cross-attention fusion scheme. AT-ViT further incorporates a mask-guided patch weighting mechanism that amplifies plant-relevant regions and attenuates background-driven features. By learning from the original scans while being guided by segmentation masks through the mask-guided patch reweighting mechanism, the model is encouraged to focus on plant organs and learn plant-centric representations more effectively. Across multiple trait classification tasks (e.g., leaf base shape, thorns), AT-ViT delivers consistent accuracy gains, improves attention localization on plant regions, and exhibits increased robustness under synthetic background perturbations. Specifically, AT-ViT substantially improves spatial attention grounding, boosting plant-region alignment (Avg IoU_p: +15.66 to +18.03 pp) while reducing background overlap (Avg IoU_b: -27.92 to -31.02 pp) relative to CrossViT, and remains markedly more robust to background perturbations, outperforming ResNet101 by up to +32.32 accuracy points and CrossViT by up to +5.07 points under background-noise conditions.

0.78
8

ModBench: A Pipeline for Building Modelica Benchmark Datasets Mined from Library Repositories

cs.SE ·2026-08-17 ·Masoud Sadrnezhaad, Martin Sjölund, Adrian Pop, José Antonio Hernández López, Torvald Mårtensson +1 more
top venuebenchmarkcode/data
Abstract · Extended abstract accepted at SAM 2026, co-located with MODELS 2026. To appear in the ACM/IEEE MODELS 2026 Companion Proceedings

Research on equation-based cyber-physical systems modeling languages, such as Modelica, is constrained by the lack of curated benchmark datasets. This limits empirical insight into the evolution and development of models. We address this gap with ModBench, a pipeline that mines Git repositories of Modelica libraries to produce benchmark datasets of model snapshots. The pipeline (1) filters repository commits to retain human-authored, Modelica-relevant revisions; (2) extracts simulation-eligible classes; and (3) builds canonical representations of Modelica classes. For empirical validation, we applied ModBench to the Modelica Standard Library (MSL) and report the resulting dataset, spanning the full commit history (since Modelica language v3), with 85,562 distinct class snapshots, and links enabling traceability to original models and Git metadata. The dataset, its API, and the data generation pipeline are publicly available to support future research on model evolution analysis, compiler testing, and automated model repair or generation.

0.78
9

A Standardized Framework for Machine Learning in Power System Protection

cs.LG cs.AIeess.SP ·2026-08-20 ·Julian Oelhaf, Georg Kordowich, Paula Andrea Pérez-Toro, Christian Bergler, Johann Jäger +2 more
publishedbenchmarkcode/data
Abstract · 32 pages, 4 figures, 26 tables. Code: https://github.com/julianoelhaf/protection-eval-framework. Dataset: PROTECT-90, doi:10.5281/zenodo.211…

Studies of machine-learning-based power-system protection increasingly report near-perfect scores, yet the meaning of those scores depends strongly on the evaluation setting. Protection task, physical scope, measurements, timing, targets, preprocessing, and validation often vary jointly and remain incompletely specified. This paper proposes a standardization-oriented framework that treats evaluation design as part of the scientific contribution. It defines seven required study dimensions: protection objective, physical scope, observability, timing and decision windows, targets and sample validity, validation protocol, and evaluation outputs. The framework is instantiated in a bounded case study on the public PROTECT-90 electromagnetic-transient benchmark, comprising 9022 simulated episodes from a 90 kV double-line topology, for onset-conditioned fault classification and localization. Under centralized sensing, simulation-metadata-aligned 20 ms windows, and episode-grouped validation, a multi-layer perceptron (MLP) achieved a five-fold mean macro-averaged F1 score of 0.991 +/- 0.001 for classification and a localization mean absolute error of 10.20 +/- 0.25% of line length (mean +/- std across episode-grouped folds). Extending the decision horizon to 50 ms preserved this task-dependent performance asymmetry, while reduced observability approximately doubled the MLP localization error but had little effect on classification. A synchronized two-ended conventional locator outperformed the learning locators under its richer clean information set, and measurement degradation showed that clean predictive performance did not determine robustness. The framework turns evaluation assumptions into explicit, reproducible evidence and provides a basis for more comparable, auditable evaluation and future certification-oriented assessment of machine-learning protection functions.

0.77
10

CaliBench: Are the Stochastic Dynamics of Video World Models Physically Calibrated?

cs.LG cs.AI ·2026-08-17 ·Jonathan Sadeghi, Jenny Seidenschwarz, Jesse Allardice, Sirish Srinivasan, Benjamin Graham +1 more
publishedcode/data
Abstract · Accepted at Transactions on Machine Learning Research (TMLR). Presented at WOOP @ ECCV 2026. Code is available at https://github.com/odyssey…

Video world models approximate the stochastic distribution of physical outcomes through generative sampling, but existing benchmarks score individual generations or compare distributions coarsely over a whole dataset, leaving the fine-grained aleatoric uncertainty of specific phenomena untested. We introduce CaliBench, which scores outcomes in a physically interpretable discrete space - a bin index, a die face, a suit, a colour - rather than a learned feature space such as in FID, so the distance from a known reference distribution is measured directly. We curate outcome spaces whose reference is known in closed form (binomial Galton boards, Bernoulli forks, uniform dice/cards/lottery, a skewed European-roulette colour), enabling an exact calibration test. We decompose performance into two orthogonal axes that a single accuracy metric conflates: scorability, the fraction of generations yielding a scoreable outcome, and calibration, the total variation distance from the reference on that sample. A chi-squared test assesses significance; as calibration is its null hypothesis it can evidence only miscalibration, and at N=32 per cell detects only large deviations. We apply it to nine scenes and six image-to-video models (WAN-2.7, SeeDance-2.0, HappyHorse-1.0, Veo 3.1, Runway Gen-4.5, Cosmos3-Super), 32 generations each. Models consistently concentrate probability mass on a few outcomes rather than reproducing the reference. Most scene-model combinations are significantly miscalibrated, in the extreme collapsing to one outcome, as Veo 3.1 does on dice. On roulette, generations often leave the ball ambiguously placed, giving several models low scorability. Performance varies by scene: no model dominates all nine. We release the protocol and a metric (mean normalised total variation, mnTV) for comparing new models against our results.

0.76
11

Incorporating Bounded Rationality into Electric Vehicle Highway Charging Decisions: A Bayesian Game Analysis

cs.GT eess.SY ·2026-08-17 ·Huanyu Yan, Xiaoying Tang
publishedtheorycode/datahighly cited
Abstract · Published in IEEE Internet of Things Journal, vol. 12, no. 11, pp. 15249-15260, 2025. An earlier version appeared in Proc. 14th ACM Internat…

Electric vehicles (EVs) represent a critical intelligent terminal within the Internet of Things (IoT). Despite the year-on-year growth in EV penetration, the highway driving experience still requires improvement. Accurate prediction of EV highway charging behavior is crucial to addressing this issue. This paper introduces a novel bounded rationality framework to analyze highway charging decisions. Specifically, we utilize prospect theory to capture the tendency of drivers to reserve more electricity than theoretically necessary. We then propose a Bayesian game in which EV drivers, unaware of others' decisions, aim to minimize costs, including range anxiety, charging fees, and queuing time. To gain insights into the game, we prove the existence and uniqueness of the Bayesian Nash Equilibrium in two practical scenarios. Our numerical experiments, based on real-life data, demonstrate that drivers' risk aversion tendency significantly influence EV charging decisions, charging demand, queuing lengths at charging stations, and the departure rate on the highway network. Furthermore, our strategy reduces cumulative EV cost and CSs' charging costs compared to other benchmarks.

0.74
12

Vorticity Dissipation Based Routing: A Fluid-Kinetic Framework for Loop-Free Transport in Ultra-Dense Networks

cs.NI ·2026-08-20 ·Wen-Yu Dong, Weiwei Jiang, Song Zhao, Rui-Si Han, Qi Bi +1 more
top venueunusualhighly cited
Abstract · 18 pages, 8 figures. Accepted for publication in IEEE Transactions on Mobile Computing

Discrete routing protocols in ultra-dense wireless networks are constrained by signaling overhead and transient routing loops that degrade radio-resource efficiency. While continuum modeling provides a scalable alternative, existing scalar density approaches lack the vector geometric structure required to characterize these topological anomalies. This paper introduces a fluid-kinetic framework, vorticity dissipation-based routing (VDR), utilizing the Helmholtz-Hodge decomposition. We demonstrate that the macroscopic traffic flux can be orthogonally decoupled into a demand-driven irrotational component and a loop-induced solenoidal component representing routing vorticity. Building on this insight, we define network vorticity as a macroscopic metric to quantify topological inefficiency. Routing optimization is formulated as a gradient flow on an enstrophy functional, yielding a vorticity dissipation equation as the governing dynamic law. Lyapunov stability analysis proves that this mechanism ensures the monotonic decay of global enstrophy toward an asymptotically loop-free equilibrium. Numerical results validate that VDR suppresses realized forwarding loops, reduces end-to-end delay, maintains robust packet delivery, and exhibits near-linear scaling under fixed-area densification while explicitly accounting for the grid-dependent Poisson-solver cost.

0.73
13

Attitude Estimation from Photometric Data using Gaussian Process Regression

eess.SY ·2026-08-17 ·Ryui Hara, Yasuhiro Yoshimura, Toshiya Hanada
publishedhighly cited
Abstract · Accepted for publication in Journal of Space Safety Engineering

The rapid growth of resident space objects in Earth's orbit has intensified the need for advanced space situational awareness and space domain awareness to manage satellite traffic and prevent collisions. Attitude estimation is critical for accurate state propagation, as non-gravitational forces like solar radiation pressure and atmospheric drag depend on the object's attitude. This study explores using light curves, time variation of an object's brightness, to estimate a space object's attitude. Light curve inversion, traditionally used in astronomy, faces challenges when applied to resident space objects due to their non-convex shapes and specular reflections. Conventional methods for attitude estimation often assume known shape and surface parameters, which are usually unknown for space debris generated by a collision or breakup. To address this issue, this study proposes the estimation method combining Gaussian process regression with the unscented Kalman filter. This study uses Gaussian process regression for a non-parametric observation model, enhancing robustness against unknown surface parameters. Numerical examples consider a box-wing object in a geosynchronous orbit and demonstrate that the proposed method has better estimation accuracy than a conventional unscented Kalman filter. The numerical simulation results also represent the attitude estimation robust against uncertainties in surface properties, contributing to practical scenarios in space situational awareness and space domain awareness where the object parameters are unknown.

0.73
14

Process Optimization Under Uncertainty for Improving the Bond Quality of Polymer Filaments in Fused Filament Fabrication

cs.CE cs.LGmath.NAmath.PR ·2026-08-19 ·Berkcan Kapusuzoglu, Matthew Sato, Sankaran Mahadevan, Paul Witherell
publishedhighly cited
Abstract · 12 pages, ASME Journal of Manufacturing Science and Engineering

This paper develops a computational framework to optimize the process parameters such that the bond quality between extruded polymer filaments is maximized in fused filament fabrication (FFF). A transient heat transfer analysis providing an estimate of the temperature profile of the filaments is coupled with a sintering neck growth model to assess the bond quality that occurs at the interfaces between adjacent filaments. Predicting the variability in the FFF process is essential for achieving proactive quality control of the manufactured part; however, the models used to predict the variability are affected by assumptions and approximations. This paper systematically quantifies the uncertainty in the bond quality model prediction due to various sources of uncertainty, both aleatory and epistemic, and includes the uncertainty and the model discrepancy in the process parameter optimization. Variance-based sensitivity analysis based on Sobol indices is used to quantify the relative contributions of the different uncertainty sources to the uncertainty in the bond quality. A Gaussian process (GP) surrogate model is constructed to compute and include the model discrepancy within the optimization. Physical experiments are conducted for calibration and validation of the physics model and also for validation of the optimum solution. The results show that the proposed formulation for process parameter optimization under uncertainty results in high bond quality between adjoining filaments of the FFF product.

0.72
15

SecOPD: Mitigating Adaptive Prompt Injections by On-Policy Distillation

cs.CR cs.AI ·2026-08-21 ·Yibo Peng, Long Lian, David Wagner, Sizhe Chen
top venuecode/datahighly cited
Abstract · EMNLP 2026 (main conference)

Prompt injection is listed as the \#1 threat to AI agents. When an agent accesses external data from websites, files, or emails, an attacker may inject a prompt into the data, saying, "Ignore all prior instructions and perform <an attacker's task>." To prevent arbitrary manipulation of agents, defenders try to train secure LLMs, which, however, still suffer from near 100% attack success rates (ASRs) against adaptive prompt injections. We note that this is because existing defensive finetuning recipes rely on sequence-level feedback signals (in DPO or GRPO). Treating an entire output equally prevents the model from learning precisely which output tokens are insecure. In this paper, we propose Secure On-Policy Distillation (SecOPD) that provides token-level feedback to guide defensive fine-tuning. The LLM receives an injected sample and produces a rollout, whose tokens are scored by the initialization model given the corresponding clean input. With more fine-grained training signals, our defended Qwen3.6-27B achieves a 9.0% ASR against the SoTA PISmith adaptive prompt injections, compared to 94.0% for the prior SoTA, Meta-SecAlign. The obtained security generalizes to domains completely unseen in training: in agentic tool calling, SecOPD achieves a 4.7% ASR compared to 5.5% for Meta-SecAlign. Code and the model are available at https://github.com/pppyb/SecOPD and https://huggingface.co/pybbb/Qwen3.6-27B-SecOPD.

0.72
16

Evaluating and Explaining Prompt Sensitivity of LLMs Using Interactions

cs.LG cs.AIcs.CL ·2026-08-19 ·Ruiyang Qin, Qingzhuo Wang, Tian Wang, Zhihua Wei, Wen Shen
top venuecode/datahighly cited
Abstract · Accepted at the 43rd International Conference on Machine Learning (ICML 2026). 46 pages, 48 figures

The remarkable capabilities of large language models (LLMs) are often undermined by their instability. Even subtle and semantically irrelevant changes in prompts can cause dramatic fluctuations in performance, a phenomenon known as prompt sensitivity. Previous studies typically evaluate prompt sensitivity by comparing the LLM's final outputs when prompts change. However, such coarse-grained metrics fail to explain the internal reasons for prompt sensitivity. In this paper, we introduce interactions as a fine-grained tool to analyze prompt sensitivity of LLMs. Specifically, we decompose the output score of the LLM into a set of interactions. Each interaction represents a nonlinear relationship involving a set of input variables. We discover that subtle changes to prompts can trigger severe instability in interactions, even when the outputs of the LLM remain the same. To this end, we propose an Interaction-based Prompt Sensitivity (IPS) metric by quantifying changes in interactions when we introduce subtle changes to prompts. We apply the IPS metric to 50 open-source LLMs and uncover four factors that reduce the prompt sensitivity of LLMs, including supervised fine-tuning, increased model scales, dense architectures, and few-shot learning. More crucially, we discover a common mechanism by which these four factors reduce prompt sensitivity: all four factors tend to reduce the prompt sensitivity of low-order interactions (i.e., interactions involving few input variables).

0.72
17

MILD: Tractable Terrain Modeling for Learning Improved Bipedal Locomotion on Deformable Surfaces

cs.RO ·2026-08-20 ·Zeren Luo, Jiahui Zhang, Zhe Xu, Wanyue Li, Xinqi Li +4 more
top venuehighly cited
Abstract · 8 pages, 9 figures

Enabling robots to walk on yielding terrain is vital for applications ranging from disaster response to planetary exploration. While bipedal robots hold immense potential, their locomotion on deformable surfaces remains limited as current simulators fail to capture the spatiotemporal heterogeneity of such yielding substrates. We present MILD, featuring a physics-grounded discrete-element contact solver that accurately simulates spatially varying foot-terrain interactions. Complementing this model, we train a terrain-aware locomotion controller via deep reinforcement learning with latent modulation and proprioceptive estimation. Quantitative comparisons against state-of-the-art methods show our approach generates more diverse and realistic contact scenarios during training, resulting in controllers that exhibit natural adaptation on real deformable surfaces. Through hardware experiments, we demonstrate the system's capability for online terrain identification and adaptation across a wide range of surface stiffness.

0.72
18

Adaptive Probabilistic Shielding by Learning MDPs for Safe Reinforcement Learning

cs.LG cs.AIcs.LO ·2026-08-20 ·Astrid Horn Brorholt, Maris F. L. Galesloot, Nils Jansen, Kim Guldstrand Larsen, Christian Schilling
publishedhot direction
Abstract · 19 pages, 3 figures, 3 tables. To be published in the proceedings of RV 2026

Probabilistic shielding is a technique for safe reinforcement learning (RL). Typically, a static observer -- called the shield -- constrains the learning agent's actions to those for which acting safely remains feasible. Traditionally, the shield is computed from the transition probabilities of the underlying Markov decision process (MDP). Thus, this technique is not applicable when the MDP model is not given a priori, which, unfortunately, is the case in typical RL applications. In this paper, we study the problem of computing a shield in the setting where the transition graph of the MDP is known, but the transition probabilities are unknown. Our approach integrates probabilistic shielding with online model learning: as the RL agent explores the environment, we estimate the transition probabilities. From this estimate, we compute a shield. While the shield may be conservative initially, it adapts as the model estimate becomes more precise. Thus, the shield improves in tandem with the RL agent. This paradigm of adaptive probabilistic shielding raises a number of challenges, such as when to recompute the shield and how to balance between exploration and safety during learning. We empirically evaluate multiple variants of this paradigm across several environments.

0.71
19

Certified but Private: Scalable Zero-Knowledge Proofs for Neural Network Guarantees

cs.LG cs.CRcs.LO ·2026-08-17 ·Youwei Zhong, Ben Merbaum, Timos Antonopoulos, Ning Luo, Charalampos Papamanthou +2 more
top venuecode/data
Abstract · 31 pages, 2 figures (10 pages for the main text), accepted to NeurIPS 2026, for code of implementation and evaluation, see https://github.co…

With the growing deployment of machine learning models, formal guarantees of the robustness and fairness of these models have become increasingly important in safety-critical and legal-compliance settings. However, model parameters are often commercial secrets that cannot be disclosed to auditors or end users. To this end, we present PANDA, a scalable system that uses zero-knowledge proofs (ZKPs) to prove the robustness and fairness properties of a model without revealing its private parameters. PANDA is built on top of CROWN, an efficient robustness certification framework that is used in many state-of-the-art formal verification tools for neural networks. The core contribution of PANDA is a novel algorithm for proving linear relaxation bounds for non-linear activation layers, yielding simple, lightweight proofs. Remarkably, our implementation can generate proofs of local robustness for neural networks with more than 2.9M parameters in 5 minutes, and can verify them in 10 seconds. Prior ZKP-based robustness system rely on exponential-time algorithms that cannot scale to nontrivial networks. In contrast, PANDA scales polynomially in the number of neurons in a network, allowing us to support neural networks 4 orders of magnitude larger than previous approaches with significantly reduced prover overhead.

0.70
20

An Experimental Study of Downwash Effects on a Continuum Manipulator Integrated with a Multirotor UAV

cs.RO ·2026-08-19 ·Anuraj Uthayasooriyan, Krishna Manaswi Digumarti, ernando Vanegas, Felipe Gonzalez
top venue
Abstract · Accepted to publish in Robotics and Automation Letters

Continuum arm aerial manipulation systems leverage soft-manipulator compliance and dexterity for tasks in confined or hazardous environments, but propeller downwash can degrade performance, particularly near walls and the ground. This effect remains uncharacterized for continuum manipulators. This letter experimentally studies downwash-induced kinematic deviations of a tendon-driven continuum manipulator integrated with a multirotor platform. Under still-air conditions, the CM is compared with a constant-curvature (CC) model. Downwash- induced end-effector pose deviations are then quantified relative to the mean still-air experimental baseline at four propeller throttle levels in free space, and at maximum throttle near a wall, and near the ground. Vertical position and yaw show the largest deviations and are amplified by ground effect. A CC-guided Gaussian process regression (GPR) residual model is learned from experimental data that improves forward pose prediction RMSE (position by 89-95%, orientation by 47-79%), and support compensation-oriented, downwash-aware modeling of continuum arm aerial manipulation systems.

0.70