Computation and Language
Repairing Speech Access After Text Updates with Frozen Affine Fields
Ming-Hao Hsu, Yuxiang Wang, Yingda Shen et al. (+1 more)
Speech-capable
language models inherit most of their knowledge from text-rich
language backbones, and continued model maintenance is likewise dominated by text updates. Knowledge acquired through a text update can nevertheless remain difficult to access when the same query is spoken. We formulate this mismatch as post-update
speech access repair, where the knowledge-bearing checkpoint stays frozen and a detachable operator repairs
speech-only access in one model pass. We introduce Affine Fields for Interface Repair across Modalities (AFFIRM), which first learns and freezes a base correction for
speech hidden states, then adds query-specific corrections with zero mean over the operator-training queries. Paired
speech and text states provide the coordinates that condition these corrections on each query. On balanced synthetic-
speech PopQA, paired comparisons do not establish a clear advantage for AFFIRM over global SALSA steering or low-rank ReFT interventions under the same frozen single-state constraint. On recorded SLUE-SQA-5 questions with text passages, a full-scale PopQA-fitted AFFIRM operator transfers without refitting and improves ROUGE-L by 0.0941 over its paired No Repair baseline. Low-rank ReFT interventions also transfer positively, whereas the matched SALSA variant falls 0.0707 below its paired baseline. These results show that text acquisition and
speech access can diverge after an update and should be verified and repaired separately.
Read the full abstract ▾
All authors Ming-Hao Hsu, Yuxiang Wang, Yingda Shen, Zhizheng Wu
Machine Learning
Adversarial Reinforcement Learning for Robust Planetary Landing
Miguel Leiva-Vélez, Nicolas Gaston-Rozado, Andrea Scorsoglio et al. (+2 more)
Deep reinforcement learning (DRL) policies for planetary landing and other aerospace guidance, navigation, and control tasks are commonly trained under randomized disturbances to improve robustness. However, typical
stochastic perturbation sampling assumes independent variations, whereas real mission disturbances often exhibit spatial and temporal correlation and cannot be reproduced through independent random draws. This work investigates
adversarial reinforcement learning to discover challenging off-nominal conditions. A secondary
agent generates physically constrained perturbations that degrade the performance of a landing controller, forming an asymmetric sequential zero-sum game. Training proceeds in three stages: baseline controller learning, robustness enhancement with
stochastic perturbations, and an iterative
adversarial phase in which the controller and disturbance generator are alternately optimized. Preliminary experiments in a three-degree-of-freedom landing environment show that
adversarial disturbances reveal vulnerabilities missed by conventional randomization and provide early indications that, with a more extensive training campaign, the approach can yield improved robustness and stronger generalization under previously unseen perturbation regimes.
Read the full abstract ▾
All authors Miguel Leiva-Vélez, Nicolas Gaston-Rozado, Andrea Scorsoglio, Hodei Urrutxua, Víctor Rodríguez-Fernández
Computer Vision
Contrastive uncertainty learning for robust multi-structure segmentation in lower-pelvic MR
Bilal Sidiqi, Yipei Wang, Wen Yan et al. (+3 more)
Boundary delineation of anatomical structures in prostate MRI is often compromised by regional ambiguity. Automated segmentation methods relying on global overlap loss functions tend to be insensitive to surface deviations, leading to significant errors in ambiguous regions. Most existing uncertainty-aware methods treat uncertainty as a post-hoc quality indicator or prediction filter. We propose Contrastive Uncertainty Learning (CUL), a supervised framework that uses predictive uncertainty to directly guide representation learning. Using Monte Carlo Dropout, CUL identifies voxel-wise uncertainty and structures the
embedding geometry accordingly: low-uncertainty, correctly predicted features form stable voxels while high-uncertainty or misclassified features are actively repelled, preventing feature collapse at difficult boundaries. We evaluate CUL on a 589-scan 3D prostate MRI multi-structure segmentation task (8 anatomical structures) using a ViT with UperNet decoder architecture. Average Dice ($83.38\%$) remains comparable to the baseline ($83.35\%$), while surface distance decreases significantly ($p<0.001$) across 6 of 8 anatomical structures. A hard-case analysis reveals a $22{\times}$ asymmetry between significantly improved and degraded cases ($18.8\%$ vs $0.9\%$). Ablation studies show that removing uncertainty-guided sample selection eliminates improvements for the transition zone, while replacing the contrastive objective with a boundary loss additionally removes bladder improvements, demonstrating that both uncertainty-guided sampling and the contrastive objective are essential for the observed gains. These findings demonstrate that the proposed uncertainty-guided representation learning is a useful mechanism for reducing the risk of extreme errors in safety-critical medical segmentation
Read the full abstract ▾
All authors Bilal Sidiqi, Yipei Wang, Wen Yan, Shaheer U. Saeed, Daniel C. Alexander, Yipeng Hu
Data Structures and Algorithms
Subexponential Parameterized Approximation for Group-Fair Euclidean $k$-Center
Rudranarayan Kar, Diya Roy and Abhishek Sahu
Clustering is a basic tool for grouping data into meaningful classes, but in many applications the resulting clusters must also respect the
fairness conditions among different groups. We study this direction for the group-fair Euclidean $k$-center problem in fixed dimension, where the input points are partitioned into disjoint color classes, and every cluster must satisfy given lower and upper bounds on the fraction of each color. We give a separator-based recursive approximation
algorithm for the continuous-center setting. The main idea is to first reduce the continuous search space to a finite candidate center set and then use the
geometric sphere separators to break the instance into smaller subproblems. Our
algorithm gives a bicriteria approximation: the clustering radius is within a factor of $(1+\epsilon)$ of the optimum exactly fair solution, while the
fairness bounds are relaxed only by a multiplicative factor. For fixed dimension, number of colors, and approximation parameters, the running time is
polynomial in input size and subexponential in $k$. A recent IJCAI-ECAI2026 result gives a $(1+\epsilon)$-approximation for group-fair $k$-center in bounded doubling metrics with running time $(k/\epsilon)^{\mathcal{O}(k)}n^{\mathcal{O}(1)}$. In the fixed-dimensional Euclidean setting considered here, we improve the dependence on $k$ to subexponential, while allowing continuous centers. The
fairness guarantees of the two results are different: the previous work allows an additive
fairness violation, whereas our
algorithm uses a controlled multiplicative relaxation.
Read the full abstract ▾
Systems and Control
Robust Data-Driven Controller Synthesis from Sampled and Uncertain Frequency Response Estimates using Integral Quadratic Constraints
Luuk Marceau Spin, Maurice W. P. M. H. Heemels, Nathan van de Wouw et al. (+1 more)
In this paper, we develop a novel
MIMO controller synthesis method that relies solely on frequency-domain data of discrete-time systems. The approach is based on an iterative design procedure using integral quadratic constraints (IQCs). It generalizes existing data-driven methods that approximate semi-infinite IQC conditions by enforcing them on a finite set of measured frequency points. Such approximations do not provide guarantees on the continuous frequency axis and may fail to capture inter-frequency behavior. We address this limitation by formulating a convex optimization problem that preserves robustness guarantees over the entire frequency range. In particular, the proposed method explicitly accounts for inter-frequency behavior of both plant and controller, leading to certified robust stability and performance. The effectiveness and computational efficiency of the approach are demonstrated using experimentally obtained frequency response data from industrial-grade
semiconductor equipment. The synthesized controller is implemented on the physical setup, and its performance is validated in real-time experiments.
Read the full abstract ▾
All authors Luuk Marceau Spin, Maurice W. P. M. H. Heemels, Nathan van de Wouw, Roland Toth
Computation and Language
Scaling Multilingual Mixture-of-Experts: How Language Coverage Changes Capacity and Compute Allocation
Joel Dag, Nikit Srivastava, Hamada M. Zahera et al. (+1 more)
Multilingual models share capacity across
languages, so adding
languages can hurt performance on existing ones. Mixture-of-experts models expand this capacity with little additional per-
token computation. Given this extra capacity, does adding experts reduce what each additional
language costs? To answer this question, we propose a repetition-aware joint scaling law relating number of active parameters, training
tokens per
language, number of experts, and
language coverage. Fitted on 26,300 per-
language loss observations from 64 pretrained configurations, our law reduces prediction error on held-out configurations by 28% relative to the strongest evaluated baseline. At matched number of active parameters and training
tokens per
language, 32 experts reduce the loss penalty of expanding from 12 to 200
languages by 83% compared with a dense model. Our law further shows that broader
language coverage favors more experts across a wider range of compute budgets, guiding capacity allocation as multilingual models scale.
Read the full abstract ▾
All authors Joel Dag, Nikit Srivastava, Hamada M. Zahera, Axel-Cyrille Ngonga Ngomo
Sound
Evaluating perceptual transparency of lossy music audio compression with Opus codec
Benjamin Martin and Romain Hennequin
Although the open-source Opus audio codec is widely used for digital audio streaming, its perceptual transparency threshold for high-bitrate music compression remains insufficiently evaluated. To establish this threshold, this study evaluates Opus across a two-phase ITU-R BS.1116-3 double-blind framework, analyzing Difference Grades using a Linear Mixed-Effects Model (LMM) and Two One-Sided Tests (TOST) for statistical equivalence. In a first phase with 21 qualified listeners and 23 music excerpts, 128 kbps achieves statistical in-distinguishability ($p = 0.456$) but narrowly fails strict equivalence to the uncompressed reference ($p = 0.064$). In Phase 2, Best Linear Unbiased Predictors (BLUPs) isolate the 10 most critical listeners and 8 most challenging samples for a stress-test. Under these worst-case conditions, 128 kbps is conclusively detected as degraded ($p = 0.030$), whereas 160 kbps successfully reaches perceptual transparency ($p = 0.747$) and strict statistical equivalence ($p = 0.024$). The study concludes that 160 kbps demonstrates perceptual transparency to uncompressed CD quality in critical listening environments. For reproducibility, we publicly release results for both phases, anonymized subject background info and sample characteristics.
Read the full abstract ▾
Cryptography and Security
P2Patch: Exploit-Guided Vulnerability Repair
Mohsen Iranmanesh, Sina Moradi Sabet, Sina Marefat et al. (+7 more)
Large
language models are increasingly deployed as autonomous
agents for automated program repair, patching software vulnerabilities through multi-step
reasoning and tool use. Yet these systems typically validate a patch against the same evidence used to construct it – a static alert, sanitizer trace, published exploit, or test suite. A patch that blocks that one piece of evidence can therefore look successful while remaining vulnerable to the same vulnerability with some variation. We present P2Patch, a generative
adversarial repair system that treats each patch as a new attack target. Starting from a normalized vulnerability finding, an exploitation
agent constructs a reproducing proof of vulnerability (PoV), a patching
agent repairs the program, and the exploitation
agent then attacks the patched program for a distinct same-vulnerability exploit. Every successful exploit becomes a permanent repair requirement, and the final patch must block all PoVs accumulated during the patching process, with construction-time PoVs kept strictly separate from held-out evaluation oracles. Across 101 C/C++ and Java CVE subjects, this
adversarial loop surfaces a distinct confirmed exploit in 41% of runs after the patch has already blocked its original construction-time PoV. Against single-pass repair from the same finding using Claude Code, P2Patch raises held-out fix-closed coverage from 78.1% to 84.7% and beyond-upstream coverage from 42.1% to 62.5%. Under the same held-out oracles, it also certifies more attack paths as blocked than recent state-of-the-art agentic repair systems on overlapping subjects. These results show that
adversarial testing and independent security oracles expose repair gaps that one-shot validation misses.
Read the full abstract ▾
All authors Mohsen Iranmanesh, Sina Moradi Sabet, Sina Marefat, Ali Javidi Ghasr, Maxime Newman Nereyabagabo, Kousha Amouzesh, Jaivir Malhi, Vinci Velasco, Alex Chung, Mohammad A. Tayebi
Computational Geometry
FPTAS for Polygonal Multi-Robot Motion Planning
Sayan Bandyapadhyay, William Lochet, Saket Saurabh et al. (+1 more)
We study multi-
robot motion planning in a polygonal environment with polygonal
robots. The setting of the problem consists of a polygonal domain $\mathcal{W}$ with $n$ vertices and $k$
robots $R_1,\dots,R_k$ translating in $\mathcal{W}$ each of which is represented by a polygon of constant complexity. Given a source configuration $\mathbf{s}$ and a target configuration $\mathbf{t}$ of the
robots in $\mathcal{W}$, the goal of the problem is to find a collision-free motion plan from $\mathbf{s}$ to $\mathbf{t}$ that is shortest with respect to some cost function. We present the first fully
polynomial-time approximation schemes (FPTAS) for motion planning with any fixed number $k$ of
robots, under the min-sum objective, the min-max objective, and the min-makespan objective. Here, the min-sum variant aims to minimize the total traveling distance of all
robots, the min-max variant aims to minimize the maximum traveling distance of a single
robot, and the min-makespan variant aims to minimize the total time cost under the assumption that all
robots move with a maximum speed $1$. The
algorithm directly generalizes to the problem in any fixed dimension $d$, with a polytope environment and polytope
robots. Our result settles an open question of Agarwal, Halperin, Sharir, Steiger [SODA'24] and Agarwal, Holmgren, Steiger [SODA'26], who gave an FPTAS for $k=2$ unit-square
robots and a bicriteria-approximation
algorithm for a fixed number $k$ of unit-square or unit-disk
robots, respectively. Compared to the previous results, our
algorithm is substantially simpler.
Read the full abstract ▾
All authors Sayan Bandyapadhyay, William Lochet, Saket Saurabh, Jie Xue
Machine Learning
Retrieval Over Training: Similarity search-based Model Selection for Time Series Anomaly Detection
Christos Panourgias, Roberto Stanzione, Adrien Petralia et al. (+2 more)
Anomaly detection is a fundamental task for time-series analytics, with important implications for the downstream performance of many applications. Despite the large number of anomaly detection methods proposed in the literature, recent
benchmark studies have shown that no single detector performs best across highly heterogeneous time series. Therefore, a practical and scalable solution is to develop a model-selection method that, for a given time series, selects the anomaly detector most likely to perform well. Nevertheless, the model selection approaches proposed in the literature suffer from a significant drop in accuracy when applied in Out-of-Distribution (OOD) settings. In this paper, we tackle the aforementioned limitation and propose RAMSAD, a
retrieval-based framework for model selection in time-series anomaly detection. Given a new time series, our method queries a knowledge base of previously observed instances, retrieves the top-k most similar series, and transfers detector recommendations from their performance profiles. The framework can operate with standard similarity measures as well as
embedding-based representations. Our results show that RAMSAD outperforms existing baselines in In-Distribution (ID) settings and is the most robust selector in OOD, where, when selecting a small subset of detectors, it matches or exceeds ensembles that run the entire detector pool, at a fraction of their cost. Overall, we demonstrate that similarity-based
retrieval constitutes a strong and efficient foundation for model selection in time-series anomaly detection.
Read the full abstract ▾
All authors Christos Panourgias, Roberto Stanzione, Adrien Petralia, Themis Palpanas, Paul Boniol
Robotics
Learning Navigation from Multimodal Demonstrations with Geometric Candidate Modes
Chengyang Peng, Zhihao Zhang, Upama Pant et al. (+3 more)
Offline navigation demonstrations are
multimodal, because one observation often allows several valid actions, such as passing an obstacle on either side. Behavior cloning averages these actions, potentially leading to unsafe routes.
Multimodal policies must discover the alternatives from the data, but similar states can lead to different routes whose current actions overlap. In navigation, the alternatives have a
geometric cause and can be computed from one observation. We propose a hierarchical neural-network policy that computes candidate modes from local geometry and learns from demonstrations which mode to follow and how. A high-level policy selects a mode using the goal and its previous choice among a set of candidate modes, and a low-level policy turns it into an action. In simulation, the policy succeeds in over 95% of seen and unseen test cases, compared with at most 43% and 20% for four offline learning baselines and 79% and 67% for a heuristic that uses the same modes without learning. The simulation-trained policy also transfers to a LimX Tron 1 bipedal
robot.
Read the full abstract ▾
All authors Chengyang Peng, Zhihao Zhang, Upama Pant, Yiming Wang, Keith A. Redmill, Ayonga Hereid
Computer Vision
PAWA: Panoramic Action-conditioned World Modeling for Multiple Agents
Siqi Yang, Yimu Wang, Ziqi Cai et al. (+6 more)
A multiplayer world model must predict how the independent actions of several players change a shared environment, including changes outside a player's current field of view. A point-of-view (POV)
video captures such changes only after they enter its field of view, whereas panoramic
video records the surroundings in every viewing direction and has served as an intermediate representation of the world state in recent world models. Learning this task therefore requires synchronized POV and panoramic
videos of interacting players together with their actions, yet no existing
dataset provides this combination in Minecraft, an established testbed in which players act independently in a shared, modifiable 3D world. We present PAWA, a
dataset and framework for action-conditioned panoramic multiplayer world modeling. The
dataset pairs each player's POV
video with world-stabilized panoramic
video and aligned actions. Its distributed pipeline decouples CPU gameplay capture from GPU rendering, scales beyond 64 simultaneous players, and re-renders each recorded session under new observation configurations without replaying the gameplay. On this
dataset, we develop a dual-tower model that jointly predicts POV and panoramic
video and couples the two streams through cross-
attention that aligns
tokens observing the same direction in a shared world frame. We further introduce a quadratic-phase player encoding that provides many more player codes than existing rotary codes at the same
embedding dimension. Experiments show that PAWA outperforms state-of-the-art multiplayer world models in POV prediction quality while also producing high-fidelity panoramic predictions. The
dataset and collection pipeline are open source to support further research on multiplayer world models.
Read the full abstract ▾
All authors Siqi Yang, Yimu Wang, Ziqi Cai, Chengxuan Zhu, Shuchen Weng, Erwin Wu, Zhaofei Yu, Kaipeng Zhang, Boxin Shi
Machine Learning
MAEM: Mitigating Recency Bias via a Replay-Free, Capacity-Controlled Dynamic Mixture of Experts for Class-Incremental Graph Learning
Junlin Chen, Wenhao Wang, Junchao Xu et al. (+5 more)
Graph Neural Networks (GNNs) excel on graph-structured data but suffer catastrophic forgetting when classes arrive sequentially. In class-incremental graph learning, predictions are often dominated by recently learned classes, causing severe recency bias. Dynamic expansion can isolate knowledge across sessions, but many methods assume task-incremental settings and require task identities at test time to select branches or heads—information unavailable in class-incremental learning. Learnable routers offer an alternative, yet continual fine-tuning the router on new data can bias routing toward recent components. We propose MAEM, a replay-free, capacity-controlled dynamic mixture-of-experts framework for class-incremental graph learning. MAEM builds representations with Simplified Graph Convolution (SGC) and trains a dedicated expert for each new session, then freezes it to protect prior knowledge. For routing without task IDs or a shared trainable router, each expert uses a masked autoencoder (MAE); test nodes are assigned to the expert with the lowest reconstruction error, reducing routing-level recency bias. When the expert pool reaches a fixed capacity, MAEM merges the least-used experts via Git Re-Basin
alignment and further distills them into a fused expert using
topology-aware pseudo data synthesized from MAE distributions (DeepInversion-style), without storing or revisiting historical graph data. On four class-incremental graph
benchmarks, MAEM mitigates recency bias, outperforms strong continual graph learning baselines, and keeps model capacity bounded under strict replay-free learning.
Read the full abstract ▾
All authors Junlin Chen, Wenhao Wang, Junchao Xu, Qingsong Yao, Fei Xue, Li Sun, Xiao Wang, Ruijie Wang
Information Theory
Exact Cap Response and Aperture Selection for Molecular Communication under Aligned Drift
Yen-Chi Lee, Chun-An Yang and Nan Yang
Spatial reception under directed molecule transport requires balancing useful molecule capture against intersymbol interference (ISI). To characterize this balance, we study a fully absorbing spherical receiver that counts absorption events only within a prescribed cap. Using the known joint first-hitting law under aligned drift, we derive exact cap impulse, cumulative, and eventual responses. We perform stable cumulative evaluation. We then assess the derived responses through particle simulations and time-step comparisons, and demonstrate that our conditional-timing analysis explains when opposite drifts of equal magnitude can favor the same wider aperture. We also show that for the studied geometry and a symbol duration of $0.15$ s, the aperture that maximizes the signal-to-interference difference (SID) increases from $29.13^\circ$ at zero drift to $61.86^\circ$ at a drift magnitude of $40$ $\mu$m/s. These results (i) connect joint arrival-time and location statistics to spatial reception design, (ii) characterize the tradeoff between useful molecule capture and ISI, (iii) support SID-based aperture selection for a given drift and symbol duration, and (iv) quantify the SID loss incurred by retaining the zero-drift optimal aperture for the same symbol duration.
Read the full abstract ▾
Networking
Multi-Cell LTE-U/Wi-Fi Coexistence Evaluation Using a Reinforcement Learning Framework
José M. de C. Neto, Sildolfo F. G. Neto, Pedro M. de Santana et al. (+1 more)
Cellular broadband Internet of Things (IoT) applications are expected to keep growing year-by-year, generating demands from high throughput services. Since some of these applications are deployed over licensed mobile networks, as long term
evolution (LTE), one already common problem is faced: the scarcity of licensed spectrum to cope with the increasing demand for data rate. The LTE-Unlicensed (LTE-U) forum, aiming to tackle this problem, proposed LTE-U to operate in the 5 GHz unlicensed spectrum. However, Wi-Fi is already the consolidated technology operating in this portion of the spectrum, besides the fact that new technologies for unlicensed band need mechanisms to promote fair coexistence with the legacy ones. In this work, we extend the literature by analyzing a multi-
cell LTE-U/Wi-Fi coexistence scenario, with a high interference profile and data rates targeting a cellular broadband IoT deployment. Then, we propose a centralized, coordinated reinforcement learning framework to improve LTE-U/Wi-Fi aggregate data rates. The added value of the proposed solution is assessed by a ns-3 simulator, showing improvements not only in the overall system data rate but also in average user data rate, even with the high interference of a multi-
cell environment.
Read the full abstract ▾
All authors José M. de C. Neto, Sildolfo F. G. Neto, Pedro M. de Santana, Vicente A. de Sousa Jr
Machine Learning · Cross-listed from stat.ML
The minimal width of neural networks and immersions of real projective space
BaoZhi Chu and Ben Weinkove
We investigate the minimal width of deep neural networks that can approximate all continuous functions from $\mathbb{R}^n$ to $\mathbb{R}^m$ in the
topology of uniform convergence on compact subsets. We show that whenever the real projective space $\mathbb{RP}^{n-1}$ admits a smooth immersion into $\mathbb{R}^n$, the minimal width is at least $n+\min\{n,m\}$, assuming that the activation function is continuous and monotone. As a consequence, the minimal width of ReLU networks is $n+m$ whenever $n$ is equal to 2, 3, 4, 7 or 8 and $1\le m \le n$, extending results of Hanin-Sellke and Hwang. This suggests an intriguing connection between the approximation theory of neural networks and differential
topology.
Read the full abstract ▾
Human-Computer Interaction
Let Me Clarify: Interactive Modeling of Soft Attributes
Steffen Holter, Rita Sevastjanova, Michaela Benk et al. (+1 more)
People commonly express preferences through soft attributes such as is interesting,” which are difficult to operationalize for computational preference modeling. Latent representations can obscure how such attributes are interpreted, limiting transparency and user control. We formalize softness as the diversity of valid interpretations a description permits and provide empirical support for this characterization. Our proposed measure estimates softness to guide clarification and determine when to generate computational approximations. This is instantiated in AttriFy, a mixed-initiative system that translates descriptions into executable Python functions over text corpora. An interactive dashboard connects the dialogue to proposed functions and computed values, enabling users to inspect, accept, reject, and refine interpretations. An exploratory within-subjects study with 32 participants compares our softness-guided clarification approach with an LLM baseline in supporting interpretable attribute construction. This work positions softness as a basis for constructing explicit, user-steerable attribute dimensions for downstream preference elicitation and decision-making.
Read the full abstract ▾
All authors Steffen Holter, Rita Sevastjanova, Michaela Benk, Mennatallah El-Assady
Robotics
Smart Fusion for Adaptive Visual-IMU Weighting in cuVSLAM Sparse Bundle Adjustment
Wonju Lee, Dara Molloy, Abhilash Nand Kumar et al. (+5 more)
In cuVSLAM, visual and inertial measurement unit (IMU) residuals are fused in sparse bundle adjustment (SBA) with a weighting fixed by pre-calibrated noise covariances, leaving no mechanism to adapt the visual-inertial balance at runtime. We introduce a scalar $\alpha\geq1$ that upscales the visual information
matrix relative to the IMU preintegration constraint. Across the candidate set $\{1.0,2.0,5.0,10.0,20.0\}$, the resulting trajectories form two empirical performance regimes. The IMU-TRUST regime contains $\alpha\in\{1,2\}$ near the calibrated baseline, while the
VISION-TRUST regime contains $\alpha\in\{10,20\}$. The intermediate value $\alpha=5$ is treated as a transition case. Differences within each regime are small relative to those observed between the regimes. This structure motivates reducing $\alpha$-selection to a binary decision. We train a lightweight Visual Quality
Estimator (VQE), implemented as a multilayer perceptron with 914 trainable parameters. It maps a 10-dimensional visual quality feature vector assembled from statistics already maintained by the tracker to a per-SBA regime prediction. The proposed method reduces mean RMSE APE by $27.7\%$ and by $14.9\%$ under leave-one-out cross-validation (LOOCV) on EuRoC MAV and TUM-VI Room, respectively.
Read the full abstract ▾
All authors Wonju Lee, Dara Molloy, Abhilash Nand Kumar, Onias Castelo, Petar Trslic, David Adley, Conor Ferguson, Hesam Rabeti
Artificial Intelligence
Design Space Exploration of Reinforcement Learning Configurations for Post-Legalization Placement
Foteini Oikonomou, Maria Pantazi-Kypraiou, George Goudroumanis et al. (+5 more)
Graph Neural Networks (GNNs) and Reinforcement Learning (RL) have recently been explored for VLSI placement optimization, but their effectiveness for post-legalization placement refinement remains unclear. This paper presents a systematic design space exploration of a GNN-Proximal Policy Optimization (GNN-PPO) framework across three ISPD2015
benchmarks. We evaluate 18 configurations covering reward functions, GNN architectures, action spaces, candidate-set sizes, and training strategies. We analyse the results we obtain to identify pitfalls and to assess the prospects and opportunities of the RL methods for post-legalization placement. On top of that we propose a design classification approach to guide the design decisions of RL models.
Read the full abstract ▾
All authors Foteini Oikonomou, Maria Pantazi-Kypraiou, George Goudroumanis, Pavlos Stoikos, Athanasios Tziouvaras, Christos Anagnostopoulos, Georgios Karakonstantis, George Floros
Robotics
ObjDream: Guiding Vision-Language-Action Models with Object-Level Understanding and Future State Prediction
Huailiang Ma, Yuxuan Li, Ziyi Zhao et al. (+7 more)
Vision-
language-action (VLA) models have emerged as a powerful paradigm for robotic manipulation, enabling
robots to generate actions from visual observations and
language instructions. However, most existing VLA models still operate on image-level visual representations inherited from pretrained
vision-
language backbones, while lacking fine-grained object understanding for manipulation. As a result, their robustness can degrade under out-of-distribution object layouts, clutter, and background variations. To address these limitations, we introduce ObjDream, an object-centric VLA framework centered on object-level understanding and future object state prediction. ObjDream uses a spatio-temporal object encoder to organize visual observations into temporal object slots, where persistent object identity and dynamic object state are represented through separate channels. These structured object representations are inserted into the
token sequence of the
vision-
language model (VLM), where identity-guided routing modulates VLM
attention to the corresponding object
tokens. In addition, an action-conditioned object dynamics module predicts compact future object states relevant to manipulation during training, explicitly supervising object state
evolution under
robot actions without requiring future prediction at inference. Experiments on LIBERO, LIBERO-Plus, and RoboTwin 2.0 show that ObjDream improves generalization under diverse distribution shifts and scene perturbations. Real-world
robot experiments further demonstrate that ObjDream transfers to physical manipulation settings with novel object arrangements and background changes.
Read the full abstract ▾
All authors Huailiang Ma, Yuxuan Li, Ziyi Zhao, Xinkai Wang, Mingyu Li, Xinyu Guo, Lifeng Zhu, Aiguo Song, Cewu Lu, Jianhua Sun
Networking
A Multiarmed Bandit Approach for LTE-U/Wi-Fi Coexistence in a Multicell Scenario
Iago Diógenes do Rego, José M. de Castro Neto, Sildolfo F. G. Neto et al. (+4 more)
Recent studies and literature reviews have shown promising results for 3GPP system solutions in unlicensed bands when coexisting with Wi-Fi, either by using the duty cycle (DC) approach or licensed-assisted access (LAA). However, it is widely known that general performance in these coexistence scenarios is dependent on traffic and how the duty cycle is adjusted. Most DC solutions configure their parameters statically, which can result in performance losses when the scenario experiences changes on the offered data. In our previous works, we demonstrated that reinforcement learning (RL) techniques can be used to adjust DC parameters. We showed that a Q-learning (QL) solution that adapts the LTE DC ratio to the transmitted data rate can maximize the Wi-Fi/LTE-Unlicensed (LTE-U) aggregated throughput. In this paper, we extend our previous solution by implementing a simpler and more efficient
algorithm based on multiarmed bandit (MAB) theory. We evaluate its performance and compare it with the previous one in different traffic scenarios. The results demonstrate that our new solution offers improved balance in throughput, providing similar results for LTE and Wi-Fi, while still showing a substantial system gain. Moreover, in one of the scenarios, our solution outperforms the previous approach by 6% in system throughput. In terms of user throughput, it achieves more than 100% gain for the users at the 10th percentile of performance, while the old solution only achieves a 10% gain.
Read the full abstract ▾
All authors Iago Diógenes do Rego, José M. de Castro Neto, Sildolfo F. G. Neto, Pedro M. de Santana, Vicente A. de Sousa Jr., Dario Vieira, Augusto Venâncio Neto
Computation and Language
Scaling Multilingual Safety and Reasoning Evaluation through Reasoning-Guided Translation
Zahraa Al Sahili, Ioannis Patras and Matthew Purver
Large
language models (LLMs) are increasingly deployed across
languages, yet their safety and
reasoning capabilities remain predominantly evaluated in English. Translating existing
benchmarks offers a scalable approach to multilingual evaluation, but preserving task-specific meaning across
languages presents significant challenges, particularly for harmful requests, mathematical
reasoning, and conversational interactions. We introduce a
reasoning-guided translation framework for constructing multilingual evaluations designed to preserve the structure and intended meaning of diverse
benchmark tasks. Our approach separates translation strategy selection from large-scale generation, combining
reasoning-guided configuration selection with task-aware validation, targeted repair, and independent quality screening. Using this framework, we develop a source-aligned evaluation collection spanning seven safety, conversational, and mathematical
reasoning resources across 11
languages. The resulting collection achieves 99.94% coverage of intended item–
language pairs in the two subsets requiring repair. Evaluations of open-source LLMs reveal distinct
language-dependent vulnerabilities, including inconsistent refusal behaviour and substantial
reasoning degradation in lower-resource
languages. These findings highlight the importance of task-sensitive
benchmark construction and systematic quality assessment for understanding multilingual model behaviour beyond English.
Read the full abstract ▾
Computer Vision
Glance Forcing: Making Bidirectional Diffusion Autoregressive at a Glance
Zhuobai Dong, Junchao Yi, Hu Jian Guo et al. (+3 more)
Autoregressive generation underlies real-time, causal
video synthesis and is the backbone of
video world models. Today's dominant approach distills a bidirectional
diffusion model into a causal few-step student, but existing pipelines make this conversion prohibitively expensive, requiring offline Probability Flow ODE} (PF-ODE) trajectories that cost tens of thousands of GPU-hours and terabytes of storage. We show it can be made dramatically more efficient. Pushing this efficiency to its extreme, we reduce trajectory supervision to a single sample, the strictest setting possible, and find that it causes severe quality collapse. We trace this to the teacher's trajectory geometry: the high-noise regime, governing semantic layout and motion, and the low-noise regime, governing fine texture exhibit fundamentally different
curvature and optimization behavior, so a single monolithic student cannot jointly fit both, causing severe representation interference. Motivated by this, we propose Glance Forcing, a lightweight
distillation framework that decouples the denoising trajectory into two complementary slow and fast experts, each guided by a tailored, stage-specific objective, while keeping the pretrained teacher entirely frozen. This decoupling further reveals a general mechanism underlying few-step
distillation: PF-ODE
distillation mainly straightens the few-step trajectory geometry, while the subsequent distribution-matching stage independently governs distributional quality. Using only one PF-ODE trajectory, Glance Forcing already surpasses the fully-trained state-of-the-art baseline, raising the VBench Total score from 84.04 to 84.22 while cutting trajectory-collection cost from thousands of GPU-hours to about one A100-GPU-hour, with markedly larger gains in dynamic degree, VisionReward, and instruction-following, and consistent preference from human raters over strong baselines.
Read the full abstract ▾
All authors Zhuobai Dong, Junchao Yi, Hu Jian Guo, Linjie Li, Rui Zhao, Alex Jinpeng Wang
Machine Learning · Cross-listed from stat.ML
Mixed Poisson diffusion models and application to posterior sampling
Thibaut Pellerin, Alain Durmus, Elinor Berger et al. (+1 more)
Diffusion models are a powerful framework for learning complex probability distributions. While widely used
diffusion models for continuous data rely on Gaussian noising processes, we instead develop
diffusion models based on Poisson noise. More precisely, we introduce and study a new mathematical framework, called Mixed Poisson
Diffusion Models (MPDM), with noising dynamics driven by multivariate counting processes. Our methodology is motivated by Poisson inverse problems. The success of Gaussian
diffusion models has led to their use as prior models in a growing number of posterior sampling methods for inverse problems. However, most of these approaches focus on Gaussian inverse problems, in which observations are generated through a deterministic forward operator corrupted by additive Gaussian noise. By contrast, Poisson inverse problems, where observations are discrete and Poisson distributed, remain comparatively underexplored in this literature. Building on our Poisson generative dynamics, we develop a natural framework for posterior sampling in Poisson inverse problems and derive several posterior sampling
algorithms based on the proposed model. We evaluate our approach on realistic Poisson inverse problems and show that the resulting framework is well suited to this class of problems.
Read the full abstract ▾
All authors Thibaut Pellerin, Alain Durmus, Elinor Berger, Eric Barat
Computer Vision
Continual pretraining Prostate MRI ViT Encoder for task alignment
Bilal A. Sidiqi, Yipei Wang, Shaheer U. Saeed et al. (+3 more)
Building foundation models for MRI has emerged as a promising direction for advancing medical image analysis and improving accessibility of task specific models. Existing approaches primarily focus on effective pretraining strategies and evaluating their performance across diverse downstream tasks. While these methods show performance gains, limited
attention has been given to understanding task
alignment between pretraining and downstream objectives. Unlike
language models, where the two stages are naturally aligned, such
alignment is less evident in
vision based applications. Motivated by this gap, we explore continual pretraining. Specifically, continually pretraining a pretrained ViT encoder using Low-Rank Adaptation (LoRA) on a prostate segmentation task to enhance task
alignment and downstream performance. We further perform layer-wise representational analysis using Centered Kernel
Alignment (CKA) to assess representational shifts and their correlation with task outcomes. Our experiments show improved performance in 3 of 6 downstream tasks and comparable results in the others. Our Feature analysis reveals that, for segmentation tasks, continually pretrained encoder features exhibit greater similarity to those of the finetuned encoder than the original pretrained encoder, correlating with observed performance gains.
Read the full abstract ▾
All authors Bilal A. Sidiqi, Yipei Wang, Shaheer U. Saeed, Shiqi Huang, Daniel C. Alexander, Yipeng Hu
Networking
Wearable Data Profiling for NDN-Based Smart Healthcare: Performance Comparison with an IP Baseline
Mohammad R. Shakournia, Nasser Yazdani and Carlos T. Calafate
Smart healthcare IoT requires low-latency and reliable delivery of patient data, yet IP-based communication remains host-centric and offers limited support for mobility, caching, and request aggregation. This paper evaluates a smartphone-centric Named Data Networking (NDN) approach in which a patient's smartphone aggregates sensor streams and publishes a stable latest profile under a consistent name, enabling effective in-network caching. Using ndnSIM simulations on a realistic medical IoT
topology, we compare NDN and IP under identical traffic and link conditions. Results show that per-sample naming provides little benefit, but smartphone aggregation with stable naming allows NDN caching to reduce delay after cache warm-up and achieve significantly higher delivery ratios under congestion compared to IP.
Read the full abstract ▾
Artificial Intelligence
Robust Counterfactuals for Markov Decision Processes under Statistical and Causal Uncertainties
Jessica Lally, Milad Kazemi and Nicola Paoletti
Counterfactual
reasoning (asking what would have happened, had a decision been different) is a powerful tool for identifying causes of failure and explaining the behaviour of AI systems in sequential decision-making tasks. In Markov Decision Processes (MDPs), two sources of uncertainty complicate counterfactual inference: statistical uncertainty in the MDP transitions when the MDP is estimated from trajectory data, and uncertainty about the unknown causal model, as there are multiple structural causal models (SCMs) compatible with each MDP. Existing work addresses these two challenges in isolation. We address both simultaneously by introducing a framework for partial counterfactual inference in MDPs that is robust to both statistical and causal uncertainty. Our approach provides: 1) closed-form analytical bounds for the counterfactual probabilities that are valid across all SCMs entailed by a given interval MDP (IMDP); 2) a method to compute minimal robust interventions to achieve a desired counterfactual outcome via pessimistic value iteration on the induced counterfactual IMDP. Since the latter is constructed using our analytical bounds, our approach remains efficient and scalable to realistic MDP environments. Experiments across multiple case studies demonstrate our method's robustness and practical utility for identifying minimal sets of actions that, if changed, would have led to improved outcomes.
Read the full abstract ▾
Machine Learning
HGRP: Heterogeneous Graph Neural Network for Routability Prediction
Yule Sheng, Yue Yuan, Shan Shen et al. (+1 more)
Routability prediction enables rapid evaluation of placement quality without routing, providing effective feedback for routability-driven placement optimization. Recent machine learning methods have achieved efficient routability prediction through data-driven approach. However, their prediction performance highly depends on the capability of input representations to capture essential
circuit information. To address the limitations of existing
circuit representations in simultaneously preserving logical
topology, physical layout and routing resource information, this paper proposes HGRP, a heterogeneous graph neural network for routability prediction. HGRP models the
cells, nets, and routing grids as distinct types of nodes and explicitly represents topological connectivity, spatial mapping, and grid adjacency, thereby constructing a heterogeneous graph representation that preserves multi-level
circuit semantics. Based on the representation, a heterogeneous message passing mechanism is developed to enable information interaction and feature fusion among distinct types of nodes, effectively learning the complex correlations between
circuit structures and routing behaviors. Experimental results on the CircuitNet
dataset show that HGRP improves F1-score by 18.69% relative improvements compared with the state-of-the-art in the congestion prediction task. The source code is publicly available at https://github.com/ShenShan123/HGPR.
Read the full abstract ▾
All authors Yule Sheng, Yue Yuan, Shan Shen, Daying Sun
Numerical Analysis
Fast spectral methods for Volterra integral equations
Xi Chen and Kuan Xu
We develop novel methods for the fast construction of spectral approximations to smooth linear and weakly singular Volterra integral operators and for the fast evaluation of smooth nonlinear Volterra integrals. The proposed methods employ the Duffy mapping, which transforms the original indefinite integral into a definite integral and maps the original causal triangular domain to a square, thereby avoiding any artificial extension of the kernel function. For smooth linear and weakly singular Volterra operators, the resulting approximations are almost-banded and lower-banded, respectively. The $N\times N$ principal finite section of these approximations can be constructed in $O(N)$ and $O(N^2)$ flops, respectively, via recurrence relations. For Volterra integrals with a smooth kernel that depends nonlinearly on a given function, recurrence relations lead to fast evaluation with a complexity of $O(N^2\log N)$ when the function is approximated by a degree-$N$ Chebyshev approximant. These spectral approximations and evaluation procedures give rise to fast and stable spectral methods for solving Volterra integral equations, as well as a broad class of problems involving Volterra integral operators. Extensive numerical experiments show that these spectral methods significantly outperform existing methods in terms of stability, speed, accuracy, and ease of implementation.
Read the full abstract ▾
Human-Computer Interaction
What and Where in Identifying and Quantifying Conventions in Humans and AI Agents
Makoto Fukushima and Tim Puphal
Cooperative success rests in part on implicit communication. Partners converge on conventions: regularities that give an action meaning beyond its direct effect. Yet conventions are usually observed only indirectly: a score drop when partners are swapped shows that a convention existed, but not what it was or where it was used. In the card game Hanabi, the exact probability that a play fails can be computed from the hints received and the cards in view. Players who use conventions succeed more often than this prediction allows; the resulting margin is the convention gap. Off-belief learning provides a hierarchy of
agents (levels 1-5) whose first level uses no conventions by construction and whose later levels use progressively more. For humans and these
agents on one scale, we ask what the conventions are and where they are used. On what: in two independently collected corpora of human games, humans show a larger gap than every
agent level. On the conventions both populations use, however, humans do no better than level 2. The human advantage is concentrated in a situation that no
agent level learns to use: hints that point to a card other than the ones they touch. On where: conventions depend on what the player already knows about the card, not on how recently it was hinted, and they are used most in the mid-game; humans use them earlier and later in the game than the
agents. In interventions on the
agents, blocking a single high-gap situation costs little, because meaning reroutes to other situations, but blocking several together costs far more than the sum of the single costs. Thus, the convention gap turns conventions from an inferred cause of score loss into a measurable, comparable, and causally testable object.
Read the full abstract ▾