Robotics
DexForge: High-Fidelity Physics-Informed Dexterous Retargeting
Meizhong Wang, Kun Cao, Ruiqi Ni et al. (+2 more)
Human demonstrations offer rich examples of precise dexterous manipulation and a promising source of
robot training data. However, high-fidelity reproduction of demonstrated motions and hand-object interactions across
robot embodiments remains challenging under physical constraints. We present DexForge, a differentiable physics-grounded framework for converting human
video demonstrations into high-fidelity
robot trajectories. We reconstruct spherical-Gaussian object models and hand-object motion from visual observations, then build a differentiable simulator combining efficient Gaussian collision detection with existing differentiable dynamics. Based on this simulator, DexForge combines contact-aware kinematic retargeting with force-aware dynamics retargeting:
robot-adapted stable contacts guide kinematic reference construction and subsequent gradient-based control refinement for precise physical motion reproduction. Experiments on 130 DexYCB and HOT3D demonstrations across seven dexterous hands show success-rate gains of approximately 35-53 percentage points over the baseline, with object position and orientation tracking errors on successful trajectories reduced by approximately 34-67% and 71-78%, respectively. Further experiments demonstrate open-loop transfer to MuJoCo and real-
robot execution. Our project page is available at https://wmz1226.github.io/DexForge/
Read the full abstract ▾
All authors Meizhong Wang, Kun Cao, Ruiqi Ni, Lihua Xie, Yiguang Hong
Computers and Society
Assessing flood-related wellbeing from public discourse in Ireland using large language model as judge, 2012–2025
Róisín Luo and Karyn Morrissey
Flooding is an environmental hazard that produces social and psychological consequences for exposed individuals, shaping threat appraisal, perceived coping capacity, access to social support, and confidence in institutional response. This paper studies flood-related wellbeing in Ireland from 2012 to 2025 using large-scale, unobtrusive public discourse from Meta Content Library. We develop a bespoke flood-wellbeing instrument organised with three domains: affective–cognitive distress appraisal, diminished perceived efficacy and agency, and perceived relational–institutional connectedness. We then design a flood-wellbeing
reasoning pipeline with large
language models to extract multi-indicator, multi-domain flood-wellbeing measures from public discourse at scale. The analysis reveals both stressor activation and social–ecological resilience mediation pathways in Irish flood discourse. Flood stressors directly activate affective–cognitive distress appraisal, diminished perceived efficacy and agency, and perceived relational–institutional connectedness. The analysis further identifies two major mediation pathways: an appraisal–efficacy pathway linking flood exposure to threat appraisal, affective burden, uncertainty, and perceived coping capacity; and a social-buffering pathway in which social and institutional protective resources are associated with perceived efficacy and appraisal of flood-related adversity. The paper contributes an unobtrusive discourse-based approach to flood-wellbeing research by introducing a bespoke instrument, identifying activation and mediation pathways in flood discourse, and producing a temporal
dataset for studying wellbeing, adaptation, and resilience under recurrent flood exposure.
Read the full abstract ▾
Machine Learning
Dynamic Minimax Regret Optimization for Robust LLM Post-Training
Chengbo Zang, Haoyu Dong, Mehmet Kerem Turkcan et al. (+3 more)
Modern LLM training increasingly relies on heterogeneous data sources spanning different domains, tasks, preference distributions, and difficulty levels. We study dynamic minimax regret for group-distributionally robust LLM post-training under instantaneous mini-batch-only bandit feedback. The framework views the training as a two-player sampler-optimizer process: a sampler adaptively selects among data sources using bandit feedback, while an optimizer updates the model parameters using
stochastic gradients from the selected source. We focus on the practically restrictive setting where source losses evolve with model training but historical data are not re-evaluated, requiring the sampler to track instantaneous worst-sources from stale partial feedback. We propose DUCB-OGD, a simple and scalable
algorithm that couples a Discounted Upper-Confidence-Bound sampler with an Online Gradient Descent optimizer. The sampler maintains exponential moving average loss estimates and confidence radii based on discounted effective sample sizes, avoiding costly re-evaluation of past data or intrusive changes to standard training pipelines. For $K$ data sources and $T$ training steps, we prove that DUCB-OGD achieves a dynamic minimax regret of $\tilde{O}(K^{1/4}T^{3/4})$, which is optimal up to logarithmic factors for the undiscounted objective under our feedback model. Extensive experiments across supervised fine-tuning, preference optimization, and reinforcement learning show that DUCB-OGD integrates seamlessly into modern LLM training pipelines and improves worst-group robustness with negligible computational overhead compared with standard sampling baselines.
Read the full abstract ▾
All authors Chengbo Zang, Haoyu Dong, Mehmet Kerem Turkcan, Gil Zussman, Zoran Kostic, Javad Ghaderi
Human-Computer Interaction
What Did the AI Take On? Characterizing Cognitive Delegation in LLM Reasoning
Yoonsu Kim, Sean Kim, Kihoon Son et al. (+2 more)
Large
language models (LLMs) often perform intermediate cognitive work while carrying out users' requests, yet it remains unclear which parts users intended to delegate and how they wanted to remain involved. This matters because consequential choices may go unnoticed, limiting users' ability to steer the process, while reviewing every step would make delegation burdensome. We examined this with 24 LLM users across three knowledge-work tasks, collecting 992 retrospective annotations of
reasoning steps. From this, we developed taxonomies of LLM cognitive work, delegation enactment, and desired delegation protocols at the
reasoning-step level. Our analysis revealed that participants viewed about half of all steps (48.6%) as AI-initiated, meaning the AI took on work they had not requested. Desired involvement varied with cognitive work and delegation enactment, even when contributions matched participants' intent. We propose design implications and sketches for supporting more deliberate cognitive delegation through flexible protocols and inspectable, revisable AI-initiated decisions.
Read the full abstract ▾
All authors Yoonsu Kim, Sean Kim, Kihoon Son, Saelyne Yang, Juho Kim
Robotics
Dual Variational Autoencoders for Efficient Sim-to-Real Transfer in Low-Cost Robotic Navigation
Álvaro Díez and Fidel Aznar
Vision-based autonomous
navigation for low-cost
robots remains a fundamental challenge, primarily due to the significant gap between simulated training environments and real-world operational conditions. Direct policy transfer from simulation is often ineffective, while training exclusively on real data is impractical. We propose a hybrid transfer learning framework that effectively bridges the sim-to-real gap by combining domain randomization with feature-level domain adaptation. Our method employs a dual convolutional variational autoencoder architecture with a shared decoder, trained on an extensive set of 45225 simulated images and a minimal set of only 4556 real-world samples. This architecture learns a compact, common latent representation space that aligns the distributions of both domains. The adaptation process is further enhanced by two complementary data augmentation techniques designed to expand the limited real-world data. Experimental evaluation demonstrates that our method achieves an average success rate of almost 91% on image classification tasks for real-world indoor
navigation, significantly outperforming both simulation-only and real-world-only training. We validate these findings through a direct, real-world deployment, where the proposed policy successfully guides a low-cost
robot in a reactive exploration task. Furthermore, we validate the model's efficiency through a rigorous computational estimation, confirming its suitability for resource-constrained embedded platforms such as the Raspberry Pi 4 and NVIDIA Jetson Nano. This work presents a practical solution for developing effective and efficient
navigation policies for low-cost robotic systems.
Read the full abstract ▾
Distributed Computing
Fine-Tuning a 3B-Parameter LLM on a Smartphone: Characterizing Sustained Training
Andrew Geyko, Marius Mosbach and André Brinkmann
Multi-billion-parameter LLMs now run on phones for inference, and training them on the device would personalize them without user data leaving the phone. Prior work has measured individual training steps of such models on phones, but not complete training runs, and not whether adapters trained on the device improve personalization. We present the first systematic characterization of a multi-billion-parameter LLM fine-tuned on a mobile device, covering
memory, per-step time, thermal behavior, and energy. An iPhone 17 Pro can fine-tune a 3B-parameter LLM to a typical user within one battery charge, and the resulting adapters improve personalization as much as adapters trained on a server. Sustained training throttles the phone to about half its initial throughput, and none of the pausing or burst schedules we tested recovers it. Nearly all of each training step is spent in the frozen base model, most of it in the backward pass, which nine of the ten other runtimes we audited do not accelerate. Apple's MLX had a kernel for it that was never dispatched and was incorrect, and our repair, now merged upstream, trains an adapter 1.47x faster on a third less energy. On-device fine-tuning is feasible on current phones, and making it efficient requires runtimes and operating systems to treat training as a first-class workload.
Read the full abstract ▾
Computer Vision
Readout Blindness: VLM Scores Miss the Spatial Direction Their Frozen Encoders Retain
Guangyuan Li, Tianming Du, Yan Jiang et al. (+2 more)
CLIP-like
vision-
language models remain a cornerstone of
multimodal systems, yet their scores stay near chance on directed spatial relations, such as whether one object is left of another. We call this failure readout blindness and analyze, theoretically and empirically, why deployed scores miss the direction: when scoring rules treat the subject and object symmetrically, direction cancels regardless of encoder training. Guided by this analysis, we introduce Antisymmetric Displacement Readout (ADR), which aligns caption words with image patches in the frozen features and scores each relation by the signed displacement between matched object centroids. Notably, ADR succeeds without additional training or learned parameters, thereby demonstrating that directional information remains in the frozen encoder. However, text and world priors can inflate accuracy, so we further introduce prior deflation, which measures the benefit of the image-text pairing as the grounded gain over a null that pairs each item with an unrelated image. Extensive experiments across encoder families show that ADR substantially improves over deployed scores, which remain near chance on most direction-balanced sets even for fine-tuned encoders. Compared with more complex readouts, ADR outperforms the evaluated MLLM likelihood readouts and is competitive with their chat inference at a small fraction of the computation. These results support our claim that directional information can be recovered from frozen features by an appropriate readout. Our implementation and evaluation kit will be publicly available.
Read the full abstract ▾
All authors Guangyuan Li, Tianming Du, Yan Jiang, Bihan Wen, Jiancheng Yang
Computation and Language
Agentic schema-guided extraction of materials process knowledge from scientific literature
Sameer Sadruddin and Jennifer D'Souza
Materials literature contains detailed experimental knowledge, but procedures, chemical entities and measurements remain difficult to aggregate because they are reported in heterogeneous forms and depend on process-specific context. We present SciKGExtract, a schema-guided framework that combines large-
language-model extraction with chemical normalization and
agent-based evaluation and refinement before knowledge-graph integration. We evaluate the framework on 176 atomic-layer-deposition papers describing zinc
oxide (ZnO) and indium–gallium–zinc
oxide (IGZO), together with an expert-annotated full-schema subset. PubChem normalization improves exact-match extraction F1 for every tested model. For ZnO, the best F1 increases from 0.591 for direct normalized extraction to 0.805 with agentic refinement, whereas the best IGZO result is 0.344, revealing the greater difficulty of multicomponent supercycle processes. Evaluation against a deeply nested schema containing 65 experimental properties and 155 quantitative measurement nodes further exposes errors in process
segmentation and numerical assignment. These results show that chemical canonicalization and targeted agentic verification provide complementary controls for converting complex materials literature into reusable, machine-actionable experimental knowledge.
Read the full abstract ▾
Artificial Intelligence
CRAFTER: Causality-based Self-adaptation for Autonomous IoT Systems
Houssam Hajj Hassan, Ajay Kattepur, Denis Conan et al. (+1 more)
This paper presents CRAFTER, an automated framework for designing and deploying self-adaptive IoT systems using Causal Reinforcement Learning (CRL). As IoT devices increasingly populate pervasive computing spaces, smart environments are enabled with advanced monitoring and interactive services. The dynamic nature of these environments, such as fluctuating workloads and evolving application demands, poses significant challenges in maintaining consistent Quality of Service (QoS) levels of IoT applications. While existing self-adaptation techniques offer adaptive capabilities, they are often designed to deal with specific application domains, hindering the design of self-adaptive solutions that can be re-used across multiple IoT verticals. In addition, there is a lack of automated pipelines that act on identifying key performance drivers to take effective adaptation decisions. CRAFTER addresses these issues by using Causality as a formal framework for performance analysis of IoT systems. CRAFTER generates causal graphs to uncover dependencies among system components and guide adaptation decisions based on cause-effect relationships. Then, adaptation
agents can leverage this knowledge to take more effective adaptation decisions in dynamic situations. Our experimental evaluation demonstrates how CRAFTER enables deriving causal graphs spanning diverse IoT use cases. Furthermore, we showcase how CRAFTER improves self-adaptation performance by 25% compared to state-of-the-art Reinforcement Learning-based approaches.
Read the full abstract ▾
All authors Houssam Hajj Hassan, Ajay Kattepur, Denis Conan, Georgios Bouloukakis
Computer Vision
Wiring Matters: Injection Topology and Initialization of Affordance Heads in Vision-Language-Action Policies
Zijian An, Linhan Wang, Jiayan Wang et al. (+4 more)
Dense affordance supervision is an appealing auxiliary signal for
vision-
language-action (VLA) policies, yet naively co-training an affordance head can severely damage instruction following. We present a controlled study of how to wire such a head into a modern VLA on the LIBERO
benchmark. Our recipe reads the backbone through a stop-gradient and re-injects an intermediate head feature into the action expert via a learned bridge. The stop-gradient is a precondition: letting affordance gradients reach the backbone drops the policy below the headless base (85.5% vs. 93.1%). With the backbone protected, a same-budget 2*2 ablation over injection
topology (concatenation vs. residual) and bridge initialization (zero vs. random) shows initialization is the dominant lever. The best wiring, an actively initialized residual bridge, reaches 96.2%, matching the far more elaborate three-expert AffordanceVLA (95.8%) with under 1% extra parameters. Two probes explain the mechanism: ground-truth affordances fed as an input hurt, and inference-time zeroing shows a lazy bridge acts only as a training-time regularizer while an active bridge becomes load-bearing.
Read the full abstract ▾
All authors Zijian An, Linhan Wang, Jiayan Wang, Shijie Geng, Ran Yang, Yiming Feng, Lifeng Zhou
Cryptography and Security
Watermarking: from Impossibility to Auditable Compliance
Fernando Delbianco, Fernando Tohmé and Hugo Acciarri
Article 50 (2) of the EU Artificial Intelligence Act requires providers of generative systems to make synthetic outputs machine-readable and detectable, while qualifying the effectiveness, interoperability, robustness, and reliability by technical feasibility, cost, content-specific limits, and the state of the art. For free-form text, one important implementation route is the implementation of a generative watermarking procedure, which poses a compliance problem that is hard to address. Strong watermarking is impossible against adaptive removal, while ordinary edits attenuate statistical evidence, and unmarked human text may overlap distributionally with machine output. This article develops an auditable alternative. First, it defines a description-length robustness profile. A finite-sample bound shows that detectable bias decays and that the required sample size grows with the inverse square of the decay rate. This replaces an unidentified Shannon-
entropy constant with collision
entropy. Second, it constructs label-conditional conformal prediction sets with separate false-attribution and false-exclusion levels, reporting “watermark supported,” “not supported,” or “inconclusive”. Coverage is obtained as a finite-sample result and is class-conditional under exchangeability. A small reproducible simulation of a tournament watermark confirms both claims and shows that the surviving-
token rule overstates the tolerable edit rate roughly twofold. The resulting premarket certificate, signed detector report, and postmarket recalibration protocol operationalize the Commission's 2026 Code of Practice without claiming universal robustness.
Read the full abstract ▾
Artificial Intelligence
RollPlace: Improving Macro Placement via Monte Carlo Rollout Search
Qi Zhou, Guojun Liu, Guangzhi Qi et al. (+5 more)
The application of Reinforcement Learning (RL) in Electronic Design Automation (EDA), particularly for chip placement, has attracted considerable
attention in recent years. While existing machine learning (ML)-based approaches have achieved notable progress, they predominantly focus on generating optimal layouts in a single attempt, often producing solutions that require subsequent refinement. To address this limitation, we propose RollPlace, a novel and generalized macro placement framework. RollPlace adopts a two-stage optimization strategy: generating initial placement solutions via machine learning methods or heuristic-based strategies, and refining these layouts efficiently by adjusting specific macros derived from the initial stage. This strategy circumvents the sequential generation constraints inherent in traditional RL-based placement methods. Furthermore, RollPlace seamlessly integrates Monte Carlo Tree Search (MCTS) to balance exploration and exploitation, and employs a rollout mechanism for efficient local search. Extensive experiments on the ISPD 2005
benchmark demonstrate that RollPlace outperforms state-of-the-art methods. Additionally, end-to-end experimental results based on OpenROAD across 19
benchmarks show that RollPlace excels in multiple metrics. The proposed framework offers a robust and scalable solution for addressing the growing complexity of modern chip design challenges.
Read the full abstract ▾
All authors Qi Zhou, Guojun Liu, Guangzhi Qi, Ming Lu, Jiechu Liu, Zhongli Liu, Jianqun Yang, Xingji Li
Machine Learning
SPDAlign: Interpretable Riemannian Alignment for EEG Forward Modeling Shifts
Shanglin Li, Shiwen Chu, Okan Koç et al. (+5 more)
Electroencephalography (
EEG) based
brain-computer interfaces enable direct
brain-to-device communication for applications such as rehabilitation and communication. However, their practical utility is often limited as the non-stationary nature of the
EEG data introduces distribution shifts across domains (e.g., sessions and subjects). Adapting machine learning models to be invariant to these shifts in an unsupervised way, without using costly labeled calibration data, would drastically improve the utility of
EEG data. In this work, we use a classic generative model of
EEG to study distribution shifts introduced by the domain-specific forward process, which is associated with factors such as head geometry. We theoretically show that such distribution shifts can be recovered solely through linear transformations on the Symmetric Positive Definite
manifold. Building on this insight, we propose SPDAlign, an interpretable framework for promoting domain-invariant
EEG learning. SPDAlign first aligns the domain-specific means and corrects global rotations across domains using a recent optimal transport technique called Wasserstein Procrustes. We systematically study the proposed approach through simulations and demonstrate its competitive performance on extensive public
EEG datasets. Additionally, SPDAlign is a globally linear framework and is intrinsically interpretable, so that the framework can identify frequency ranges of interest, determine the spatial patterns reflecting source-sensor relationships, and address cross-subject variability.
Read the full abstract ▾
All authors Shanglin Li, Shiwen Chu, Okan Koç, Chenyu Liu, Qibin Zhao, Motoaki Kawanabe, Mitsuo Kawato, Yi Ding
Cryptography and Security
Cryptanalysis of a Class of Ideal Secret Sharing Schemes Based on the CRT for Polynomial Rings
Jian Ding, Zhiyuan Guo, Hongju Li et al. (+1 more)
Based on the CRT for
polynomial rings, Yang, Zhu, Fu and Xia (ISIT 2026) proposed a compartmented secret sharing scheme for the compartmented access structure with lower bounds, claiming it can be ideal. We exhibit three families of unauthorized subsets that reconstruct the secret. The scheme is therefore insecure, except for a degenerate choice of parameters in which the only authorized subset is the whole participant set. The flaw in the security analysis is that it does not take all published
polynomials into account. Similar flaws appear in the same first author's hierarchical schemes (ISIT 2024, 2026).
Read the full abstract ▾
All authors Jian Ding, Zhiyuan Guo, Hongju Li, Yuying Man
Data Structures and Algorithms · Cross-listed from math.ST
Sharp dimensional analysis of midpoint methods for Langevin sampling
Fan Chen, Sinho Chewi, Jianfeng Lu et al. (+1 more)
We study deterministic and randomized midpoint discretizations of Langevin dynamics for a target $\pi \propto e^{-V}$, where $0 \prec \alpha I\preceq\nabla^2V\preceq\beta I$ and $\kappa=\beta/\alpha$. To achieve $\sqrt\alpha\,W_2\leqslant\varepsilon$, we show that deterministic Heun uses at most $\widetilde O(\kappa^{4/3}d^{1/3}\varepsilon^{-2/3})$ gradient queries, and underdamped exponential midpoint uses $\widetilde O(\kappa^{5/4}d^{1/4}\varepsilon^{-1/2})$. The proofs exploit cancellation at stationarity and smoothing using techniques from Malliavin calculus, outperforming previous upper bounds based on standard couplings. At bounded condition number, a lower bound matches the $d$ and $\varepsilon$ powers of both deterministic methods. To contrast, for the randomized midpoint methods and Poisson midpoint with at least two grid points (both overdamped and underdamped variants), a simple Gaussian calculation yields a lower bound $d^{1/3}\varepsilon^{-1/3}$ to get an $\varepsilon$-close sample despite starting at a benign initialization. This shows surprisingly that in high dimensions, deterministic discretizations can outperform their random counterparts.
Read the full abstract ▾
All authors Fan Chen, Sinho Chewi, Jianfeng Lu, Matthew S. Zhang
Robotics
Inspect Robots: Evaluating the Capabilities and Safety of Embodied AI
Christopher Leet, Achu Menon, Sravanthi Machcha et al. (+12 more)
General purpose
language models are increasingly able to control robotic hardware. Understanding the capabilities and safety of these models when
embodied is therefore increasingly important for understanding their societal impact and risks. To this end, we introduce Inspect
Robots, a modular, open-source framework for developing and running evaluations of
embodied agents. Inspect
Robots pairs customizable, reusable abstractions for specifying physical evaluations and analyzing their results with infrastructure that automates evaluation setup, execution and termination. We demonstrate Inspect
Robots by using it to evaluate the capabilities and safety of six policies based on frontier
language models. Inspect
Robots has seen significant early uptake, receiving nearly 100,000 downloads in the three months since its release.
Read the full abstract ▾
All authors Christopher Leet, Achu Menon, Sravanthi Machcha, Sabrina Zou, Aayushya Patel, Aditya Kumar Singh, Anish Kr Singh, Galaba Vamsi, Javin Ahuja, Sai Asish Yamani, Tushar Anand, Vedang Alle, Zihan Jack Zhang, Tzu Kit Chan, Jay Chooi
Artificial Intelligence
Teaching a Minimalist Machine to Discover Recursive Programs for Arithmetic
Dominik Magiera, Christiane Wiebel-Herboth and Frank Jäkel
Humans can often acquire and synthesize complex, recursive concepts from minimal experience. Leveraging cognitive insights, we propose the Minimalist Machine, a framework for inductive program synthesis designed to model such conceptual learning. The system uses a compact relational subset of Prolog: Programs are searched within a fixed schema of body-free facts and two-body conjunctive Horn clauses. Recursion is not defined by a dedicated metarule. Instead, it emerges when a target predicate is reused inside the body of a learned clause. Inspired by a primary school curriculum, the model is taught through a human-curated, sequential introduction of new concepts in arithmetic. Starting from initially empty knowledge base, it first acquires simple structural predicates, then successor-based state transformations, and finally recursive programs for addition, subtraction, multiplication, and division. Ultimately, this approach yields the fully transparent, inductive
reasoning trace necessary for human-like conceptual learning.
Read the full abstract ▾
Computational Complexity · Cross-listed from quant-ph
Robust subspace designs and the power of a unique small quantum witness
Simon Apers, Roman Edenhofer, Benjamin Mathieu-Bloise et al. (+1 more)
The concept of subspace designs was introduced by Guruswami and Xing (STOC'13), and explicit constructions were given by Guruswami and Kopparty (FOCS'13). These are families of subspaces that have small intersection with any given subspace of a fixed dimension. We introduce robust subspace designs. Informally, these are a quantitative extension in which we demand that not too many subspaces of the family contain directions that lie close to any given subspace of a fixed dimension. We give a probabilistic construction of such a robust subspace design of
polynomial size, as well as a non-trivial explicit construction of superpolynomial size. Our main application of this new concept is a
quantum space-bounded variant of the Valiant-Vazirani
theorem (Theor.Comput.Sci.'86), which shows that restricting $\mathsf{NP}$-complete problems to instances with at most one accepting witness preserves hardness under randomized reductions. For
quantum witnesses, the analogous quantity is the dimension of an accepting witness subspace. We use our probabilistic construction of robust subspace designs to isolate a unique witness for space-bounded
quantum Merlin-Arthur protocols with perfect completeness and an acceptance gap outside their perfectly accepting subspace. As further applications, we give a randomized reduction of well-conditioned nullity testing to space-bounded
quantum Merlin-Arthur protocols with perfect completeness. Using a similar idea, we find that ordinary subspace designs allow us to recover the classical $\mathsf{C_= L}$ containment of Allender, Beals, and Ogihara (STOC'96) for general nullity testing through a simpler proof.
Read the full abstract ▾
All authors Simon Apers, Roman Edenhofer, Benjamin Mathieu-Bloise, Partha Mukhopadhyay
Computation and Language
DialectSentEval 2026: Arabic Dialect Sentiment Analysis and Swapping Shared Task
Saad Ezzini, Shadi Abudalfa, Maram Alharbi et al. (+6 more)
Sentiment analysis is a fundamental problem in Natural
Language Processing (NLP). Standard sentiment classification for the Arabic
language remains challenging due to the high volume of dialectal Arabic. To advance research in this area, this paper proposes the Shared Task on Sentiment Analysis and Swapping in Arabic Dialects (DialectSentEval), hosted with the Arabic Natural
Language Processing Conference (ArabicNLP 2026). This shared task consists of two subtasks: Subtask 1 focuses on multi-class and multi-dialect sentiment analysis, requiring models to identify sentiment polarity across various Arabic dialects. Subtask 2 introduces a generative task for Arabic sentiment swap, challenging models to invert sentiment polarity while preserving core semantics. In this overview paper, we present the motivation,
dataset creation, and summarize the main findings from participating models.
Read the full abstract ▾
All authors Saad Ezzini, Shadi Abudalfa, Maram Alharbi, Salmane Chafik, Hind Alatawi, Mo El-Haj, Ahmed Abdelali, Osamah Alnahari, Salima Lamsiyah
Networking
Graph Neural Network-Driven Deep Reinforcement Learning for Scalable RIS Allocation
Martin Mark Zan and Stefan Schwarz
Reconfigurable Intelligent Surfaces (RISs) offer a promising paradigm to mitigate blockage and extend millimeter-wave coverage in 6G multi-
cell networks. However, dynamically allocating shared RIS infrastructure across competing base stations is an NP-hard problem posing severe scalability bottlenecks. In this paper, we propose a scalable framework combining Graph Neural Networks (GNNs) with Deep Reinforcement Learning (DRL) for dynamic shared RIS orchestration. By formulating allocation as a Markov Decision Process, we introduce a physical
topology sparsification strategy that prunes dense channel
matrices into a sparse tripartite graph. This
pruning reduces edge density by 77% and removes representation noise, thereby improving global coverage probability while reducing computational complexity. Our relational message-passing architecture naturally generalizes to arbitrary network dimensions without model retraining. Furthermore, structural ablation studies reveal that physical path loss localizes surface dependencies, enabling a highly efficient localized graph design with linear computational scaling. Extensive simulations in dense urban environments demonstrate that under strict infrastructure budget constraints, the proposed GNN-DRL framework consistently outperforms greedy heuristic baselines by up to ~12% in coverage while delivering faster inference speed via GPU acceleration.
Read the full abstract ▾
Numerical Analysis · Cross-listed from math.AP
Comparison of neural and spline representations for physics-informed learning
Régis Duvigneau
Physics-informed machine learning as recently emerged as a new paradigm for the resolution of partial differential equations, including functionalities for parametric modeling and inverse design, using neural networks to represent the solution fields. However, several difficulties have been reported concerning the training of such networks, resulting in slow convergence, low accurate solutions and sensitivity to the choice of hyper-parameters. In order to better understand the mechanisms underlying these difficulties, the present work proposes a rigourous comparison of neural networks and B-Splines representations within the same physics-informed learning framework. Four problems with closed-form solutions are numerically studied to establish a rigorous analysis of the accuracy and efficiency of the two representations, in terms of asymptotic convergence rates, sampling requirements, loss function minimization and arithmetic precision needed.
Read the full abstract ▾
Computer Vision
VepAgent: Bridging Causal-Transition via Tool-Augmented Reinforcement Learning for Video Event Prediction
Qiutong Chen, Yuchan Guo, Zhenlong Yuan et al. (+10 more)
Multimodal Large
Language Models (MLLMs) have demonstrated remarkable potential in
video understanding, yet their reliance on retrospective summarization and text-centric priors often limits their ability to bridge unobserved causal transitions when applied to
Video Event Prediction (VEP). To address this, we propose VepAgent, an agentic framework that integrates causal-transition
reasoning with tool-augmented reinforcement learning (RL) for robust VEP. Unlike prior methods that passively project future trajectories from historical dependencies, our approach explicitly models the logical progression from terminal observed states to future events. Specifically, we first construct futurebench-4K, a high-quality chain-of-thought
dataset for supervised fine-tuning (SFT) that effectively bridges the causal-logic gap by structuring the deduction of unobserved intermediate states. Subsequently, we develop a diagnostic tool library integrating state tracking, frame
retrieval, and region magnification, enabling the
agent to dynamically augment
reasoning with external tools to recover missing spatio-temporal evidence and resolve visual ambiguities during inference. Moreover, we propose a composite reward mechanism that jointly optimizes prediction accuracy, causal coherence, and reliable prior, compelling the
agent to rely on genuine visual grounding rather than superficial textual similarities. Extensive evaluations on FutureBench and NEPBench
datasets demonstrate that our method achieves state-of-the-art performance, significantly outperforming larger MLLMs and validating the empirical effectiveness of our agentic, future-oriented
reasoning paradigm.
Read the full abstract ▾
All authors Qiutong Chen, Yuchan Guo, Zhenlong Yuan, Haobo Yang, Fangfang Lin, Xinyi Long, Yin Wang, Zijian Song, Rui Lan, Shi Qiu, Boyuan Pan, Yang Luo, Yuyin Zhou
Distributed Computing
Acceleration of Data Analytics on Heterogeneous Supercloud Systems
Georgios Zacharopoulos, Ilias Bournias and Lukas Cavigelli
Heterogeneous Supercloud systems are transforming data analytics by enabling scalable and efficient task distribution across diverse resources. This paper presents computational models and performance estimation techniques tailored for accelerating Dense Cholesky (CH) Decomposition and Singular Value Decomposition (SVD)-based analytics on Heterogeneous Superclouds. Our ReDSEa tool-chain automates mapping, load balancing, scheduling, parallelism, and computation overlap. Implemented on a heterogeneous system with a Huawei Kunpeng 920 ARM CPU and an Ascend 910 AI accelerator, our LLVM compiler tool-chain employs novel performance models for recursive, iterative, and blocked computations, achieving up to 17x speedup for CH and 88x for SVD over fully optimized 48-core CPU implementations.
Read the full abstract ▾
Robotics
GAMBIT: Learning to Plan Continuous Multi-Robot Trajectories
Rishabh Jain, Akmaral Moldagalieva, Lorenzo Magnino et al. (+5 more)
GAMBIT is an opening chess move in which a player sacrifices a piece, typically a pawn, to gain a positional advantage later in the game. Analogously, in multi-
robot coordination, individual
robots may need to forgo locally reward-maximising behaviours to improve overall team performance. Such self-sacrificial behaviours are difficult to capture with manually designed heuristics, particularly in dense, interaction-rich environments. Focusing on double-integrator continuous dynamics, this work studies how to learn such coordinated heuristics over motion primitives for multi-
robot trajectory execution. Our framework, GAMBIT, first learns coordinated motion-primitive selection through imitation learning and subsequently fine-tunes the policy through reinforcement learning. We further introduce a safeguarded rollout mechanism with backup trajectories that guarantees collision-free execution at all times. Experiments demonstrate that GAMBIT substantially outperforms a range of baselines, including centralised motion planners and decentralised reactive planners, while exhibiting strong scalability. In particular, it coordinates over a thousand
robots with planning latency below a few hundred milliseconds in continuous domains.
Read the full abstract ▾
All authors Rishabh Jain, Akmaral Moldagalieva, Lorenzo Magnino, Michael Amir, Keisuke Okumura, Ajay Shankar, Wolfgang Hönig, Amanda Prorok
Machine Learning
Trajectory-Guided Tokenization of Complex CSI for Wi-Fi Sensing
Ziyi Wang, Kenuo Xu, Jichu Jiang et al. (+8 more)
Wi-Fi channel state information (CSI) enables contactless presence detection and gesture recognition. Its high-dimensional complex-valued time series require input representations that preserve informative temporal variations during compression. We propose Trajectory-Guided Tokenization (TGT), which combines complex trajectory decomposition with asymmetric
attention to construct compact continuous
tokens. For each
antenna link and subcarrier, an orthonormal Helmert transform decomposes short, ordered temporal patches into local-center and centered-trajectory coordinates. Keys are learned from the centered-trajectory coordinates, while values retain both components. Learnable queries aggregate subcarriers into frequency slots, which are fused into temporal
tokens. Trained jointly from scratch, TGT with TokenMLP achieves the highest mean accuracy of 92.83% among all evaluated frontend-backend combinations on the self-collected
dataset. Experiments on EHUNAM and Widar further support the applicability of TGT to cross-domain presence detection and gesture recognition.
Read the full abstract ▾
All authors Ziyi Wang, Kenuo Xu, Jichu Jiang, Yumeng Yang, Zheng Chen, Xiaofei Bai, Muge Chen, Xuyang Chen, Jinglei He, Jannik Hammel Nielsen, Stefan Schmid
Computation and Language
From Abusive Language Classification to Sequence Labeling Identification
Nicolas Zampieri, Ignacio Lopez, Manon Girard et al. (+1 more)
Industrial content moderation must process massive message streams under tight latency constraints, yet most abusive
language (AL) detection systems rely on sentence-level classification (ALC), which neither localizes abusive spans nor identifies who is targeted. We define Abusive
Language Identification (ALI) as a sequence-labeling task that jointly extracts AL spans and target mentions, and assess whether this approach can be used for text moderation. On a pilot corpus drawn from a production moderation pipeline, we compare ALI with ALC on cross-domain generalization and implicit abuse, and we also evaluate AL and target span detection. ALI remains competitive with ALC while providing localized outputs for moderators, with a modest and configuration-sensitive advantage on implicit abuse. Exact AL boundaries and target spans remain difficult to recover. We complement this comparison with a qualitative analysis and discuss perspectives on complete target–span linking and on structured
benchmarks for ALI.
Read the full abstract ▾
All authors Nicolas Zampieri, Ignacio Lopez, Manon Girard, Jeremy Auguste
Computation and Language
DeferKV: Rethinking Eviction Timing for One-Shot KV Cache Compression
Zhe Wang, Jiakai Li, Yujia Sun et al. (+2 more)
Long-context large
language models (LLMs) have demonstrated strong capabilities across a wide range of tasks, but the growing KV cache introduces substantial
memory and inference overhead. Existing one-shot KV cache compression methods typically commit to irreversible eviction immediately after prefill, before any signal from actual generation becomes available. Our quantitative analysis shows that early queries from the actual generation stage provide
attention signals that are more consistent with subsequent decode
attention, with the largest single-step gain occurring at the prefill-decode boundary. Based on this observation, we propose DeferKV, which moves the eviction decision from the end of prefill to the first real decoding step and temporally combines
prompt-side and decode-side observations, thereby better aligning KV importance estimation with subsequent generation requirements. DeferKV requires no additional training, draft model, or future-query prediction module, making it simple and easy to deploy. Experiments on LongBench, RULER, and Needle-in-a-Haystack demonstrate that DeferKV consistently improves model performance under KV cache compression while maintaining low inference latency.
Read the full abstract ▾
All authors Zhe Wang, Jiakai Li, Yujia Sun, Rongzheng Wang, Shuang Liang
Machine Learning
When Are Concept Bottleneck Model Explanations Faithful and Compact?
Stefano Teso, Emanuele Marconato, Steve Azzolin et al. (+1 more)
Concept bottleneck models (CBMs) are neural classifiers that allow to explain their decisions via high-level concepts, potentially enabling understanding, steering and debugging. However, their explanations are often derived heuristically. Building on formal explainability, we argue they should also be faithful, i.e., not misreport which concepts actually matter. We show that, for widespread CBM architectures, including recent VLM-based variants, faithful explanations must include all concepts in the bottleneck, compromising interpretability when this is large. This result applies to both heuristic and faithful-by-construction formal explanations. To encourage the existence of compact faithful explanations, we suggest i) modeling concepts probabilistically as binary or categorical random variables (rather than logits), and ii) employing per-concept training-time sparsification via group lasso (rather than regular elastic net). We also extend
algorithms from formal explainability to CBMs, and show they outperform natural heuristics in terms of guarantees and explanation size. Overall, our work warns against naive interpretability claims and provides formal conditions and practical strategies for ensuring CBMs are as interpretable as advertised.
Read the full abstract ▾
All authors Stefano Teso, Emanuele Marconato, Steve Azzolin, Antonio Vergari
Systems and Control
Safe Receding-Horizon Control of Fixed-Wing Aircraft Using Constrained Approximate Dynamic Programming
Felipe Arenas-Uribe, Ricardo Gutierrez and Jesse B. Hoagg
We present a receding-horizon optimal control for fixed-wing aircraft subject to state constraints. These constraints include operational constraints such as altitude, geofencing, and obstacle avoidance, as well as bounds on flight-path angle, roll angle, and airspeed. The state constraints are composed into a single soft-minimum control barrier function (CBF). We use this composite CBF in a constrained-approximate dynamic program to obtain a sequence of analytic closed-form control functions that approximately minimize a quadratic finite-horizon integral cost subject to the CBF constraint. The resulting receding-horizon control is non-myopic in the sense that it approximately optimizes the integral cost while satisfying the state constraint at all times along the entire prediction horizon. We demonstrate constraint satisfaction and performance in simulations of a fixed-wing aircraft navigating an obstacle-filled airspace under wind uncertainty. We also compare this receding-horizon control with 2 other methods.
Read the full abstract ▾
Machine Learning
dIon: Fragmentation-Based Invariance for Self-Supervised Learning of Tandem Mass Spectra
Alfred Nilsson, Joel Lapin, Samuel H. Payne et al. (+2 more)
We introduce a novel invariance for peptide tandem mass spectrometry data, unlocking self-supervised representation learning that improves de novo sequencing of peptides. This invariance exploits the physical relationship between precursor properties (mass and charge) and fragment-ion evidence, without requiring peptide sequence labels. We introduce dIon, which adapts the DINO framework with two latent prediction tasks, both recovering a clean teacher representation: one from a spectrum mixture, using the precursor as a selection query, and one from a partial spectrum with the precursor withheld. The first associates precursor information with fragment-ion evidence; the second prevents representational collapse onto that information alone. Mechanistic probes support both effects, and ablations show that the full objective performs best. Under identical end-to-end training, dIon initialization improves de novo peptide precision over training from scratch by 5.5 and 8.4 percentage points on the held-out MassIVE-KB and Kingdoms test sets, and by 2.3 and 4.8 percentage points with a larger supervised training corpus. The resulting models surpass fully supervised state-of-the-art de novo sequencing models on the diverse, multi-species Kingdoms corpus under the same greedy-decoding protocol. Without peptide labels, dIon learns strong native peptide-similarity geometry compared with other learned models; with limited peptide-supervised adaptation, it achieves the best
retrieval and pair-discrimination performance across all representation
benchmarks.
Read the full abstract ▾
All authors Alfred Nilsson, Joel Lapin, Samuel H. Payne, Mathias Wilhelm, Lukas Käll