Artificial Intelligence
CERA-MoA: Co-Evolving Routing Mechanisms with Continually Learning LLM Agents
Jiaxuan Jiang, Liyuan He and Zhixuan Fang
Current Mixture-of-
Agents (MoA) paradigms generally treat query routing and
agent fine-tuning as separate processes, limiting their ability to respond to evolving
agent capabilities. This disconnect prevents routing strategies from adapting to evolving
agent capabilities during post-training and prevents
agents from achieving synergistic data-driven specialization. To resolve this, we introduce CERA-MoA (Co-Evolving Router with continually learning
Agents for Mixture-of-
Agents), an iterative reinforcement learning framework where the dynamic router and independent
agent policies co-evolve. We design a predictive familiarity
estimator that leverages mid-layer hidden states to evaluate semantic competence among
agents, avoiding the overhead of full rollouts. Based on these familiarity scores, a cumulative-threshold adaptive routing mechanism dynamically activates a tailored minimal
agent subset, achieving a trade-off between task performance and efficiency. By proactively allocating targeted training samples to
agents based on their evolving competence, CERA-MoA promotes capability differentiation. Extensive experiments across various domains demonstrate that CERA-MoA outperforms state-of-the-art static-
agent routing and fix-workflow fine-tuning baselines.
Read the full abstract ▾
Distributed Computing
Vigil: Accountable Liveness against Selective Silence
Jiawei Cheng, Huiping Sun, Rui Zhou et al. (+2 more)
BFT accountability is well understood for safety violations, and recent work attributes global liveness violations; recipient-selective silence remains unresolved. A selectively silent adversary withholds messages from some honest nodes while behaving correctly toward others. It can stall consensus yet evade every existing mechanism. We initiate a systematic study of accountability against selective silence. Negatively, a lone attacker silent toward at most $f$ honest nodes is indistinguishable from an honest node, yielding a universal lower bound $K_{\mathrm{SI}} \ge f{+}1$ on the silence identification threshold; moreover, any feedback-free repair after a silence-induced violation costs $\Theta(n^3)$. Positively, Vigil, a Tendermint variant, matches these bounds with attack-adaptive forwarding, via bitmap cross-attestation, core-based membership, and challenge–response
auditing. It pays $O(n)$ authenticators per node when no selective silence occurs (plus $\Theta(n^2)$ bitmap metadata bits per node), relays in proportion to the attack's width (sub-threshold silence can force up to $n^3/27$ relays per view, a cost we price exactly), and majority-accuses any node silent toward more than a tunable resilience $\tau_A$ of honest peers ($K_{\mathrm{SI}} = \tau_A{+}1$, optimal at $\tau_A = f$). We also price the residual sub-threshold griefing surface exactly and extend identification to $x$-partial synchrony. Real-network experiments on a three-region WAN, together with a simulator held to exact equality with every closed form, confirm each threshold and cost: at $2\%$ loss, an $f{+}1$ accusation bar falsely accuses $91.2\%$ of honest nodes, while our majority bar accuses $0.002\%$.
Read the full abstract ▾
All authors Jiawei Cheng, Huiping Sun, Rui Zhou, Jinjue Zhou, Zhong Chen
Robotics
TRACER: Adaptive Multi-Robot Social Navigation via Joint Human-Response Prediction and Interaction-Aware Replanning
Lan Hu, Minghui Liwang, Wenbo Zhu et al. (+4 more)
Multi-
robot navigation in human-shared spaces is inherently interactive: coordinated
robot motions influence how nearby entities respond, while those responses provide valuable information for subsequent
robot decisions. However, existing methods typically address action-conditioned prediction, multi-
robot planning, or online adaptation separately, and therefore lack a unified mechanism for modeling joint
robot-entity interactions and adapting future decisions from executed interaction outcomes. To address this gap, we propose TRACER, a bi-directional receding-horizon framework that closes the loop between prediction and adaptation. TRACER evaluates candidate (i.e., alternative feasible future motion plans for the
robot team) trajectories using a per-entity probabilistic response model that separates individual-
robot effects from non-additive pairwise interactions; after executing the selected trajectory prefix, it updates persistent identity-bound beliefs over latent response modes using the synchronized observed responses. These updated beliefs then guide subsequent candidate evaluation under probabilistic safety and response-aware cost criteria. Experiments show that (i) TRACER more accurately captures non-additive multi-
robot interaction effects than a capacity-matched additive predictor, (ii) persistent identity-consistent evidence improves response prediction and downstream replanning, and (iii) the complete TRACER framework improves collision-free completion over an independent-
robot baseline on the SocialGym2 multi-
robot social-
navigation benchmark.
Read the full abstract ▾
All authors Lan Hu, Minghui Liwang, Wenbo Zhu, Xinlei Yi, Wei Gong, Yiguang Hong, Seyyedali Hosseinalipour
Computer Vision
DISTA-Net++: Rethinking Infrared Small Target Unmixing Beyond Sub-Pixel Separation
Mengze Xu, Zhu Liu, Weidong Sheng et al. (+4 more)
Long-range infrared imaging frequently confronts dense target clusters whose diffraction-limited signatures merge into a single indistinguishable blob, concealing the number, sub-pixel positions, and radiant intensities of the underlying sources. While deep learning has advanced general object detection, resolving such Closely-Spaced Infrared Small Targets (CSIST) remains largely unexplored, owing to a systemic infrastructure void and a fundamental paradigm mismatch. The dominant formulation, which reduces unmixing to a blind, discrete sub-pixel separation, is inherently insufficient: without semantic guidance, the ill-posed inverse problem admits ambiguous solutions plagued by false and missed detections, while grid-based discretization locks predictions onto fixed
lattice centers, chaining precision to prohibitively expensive grid refinement. We argue that CSIST unmixing should instead be informed and continuous. To ground this paradigm shift, we establish the first comprehensive open-source ecosystem for the field, comprising the large-scale CSIST-100K
benchmark, a tailored metric suite, and the GrokCSO toolkit. Upon this foundation, we propose DISTA-Net++, which anchors a dynamic deep unfolding backbone with two synergistic mechanisms: a Count-Guided Prior that injects the global target count as an explicit semantic constraint to regularize the solution space, and a Continuous Coordinate Rectification that regresses off-grid offsets to decouple localization accuracy from grid resolution. Extensive experiments validate our paradigm: even under the most economical 3x division, DISTA-Net++ surpasses 7x-division state-of-the-art methods by 16.15% in CSO-mAP and 62.96% in count accuracy at merely one-sixth of their computation, demonstrating that unmixing precision need not be purchased with finer discretization. The complete ecosystem is available at https://github.com/GrokCV/GrokDet.
Read the full abstract ▾
All authors Mengze Xu, Zhu Liu, Weidong Sheng, Boyang Li, Yimian Dai, Ming-Ming Cheng, Jian Yang
Computation and Language
Zero-Shot Cross-Lingual Recognition of Sign Language Handshapes
Marcel Granero-Moya, Carolina del Corral Farrarós, Gloria Haro et al. (+2 more)
Sign
language processing advances rapidly for high-resource
languages such as American Sign
Language (ASL), yet most of the world's sign
languages lack the phonological annotations new methods require. We present the first zero-shot cross-lingual framework for handshape recognition, transferring from ASL to Catalan Sign
Language (LSC). Our approach leverages the decomposition of handshapes into five phonological features – selected fingers, flexion, spread, thumb position, and thumb contact – shared across both
languages, to decode LSC handshapes from predicted features via a composite phonological distance metric. We evaluate three architectures (MLP, SL-GCN, SHuBERT) trained on two ASL corpora (PopSign, Sem-Lex) against a 37-handshape, single-signer LSC
benchmark. Zero-shot transfer proves viable once recording-format disparities are harmonized, reaching 80.0% phonological feature accuracy and 54.5% expected handshape accuracy. Phonological decomposition thus offers a bridge for extending sign
language technologies to low-resource
languages without any target-
language video training labels.
Read the full abstract ▾
All authors Marcel Granero-Moya, Carolina del Corral Farrarós, Gloria Haro, Coloma Ballester, Ricardo Marques
Artificial Intelligence
Version- and Scope-Aware Question Answering over Normative Documents: A Deployed System and an End-to-End Evaluation at Production Scale
Liuyin Wang, Shuaipeng Jin, Jiwei Shi et al. (+1 more)
Correctly answering a question grounded in normative documents often depends on information outside any single passage: whether the retrieved document is the version currently in force; whether it applies to the jurisdiction, subject (such as an institution or applicant), and date at issue; and whether each normative claim can be traced to its supporting source text. Hosted
retrieval services have substantially lowered the engineering cost of building an initial system over such corpora, making "upload the documents and ask" a common default. We evaluate this default on approximately 73,000 candidate normative documents supplied to a production deployment. The evaluation uses a stratified sample of 200 questions from our published
benchmark, with a gold source document for every question; the released sampling rule reads no system outputs or scores. We compare the hosted service with a governed system that resolves version and scope through explicit rules before generation. The governed system scored 97.7 overall, while the hosted service scored 88.1, a gap of 9.6 points computed from unrounded means. The question set, the answer text evaluated for both systems, the scores, and the scripts used to reproduce the reported
benchmark statistics are public. The governed configuration has operated as a commercial product since January 2026 and serves 1,126 registered users; named customer organizations include Zhipu AI and Lecheng Health. By mid-April 2026, it had reached roughly 100,000 calls per workday.
Read the full abstract ▾
All authors Liuyin Wang, Shuaipeng Jin, Jiwei Shi, Jensen Hsu
Sound
FRAUDSkill: Structured Frozen-Weight Skill Optimization for Audio Anti-Fraud Detection
Chengxian Hu, Zhiming Ma, Mingjun Pan et al. (+9 more)
Large audio-
language models have shown promise for anti-fraud detection by directly processing
speech and
reasoning over fraud-related evidence. Their deployment, however, requires predictions to follow a predefined label space and a structured decision protocol consisting of service-scenario identification, fraud detection, and conditional fraud-type classification. Existing fine-tuning and
prompt-based approaches typically encode task knowledge, constraints, and decision rules into model parameters or manually maintained
prompts, making them difficult to adapt as fraud patterns and labeling policies evolve. To this end, we propose FRAUDSkill, a structured frozen-weight adaptation framework that leaves the underlying audio-
language model unchanged while optimizing an external layer of skill programs, route-specific policies, and decision rules. We further combine structured output control with validation-guided multi-path inference to ensure protocol-compliant predictions. On the TeleAntiFraud
benchmark, FRAUDSkill achieves 73.50% Macro-F1, outperforming the shared frozen-model baseline by 31.96% while reducing invalid outputs to 1.94%. Extensive experiments demonstrate that external skill optimization provides an effective and adaptable solution for structured audio anti-fraud detection without modifying the underlying model. The source code is available at https://anonymous.4open.science/r/FRAUDSKILL-114514.
Read the full abstract ▾
All authors Chengxian Hu, Zhiming Ma, Mingjun Pan, Yifan Wang, Shun Zhang, Qifan Wang, Zhilei Zhao, Yijin Zhou, Yuxi Zhao, Huiyuan Liu, Peidong Wang, Peng Chen
Robotics
Gated Residual Body-Hand Coordination for Whole-Body Humanoid Teleoperation
Ruiming Wu, Shuang Li, Liding Zhang et al. (+2 more)
Whole-body
humanoid teleoperation commonly combines a motion-tracking policy with a separate dexterous-hand retargeter. However, independently generated commands do not explicitly preserve body-hand
geometric relations, leading to mismatches in relative wrist poses and fingertip positions during bimanual interaction. We present a gated residual coordination framework that keeps both modules frozen and applies bounded corrections to their outputs. A motion-conditioned action gate allocates correction authority across joint groups, while reference-geometry-dependent reward gates emphasize relevant interaction objectives during training. To establish the nominal body controller on Agile One, we introduce multi-pose morphology calibration that jointly estimates triaxial scales and effector-local offsets, together with staged motion
dataset curation for training a SONIC-based tracker. The residual policy uses human motion references, initial commands, and
robot proprioception without explicit object or contact observations. In simulation, it reduces wrist and fingertip geometry errors by 39.2-56.3% over direct composition on held-out GRAB motions, while preserving whole-body tracking on AMASS, with success rates of 89.03% without residual coordination and 89.29% with it. Ablations characterize the contributions of reward gating, adaptive correction authority, and separate body and hand correction heads.
Read the full abstract ▾
All authors Ruiming Wu, Shuang Li, Liding Zhang, Alois Knoll, Zhaopeng Chen
Machine Learning · Cross-listed from eess.SP
Stable Filters for Generative Modeling of Graph Signals
Martin Schmidt and Gonzalo Mateos
Generating signals on graphs requires permutation-equivariant models that exhibit stability with respect to relative structural perturbations. While recent graph-aware Schrödinger bridge models incorporate
topology information directly into their reference dynamics, it is unclear how perturbations of the graph propagate through these dynamics and affect the resulting generated distributions. In this paper, we analyze the structural stability of graph-aware continuous-time generative models whose drift combines a graph filter with a learned graph neural network. We derive explicit Wasserstein stability bounds that quantify the effect of relative graph perturbations on the generated distributions. Motivated by these bounds, we introduce a principled framework for designing stable graph filters that preserve the smoothing behavior of graph heat
diffusion, while boosting structural stability. Experiments on synthetic and fMRI signals show our stable filters enhance structural robustness while matching or exceeding the generative quality of the heat equation baseline.
Read the full abstract ▾
Data Structures and Algorithms · Cross-listed from quant-ph
Query-Optimal and Gate-Efficient Lindbladian Simulation
Boyang Chen, Minbo Gao, Xinzhao Wang et al. (+1 more)
We give a
quantum algorithm for Lindbladian simulation given a block encoding of the
Hamiltonian $H$ and a projected
unitary encoding of the stacked jump operator $B=\sum_{k=1}^m \lvert k\rangle\otimes L_k$, with normalization factors $\alpha_H$ and $\alpha_B$, respectively. For
evolution time $t$, set $\tau=(\alpha_H+\alpha_B^2)t$. The
algorithm approximates the
evolution channel to diamond-norm error $\varepsilon$ using $O\!\left(\tau+\frac{\log(1/\varepsilon)}{\log\!\left(e+\log(1/\varepsilon)/\tau\right)}\right)$ oracle queries, matching the query lower bound for
Hamiltonian simulation. The number of additional one- and two-
qubit gates is linear in the query complexity up to polylogarithmic factors. The query- and gate-complexity bounds extend to Lipschitz-continuous time-dependent Lindbladians under coherent time-indexed oracle access. Our construction uses a one-query transducer that implements a product of rational approximations to short-time
evolution when supplied with a catalyst. We bound the error from omitting the catalyst by exploiting orthogonality between different sequences of Kraus labels. The gate implementation combines a compressed Kraus-label representation, which stores only the positions and values of the nonzero labels, with the rotation factorization of Chen et al.
Read the full abstract ▾
All authors Boyang Chen, Minbo Gao, Xinzhao Wang, Shuo Zhou
Numerical Analysis
A Highly Scalable Quantized Tensor-Train FDTD Framework for the Simulation of Three-Dimensional Electromagnetic Scattering Problems
Daan Vanhaecke, Emile Vanderstraeten and Dries Vande Ginste
In this letter, a novel 3-D Finite-Difference Time-Domain (FDTD) framework is proposed that circumvents the costly volumetric scaling of conventional FDTD methods. By representing the electromagnetic fields as low-rank Quantized Tensor Trains (QTT), the
memory requirements scale logarithmically with system size. Moreover, the various numerical operations that constitute the FDTD scheme can be efficiently implemented in this format, with their computational cost also exhibiting a logarithmic complexity. The simulation of systems in open space is enabled by the inclusion of a uniaxial PML. A validation example demonstrates that the method achieves excellent accuracy compared to the traditional full-grid (FG) FDTD method, while significantly reducing the required computational resources.
Memory savings of several orders of magnitude are obtained, highlighting the potential of the proposed framework for the simulation of large multiscale electromagnetic systems.
Read the full abstract ▾
Computer Vision
Toward Markerless Video-based Tremor Analysis: Objective Quantification of Pathological Tremor in Mouse Preclinical Models
Yota Koshimoto, Akihiro Tsukahara, Yasuhiro Moriwaki et al. (+1 more)
Tremor is a movement disorder characterized by involuntary, rhythmic oscillations of body parts and is a hallmark of several neurological conditions, including Parkinson's disease and essential tremor. Elucidating its underlying mechanisms relies heavily on mouse models, which offer genetic manipulability and translational relevance to human neural circuitry. Accordingly, these models are indispensable for studying tremor pathophysiology. So far, electromyography and accelerometers have been used as methods to quantitatively observe tremors in mice. However, these methods have several drawbacks, such as high costs and complex setups. In particular, the invasive
surgical implantation of devices causes significant stress to the animals. Although RGB-based methods offer non-invasive and cost-effective alternatives, they often lack the sensitivity required to detect subtle tremors. Therefore, this paper addresses these challenges by achieving mouse tremor severity estimation using conventional RGB cameras only. To address the challenging task of isolating tremor-related vibrations while the mouse itself is also in motion, our pipeline incorporates
segmentation-based pre-processing to extract the mouse region and a Tremor Score Estimation Module that captures subtle tremors with high sensitivity. In the experiments, we assessed tremors in unrestrained mice using a non-invasive method with two standard cameras. The results demonstrated a strong correlation with accelerometer measurements and confirmed that the method accurately captured the intensity-dependent characteristics of tremors. The project page is available at https://isogawalab.github.io/
Video-based-Tremor-Analysis-Project/.
Read the full abstract ▾
All authors Yota Koshimoto, Akihiro Tsukahara, Yasuhiro Moriwaki, Mariko Isogawa
Robotics
QMSR: Query-Conditioned Mask-wise Expert Routing for Robust Open-Vocabulary Underwater Object Retrieval
Fuming Zhang, Dongyue Huang, Junjie Wen et al. (+1 more)
Open-vocabulary object
retrieval remains challenging in complex
underwater environments. Although
underwater image enhancement (UIE) can improve visual quality, fixed UIE strategies may even underperform the Raw representation in
retrieval, indicating that enhancement should not be applied as a uniform preprocessing step. To address this problem, we propose QMSR, a query-conditioned mask-wise expert routing framework for
underwater open-vocabulary
retrieval. Specifically, QMSR selects one pretrained UIE expert for each query–candidate pair and predicts a continuous Raw–Expert fusion strength, enabling adaptive enhancement while preserving useful Raw semantics. During training, a privileged ranking oracle provides expert-selection and fusion-strength supervision, while an annealed soft-routing relaxation facilitates optimization of the hard Top-1 routing policy. Experiments show that QMSR improves NDCG@10 by 17.6% over an image–query shared router, while consistently outperforming fixed UIE strategies and remaining effective on held-out query categories. These results demonstrate the effectiveness of query-conditioned and candidate-specific enhancement routing for
underwater open-vocabulary
retrieval.
Read the full abstract ▾
All authors Fuming Zhang, Dongyue Huang, Junjie Wen, Lihua Xie
Cryptography and Security
Normal Alignment: Improved Cryptanalytic Sign Recovery on Hard-Label Networks
Shi Tang, Zirui Chen, Yongjia Su et al. (+3 more)
At EUROCRYPT 2025, Carlini et al. proposed a breakthrough in the cryptanalytic extraction on hard-label (S1) deep neural networks (DNNs), demonstrating
polynomial-time signature and sign recovery. However, Carlini et al.'s sign-recovery method (which we call Future Toggle) suffers only a marginal advantage over random guessing, producing high-confidence wrong sign predictions in deeper layers. Such errors trigger expensive exponential-time enumeration. This work presents Normal
Alignment, a novel statistical sign-recovery approach for S1 DNNs. Drawing on the expected length difference between projected normals of adjacent decision facets at dual points, our method infers
neuron signs via normal-signature
alignment. It delivers higher voting accuracy and pushes erroneous predictions to low-confidence ranks, which further enables a more efficient combined method, eSOE +
Alignment, by combining Normal
Alignment with the hard-label SOE extension. This combined strategy removes heavy enumeration overhead and realizes exact
polynomial-time full sign recovery. Experiments demonstrate the effectiveness of our method, especially for deep layers. For example, with our method, the signs for CIFAR-10 (architecture 192-64$\times$8-10) and MNIST (architecture 64-96$\times$3-32-10) models can be fully recovered in
polynomial time; in contrast, Carlini et al.'s sign-recovery method would require exponential-time enumerations involving $2^{52}$ or $2^{82}$ guesses of the signs, respectively.
Read the full abstract ▾
All authors Shi Tang, Zirui Chen, Yongjia Su, Zhengchao Gao, Lingyue Qin, Xiaoyang Dong
Sound
TeleAntiFraud 2.0: A Refreshable, Profile-Grounded, and Audio-Based Benchmark for Telecom Fraud Detection
Huiyuan Liu, Zhiming Ma, Yanxing Liu et al. (+11 more)
Telecom fraud scripts evolve rapidly and are often designed to resemble routine service conversations, creating two key requirements for audio-based telecom-fraud evaluation. First,
benchmarks must incorporate newly observed scam patterns without overwriting previously established test sets. Second, they must distinguish fraud from lawful, near-domain calls rather than relying on topic-separated negative examples. We present TeleAntiFraud 2.0, constructed with our Mixed-Tree Anti-Fraud Generation Pipeline and evaluated under a monthly frozen evaluation protocol. The pipeline transforms online fraud-case abstracts into profile-grounded scenarios, expands them through mixed-tree generation, realizes fraud and non-fraud dialogue paths under shared contexts, renders validated dialogues as role-matched
speech, and freezes the resulting audio, labels,
prompts, manifests, and provenance records for each monthly evaluation set. Each frozen set contains 900 Chinese calls, comprising 600 fraud and 300 near-domain non-fraud cases. Controlled text experiments show that three classifiers achieve perfect macro-averaged F1 (Macro-F1) when evaluated against unrelated or ordinary negatives, but drop to 0.65-0.68 with near-domain sibling negatives. Full-set audio and automatic-
speech-recognition plus large-
language-model (ASR+LLM) evaluations further reveal class-prior shortcuts, prediction collapse, and snapshot sensitivity. Together, these findings establish near-domain construction and collapse-aware reporting as core requirements for evaluating audio-based telecom-fraud models under realistic confusable conditions. The accompanying research artifact includes the construction code, evaluation scripts, manifests, and documentation. Our
dataset and code are available at https://anonymous.4open.science/r/TeleAntiFraud-2_0-EEB2/.
Read the full abstract ▾
All authors Huiyuan Liu, Zhiming Ma, Yanxing Liu, Shun Zhang, Qifan Wang, Di Liu, Yifan Wang, Yuyang Deng, Haoyang Meng, Yijin Zhou, Yuxi Zhao, Chengxian Hu, Peidong Wang, Peng Chen
Machine Learning
When Edit Flows are Edit Jumps: replicating Edit Flows and EvoFlows
Gabriel Bénédict, Melanie Buechler, Gerard Riera-Solà et al. (+3 more)
Antibody lead optimization calls for a small, bounded set of edits to an existing candidate: substitutions, but also insertions and deletions. Edit-based generative models are the only ones that allocate such an edit budget without fixing the edit positions, the edit count, or the output length in advance. However, the existing approaches Edit Flows and EvoFlows did not release code or complete training specifications. Here, we show that both methods follow the same underlying process – edits firing one at a time, at learned rates, in continuous time – the pure-jump case of generator matching over finite sequences. With EditJumps we introduce the first open implementation of this framework, with a single generalist antibody editor trained on 1.66M Observed Antibody Space homolog pairs to propose homolog-like variants of a seed sequence, editing unseen leads zero-shot, without the per-family retraining original approaches require. Replicating this system from scratch exposes why open code is essential for generative biology: reconciling published edit distributions required reverse-engineering an undocumented rate-scaling hyperparameter that dictates realized mutation counts. Moreover, we show that published evaluation metrics are highly sensitive to reference sample size, frequently flipping method rankings. We release our full codebase, automated test suite, and configurations at: https://github.com/VisiumCH/editjumps
Read the full abstract ▾
All authors Gabriel Bénédict, Melanie Buechler, Gerard Riera-Solà, Chloé de Ancos, Yves Gaetan Nana Teukam, Moritz Freidank
Computers and Society · Cross-listed from physics.soc-ph
Towards stratified sampling for redistricting plans
Zijian Wang, Gregory J. Herschlag, Joon-Hyeok Yim et al. (+2 more)
Rapid algorithmic developments have accelerated the sampling of redistricting ensembles (balanced graph partitions), yet evaluating rare events and sampling complex target measures remains a core challenge due to the high-dimensional and combinatorial nature of the phase space. We address a prerequisite for stratified sampling on this space: constructing and diagnosing candidate strata with suitable coverage and overlap. We build a grammar on observed plans by clustering districts into representative “letters” and using them to form plan-level “words.” A partition of unity over these words gives a soft assignment of plans to strata and allows us to estimate stratum masses and an overlap-induced flux
matrix. We demonstrate this computational pipeline using real-world congressional redistricting data from Connecticut and examine how strata learned from one target distribution behave under related distributions. The resulting construction provides a foundation for future stratified sampling on spaces of redistricting plans or balanced graph partitions. We do not implement a complete stratified sampler here; evaluating whether the proposed strata improve sampling efficiency or reduce
estimator variance is left for future work.
Read the full abstract ▾
All authors Zijian Wang, Gregory J. Herschlag, Joon-Hyeok Yim, Jonathan C. Mattingly, Anna C. Gilbert
Computation and Language
A Scalable Framework for Automated NER Annotation Correction in Low-Resource Languages
Toqeer Ehsan and Thamar Solorio
Poor quality or noisy annotations in Named Entity Recognition (NER), as in any other NLP task, make it challenging to achieve state-of-the-art performance. In this paper, we present a multi-step framework to enhance the annotation quality of NER
datasets by employing automated techniques. We propose a frequency-based iterative approach that leverages self-training and a dual-threshold mechanism to enhance inference confidence. Experimental evaluations on different NER
datasets demonstrate significant improvements in NER performance with respect to the original
datasets. This work further explores the potential of generative Large
Language Models (LLMs) to perform NER for low-resource
languages.
Read the full abstract ▾
Robotics
Active perception for robotic harvesting: 3D reconstruction and localisation of tomatoes hidden within clusters in a Mediterranean greenhouse
Fernando Cañadas-Aránega, Rowan Border, José C. Moreno et al. (+1 more)
Automating robotic harvesting in intensive agriculture within Mediterranean greenhouses requires overcoming significant challenges related to the
geometric complexity of plants and occluded fruits. Although existing literature offers solutions targeting crops that grow in isolation (e.g., apples, sweet peppers, or peaches), the fundamental challenge lies in cluster-growing vegetables, where fixed sensors mounted on robotic systems fail to detect fruits hidden behind the visible surface. To address this limitation, this study presents a comprehensive pipeline for the 3D reconstruction and precise localization of each fruit within a cluster, including heavily occluded instances. The proposed methodology is structured into five sequential stages: i) point cloud acquisition using the AgriSEE Next Best View (NBV) active planner; ii)
stochastic noise filtering via Statistical Outlier Removal (SOR); iii) surface classification and
segmentation using Region Growing (RG); iv) isolation and recovery of occluded fruits through Density-Based Spatial Clustering of Applications with Noise (DBSCAN); and v) 3D pose estimation (position and orientation). This approach extracts the complete cluster geometry, ensuring the reliable identification of partially hidden tomatoes. Evaluated across multiple scenarios with varying occlusion levels within a simulation framework rigorously validated against real-world conditions, the system achieves a precision exceeding 90%, an average recall of 82.8%, and a mean Intersection over Union (mIoU) of 80.7%. Furthermore, it demonstrates high repeatability in centroid estimation with a Root Mean Square Error (RMSE) of merely 4.2~mm, verifying its technical feasibility and high accuracy for autonomous harvesting operations.
Read the full abstract ▾
All authors Fernando Cañadas-Aránega, Rowan Border, José C. Moreno, José L. Blanco-Claraco
Computer Vision
Geometry beneath the Waves: Dense Priors for Sparse-View Underwater 3D Gaussian Splatting
Harvey Caldeira, Haoran Wang, Guoxi Huang et al. (+3 more)
Underwater 3D reconstruction remains challenging under sparse views, where scattering, absorption, and suspended particles degrade feature correspondences and
geometric estimation. Although feed-forward geometry foundation models offer an alternative to conventional Structure-from-Motion, their direct application
underwater produces noisy and fragmented geometry that limits subsequent 3D Gaussian Splatting (3DGS). We propose a sparse-view
underwater reconstruction framework that adapts feed-forward geometry to
underwater degradation and exploits its dense
geometric priors for view synthesis. First, we adapt VGGT using LoRA and teacher–student
distillation, training on synthetically degraded
underwater images while preserving clean
geometric supervision. This improves robustness to
underwater appearance distortions without modifying the pretrained prediction heads. Second, the predicted dense geometry initialises an intermediate 3DGS representation that generates geometry-guided pseudo-views, increasing view overlap and strengthening feature tracks for subsequent RUSplatting optimisation. Experiments on SeaThru-NeRF and Submerged3D demonstrate improved reconstruction quality under sparse-view conditions. On SeaThru-NeRF, our method improves RUSplatting from 24.37 to 27.11 dB PSNR and increases SSIM from 0.7611 to 0.8634, while achieving the best average PSNR and LPIPS on Submerged3D. These results demonstrate the potential of domain-adapted
geometric priors for robust sparse-view
underwater 3D reconstruction.
Read the full abstract ▾
All authors Harvey Caldeira, Haoran Wang, Guoxi Huang, Shaoyu Cai, Rachel Fu, Nantheera Anantrasirichai
Artificial Intelligence
Clueing up LLMs with Tool-Augmented Deductive Reasoning
Rebecca Ansell and Autumn Toney-Wails
Despite recent advances in large
language models (LLMs), performing logically consistent deductive
reasoning over extended interactions remains challenging. Tasks that require integrating evidence across multiple
reasoning steps, maintaining consistency with prior inferences, and updating beliefs under new constraints can surface limitations in current models while providing a useful testbed for evaluating
reasoning enhancements. In this paper, we implement a text-based, multi-
agent version of the classic board game Clue as an environment to evaluate multi-step, agentic deductive
reasoning. In this setting,
agents must infer hidden information from a sequence of observations, maintain consistency across turns, and reason over an evolving set of logical constraints. We instantiate six LLM-based
agents (GPT-4o-mini and Gemini-2.5-Flash) as players that engage in turn-based gameplay; using three
agents per model family, we establish baseline performance across repeated games. We then introduce a tool-augmented approach in which a structured possibility
matrix converts implicit game state from generated
reasoning logs into an explicit representation of remaining possibilities. The possibility
matrix encodes extended-turn
memory and deductive constraints, offloading these tasks from the
agent. We compare this approach against the baseline to evaluate how tool augmentation supports
reasoning quality and task success for autonomous
agents in a strategic
reasoning environment.
Read the full abstract ▾
Robotics
PASSAGE: Scaling Scene-Aligned Motion Learning for Perceptive Humanoid Traversal in Cluttered Environments
Yuxuan Ma, Zicheng Zeng, Chunlin Peng et al. (+17 more)
Humanoid robots can step over, squeeze past, and duck under obstacles, but learning to select and coordinate these behaviors from onboard perception remains challenging. Many existing approaches rely on task-specific reinforcement-learning objectives or curated motion libraries, making broad behavioral coverage costly. We present PASSAGE, a perception-conditioned planner–tracker framework for
humanoid traversal. Using virtual reality and inertial motion capture, we collect 100 h of scene-aligned human motion across 1,500 cluttered scenes. A conditional flow-matching planner generates short-horizon references from motion history, a local destination, and a
robot-centric multi-layer elevation map, while a perceptive whole-body tracker executes them at 50 Hz with
geometric feedback. Real-time chunking promotes inter-chunk consistency, and planner-side RL post-training under the frozen tracker further improves closed-loop performance. Without skill annotations or obstacle-specific policies, one planner–tracker pair selects and composes traversal behaviors across unseen geometries. In simulation, component ablations quantify the contribution of each stage. Across three independent training seeds, scaling captured data from 6 to 100 h increases mean contact-free success from 48.1% to 68.9% on held-out scenes, while the final model with validated scene augmentation reaches 70.3%. The fully onboard system integrates
egocentric 3D
LiDAR perception, online occupancy mapping, 6.25 Hz planning, and 50 Hz control on a Jetson AGX Orin; tests across 50 unseen physical layouts demonstrate traversal without prebuilt maps or offboard computation.
Read the full abstract ▾
All authors Yuxuan Ma, Zicheng Zeng, Chunlin Peng, Zhoujian Li, Zetong Zhao, Zhikai Zhang, Yunrui Lian, Han Xue, Sikai Liang, Weiyi Zhu, Mulin Chen, Chenghuai Lin, Jiayu Zeng, Yanwei An, Songan Zhang, Jiayuan Gu, Jilong Wang, Jingbo Wang, He Wang, Li Yi
Artificial Intelligence
Which LLM is Best for Translating Natural Language Goals to PDDL
Tomas Balyo, Lukas Chrpa and G. Michael Youngblood
Bridging the gap between human intent and machine execution remains a challenge in automated planning, where expressing goals in formal
languages like PDDL restricts accessibility to non-experts. This paper empirically evaluates whether current Large
Language Models (LLMs) can reliably translate natural
language testing goals, written in informal
language by
video game testers, into well-formed PDDL targets suitable for classical planning. We present a carefully designed
prompt template, integrating insights from iterative experimentation, aimed at maximizing both accuracy and response coherence from multiple state-of-the-art LLMs. Six contemporary models are systematically assessed on correctness, speed, and error tendencies using real-world, domain-specific
benchmarks. All models demonstrate high correctness, exceeding 92%, with Gemini 2.5 Flash achieving the highest accuracy at 96% and the lowest incidence of false positives, while GPT-4.1 leads in response speed. Despite these advances, critical distinctions exist in model performance, and occasional failures arise from
language ambiguity and limitations in domain representation. Our analysis underscores both the significant progress and ongoing gaps in enabling LLMs to act as robust bridges between natural
language objectives and automated planning pipelines.
Read the full abstract ▾
Computers and Society
"If I Had to Buy Just ONE: Galaxy S26 Ultra": Auditing AI-Generated Product Recommendations
Lucas G. Uberti-Bona Marin, Thales Bertaglia, Giovanni Astante et al. (+5 more)
Consumers increasingly use AI chatbots for advice on what to buy. With companies like OpenAI and Google monetising their AI through advertising, this raises difficult questions about the bias and impartiality of such advice. In response, we conduct an AI audit of popular chatbots using real commercial-advice queries. First, we curate a
dataset of 2,528 real commercial-advice queries (ConsumerQ). Then, we evaluate 1,536 responses to product queries from popular AI chatbots: ChatGPT (chatbot and API), Google Gemini (chatbot and API), and Google Search (AI Overviews). We find that ChatGPT expresses a first-person product preference in 79% of product-recommending responses, compared with 7% for Gemini and 2% for AI Overviews, while the products recommended often change across repeated requests. Displayed sources vary strongly: for the same query, the ChatGPT and Gemini interfaces share only 5.4% of domains on average, with no domain in common in 76.7% of comparisons. APIs provide a different view from their corresponding interfaces, with mean domain overlaps of 12.0% for ChatGPT and 14.8% for Gemini, and also differ in the types and layers of source information they expose. Our findings show that neither isolated responses nor API observations can be assumed to represent the commercial advice consumers encounter. Independent audits of AI-mediated commercial advice should therefore account for repeated responses, consumer-facing conditions, and the source layer being observed.
Read the full abstract ▾
All authors Lucas G. Uberti-Bona Marin, Thales Bertaglia, Giovanni Astante, Bram Rijsbosch, Gijs van Dijck, Anikó Hannák, Gerasimos Spanakis, Konrad Kollnig
Information Theory
Counterexample to a Proposed Capacity Characterization of the Relay Channel
Chun Hei Michael Shiu
We present a counterexample to the relay channel capacity characterization proposed in a recent work, which is based on properties of typical sequences. The counterexample uses a binary relay channel with a noiseless source-destination component and binary symmetric relay links. An achievable scheme exceeds the proposed capacity characterization, thereby disproving the characterization of the capacity for general relay channels. We highlight that the counterexample is obtained with the assistance of ChatGPT-6 Astra and the proofs are simplified with human effort.
Read the full abstract ▾
Human-Computer Interaction
Calmables: Demonstrating Closed-Loop Infrared Earables for Thermal Biofeedback and Relaxation Support
Valeria Zitz, Michael Küttner, Jonas Hummel et al. (+3 more)
We present Calmables, a walk-up demo of a closed-loop infrared earable that uses smart-ring heart rate to create subtle, ear-localized warming cues. Building on work on thermal comfort and in-ear infrared stimulation, Calmables explores warmth at the ear as a biosignal-adaptive cue for brief recovery moments following acute activation. A smartphone first establishes an individual resting baseline and derives a personalized heart-rate threshold, while the earable controller independently enforces an over-temperature cut-off and communication fail-safes. During the guided demo flow, attendees complete a brief rapid-breathing activation phase until their heart rate reaches the personalized threshold. This triggers an ear-localized warming cue followed by a short relaxation phase, while physiological changes are displayed on a live dashboard. Attendees can also manually explore different infrared stimulation intensities. To contextualize the demo, we report preliminary placebo-controlled UX ratings from 18 participants: participants rated the active prototype higher on perceived relaxation and perceived recovery support than an identical-looking placebo. Together, the demo illustrates how infrared earables can make physiological feedback tangible through subtle, biosignal-adaptive thermal cues.
Read the full abstract ▾
All authors Valeria Zitz, Michael Küttner, Jonas Hummel, Taku Inoue, Tobias Rödiger, Michael Beigl
Game Theory
Second-Best Gains from Trade in Matching Markets
Xiaohui Bei, Bo Li, Wenhao Wu et al. (+1 more)
We study gains from trade (GFT) in two-sided matching
markets with independent private types and arbitrary downward-closed feasibility constraints. The second-best
benchmark is the maximum expected GFT achievable by a
Bayesian incentive-compatible, interim individually rational mechanism that is strongly budget balanced at every report profile. These constraints generally preclude attaining the first-best GFT and raise the question of how much efficiency must be lost. We prove that the second-best GFT is at least one half of the first-best GFT in every such matching
market. This recovers and generalizes the recent $1/2$ guarantee for bilateral trade by Liu, Qin, Ren, and Wang to
markets with multiple buyers and sellers and arbitrary downward-closed feasibility constraints. Together with their matching upper bound for bilateral trade, our result establishes a tight worst-case ratio of $1/2$ for this general class of matching
markets. Our proof builds on the virtual-GFT framework of Brüstle, Cai, Wu, and Zhao to reduce the problem to a one-parameter Lagrangian. The main step is a
geometric, edge-by-edge analysis based on first-best edge-selection regions, combined with a randomized contraction in rank space. The same analysis also determines the exact worst-case efficiency for every level of outside subsidy. In particular, even a small outside subsidy can significantly improve the worst-case guarantee.
Read the full abstract ▾
All authors Xiaohui Bei, Bo Li, Wenhao Wu, Shengwei Zhou
Artificial Intelligence
Beyond Truncation: Rethinking LLM Decoding as Ensemble Pruning
Dunyao Xue, Chengshuo Du, Zhengbo Wang et al. (+2 more)
We introduce Mahalanobis-Ensemble Decoding (ME-Decoding), a novel Large
Language Model (LLM) decoding framework that frames candidate
token selection as ensemble
pruning. Existing selection strategies rely predominantly on scalar probabilities, ignoring
geometric semantic relationships and causing candidate redundancy. Meanwhile, current geometry-aware methods often require complex optimization or directly reweighting the original
token probabilities, leading to significant computational overhead or inference instability. To address this, we formulate decoding as a subset optimization problem using a Mahalanobis distance-driven objective to enhance semantic diversity while preserving high probabilities. Specifically, we dynamically discount redundant generation paths using a
token similarity
matrix, constructed via an adaptive-bandwidth kernel over
token embeddings. We further devise an efficient greedy selection
algorithm with near-linear complexity in the candidate size under early stopping, while establishing its theoretical approximation guarantees. This renders ME-Decoding a robust, plug-and-play module with negligible inference overhead. Extensive experiments across diverse
reasoning and generation tasks demonstrate that our method consistently achieves strong performance.
Read the full abstract ▾
All authors Dunyao Xue, Chengshuo Du, Zhengbo Wang, Wenlin Dai, Cheng Meng
Computational Complexity
A Structural Proof of the Lower Bound 21 for $3\times3$ Matrix Multiplication over $\mathbb F_2$
Shuxing Yang, Rui Zhao, Junyao Wu et al. (+13 more)
We prove that the tensor rank of $3\times3$
matrix multiplication over $\mathbb F_2$ is at least $21$. The structural proof, independently developed by Qiushi Engine, converts occupation constraints on a single tensor factor into algebraic relations coupling all three factors. Certified quotient-rank bounds and finite geometry force any hypothetical $20$-term decomposition to have first-factor
matrix-rank profile $(16,1,3)$. The ranks of the corresponding split-flattened summands therefore sum to $27$, exactly the rank of the full split flattening. Equality in rank subadditivity forces their images to form a direct sum; normalization by the inverse flattening then makes the summands pairwise annihilating idempotents. An explicit product identity for
matrix multiplication implies that at most one first factor can be invertible, contradicting the three forced by the profile. The same obstruction constrains $22$-term decompositions attaining the split-rank bound. The complete proof, including the finite quotient bounds, is formalized in Lean. The accompanying research trajectory records Qiushi Engine's long-horizon autonomous research, from numerical experiments and quotient constructions to the structural proof.
Read the full abstract ▾
All authors Shuxing Yang, Rui Zhao, Junyao Wu, Yize Wang, Wenhao Li, Fujia Chen, Taowen Deng, Shenzhan Hong, Yaqi Li, Zichen Li, Jincheng Mi, Yuang Pan, Kaihao Zhu, Junjie Yang, Hongsheng Chen, Yihao Yang
Computation and Language
LocQE: Principled Domain Adaptation for Localisation Quality Estimation by Leveraging Post-Edits
Kathy Hämmerl, Gabriel Bretschner and Joern Wuebker
Learned quality estimation (QE) models such as COMETKiwi are widespread and work well for general machine translation evaluation. However, they are known to struggle on unseen domains, limiting their performance in a real-world localisation context. We show that they are insensitive to some important factors in localisation, such as whether numbers are translated accurately, or even whether the correct number of spaces and punctuation are preserved in a translation. Further, a key capability for optimisation of machine translation is the ability of QE models to accurately rank different translations of a single segment, which suffers significantly from the domain transfer. In the absence of large-scale direct assessment data, we propose principled fine-tuning approaches to reduce the domain gap with even small amounts of post-editing data. Using a multi-task fine-tuning approach and a simple tokeniser intervention, we create a QE model which proves markedly better at distinguishing preferred post-edits from rejected initial translations in a localisation context. We show that preferences and artificial continuous scores stabilise each other, and argue that to calibrate metrics both in terms of their absolute scores and comparisons between translation of the same source, both types of signal are needed.
Read the full abstract ▾