Numerical Analysis
An algebraic multiscale framework for two-level overlapping Schwarz preconditioners
Filipe Cumaru, Hadi Hajibeygi, Cornelis Vuik et al. (+1 more)
The robustness of two-level overlapping additive Schwarz (OAS) preconditioners for highly heterogeneous elliptic problems hinges on the choice of the coarse space. We propose an algebraic multiscale (AM) coarse space built from the system
matrix alone through an algebraic formulation of the multiscale finite element method (MsFEM). The coarse basis functions are energy-minimizing extensions of the solutions of reduced boundary condition (RBC) problems on the subdomain interface, so that coefficient variations along the interface enter the coarse space. By posing the RBC problems on slabs that extend the interface, the construction also applies to general unstructured domain decompositions.
Embedding the AM formulation in an energy-minimizing framework extends it to linear elasticity, and we show that existing condition number bounds for OAS with MsFEM coarse spaces carry over to the algebraic setting. For problems with high coefficient inclusions on the coarse nodes, the AM iteration count and condition number are unaffected by increasing the contrast. In 3D scalar
diffusion with log-normal coefficients, AM needs about as many iterations as the generalized Dryja–Smith–Widlund (GDSW) coarse space, while solving a coarse problem ten times smaller. For linear elasticity, omitting the coarse basis functions associated with the rotational rigid body modes yields a fully algebraic coarse space that still scales well for homogeneous problems.
Read the full abstract ▾
All authors Filipe Cumaru, Hadi Hajibeygi, Cornelis Vuik, Alexander Heinlein
Computational Complexity
NP-hardness of additive approximation for generalized Turán problems
Yihan Chen, Jialin He, Xihe Li et al. (+2 more)
For a fixed graph $T$ and a fixed nonempty family $\mathcal{F}$ of graphs, let $\operatorname{ex}(G, T, \mathcal{F})$ denote the maximum number of copies of $T$ in an $\mathcal{F}$-free subgraph of a graph $G$. Alon and Shikhelman~[Algorithmica, 2022] conjectured that if $e(T)> 0$ and no member of $\mathcal{F}$ is a subgraph of a blow-up of $T$, then for every $\varepsilon>0$, approximating $\operatorname{ex}(G, T, \mathcal{F})$ within an additive error $n^{v(T)-\varepsilon}$ is NP-hard for an input graph $G$ on $n$ vertices. The previously established general cases for this
conjecture include $\operatorname{ex}(G, K_2, \mathcal{F})$ by Alon, Shapira and Sudakov~[Ann. of Math., 2009], and $\operatorname{ex}(G, K_m, K_k)$ by Alon and Shikhelman. In this paper, we confirm this
conjecture for every bipartite graph $T$ and every clique $T$. Our reductions use iterative leaf additions, symmetric rooted extensions and random transversals to encode the maximum number of edges in a $(k-1)$-colorable subgraph of $G$, where $k=\min_{F\in \mathcal{F}}\chi(F)$.
Read the full abstract ▾
All authors Yihan Chen, Jialin He, Xihe Li, Jie Ma, Tianying Xie
Computer Vision
VideoSlate: Stateful Commit Control for Temporally Grounded Agentic Video Reasoning
Shuo Zheng, Yuanjie Dang, Peng Chen et al. (+4 more)
Agentic
video reasoning systems gather and assess
video evidence across stages, selecting relevant spans as visual evidence for answering questions. New candidates and observations
prompt reassessment of the current span, but revisions can correct localization errors or discard useful evidence already present in the adopted span. Systems therefore need to connect evidence organization across stages with temporal state control, allowing accumulated information to jointly inform revision assessment while explicit adoption decisions govern how assessment outcomes affect downstream visual evidence. We introduce VideoSlate, a stateful commit-control framework built around shared evidence. A typed evidence blackboard links candidate spans, provenance, construction, and verifier observations, enabling an incumbent-relative certifier to assess revision support from the candidate, current span, and related proposals. Based on certification, the controller authorizes a revision or retains the current span, separating evidence accumulation from state updates and recording each decision and its evidence on the blackboard. Extensive evaluations across
video grounding and grounded question-answering
benchmarks show that VideoSlate can improve temporal localization through selective revision.
Read the full abstract ▾
All authors Shuo Zheng, Yuanjie Dang, Peng Chen, Jianjun Xiang, Ronghua Liang, Mohammed Bennamoun, Qiuhong Ke
Neural and Evolutionary Computing
naspaclust: A hybridisation of spatial fuzzy clustering with nature-inspired optimisation
Bahrul Ilmi Nasution, Rezzy Eko Caraka and Robert Kurniawan
We present an overview of R package called naspaclust, a tool for spatial fuzzy clustering improvement by hybridising the Fuzzy Geographically Weighted Clustering (FGWC) with nature-inspired optimisation
algorithms. There are seven optimisation
algorithms in general, namely Artificial Bee Colony, Flower Pollination
Algorithm, Gravitational Search
Algorithm, Harris-Hawk Optimisation, Intelligent Firefly
Algorithm, Particle Swarm Optimisation, and Teaching-Learning Based optimisation. The optimisation
algorithms available do not only use the basic
algorithms, but also the modified version of several parts such as randomisation terms and updating rules. Furthermore, we also provide additional options by providing more distance metrics options based on the rdist package. This study showed the implementation of the naspaclust package in various cases, as well as comparing the performance of the
algorithms in the scope of basic
algorithms. The naspaclust package allows to improve the performance of fuzzy clustering, mainly in spatial context.
Read the full abstract ▾
Robotics
PINT: A Unified Model with Shared Predictive Intent for Robot Manipulation
Xinyu Guo, Chao Jing, Li Yi et al. (+2 more)
Generalist
robot manipulation can benefit from pretrained
vision-
language models (VLMs) for semantic
reasoning and
video generation models (VGMs) for world modeling. However, existing unified models that directly fuse them through shared
attention at multiple layers can make it harder to draw on their specialized capabilities. We introduce PINT, a unified model that coordinates semantic
reasoning, world modeling, and action generation through a shared chunk-level Predictive Intent while preserving expert-specific pathways. PINT inserts learnable Intent
Tokens into the VLM sequence to form this representation, conditioning both the VGM and an Action Expert (AE). It replaces only the VGM's
prompt conditioning and retains the VGM at inference, where the AE reads its representations through one-way
attention. Rather than prescribing what Predictive Intent should encode, PINT learns it jointly from the native prediction objectives of the VLM, VGM, and AE, which provide complementary views of the same upcoming task execution. Training uses two stages: Stage 1 freezes the VGM so that future
video prediction shapes Predictive Intent with task-relevant future dynamics, while Stage 2 fixes the learned Intent and adapts the VGM and AE. Without embodied pretraining, PINT achieves strong in-distribution (ID) performance and substantially improves out-of-distribution (OOD) generalization, reaching 15.5% on RoboTwin 2.0-Hard compared with 1.8% for Fast-WAM and 3.2% for StarVLA, and 79.5% on LIBERO-Plus compared with 51.5% and 75.0%, respectively. Across five real-world bimanual tasks, PINT reaches 68% ID and 24% OOD success, compared with 35%/9% for pretrained Motus and 67%/35% for pretrained $\pi_{0.5}$.
Read the full abstract ▾
All authors Xinyu Guo, Chao Jing, Li Yi, Xingyu Chen, Zhengxing Wu
Computation and Language
Self-Distillation with Verbal Regularization
Jiazheng Li, Yawei Li, Junru Lu et al. (+7 more)
On-policy self-
distillation (OPSD) trains a large
language model using supervision from a teacher instantiated from the same model as the student. The teacher is conditioned on privileged information (PI), such as verified solutions. The student, which does not observe PI, learns from the teacher's next-
token distributions along its own sampled responses. However, PI can bias supervision toward shortcut
reasoning with limited verification or reconsideration, accompanied by a sharp drop in the
entropy of the output distribution. To address this challenge, we introduce self-
distillation with verbal regularization (VRSD), which uses system
prompts to regulate how the teacher uses PI, thereby encouraging rethinking and exploration to counteract premature commitment. Theoretically, we model prompting as attenuating the influence of PI on the teacher distribution and derive conditions for
entropy preservation. Across three models and four tasks, VRSD improves Pass@1 over OPSD in 11 of 12 model-task settings, by 3.9 percentage points on average, while generally maintaining higher
token entropy.
Read the full abstract ▾
All authors Jiazheng Li, Yawei Li, Junru Lu, Zhenyi Shen, Di Yin, Lin Gui, Xing Sun, David Rügamer, Xinpeng Wang, Yulan He
Machine Learning
A Production-Grade, High-Efficiency Agentic RL Framework for Frontier LLMs with Validated Recipes
LoonSage Team: Bowei Song, Caiwei Zhao, Chuwen Liu et al. (+44 more)
Reinforcement learning (RL) has emerged as a critical phase in the post-training pipeline of large
language models (LLMs). As the frontier of LLM capabilities shifts from static
reasoning to agentic tasks–characterized by external tool invocation, multi-turn interactions, and long-horizon decision-making–existing mainstream RL frameworks have grown increasingly unwieldy, raising the overhead of adoption, usage, and debugging. To address these challenges, we present LoongSage, an
agent-native, fully asynchronous RL framework with a lightweight core of roughly 14K lines of code. Built upon Megatron for distributed training and SGLang for high-throughput inference, LoongSage centralizes orchestration within a single controller process and encapsulates all GPU-resident components as Ray actors. It introduces AgentFlow, a unified execution paradigm that orchestrates both white-box and black-box
agents. For asynchronous execution, it integrates sliding-window strategies that bound trajectory staleness, and employs TransferMesh, a
topology-aware synchronization mechanism that routes weights after each step over the fastest transport available to each receiver. Beyond agentic RL, LoongSage incorporates a
memory-efficient Teacher Manager that decouples the scaling of teacher models from GPU
memory constraints, natively supporting Multi-Teacher On-Policy
Distillation. Extensive evaluations across four complete training runs, spanning complex reinforcement learning and multi-teacher
distillation, demonstrate that task rewards improve steadily while the train-inference gap is kept under continuous control, and the fully asynchronous pipeline removes synchronous idle bubbles, sustaining hardware utilization.
Read the full abstract ▾
All authors LoonSage Team: Bowei Song, Caiwei Zhao, Chuwen Liu, Dechuang Gu, Dong Fang, Feiyu Xie, Huaiyu Li, Hui Zhang, Jian Tian, Jian Wang, Jie Zhao, Liguang Li, Maoyun Wang, Meiyan Yang, Minghan Zhu, Pai Liu, Pandeng Yao, Renbao Tian, Ru Yang, Shuai Jia, Shuai Tan, Shuailong Li, Shuliang Li, Teng Jin, Tianze Yang, Wenbo Cui, Wenjing Bai, Wenkang Wu, Xiaowei Jiang, Xiaoyi Dong, Yanpeng Wang, Yanwen Wang, Yaohui Ma, Yawen Wang, Yihang Zhang, Yingjie Yan, Zhanbiao Lian, Zhenyu Lu, Zhida Hu, Zhihui Hao, Zhihui Hu, Zhiwen Xiao, Zhiyi Gao, Zhongwei Qi, Zhuangzhuang Wu, Ziqian Liu, Ziyue Zheng
Computation and Language
RIFT: Token Influence Follows the Path of Least Resistance
Tingan Jin, Shuhang Dong and Haosong Li
Which context
tokens drive a
language model's answer? Graph-based tools such as
attention rollout and
attention flow answer this from a single forward pass, yet their faithfulness in decoder-only models is rarely tested against interventions. We view the layers of a decoder as a causal network whose conductances are
attention weights, and read a
token's influence on the answer from the resistance between them. We propose RIFT (Resistance-based Information Flow in
Transformers), which scores a
token by the series resistance of its path of least resistance to the answer, found exactly by a classic shortest-path dynamic program. On synthetic in-context
retrieval tasks and extractive question answering over Wikipedia paragraphs, RIFT predicts the effect of replacing a
token with a Spearman correlation of 0.52-0.68; predicting a single replacement, it reaches 77-96% of the agreement between two different random replacements. It needs no gradients and no extra forward passes, scoring every
token of a
prompt in 0.9-3.4 ms on one CPU thread, whereas the replacement experiment needs a forward pass per
token. On 576 held-out
prompts from four models of two families (Qwen3 and Llama 3.2), it outperforms
token distance,
attention rollout and
attention flow in every pre-specified comparison, by 0.23 to 0.88 in mean Spearman correlation, and it is the best or tied-best of all
attention-based scores we test. Aggregates that add up all routes (
attention flow, effective resistance and rollout) instead mostly encode
token position: as a simple proposition shows, early
tokens have many more parallel routes to the answer.
Read the full abstract ▾
Machine Learning
DWI Connectome-based Sex Classification in Young using Supervised Variational Autoencoder
Aditya Kothapalli, Aaryan Gera, Sathvik Reddy V et al. (+3 more)
During adolescence, significant changes in
brain development are influenced by hormonal changes that impact both the body and the
brain. This study presents sex classification in 787 young adults having age range of 15-25 years using
Diffusion-weighted (DWI) structural connectome, focusing on 82 Desikan-Killiany atlas ROIs. A supervised variational autoencoder (SVAE) is used to extract latent space features from DWI connectome data. Although several studies explored differences in
brain structure and function between sexes, the main contribution of this study lies in incorporating SVAE to learn a compact, regularized latent representation for the task of sex classification. Initial exploratory data analysis shows that these features can capture the differences in sex-specific latent space patterns. Subsequently, the learned latent space SVAE features are fed to different ML models for sex classification. Among the considered ML classifiers, the multi-layer perceptron yields the highest accuracy of 80% in classifying sex. This demonstrates the effectiveness of SVAE in learning compact, informative representations from DWI connectome for sex classification. The present work highlights the potential of using DWI
brain connectomics and deep learning to differentiate sex, paving the way for future research on diverse populations that may include transgender individuals, to better understand sex-related variations in
brain structure.
Read the full abstract ▾
All authors Aditya Kothapalli, Aaryan Gera, Sathvik Reddy V, Ninad Aithal, Debanjali Bhattacharya, Neelam Sinha
Machine Learning
Rescuing Points Trapped Inside Incorrect Decision Regions: A target for Evaluating and Improving Forward-Forward Learning
Alireza Rahmansetayesh, Amirhossein Yousefiramandi, Maxwell Spiridonov et al. (+3 more)
Forward-Forward learning replaces end-to-end backpropagation with local, layer-wise training objectives. Its variants are evaluated primarily by classification accuracy, often measured with linear probes trained on their representations. We show that this evaluation can over-credit the learning method: a linear probe on the representations of an untrained convolutional neural network already reaches accuracy well above chance. Moreover, a single accuracy value does not reveal which datapoints become correctly classified after training and which remain misclassified. To examine what learning contributes beyond the random, untrained baseline, we present an analysis methodology built on the Boundary Proximity Index (BPI), a multiclass margin normalized by a class-centroid reference. We apply our analysis to seven Forward-Forward variants and related layer-local methods and find that initially misclassified points near the probe's decision boundary generally have higher rescue rates than those farther inside incorrect decision regions. Rescue rates vary substantially across methods, with some correcting a substantial fraction of these deeply embedded points. Together, these analyses offer a way to evaluate representation learning beyond accuracy and identify the rescue of points far inside incorrect decision regions as a target for improving local learning methods.
Read the full abstract ▾
All authors Alireza Rahmansetayesh, Amirhossein Yousefiramandi, Maxwell Spiridonov, Sumit Raut, Kent Ziti, Pierre Baldi
Databases
CellChain: Benchmarking Cross-Scale Evidence Use for Perturbation Reasoning
Xue Xia, Yue Wang, Shuizhou Chen et al. (+6 more)
Recent advances in foundation models and large-scale cellular perturbation
datasets have driven growing interest in using LLMs to predict and reason about cellular responses. Biological
reasoning in this setting involves relating molecular mechanisms, cellular responses, and functional outcomes across scales. Evaluating foundation models therefore requires assessing not only whether their predictions are correct, but also how those predictions depend on the biological evidence provided. We introduce CellChain, an experimentally grounded
benchmark comprising 590 biological cases and 2,360 matched evidence-condition instances across gene-dependency prediction, cytokine-axis identification, and drug-sensitivity ranking. CellChain links perturbation experiments and external biological resources through a provenance-aware evidence graph spanning molecular, pathway, transcriptional, and phenotypic information. Task-specific conditions vary evidence coverage, composition, or assignment while preserving questions, candidate answers, reference targets, and scoring rules. Across 18 foundation models, the highest accuracies under prespecified target-evidence conditions are 57.5%, 75.5%, and 70.8%, respectively, and broader evidence coverage does not consistently improve accuracy. On the drug-sensitivity
benchmark cohort, matched reference histories outperform swapped histories by an average of 13.0 percentage points in cluster-weighted accuracy. Decision-transition analysis separates corrections, newly introduced errors, and wrong-answer switches, revealing substantial answer changes hidden by small net accuracy differences. CellChain provides controlled comparisons for attributing changes in model predictions to prespecified expansions of biological context, including changes in evidence coverage, composition, and biological assignment.
Read the full abstract ▾
All authors Xue Xia, Yue Wang, Shuizhou Chen, Lang Yu, Hao Wu, Wenxuan Huang, Chengkai Yao, Zhangyang Gao, Siqi Sun
Artificial Intelligence
ChronoScribe: Semantic-Numerical Specialization for Instruction-Driven Time Series Forecasting
Yuchen Jiao, Miao Zhang, Yuxuan Liu et al. (+1 more)
Recent advances in instruction-driven time series forecasting highlight a fundamental tension: systems must simultaneously master natural-
language instruction following and precise numerical prediction. Current approaches often force a compromise. Large
language models (LLMs) can interpret unstructured requests but may be inaccurate when asked to produce forecast values directly, whereas time series foundation models (TSFMs) provide numerical forecasts but typically require structured inputs specifying the target series, context window, and horizon. We present ChronoScribe, which applies semantic-numerical specialization to this workflow. A LoRA-adapted LLM proposes an execution path and context length; deterministic rules resolve the executable configuration. On the specialist path, a frozen TSFM produces
quantile trajectories for the task-specified horizon. Deterministic trajectory summaries condition the response, while the LLM neither generates nor revises predicted values. We evaluate a Qwen3.5-9B–Chronos-2 implementation across 23 evaluation dimensions and 30 public
datasets against eleven proprietary direct LLMs and three open TSFMs. ChronoScribe has the lowest error on sMAPE, MASE, WAPE, RMSE, and MAE among all evaluated systems, including fixed-context controls. Across these metrics, even the lowest direct-LLM error remains 2.0–2.7 times the corresponding ChronoScribe error. At the system level, ChronoScribe achieves a Task-Level Score (TLS) of 65.5, 10.6 points above the strongest direct-LLM baseline. The results support ChronoScribe's division of labor, in which the LLM handles interpretation, configuration, and communication while the TSFM handles numerical forecasting.
Read the full abstract ▾
All authors Yuchen Jiao, Miao Zhang, Yuxuan Liu, Chengxi Li
Human-Computer Interaction
STEPwise: Supporting Teachers in Diagnosing Students' Mathematical Problem-Solving Skills through LLM-Generated Questions and Rubric
Yoonsu Kim, Hayeon Doh, Eunhye Kim et al. (+2 more)
Problem-solving is central to mathematics education. However, diagnosing where students'
reasoning breaks down requires individualized probing and consistent criteria that teachers cannot sustain at classroom scale. We introduce STEP (STage-based Evaluation of Problem-solving skills), co-designed with six mathematics education experts, which operationalizes problem-solving as four stages and eight diagnostic sub-skills. By specifying what evidence to elicit and assess at each stage, STEP enables an LLM pipeline to generate stage-specific questions and rubrics for any math word problem, reducing the manual design of diagnostic materials. An expert review (N=8) assessed the pedagogical validity of the generated materials and informed STEPwise, a teacher-in-the-loop system for diagnostic material generation and process-level assessment. In a classroom study with 5 teachers and 64 students, STEPwise helped teachers and students locate
reasoning breakdowns and supported students in reflecting on their
reasoning. Together, STEP and STEPwise offer a structured approach to fine-grained diagnosis at classroom scale.
Read the full abstract ▾
All authors Yoonsu Kim, Hayeon Doh, Eunhye Kim, Jinho Son, Juho Kim
Artificial Intelligence
Efficient Multi-Agent Reasoning via Confidence-Guided Adaptive Debate
Seungdong Yoa, Ye Seul Sim, Suhee Yoon et al. (+5 more)
Multi-
agent debate has shown promise for improving the
reasoning of large
language models, yet recent theory suggests its benefits are highly regime-dependent. While interaction can amplify informative signals under corrective conditions, symmetric debate dynamics are neutral in expectation, often making majority voting preferable. We reconcile these views by arguing that debate is effective only when invoked at the right time and with appropriate structure. Based on this insight, we propose LASE: Leader-Adaptive Structured Engagement, a leader-centric multi-
agent debate framework that selectively engages interaction only in non-neutral regimes. LASE introduces an asymmetric leader-supporter architecture that enables directed information flow and selective signal amplification, while defaulting to simple aggregation otherwise. Experiments across diverse
reasoning benchmarks show that LASE achieves multi-
agent-level performance with near single-
agent token cost, substantially improving efficiency over static debate and voting baselines.
Read the full abstract ▾
All authors Seungdong Yoa, Ye Seul Sim, Suhee Yoon, Sanghyu Yoon, Dongmin Kim, Soonyoung Lee, Bumsoo Kim, Junhyun Lee
Computer Vision
SyncReward: Human-Aligned Synchronization Reward for Audio-Visual Generation
Kaisi Guan, Ying Ba, Wenjing Wang et al. (+4 more)
Recent years have witnessed rapid progress in joint audio–visual generation. However, audio–visual synchronization remains a challenge, as generated
speech and sound often temporally misalign with visual events. A key bottleneck is the lack of human-annotated data, reliable evaluation
benchmarks, and synchronization-aware evaluation models for generated audio–visual outputs. To address these limitations, we conduct a comprehensive study spanning data, benchmarking, and reward modeling. We first introduce SyncReward-Data-80K, a
dataset containing 80K professional synchronization ratings for clips from eight audio–visual generators. A taxonomy-guided construction pipeline covers four sound-event families:
Speech, Onset, Instrument, and Ambient. We further construct SyncReward-Bench, a held-out
benchmark of 1K clips, each independently rated by multiple professionals. Using this
benchmark, we systematically evaluate specialized synchronization metrics and omni-modal models, revealing their substantial misalignment with human judgments. Finally, we develop SyncReward, a reward model that combines semantic–temporal contrastive pretraining on real clips with human supervision on generated clips. As an evaluation metric, SyncReward achieves the strongest agreement with human ratings among the evaluated methods. As a reward, it improves synchronization through inference-time best-of-$N$ selection and reinforcement learning based post-training. We will release the data,
benchmark, model, and code at https://github.com/WeChatCV/SyncReward.
Read the full abstract ▾
All authors Kaisi Guan, Ying Ba, Wenjing Wang, Xihua Wang, Chen Li, Jing Lyu, Ruihau Song
Computer Vision
WorldRoPE: Probabilistic World-Centric Rotary Embedding for Multi-View Attention
Mijeong Kim, Kyujin Lim and Bohyung Han
Rotary Positional
Embedding (RoPE) is widely used to encode relative positions in
Transformers. In multi-view settings, however, patch coordinates are defined independently in each image: the same 3D point can therefore have different coordinates across views, making them insufficient for establishing cross-view correspondences. We introduce WorldRoPE, a probabilistic world-centric RoPE for multi-view
attention. At each layer, WorldRoPE back-projects each patch
token into a set of volumetric Gaussian primitives in a shared world frame. These primitives represent multiple plausible 3D supports for a
token, jointly capturing alternative depth hypotheses, depth uncertainty, and the finite spatial extent of its patch frustum. When a key
token's support is projected into a query view, it induces a distribution over where that key may appear in the query image. WorldRoPE integrates the rotary operator over this distribution in closed form, combining rotations at the projected primitive centers according to their mixture weights with covariance-dependent attenuation. This makes
attention less sensitive to uncertain key locations in the query view, without rasterizing or warping
token features. The formulation reduces to deterministic RoPE when the support collapses to a point. Across layers, the predicted geometry guides cross-view
attention, while the updated features refine the geometry used at the next layer. Experiments on novel view synthesis, depth estimation, and 3D geometry reconstruction demonstrate the effectiveness of WorldRoPE for multi-view
Transformers.
Read the full abstract ▾
Cryptography and Security
Doctor Trigger: A Framework for Release-Bound Face Verification
Chia-Ming Lee, Chia-Yu Lin, Hung-Kai Huang et al. (+3 more)
Face swapping and generative editing enable realistic facial manipulation, while online redistribution complicates publisher oversight of circulating face images. Existing approaches establish provenance, detect manipulation, recover embedded watermarks, verify image integrity, or disrupt unauthorized face manipulation. These capabilities do not necessarily establish consistency with a specific publisher-enrolled release, limiting the evidence available for verification and human review. To address this gap, we introduce Doctor Trigger, a framework for verifying circulating faces against private publisher-held release records. Before publication, the publisher embeds a weak keyed
Fourier-phase signal in each face while preserving visual fidelity and stores its spectral reference. Afterward, verification compares the circulating face with that reference and uses key projection to measure retention of the release-specific signal. Therefore, relation and key evidence jointly help publishers identify suspicious copies for review, potentially reducing the circulation of manipulated images. Experimental results across FF++, DFDC, and Celeb-DF show that spectral agreement separates tested face swaps and generative manipulations from enrolled releases, while the keyed signal distinguishes published versions from their unreleased originals under the evaluated key-preserving benign transformations. Doctor Trigger complements provenance metadata with release-specific face verification and record-linked evidence for further assessment.
Read the full abstract ▾
All authors Chia-Ming Lee, Chia-Yu Lin, Hung-Kai Huang, Yi-Ting Ku, Yu-Chen Liang, Chih-Chung Hsu
Robotics
Toward Study on the Effects of Robot's Humorous Apology on Human's Trust Recovery
Gayoung Kim, Go-Eum Cha and Wonse Jo
Robot errors can disrupt human-
robot collaboration by reducing user trust and willingness to rely on the
robot.
Robot apologies can support trust recovery after such errors, but their effects may vary with apology strategy and error severity. This study therefore presents a user experiment based on a 2x2 between-subjects factorial design to examine the effect of humorous
robot apologies on user trust recovery and the moderating role of error severity. The design crosses
robot error severity (low vs. high) with apology strategy (generic vs. humorous). An online experiment will be conducted using the open-source Warehouse
Robot Interaction Simulator. Participants will complete a collaborative task, experience a
robot error followed by an apology, and report trust, trust recovery, interaction experience and reuse intention. We hypothesize that humorous apologies will produce greater trust recovery than generic apologies after low-severity errors, but that the advantage of humor will weaken or reverse after high-severity errors.
Read the full abstract ▾
Artificial Intelligence
TRAP: Tool-result Replay Attack for Probing Misbinding in LLM Agents
Yutong Zhi, Jie Zhang, Xiuqi Lu et al. (+2 more)
As AI
agents increasingly act through external tools, tool results are no longer simple outputs but execution artifacts that must remain correctly associated with the context that produced them. Yet as results persist across caches, recovery mechanisms, and shared runtime state, this association can break, causing a real and unmodified result to be consumed in an incompatible execution context and lead the
agent to an unsafe action. We characterize this failure as tool-result misbinding. To systematically study this failure, we introduce ReplayBench, a
benchmark that uses controlled tool-result replay to evaluate misbinding across 19 representative
agent scenarios, 4 failure properties, and 3 replay mechanisms. Across eight LLMs, three
agent frameworks, and diverse stateful workflows, we find widespread replay-induced failures, with a mean Final-State Error Rate of 0.649 under cross-task replay. Stage-wise analysis localizes these failures to model-side action generation. Further analyses show that replay susceptibility varies with task similarity, shows little dependence on object similarity, and remains high under result staleness and implicit environment changes. These findings motivate runtime validity mechanisms that eliminate final-state errors in our evaluated settings while preserving legitimate recovery. The results call for explicit contextual binding in tool-using
agent runtimes. Our work is public at https://github.com/Phitooo/Replaybench.
Read the full abstract ▾
All authors Yutong Zhi, Jie Zhang, Xiuqi Lu, Jiayuan Xu, Jing Shao
Computer Vision
BAT3R: Robust Online 3D Reconstruction with Bayesian Adaptive State Updates
Lijian Li, Yuanpeng He, Yudian Zheng et al. (+6 more)
Feed-forward
transformer models have driven remarkable progress in 3D
vision,yet their quadratic complexity renders them impractical for long
video sequences. Streaming 3D reconstruction addresses this bottleneck by processing frames sequen?tially with constant
memory. However, existing recurrent architectures inevitably suffer from progressive degradation over long sequences, as they fail to account for the intrinsic reliability of observations and the accumulated confidence of the historical state, leading to severe error accumulation. To address these issues, we introduce BAT3R, a training-free
Bayesian adaptation framework comprising two synergistic modules: State Innovation Gating (SIG) and
Bayesian-guided Adaptive State Updating (BASU). SIG acts as a distributional regularizer that anchors state
evolution to its
geometric initialization, effectively arresting representational drift during long-term inference. Building on this, BASU reformulates state update as a recursive
Bayesian inference process within a Kalman filtering framework. By jointly modeling the temporal reliability of observations via information-theoretic gain and spatial relevance via cross-
attention maps, BASU achieves an asymmetric spatio-temporal state fusion: well-consolidated historical regions are protected from redundant updates, while genuinely novel scene content is aggressively incor?porated. Extensive experiments on standard
benchmarks (7-Scenes, TUM, ScanNet, KITTI, etc.) demonstrate that BAT3R consistently outperforms state-of-the-art online 3D reconstruction methods, with the most significant gains observed on long sequences and complex scenes.
Read the full abstract ▾
All authors Lijian Li, Yuanpeng He, Yudian Zheng, Chung-ju Huang, Linyu Li, Dongming Jin, Wenpin Jiao, Zhi Jin, Chi-Man Pun
Computer Vision
Explicitly Aligned Multi-View Breast Cancer Risk Prediction from Variable-Length Screening Histories
Solveig Thrun, Zijun Sun, Suaiba A. Salahuddin et al. (+5 more)
Accurate breast cancer risk prediction from screening mammography is essential for improved risk stratification and personalized screening. It can benefit from both temporal breast tissue changes across longitudinal examinations and complementary anatomical information from craniocaudal (CC) and mediolateral oblique (MLO) views. Leveraging longitudinal information requires identifying corresponding tissue regions across examinations, yet most approaches rely on implicit feature
alignment without explicitly enforcing spatial consistency. Recent work has demonstrated the benefits of explicit temporal
alignment; however, existing methods model each view independently, preventing them from exploiting complementary CC and MLO information. Furthermore, explicit approaches have been limited to a single prior examination. To fill these gaps, we propose (github.com/sot176/FlexLMV-Net), a breast-wise longitudinal multi-view framework that jointly models CC and MLO views across screening examinations while accommodating a variable number of prior examinations. FlexLMV-Net explicitly aligns longitudinal feature maps and integrates complementary views through cross-view temporal fusion and a dual-stream
attention block. Evaluated on EMBED and CSAW-CC, FlexLMV-Net consistently outperforms existing approaches across breast density, cancer subtypes, and demographic subgroups, highlighting the benefits of explicit longitudinal
alignment, multi-view modeling, and flexible use of available screening history. We further introduce (github.com/sot176/BCRBench), an open-source
benchmark that unifies state-of-the-art single- and multi-timepoint breast cancer risk prediction models under standardized preprocessing, training, inference, and evaluation protocols, enabling fair and reproducible comparison of existing methods.
Read the full abstract ▾
All authors Solveig Thrun, Zijun Sun, Suaiba A. Salahuddin, Kristoffer Wickstrøm, Elisabeth Wetzer, Stine Hansen, Robert Jenssen, Michael Kampffmeyer
Information Theory
More Interactions Make Communications More Efficient: A Directed Information Bottleneck Approach to Task-Oriented Communication
Zhirun Zheng, Yiqin Deng, Phone Lin et al. (+1 more)
Task-oriented communication improves communication efficiency by transmitting semantic information required for downstream tasks, but may incur redundancy with previously transmitted information. To address this issue, we propose a variational directed information bottleneck joint source-channel coding (VDIB-JSCC) framework that transmits only previously unacquired information. Specifically, we use directed information to characterize the causal flow of task-relevant incremental information and theoretically demonstrate its advantages over mutual information and conditional mutual information. Based on this metric, we formulate a directed information bottleneck (DIB) objective that balances task-relevant information preservation and redundant information compression. We further derive a variational formulation, termed VDIB, whose tractable upper bound serves as the training loss. The encoder integrates a
Vision Transformer for frame-wise semantic extraction and a Mamba-based causal state-space model for capturing temporal dependencies and extracting incremental information, while the decoder uses a Mamba-based state-space model for task inference. Experiments on CIFAR-10 and CIFAR-100
video streams demonstrate that VDIB-JSCC achieves higher classification accuracy with less transmitted information than state-of-the-art semantic communication methods. These results show that leveraging historical knowledge enables task completion with less information, improving communication efficiency.
Read the full abstract ▾
All authors Zhirun Zheng, Yiqin Deng, Phone Lin, Yuguang Fang
Machine Learning
Probabilistic Simulation of Gas-Liquid Interfaces with Coupled Flow Matching on Spherical Harmonics
Kiet Bennema ten Brinke, Rachna Ramesh, Douwe Orij et al. (+2 more)
Bubbly flows involve strongly coupled bubble motion, deformation, and hydrodynamic interactions, making high-fidelity simulation computationally expensive. We propose a neural surrogate that jointly predicts bubble trajectories and interface deformation in a compact, shared representation, replacing costly mesh-resolved simulation with fast generative inference. Because two-phase flow dynamics is nonlinear and chaotic, we treat forecasting as a conditional generative problem rather than deterministic regression, predicting entire future windows in a single pass. We train and evaluate the surrogate on BubbleSH, a Front-Tracking
dataset of rising deformable bubble swarms, assessing performance using trajectory, shape, and distributional metrics over kinematic, morphological, and interaction-based properties. The surrogate reproduces key flow statistics while running several orders of magnitude faster than the underlying DNS solver.
Read the full abstract ▾
All authors Kiet Bennema ten Brinke, Rachna Ramesh, Douwe Orij, Ivo Roghair, Vlado Menkovski
Robotics
Imitation Learning of Avoidance Modes for Efficient Multimodal Model Predictive Control
Changyu Lee, Byung-Kwan Lee and Kanghoon Yoon
Multimodal model predictive control (MM-MPC) avoids local minima among moving obstacles by solving one optimal control problem (OCP) per combination of avoidance sides, so its computational cost grows exponentially with the number of decision-critical obstacles. We propose SideNet-MPC, which replaces this enumeration with a mode decision learned by imitating MM-MPC as an expert. A graph neural network is trained to predict the expert's minimum-cost mode, one avoidance side per obstacle. Its edges encode, for each obstacle pair, the gap predicted for the moment the vehicle first reaches either obstacle, so a neighbor that blocks a preferred passage can reverse the proposed side. The expert's selection rule compares its minimum-cost mode with the previously executed mode; SideNet-MPC keeps this rule and substitutes the network proposal for the minimum-cost mode. Hence at most two OCPs are solved per control period, and every applied input still comes from an OCP with control barrier function constraints rather than from the network. In $100$ seed-matched closed-loop Monte Carlo runs of mixed traffic, SideNet-MPC reaches $93\%$ of the expert's success rate and needs \SI{18.6}{ms} per control period on a single thread, 48% less than the expert's \SI{35.5}{ms} on sixteen parallel threads. In a controlled gap sweep, its proposed side reverses in the same gap interval as the expert's, whereas proposers without pairwise edges, trained on the same data, never reverse and all deadlock at the blocked gates of a deterministic scene.
Read the full abstract ▾
Artificial Intelligence
When a Conceptor Complement Becomes Gain: Operator Geometry and Behavioral Attribution in Language Models
Shuhul Razdan and R Balamurugan
When a steering intervention changes a
language model's behavior, which part of the intervention deserves the credit? We test this question for a target-centered, scaled conceptor complement by removing its fitted covariance filter while preserving the same target-specific center and gain. At the original aperture $\alpha=.05$ and gain $\beta=2$, all 21 fitted maps across three models and seven targets expand every direction at the generation intervention layers. The
matrix correction is $0.093\%$–$7.815\%$ of the matched-control displacement on held-out extraction activations. In 480 paired comparisons within a 1,920-response study, retaining the
matrix changes many individual texts but does not establish a consistent additional target-suppression benefit on the four-target panel. A
geometric aperture sweep shows that the operating regime changes with the filter setting. Separately, an invertible soft filter preserves what an unrestricted affine readout can recover, whereas dedicated erasure methods reduce prediction by newly fitted probes. Together, the results show why a whole-intervention comparison cannot by itself attribute generated behavior to the fitted
matrix: analyze the complete transformation, hold shared components fixed, and test its output consequences directly.
Read the full abstract ▾
Computer Vision
Anomaly-Guided Observation and Two-Level Semantic Feedback for Training-Free Video Anomaly Analysis
Hangil Park, Seungheon Kim and Tae-Kyun Kim
Training-free
language-based
video anomaly detection (VAD) uses frozen
vision–
language models (VLMs) and large
language models (LLMs) to localize abnormal events without task-specific model-weight optimization. Existing approaches increasingly exploit broader temporal and semantic context, yet generic context does not necessarily foreground abnormal events or specify how
video-level semantics should modify local anomaly scores. We introduce a training-free semantic feedback framework that uses VAD-guided active observation for
video anomaly understanding (VAU) and returns the resulting anomaly-focused description to refine temporal detection. Starting from an upstream anomaly-score curve, we adapt
reasoning-based iterative frame selection: high-score regions seed the observations, and anomaly scores together with VLM relevance assessments guide subsequent temporal exploration. A frozen
video-
language model generates a single open-ended anomaly description from the selected frames. The description is returned through two complementary feedback levels:
video-level feedback determines whether the score distribution should be suppressed, preserved, or sharpened, with selective visual rechecking, while local feedback retrieves event-related windows and promotes scores only after target-local visual verification. All model weights remain frozen, and feedback is applied once without regenerating the description. On the HIVAU
video-summary evaluations of UCF-Crime and XD-Violence, VAD-guided observation improves GPT-rated reasonability, detail, and consistency over the matched CLIP-guided variant. For VAD, semantic feedback improves the re-evaluated upstream detector from 84.36% to 86.25% AUC on UCF-Crime and from 68.07% to 72.58% AP on XD-Violence, where the final AUC is 91.74%.
Read the full abstract ▾
Logic in Computer Science · Cross-listed from math.NT
A Lean formalisation of the disproof of Ramaekers's conjecture
Jeremy Tan
We describe Redhill, a Lean formalisation of the major results in Hölzl, Kleine and Stephan's "Improved Lower Bounds for Strong $n$-
Conjectures" (arXiv:2409.13439). Design decisions regarding types and data structures are justified as enabling canonical versions of the paper's claims, and from there the most direct proofs of said claims. The formalisation process also uncovered many errors, omissions and optimisation opportunities in the informal proof, all of which are addressed in the final library. Although Redhill is meant to stand alone, a few lemmas were upstreamed to the primary Lean mathematics library mathlib. We discuss the tension between upstreaming and leaving lemmas in separate libraries. Unlike many other contemporary formalisation projects, Redhill was completed without any assistance from large
language models (LLMs). We compare our work with LLM-assisted projects, in particular an extension of arXiv:2409.13439 to $n=4$, aiming to establish design and style guidelines that define good Lean formalisations.
Read the full abstract ▾
Machine Learning
BehaviorFormer: Discovering Behavioral Patterns via Clusterable Next-Token Prediction
Tobias Schneider, Danial Fahrner, Soren Antebi et al. (+4 more)
Discovering behavioral patterns in open-ended games is challenging due to the lack of clear objectives or ground-truth annotations. In this work, we extend a next-
token prediction
Transformer with the deep clustering
algorithm DCSS to learn meaningful representations with well-separated clusters. In a controlled Minecraft session with 26 players, the method discovers 23 distinct behavioral patterns that generalize across the studied players, further refining structures present in self-supervised representations into clearly separable clusters. We group the clusters into seven interpretable categories covering stationary, roaming, travel, mining, base work, logging, and farming behavior.
Read the full abstract ▾
All authors Tobias Schneider, Danial Fahrner, Soren Antebi, Daniel Uedelhoven, Lennard Bodden, Sandra Halscheidt, Rafet Sifa
Computer Vision
Building age estimation based on widely available multi-source1 geospatial data
Jialu Sui, Hongsheng Zhang, Rui Liu et al. (+4 more)
Building age is fundamental for urban infrastructure safety, operation, and planning, as it directly affects structural safety, and sustainable development. Existing methods mostly rely on detailed building information such as street view, function, or materials, which are harder to obtain than geospatial data like satellite imagery and Digital Surface Models (DSMs). However, existing methods based on those geospatial data mainly rely on optical imagery and local texture features, limiting their ability to capture structural information and distinguish buildings from different periods. Moreover, the inherent temporal ordering among building age categories is often overlooked. To address these limitations, we propose the first deep-learning framework for multi-building age estimation using widely available multi-source geospatial data, including remote sensing data and their derived products, as well as building footprint information that estimates age at both pixel and instance levels within a unified pipeline. Specifically, a large pretrained backbone with fine-tuning adapters extracts representative features, and raster-derived and property-derived fusion modules support pixel-wise and instance-wise predictions. Pixel-level estimation employs a pyramid decoder with Cosine-guided Mixture-of-Experts (CMoE) to fuse multi-source raster data across scales, capturing fine-grained building age differences, while instance-level prediction uses
attention pooling and Property-Conditional Adaptive Instance Normalization (PCAdaIN) to extract instance-level representations and integrate property attributes. A Temporal Ordinal Constraint Loss (TOCL) enforces the sequential ordering of predicted ages. We also construct a building age
benchmark for Hong Kong to enable comprehensive evaluation. The source code and
datasets are available at https://github.com/littlebeen/RS-buildingAge.git.
Read the full abstract ▾
All authors Jialu Sui, Hongsheng Zhang, Rui Liu, Jing Ling, Ruisheng Wang, Hao Wu, Gang Chen
Artificial Intelligence
HyWe: Unifying Search and Operation for Real-World Hybrid Web Tasks
Zijian Cai, Haowei Liu, Kailai Chen et al. (+7 more)
Real-world hybrid web tasks need both information gathering and page interaction, yet search-based and operation-based
agents are developed and evaluated separately. To bridge this gap, we introduce HyWe, a framework that unifies both capabilities within one model and trajectory. Its two modes use dedicated
prompts and tool sets to sustain sub-goal execution; explicit switching selects the needed capability, and shared history lets each mode build on the other's findings. To provide demonstrations of these behaviors, we develop HyWeCollector, a fully automatic pipeline that uses task prototypes, four switching patterns, and multi-
agent synthesis to produce verified hybrid trajectories. We train HyWe-35B on these demonstrations to unify efficient information gathering and browser interaction in a single 35B web
agent. To evaluate hybrid task completion, we introduce HyWeBench: 100 human-written tasks on websites distinct from training, with human-written sub-goal checklists and an outcome-based evaluation pipeline. Hybrid training enables HyWe-35B to achieve 47.0% success on this
benchmark, improving on the untrained base model by 19.0 percentage points and outperforming existing search-based and operation-based
agents. Even before training, the same base model solves 28.0% of tasks with HyWe, versus 11.0% with all tools under one
prompt. Beyond hybrid tasks, HyWe-35B achieves 59.0% and 88.3% success on Online-Mind2Web and WebVoyager, outperforming existing open-source baselines and cutting action cost per successful task by 48.3% and 51.9% compared with Fara-7B.
Read the full abstract ▾
All authors Zijian Cai, Haowei Liu, Kailai Chen, Lin Peng, Cong Wan, Ziqi Zhang, Chunfeng Yuan, Bing Li, Weiming Hu, Haiyang Xu