Information Retrieval
Routing Between Generative and Collaborative User Profiles: A Serving-Time Gate for Controllable Novelty
Milad Sabouri, Neeraj Sharma, Sardar Hamidian et al. (+1 more)
Large
language models (LLMs) enable rich semantic user profiles for recommendation, but such profiles are more expensive to generate and are not necessarily desirable to deploy uniformly. We study whether LLM-generated profiles can instead be invoked selectively within a production recommendation pipeline. Using a real-world streaming
dataset covering movies, TV shows, and sports content, we train a serving-time routing gate that assigns each user to either a collaborative sequential recommendation model or a recommendation model driven by an LLM-generated profile. The gate uses only serving-time features and learns to identify users for whom profile-based routing can increase Novelty@10 while preserving ranking relevance. A routing threshold controls how aggressively users are sent to the generative model, exposing a tunable novelty–relevance trade-off. At an overall NDCG-loss budget of 5%, the learned gate increases Novelty@10 by 6.5% while routing 12.5% of users, outperforming simple heuristic and random routing policies at comparable relevance cost. These results show that LLM-generated user profiles can serve as a controllable complement to collaborative recommendation, while results with non-generative semantic profiles indicate that the benefit stems from selective routing rather than LLM generation alone.
Read the full abstract ▾
All authors Milad Sabouri, Neeraj Sharma, Sardar Hamidian, Shaghayegh Agah
Data Structures and Algorithms · Cross-listed from quant-ph
Provable Classical and Quantum Local Algorithms for Max-$k$-Cut and Quantum Advantage at Moderate Girth
Anuj Apte, Abid Khan, Edward Farhi et al. (+3 more)
Broadening the study of
quantum optimization
algorithms from binary to $k$-element alphabets has been shown to open new avenues for potential
quantum advantage. A
quantum advantage claim for approximate optimization requires showing that, under the same assumptions, an efficient
quantum algorithm provably achieves a better performance than can be proven for the best known efficient classical
algorithms. We study local classical and
quantum algorithms for Max-$k$-Cut on $d$-regular graphs of girth $g$. We advance classical
algorithms for this problem by developing a local vector
algorithm based on the explicit vector construction of Thompson, Parekh, and Marwaha (TPM). Our
algorithm gives the best provable cut fraction guarantee among known efficient classical
algorithms on regular graphs for $k\geq3$. To evaluate the performance of QAOA under identical assumptions of girth and regularity, we develop tensor network techniques for general $d$ and $k \geq 2$. In addition, using an equivalence to a coupled qudit–
boson system, we compute the QAOA performance in the infinite-degree limit. Together, these techniques give provable guarantees on QAOA performance on large graphs. Despite the improvements we introduce to the classical
algorithm, QAOA achieves a better cut fraction guarantee for depths $p\geq 9$, corresponding to girth $g\geq 20$, for both finite- and infinite-degree regimes. Thus, we obtain an apparent
quantum advantage from applying QAOA to the Max-$k$-Cut problem.
Read the full abstract ▾
All authors Anuj Apte, Abid Khan, Edward Farhi, Kunal Marwaha, Sami Boulebnane, Ruslan Shaydulin
Robotics
Looking Back to Move Forward: Temporal Verification for Generative Robot Policies
Haoxuan Wang, Wayne Wu, Yan Yan et al. (+1 more)
Generative policies have emerged as a promising paradigm for
robot learning, combining expressive generative action modeling with scalable imitation learning from large demonstration corpora. However, heterogeneous demonstrations can induce suboptimal action chunks whose errors compound over time, eventually driving the
robot into out-of-distribution states from which recovery is difficult. Action verification offers a test-time scaling strategy for mitigating this failure mode by sampling multiple candidate actions and using a verifier to select one for execution. Existing approaches, however, remain temporally myopic and costly to train, evaluating candidates from the current observation alone without accounting for trajectory continuity and often relying on large verifiers and additional expert demonstrations. In this paper, we introduce Temporal Verification (TeV), an efficient temporally aware action verification framework for flow-matching VLAs. TeV first learns a temporal
token that summarizes recent observation–action history, enabling candidate chunks to be evaluated as continuations of the execution trajectory rather than as isolated predictions. Conditioned on this
token, TeV constructs positive–negative pairs without additional expert demonstrations or preference annotations and trains an energy-based verifier contrastively to assign lower energy to higher-quality, trajectory-consistent action chunks. Beyond post-hoc ranking, TeV further uses the learned energy landscape to guide intermediate flow samples toward lower-energy regions, improving candidates before final selection. Extensive experiments in simulation and real-world settings demonstrate that TeV provides reliably ranks action candidates, improves task success rates, and produces smoother execution trajectories.
Read the full abstract ▾
All authors Haoxuan Wang, Wayne Wu, Yan Yan, Bolei Zhou
Machine Learning
Hard-Gate Candidacy in a Deployed Validator Suite
Xin Xu
Before a validator can be promoted to a hard gate on a deployment pipeline, it has to be shown that its firing separates outputs that reach users in working order from those that do not. We run that screen on 13 validators in a deployed generative
agent, against 550 runtime and 350 static builds labelled by downstream outcome, and report each check's marginal separation $J=\mathrm{TPR}-\mathrm{FPR}$ with Newcombe intervals and Fisher exact tests. Two checks survive correction for multiple comparisons, two more are nominal only, and the remaining nine are not distinguishable from zero, three of them because they never fired on any sampled build. Execution itself is not random with respect to the property being gated, and this replicates: across four runs covering 1,867 builds and ten distinct runtime checks, probes were skipped on 144 of 895 broken builds and 1 of 972 acceptable builds (per-run rates 15.6% to 16.6% against at most 0.3%), every skip carrying the same unsafe-to-probe reason. Because a skipped check is recorded as a pass, this imposes a ceiling that no check quality can lift: a check that needs a live artifact cannot operationally detect more than about 84% of broken builds in this harness. For the one check with construct-specific labels, a detector built for blank output fires on 0 of 90 human-labelled blank builds (95% upper bound on sensitivity 3.3%), and the global frame statistic it approximates separates the classes only weakly (AUC 0.59), so the gap is not a threshold that needs tuning. The same gap appears one layer up: on a census of tens of thousands of judge-scored builds, 32.5% of rejections carry no recorded issue at all. We argue that evaluation records must distinguish a check that ran and passed from one that did not run, must carry the evidence for a rejection, and that an inventory of checks is not evidence about a gate.
Read the full abstract ▾
Machine Learning
Cycle-Aware Autoencoder with Cross-SignalConsistency for Railway Door Anomaly Detection
Ammar Bouketta, Smail Niar, Hamza Ouarnoughi et al. (+1 more)
Passenger access doors are safety-critical subsystems in railway vehicles, yet detecting abnormal door behavior in real operation is challenging because faults are rare, diverse, and often unlabeled. This paper addresses railway door condition monitoring as a cycle-level unsupervised anomaly detection problem, where each complete opening-dwell-closing cycle is treated as a single monitoring unit. We propose the Temporal Cycle-Aware
Attention Autoencoder with Cross-Signal Consistency (TCAA-CS), trained exclusively on nominal cycles. It combines a dual-stream encoder that processes continuous physical measurements (position, current, voltage) and binary logical states (door-closed, door-locked) through separate 1D-CNN branches, an LSTM encoder with temporal
attention pooling, and a triple hybrid anomaly score fusing reconstruction error, latent-space deviation, and phase-aware cross-signal consistency. The consistency term helps identify cases where individual signals appear plausible but their inter-signal relationships become physically or logically inconsistent. On real industrial data from a passenger train in commercial service, TCAA-CS achieves 93.8% recall, 97.3% precision, and a 0.5% false-alarm rate, outperforming representative unsupervised baselines. System-level evaluation on an NVIDIA Jetson AGX Xavier supports the feasibility of real-time onboard deployment.
Read the full abstract ▾
All authors Ammar Bouketta, Smail Niar, Hamza Ouarnoughi, Eva Mutuzo Brindle
Machine Learning
Hyun Dong Lee, Xavier Gonzalez, Nicolas Zucchet et al. (+3 more)
Designing expressive sequence layers with efficient inference remains a central challenge in modern machine learning. Standard softmax
attention achieves excellent sequence modeling performance through rich nonlinear
token interactions, but it requires a key-value cache that grows linearly with sequence length, limiting its scalability. Linear
attention enables efficient recurrent computation with a constant
memory footprint, yet its reduced expressivity often yields inferior modeling performance. We introduce Switching Linear
Attention (SwiLA), a novel sequence layer that bridges this gap by enhancing representational capacity while retaining the fixed-size recurrent state of linear
attention. We derive the SwiLA recurrence from the test-time regression framework, casting the state update rule as online expectation-maximization in a mixture of linear regressions model. At test time, each output dimension dynamically selects among multiple linear
attention components based on the input. Across associative recall, in-context
language learning, and
language modeling
benchmarks, SwiLA shows strong performance and narrows the gap to softmax
attention, even surpassing it in several settings.
Read the full abstract ▾
All authors Hyun Dong Lee, Xavier Gonzalez, Nicolas Zucchet, E. Kelly Buchanan, Emily B. Fox, Scott W. Linderman
Computer Vision
TED:Text-Axis Evidence Decomposition for Prompted Anomaly Localization
JinYoung Kim, Geonho Kim, GiJeong Park et al. (+2 more)
CLIP is a powerful
vision-
language model, but it was not designed for fine-grained defect localization; CLIP-based anomaly detectors therefore adapt it with
prompts or lightweight modules to increase defect sensitivity. We show that stronger sensitivity does not necessarily make local evidence reliable: under domain shift, adapted CLIP-AD models often assign high anomaly scores to both true defects and visually complex normal regions. The issue is not simply missing defect information, but a local scoring rule that decodes defect and hard-normal evidence, having the same anomaly evidence. We propose TED (Text-Axis Evidence Decomposition), a post-hoc scoring method that asks whether each ambiguous response is better supported by source defect patches or by source normal patches mistaken as anomalous. TED compares these supports under the host's normal-versus-anomaly text response, leaves the backbone and
prompts unchanged, and requires no target-domain training. It works as a train-free score for raw VLM backbones or as a source-calibrated residual correction for adapted CLIP-AD hosts. Across frozen VLM backbones, TED substantially improves pixel-level localization over raw
prompt similarity; across adapted hosts, it improves most pixel-level settings over P-AUROC, P-PRO, and P-AP. Gains are largest under stronger hard-FP competition, with mean localization gain increasing from +5.0 in low-competition regimes to about +10.9 in mid/high-competition regimes. These results suggest that recoverable defect evidence can already exist in pretrained
multimodal representations, but reliable localization requires decoding it against hard-normal competitors. Code will be released at TED GitHub repository.
Read the full abstract ▾
All authors JinYoung Kim, Geonho Kim, GiJeong Park, Geonu Lee, YoungJoon Yoo
Sound
How Reliable Are Predicted MOS for Reproducing Human System-Level Preferences in Speech Enhancement?
Nahomi Kusunoki, Tsubasa Ochiai, Naohiro Tawara et al. (+4 more)
We investigate whether predicted Mean Opinion Scores (MOS) can reliably support system-level comparisons of
speech enhancement (SE) methods by introducing system-level preference accuracy (SPA). Although MOS prediction models are widely used to evaluate SE systems, their performance is typically assessed by correlation with human-rated MOS, which does not guarantee agreement on which system is better. SPA addresses this gap by directly evaluating whether predicted and human-rated MOS yield the same system preferences. Using SPA, we systematically evaluate three settings: single prediction models, ensembling, and domain adaptation. Through experiments, SPA varies substantially across single prediction models, from 9.4% to 76.8%. Even the best model disagrees with human judgments in approximately 23% of system comparisons. Ensembling yields only limited improvement, while domain adaptation tends to substantially improve SPA in the closed condition but brings only modest gains in the more practical open condition, where neither the target systems nor the speakers are known. These results suggest that SPA can reveal errors correlation-based evaluation alone does not expose, and that predicted MOS alone can lead to unreliable conclusions in practical SE system comparison.
Read the full abstract ▾
All authors Nahomi Kusunoki, Tsubasa Ochiai, Naohiro Tawara, Marc Delcroix, Naoyuki Kamo, Tetsuji Ogawa, Shoko Araki
Sound · Cross-listed from eess.AS
Improving Predicted MOS Scores, Not Perceived Quality: Multi-Predictor Test-Time Optimization of Enhanced Speech
Tsubasa Ochiai, Marc Delcroix, Nahomi Kusunoki et al. (+5 more)
Non-intrusive MOS predictors are widely used instead of subjective listening tests to evaluate and rank
speech enhancement (SE) systems. If they accurately reflect perceived quality, raising their scores should lead to higher-quality
speech. We present the first comprehensive analysis of test-time optimization for the SE task, which directly modifies the enhanced signal to raise the average of multiple MOS predictor scores. On seven systems from the URGENT 2026 challenge, we find that 1)~all the optimized predicted scores increase while reference-based metrics remain nearly unchanged, 2)~a non-optimized predicted score does not increase, and 3)~a MUSHRA listening test shows no improvement in perceived quality. These findings reveal a risk that such optimization can distort evaluations, e.g., biasing comparisons of SE systems regardless of their perceived quality. We believe these findings can inform future evaluation practices: they suggest that predictors used for optimization should not be used for evaluation, and that challenges should keep the predictors used for ranking undisclosed.
Read the full abstract ▾
All authors Tsubasa Ochiai, Marc Delcroix, Nahomi Kusunoki, Rintaro Ikeshita, Naohiro Tawara, Naoyuki Kamo, Tetsuji Ogawa, Shoko Araki
Computation and Language
A Missing Piece for Trustworthy AI Reviewers: From Benchmarking Rhetorical Robustness to SciCore Review
Chenguang Wang, Ming Li, Chengrui Fan et al. (+4 more)
AI reviewers can assign different judgments to manuscripts that report the same science in different wording, potentially rewarding rhetorical optimization over scientific improvement. We formulate Rhetorical Robustness as the joint requirement of stability across content-preserving rewrites and discrimination across papers. We introduce RobustReview, a controlled full-manuscript
benchmark with 1,260 manuscript versions, and evaluate 30 reviewer configurations. The
benchmark reveals false robustness, where low rewrite sensitivity coincides with score collapse across papers, and shows that human
alignment and rhetorical robustness rank reviewers differently. Moreover, the evaluated content-focused prompting protocol does not consistently improve robustness across backbones. Motivated by these findings, we introduce SciCore, a dual-branch reviewer that averages a full-manuscript judgment with a judgment based on an extracted, structured science core. This design combines manuscript-level assessment with a content-normalized view intended to reduce rhetorical sensitivity. In our primary GPT-5.5 comparison, SciCore achieves a leading joint stability-discrimination profile among the benchmarked reviewers while maintaining competitive human
alignment. These results identify rhetorical robustness as a distinct evaluation target and demonstrate the potential of science-core review to improve it.
Read the full abstract ▾
All authors Chenguang Wang, Ming Li, Chengrui Fan, Jianpeng Chen, Han Chen, Tianyi Zhou, Dawei Zhou
Artificial Intelligence
Search Shapes Conclusions: Auditing Evidence Selection Bias in Deep Research Agents
Shuyao Xiao, Shengling Wang, Xuan Chen et al. (+8 more)
Deep Research
agents synthesize evidence into cited reports, yet a well-cited report can still reach a misleading conclusion. Citation correctness checks whether cited sources support individual claims. It does not show whether adaptive search exposed a representative view of all documents made available for evaluation, which we call the candidate pool. Early findings redirect later queries, document choices, and stopping, so the documents an
agent reads form a selective sample. Existing evaluations rarely account for this selection. We formulate the problem as adaptive evidence sampling and introduce Causal Evidence Selection Correction (CESS). CESS predicts each candidate document's evidence direction and corrects the candidate-pool average using the logged probabilities of selecting each document and reaching each search round. Shrinkage stabilizes short searches, while intervals replace point estimates when some documents cannot be sampled. We also prove that estimating the average evidence direction of a common pool differs from measuring how a change in search policy alters the evidence read. The latter requires intervention. On questions from the MS2 systematic-review
benchmark, CESS reduces mean absolute error against the candidate-pool average by $9.2\%$ and reduces the estimate's change under opposing document rankings by $39.4\%$ relative to averaging the evidence scores of documents read. Across trajectories from a public Open Deep Research
agent, the corresponding reductions reach $60.1\%$ and $87.2\%$. A further 4,800 trajectories under paired interventions confirm that correcting a pool estimate and measuring a policy effect are different tasks. CESS therefore audits whether the evidence direction underlying a report reflects the documents available for evaluation, while a separate intervention analysis measures the effect of search decisions.
Read the full abstract ▾
All authors Shuyao Xiao, Shengling Wang, Xuan Chen, Ke Chao, Ming Cui, Feifei Qian, Chaoyang Mei, Fanlin Meng, Lulu Wang, Ziming Yu, Junxi Yin
Machine Learning
A Rank Graduation metric for Algorithmic fairness
Dalia Atif and Paolo Giudici
Fairness assessment in algorithmic decisions that affect individuals, such as credit scoring, often relies on parity measures calculated at the aggregate group level. Such measures may not reveal which individuals experience unfairness or which explanatory factors contribute to it. In this paper, we propose a rank-based framework that evaluates
fairness through the distribution of model prediction errors, thereby linking
fairness assessment with predictive accuracy and explainability. The framework combines Rank Graduation
Fairness (RGF), its integrated measure AURGF, a centered Cramer–von Mises permutation test, and a feature removal procedure for
fairness explainability. We evaluate the methodology using logistic regression, random forest, gradient boosting, and a multilayer perceptron. The simulation study shows that protected-group imbalance can reverse descriptive
fairness comparisons, whereas the proposed inferential procedure correctly distinguishes fair from unfair mechanisms. Its application to HMDA mortgage data produces model rankings that differ from those obtained with classical
fairness criteria. Tree-based models, rather than logistic regression, provide the strongest combination of predictive accuracy and rank-based
fairness, while the
fairness null hypothesis is rejected for all four models. The persistence of disparity across statistical, bagging, boosting, and neural network specifications, together with the feature removal results, indicates that the observed unfairness is not specific to a single
algorithm or predictor, but is associated with group differences embedded in the characteristics of the lending data. These findings support a broader approach to trustworthy artificial intelligence that combines predictive accuracy,
fairness measurement, statistical inference, and explainability.
Read the full abstract ▾
Computer Vision
Persistent Watermarking of Text-to-Image Models
Dixi Yao, Kaiwen Chen, Tahseen Rabbani et al. (+1 more)
Text-to-image (T2I) generation is gaining increasing popularity with the general public, motivating the development of reliable mechanisms for copyrighting such models given their expensive training costs. An adversary may obtain and reuse a pretrained T2I model without authorization, and then serve a modified version through an API service. Such modifications may arise from ordinary downstream adaptation or deliberate attempts to erase ownership, including input-
prompt preprocessing, model fine-tuning, and output post-processing. From the model owner's perspective, a key challenge is therefore to embed trigger data that remain persistent under such changes while preserving the model's normal image-generation capabilities. In this work, we propose a contrastive-style watermarking objective with a term that explicitly encourages the watermarked model to behave differently from the original model on trigger inputs. Experiments show substantially stronger trigger-data persistence than prior methods across a wide range of downstream modifications and deliberate attempts to weaken the watermark, resulting in higher detection rates, often approaching 100% TPR@FPR<$10^{-4}$.
Read the full abstract ▾
All authors Dixi Yao, Kaiwen Chen, Tahseen Rabbani, Tian Li
Human-Computer Interaction
When Attention Guardrails Become Barriers to Learning: Towards the Tipping Point
Meenakshi V., Pavani Ayinampudi, Aditya B. M. V. et al. (+5 more)
Online learning offers flexibility but lacks the structure of a classroom, where a teacher's presence guides
attention. The platform we study restores that structure by monitoring the learner through the webcam during ordinary coursework, interrupting or restarting a
video when the learner appears distracted. What such monitoring does to a learner across a whole course, rather than in a single examination, is largely unexamined. We report a convergent mixed-methods study of one monitored course pipeline in a summer internship program. We read two free-text surveys alongside three platform channels. The dropout exit survey yielded 15 analyzable responses; the persisting-learner reflection survey, 36. The channels are camera-verification telemetry (14,529 flags from 448 students), an in-
video emotion widget (615 submissions from 273 students), and a mandatory end-of-course survey (up to 634 respondents per item). Neither survey named monitoring, so every mention analyzed here was raised by the respondent. Focus-monitoring was raised by 18 of the 51 free-text respondents: 7 of 15 dropouts and 11 of 36 persisting learners. Among the dropouts who raised it, focus-monitoring was the stated primary cause of departure in 4 of 7 cases. None of the 18 questioned being observed in principle. What learners contest is the misreading of ordinary actions, drinking water or moving the head, and the severity of what follows a flag: a
video already watched returns to the start of its segment. These findings identify two targets for redesign: the severity of the response to a flag, and the environment check, which can flag a learner before any content has been seen. We argue that the proportionality of that response marks the point at which an
attention guardrail becomes a barrier to learning, the tipping point this study approaches.
Read the full abstract ▾
All authors Meenakshi V., Pavani Ayinampudi, Aditya B. M. V., Jinal Gupta, Prakash Hegade, Rohit Sharma, Sakshi Sharma, S. R. S. Iyengar
Software Engineering
From Verification Failures to Reusable Guidance for Coding Agents
Yuqing Zhai, Xiaohong Chen, Lingming Zhang et al. (+2 more)
Coding
agents need to establish that a program satisfies a specification and that the specification captures the requested behavior. We study how expert diagnosis of verification failures can become reusable guidance for this work. Our approach combines executable
language definitions in the K framework with a kit of procedures for constructing specifications, repairing proofs, and
auditing their adequacy. A human-guided development campaign on HumanEval, a
benchmark of 164 Python programming tasks, achieves a 164/164 success rate with the semantics and the kit, measured by final AI audit Pass verdicts after two targeted repairs. To examine whether
auditing detects problems that successful proofs leave unresolved, we construct 12 author-reviewed pairs of clean and defective packages. Every package passes its K proofs, and completed audits identify all defects and accept all clean packages. We then use KleverBench to test specification and proof construction for 31 programs with changed operator meanings. Comparisons with complete acceptance rules and equally long generic advice yield mixed results across two model and budget settings, motivating further work on selecting useful guidance within resource limits. Human-reviewed Optimism proofs establish expected pause reverts for six operations within declared input bounds under London semantics with unbounded gas. We report progress, difficulties, and lessons toward
agents that deliver programs with checkable correctness arguments.
Read the full abstract ▾
All authors Yuqing Zhai, Xiaohong Chen, Lingming Zhang, Sriram Vishwanath, Grigore Rosu
Computer Vision
Haiying He, Xin Zheng, Shaoli Hu et al. (+4 more)
Reinforcement learning (RL) has substantially improved the
reasoning ability of
multimodal language models through verifiable rewards and increasingly fine-grainedvisual or temporal credit assignment. In
video reasoning, however, current RL methods typically train with a fixed sparse frame budget: increasing the number of frames makes autoregressive rollouts expensive, while too few frames may miss temporally localized events and fine-grained visual details. We present Frame Differential On-Policy Self-
Distillation (FD-OPSD), which transfers the useful evidence of dense frame observations to a sparse frame policy during RL training. FD-OPSD compares the policy's
token level preferences for the same sampled response under sparse and dense views, and distills the resulting frame differential signal without an external teacher or dense autoregressive rollout. The method preserves sparse-frame rollouts and leaves inference unchanged. Across Qwen2.5-VL-7B and Qwen3-VL-4B on six
video reasoning benchmarks, FD-OPSD yields higher overall average performance than the strongest corresponding GRPO, T-GRPO, or
Video-KTR baselines across the 16, 32, and 64 frame evaluation settings. These results show that dense visual evidence can be transferred selectively during training through
token level self-
distillation while retaining sparse frame rollouts and unchanged inference.
Read the full abstract ▾
All authors Haiying He, Xin Zheng, Shaoli Hu, Shijun Xiao, Xuanhe Liu, Bing Li, Harry Yang
Machine Learning · Cross-listed from stat.ML
Minimax rates for learning spectral Barron functions by deep ReLU neural networks
Songqiu Ma and Yunfei Yang
We study how well deep neural networks approximate and learn spectral Barron functions. Recent studies have shown that these function classes can be efficiently approximated by shallow neural networks without suffering from the curse of dimensionality. We complement these results by providing new approximation bounds for deep networks with ReLU activation and establishing the minimax rates for learning these function classes. Specifically, we show that $d$-dimensional spectral Barron functions with smoothness index $s>0$ can be approximated by deep ReLU neural networks with approximation rate $\widetilde{\mathcal{O}} (S^{-\frac{1}{2}-\frac{s}{d}})$, where $S$ denotes the number of nonzero parameters in the network. Using this approximation result, we further show that deep ReLU neural networks can learn spectral Barron functions in a fast rate $n^{-\frac{d+2s}{2d+2s}}$ with $n$ training samples. Finally, we prove that this convergence rate is minimax optimal up to logarithmic factors.
Read the full abstract ▾
Machine Learning
Synchronous Multi-view Neural Diffusion
Yongquan Shi, Weijun Huang, Yueyang Pi et al. (+3 more)
Multi-view learning seeks to learn more comprehensive representations by exploiting the complementarity and consistency across diverse modalities or views. However, existing multi-view fusion strategies treat intra- and inter-view fusion as independent stages, without simultaneously considering the
evolution within views and the dependency across views. Such an asynchronous fusion paradigm inevitably constrains cross-view interactions due to conflicting view-specific structural inductive biases. As a result, information flow is prone to distortion and compression along intermediate pathways, confining the model to learn within a restricted solution space. To address this, we propose Synchronous Multi-view Neural
Diffusion (SynMDiff), which conceptualizes the multi-view feature space as a unified dynamical system driven by a
diffusion process. By modeling the
diffusion flow across arbitrary dyadic feature interactions in a joint space, SynMDiff enables the concurrent and adaptive intra- and inter-view information fusion. While a direct implementation of this synchronized mechanism incurs prohibitive computational costs, we further introduce an energy-based topological sampling strategy and an Ego-Net style centralized training architecture, ensuring both efficiency and scalability during learning and inference. Due to its conceptual elegance and computational efficacy, evaluations on real-world
datasets demonstrate that SynMDiff outperforms the baselines by a large margin.
Read the full abstract ▾
All authors Yongquan Shi, Weijun Huang, Yueyang Pi, Wendi Zhao, Yiqing Shi, Shiping Wang
Robotics
Make Code as Policy Great Again: Frontier Agents Write, Call, and Evolve Robot Tools
Shijia Ge, Alex Zhou, Jianshu Zeng et al. (+12 more)
Frontier models can control
robots, but
reasoning through every reach, grasp, and retreat makes manipulation slow and
token-intensive. We revisit code as policy with a different division of labor: models build executable tools, code handles multi-phase motions, and models decide what to do next. We introduce URAI (Universal
Robot-
Agent Interface), which couples a programming
agent that constructs
robot tools with an execution
agent that uses them in a feedback loop. The programming
agent writes reusable and task-specific tools from task intent and refines them through execution feedback and human guidance. The execution
agent selects and parameterizes these tools from current observations; each call runs a complete motion locally before returning control to the
agent. Unlike delegating subsequent decisions to a generated program, this design retains model-level decision-making between tool executions. Validated tool revisions persist across episodes without updating foundation-model weights, and a shared GUI and API make the same tools available to humans and
agents. Across five RoboDojo tasks and four frozen execution
agents, URAI raises aggregate success from 18.0% to 53.0% relative to direct fingertip control, with the largest gain on Swap Blocks; with the same tools, a program written in advance reaches only 24% against 56% for two
agents deciding after each call. Three of the four
agents also finish episodes 1.3-1.5 times faster with 1.5-1.7 times fewer execution-
agent output
tokens; DeepSeek-V4-Flash's cost barely changes. We further evaluate URAI on seven real-world AgileX dual-arm tasks, spanning object manipulation, cloth folding, and human-interactive tic-tac-toe. URAI connects the coding and decision-making capabilities of frontier
agents, organizing
robot control around reusable tools that
agents can both invoke and revise.
Read the full abstract ▾
All authors Shijia Ge, Alex Zhou, Jianshu Zeng, Yexing Wan, Di Wu, Zelin Zheng, Yazhe Wang, Zhiqi Jia, Xuan Shangguan, Jay Zhu, Yijun Liu, Lingyu He, Sihang Wu, Xiao He, Hongcheng Gao
Robotics
OccluDex: Hierarchical 3D Visuo-Tactile Representation Learning for Egocentric Dexterous Manipulation under Self-Occlusion
Ziheng Xu, Yueyuan Chen, Xinyuan He et al. (+6 more)
Reliable dexterous manipulation requires continuous estimation of object geometry and hand-object contact throughout interaction. With
egocentric sensing, however, the manipulating hand frequently occludes task-relevant object surfaces and contact regions, reducing the visual evidence available for state estimation and thereby making robust closed-loop control and generalization to unseen object geometries particularly challenging. To address this, we present OccluDex, a hierarchical 3D visuo-tactile representation learning framework that integrates global
geometric structure with local contact information for robust manipulation under dynamic self-occlusion during hand-object interaction. OccluDex adopts multi-scale masked autoencoding to progressively encode partial 3D geometry and fuses tactile contact
tokens with high-level
geometric features through cross-modal
attention. The encoder is pretrained from synchronized human visuo-tactile demonstrations and transferred as a frozen perceptual backbone for downstream reinforcement learning. We evaluate OccluDex on a faucet rotation task, requiring one full clockwise handle revolution, and a tabletop object reorientation task, requiring a 180-degree tabletop object reorientation without toppling. In simulation experiments, OccluDex demonstrated 12.6% higher accuracy for unseen objects and 8.3% higher accuracy for previously seen objects than the strongest state-of-the-art baseline models. Physical experiments were further performed with a Shadow Hand to demonstrate successful zero-shot sim-to-real generalization on unseen physical objects. This results could enable
humanoid egocentric object manipulation for seen and unseen objects even when the manipulating robotic hand occludes
vision.
Read the full abstract ▾
All authors Ziheng Xu, Yueyuan Chen, Xinyuan He, Guoxing Liu, Yuanshuo Tan, Huiming Pan, Bin He, Shuo Jiang, Peter B. Shull
Computation and Language
Evidence First, Arithmetic Second: A System Report and Failure Analysis for DocSem
Divya Godara and Sachin Gupta
EVICALC, our system for the DocSem shared task, achieved 8.61% joint accuracy on 1,730 tasks in the official final test evaluation. It reads a PDF, selects a passage, asks a
language model to write an arithmetic expression, and evaluates that expression in local code. Saved intermediate results support inspection of failures. A separate public-validation run achieved 92.17% answer accuracy and 1.00 evidence F1. The configurations and metrics differ, so these scores are not a controlled comparison. Our manual, post-hoc analysis is descriptive: in one inspected case, optical character recognition (OCR) and block grouping merged the relevant passage into another block, and the system answered from unrelated text. An exploratory study of reading page images on 100 documents returned evidence identifiers for only 22 documents. These descriptive findings motivate further evaluation; they do not establish the causes of the overall score.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from physics.med-ph
An Uncertainty-Guided Digital Twin Framework for Online Adaptive Proton Therapy in Head and Neck Cancer: A Feasibility Study
Yizhou Wu, Ryan J. Sanford, Huiqiao Xie et al. (+12 more)
Objective: Head and neck (HN)
proton therapy spans six to seven weeks of anatomical change, while offline replanning takes about a week. We present an uncertainty-guided digital twin (UGDT) framework that forecasts treatment-day anatomy before treatment and evaluate whether it generates online adaptive
proton therapy (APT) plans of clinical quality. Approach: A library of 302 longitudinal deformations from 88 previously treated HN patients was transported onto each new patient's treatment planning CT (TPCT) using two-step multi-atlas deformable image registration (DIR) built on a pretrained CT foundation model, generating about 284 predicted CTs (pdCTs) with contours per patient. Dispersion of propagated clinical target volume (CTV) contours defined a patient-specific robust margin. In ten patients, the quality assurance CT (QACT) triggering a replan represented treatment-day anatomy, and the physician-approved replan was the baseline. The pdCT most similar to the QACT (pdCT-H) and one from the lowest quartile (pdCT-L) were planned to within about 5% of baseline plan quality, forward-calculated on the QACT, and reoptimized to generate online APT plans. Main results: pdCT plans scored within -0.7% (pdCT-H) and -1.0% (pdCT-L) of baseline. Forward calculation on QACT reduced high-dose CTV D98% to 88.3% and 85.5%. After online reoptimization, D98% recovered to 98.3 +/- 0.3% and 98.2 +/- 0.3%, versus 98.5 +/- 0.4% at baseline. Spinal cord and brainstem doses remained below tolerance, and plan quality scores were within -1.1% (p = 0.19) and -1.7% (p = 0.01) of baseline. Significance: UGDT generated online APT plans comparable in quality to physician-approved offline replans using anatomy forecast before treatment, enabling a transition from reactive offline replanning toward anticipatory online adaptation.
Read the full abstract ▾
All authors Yizhou Wu, Ryan J. Sanford, Huiqiao Xie, Jie Ding, Shupeng Chen, Tung-Ho Wu, Ping-Hsiu Wu, Justin Roper, Jun Zhou, Minglei Kang, Bill Stokes, Sibo Tian, David S. Yu, Xiaofeng Yang, Chih-Wei Chang
Logic in Computer Science
Improved Tristate Multiplication With Formalization in Rocq
Nandakumar Edamana, Piyush P Kurur and Unnikrishnan Cheramangalath
We give a new multiplication
algorithm for tristate numbers improving upon the state-of-the-art implementation from the Linux kernel in terms of precision and formal proofs. Our
algorithm is significantly more precise as shown by experimental evaluation (at the peak, giving better results in 95.59% cases compared to the previous work for 31-bit samples). Importantly, we achieve this additional precision with performance comparable to the previous
algorithm, as demonstrated by
benchmarks. Finally, we formalize and prove the soundness of the
algorithm in the Rocq proof assistant, adding to the trust in the resulting implementation. Our
algorithm is now part of the upstream Linux kernel. Our soundness proof in Rocq for the new multiplication
algorithm works for all bit widths, while the SAT/SMT-based machine-checked proof accompanying the previous
algorithm was restricted to 8 bits. We also provide Rocq proofs for the soundness and optimality of the newly added tnum union operation and the existing tnum addition
algorithm from the Linux kernel. Our optimality proof for tnum addition presents a simpler and straightforward lemma compared to prior work.
Read the full abstract ▾
Information Retrieval
RouteRec: Behavior-Guided Sparse Routing for Sequential Recommendation
Junyeong Song and Jaemin Yoo
Sessionized interaction histories contain behavioral patterns that can improve sequential recommendation. However, existing models process all sessions through the same parameterized blocks, regardless of their behavioral differences. Mixture of Experts (MoE) enables conditional computation, but it leaves open what should guide expert allocation. We propose RouteRec, a sequential recommender that uses observed session behavior as the routing criterion. RouteRec summarizes four types of behavioral evidence from sessionized histories: interaction tempo, item-group focus, repetition and carryover, and popularity tendency. It uses these cues to route computation at macro, mid, and micro scopes. Cue-derived scores first select expert groups; within each selected group, the current backbone state then refines expert selection. Across six public
datasets and 18
dataset-metric combinations, RouteRec ranks first in 12 and second in three, yielding the best overall average rank of 1.61 compared with 4.11 for the next-best baseline. Additional analyses suggest that the behavioral cues guide expert allocation beyond added capacity and produce routing patterns aligned with observed behavior. Our code is available at https://github.com/jy1559/RouteRec
Read the full abstract ▾
Robotics
Function beyond Form: Functional Correspondence for Cross-Embodiment Dexterous Grasp Generation
Bolin Zou, Wenlong Dong, Mu Ai et al. (+4 more)
Cross-embodiment dexterous grasp generation remains challenging because robotic hands differ substantially in geometry,
topology, and kinematics. Existing approaches often lack explicit correspondences between structurally different hand regions that play similar functional roles in a grasp, a concept we refer to as functional correspondence. Consequently, their models tend to learn hand-specific interaction patterns rather than transferable grasp knowledge, limiting generalization to unseen hands. To address this limitation, we introduce FunCo-Grasp, which establishes functional correspondences across heterogeneous hand embodiments. Specifically, Functional Part
Alignment aligns each hand to a canonical functional schema by mapping physical links to shared functional parts according to their grasping roles, while Canonical Frame
Alignment expresses these parts in canonical local frames. These two
alignments provide a consistent representation for inter-part and hand-object interactions, allowing the model to learn transferable grasp knowledge across hands. Conditioned on the aligned hand representation and object geometry, a
diffusion model generates the target spatial arrangement of the functional parts, which are then converted into an executable joint configuration. Adapting FunCo-Grasp to an unseen hand requires only its
geometric and kinematic models and a one-time lightweight functional annotation, without target-hand grasp data, fine-tuning, or learned retargeting. In simulation on held-out objects from the filtered CMapDataset, we achieves average success rates of 92.40% on three seen hands and 74.02% on four unseen hands. In real-world experiments, the same model achieves an overall success rate of 76.00% on two unseen hands without additional training or fine-tuning. These results demonstrate the effectiveness of FunCo-Grasp in transferring grasp knowledge to unseen hands.
Read the full abstract ▾
All authors Bolin Zou, Wenlong Dong, Mu Ai, Chao Tang, Aoxiang Gu, Lipeng Chen, Hong Zhang
Artificial Intelligence
C-STRIDE: An Observation-Driven AI Digital Twin for Predicting Basin-Wide Flood Fields from Sparse Stream-Gauge Histories
Yanjie Tong, Phillip Si, Yuan Qiu et al. (+1 more)
Emergency managers need to know where floodwater is, how deep it is, and how it will change over the coming hours across an entire river basin. During a flood, however, real-time measurements come from only a handful of stream gauges, and high-resolution hydrodynamic models are too costly to rerun each time new data arrive or to run as large ensembles. We present C-STRIDE, an observation-driven AI digital twin that turns short records from a few stream gauges, together with terrain and rainfall, into basin-wide maps of water depth and extends these predictions up to a day ahead. It is trained on simulations from a calibrated two-dimensional hydrodynamic model and needs no separate data-assimilation step. In the Des Plaines River basin near Chicago, six gauges inform predictions over 4.2 million 30-m grid
cells. Terrain improves the predictions most, rainfall keeps errors from growing over longer horizons, and together they reduce errors by about 40% compared with gauge records alone. When future rainfall is known, errors remain near 15% one day ahead, compared with nearly 40% without rainfall. Given real instead of simulated gauge records, the model shifts its predictions toward the observed hydrographs at three of six gauges without retraining, and it runs about 150 times faster than the hydrodynamic model. These results show how sparse gauges, terrain, and rainfall can be combined into fast, continuously updated flood predictions, a step toward operational flood digital twins that still requires testing with real-time data and rainfall forecasts.
Read the full abstract ▾
All authors Yanjie Tong, Phillip Si, Yuan Qiu, Peng Chen
Computer Vision
When Integral Meets Decomposition: A Signal-Level Self-Supervised Feature Decompose Paradigm for Multi-Modal Image Fusion
Zeyu Wang, Jiayu Wang, Haiyu Song et al. (+1 more)
Multimodal image fusion (MMIF) aims to integrate complementary information from different modalities into a high-quality fused image and support downstream tasks. Recently, feature decomposition has become an important paradigm by separating source images into common and modality-specific unique features. However, existing methods lack clear supervision because ground-truth (GT) decomposition feature maps are unavailable. They usually combine multiple image-level metrics as losses, which are inherently incomplete and may conflict since each pixel couples attributes such as texture, edge, and contour. To address this, we propose a 1D signal-level self-supervised feature decomposition paradigm. Our core insight is to reformulate feature decomposition from unclear 2D image-level supervision into an integral-driven 1D signal-level optimization problem. This objective-level reformulation uses the 1D signal form to compute the integral constraint. The decomposer is optimized by the integral area between common and original signals, enabling more stable optimization with a clear optimization objective. Our model follows a two-stage SSL framework. Stage I designs dual pretext tasks for integral-driven decomposition at the signal level and structure-preserving reconstruction at the image level. Stage II fuses unique features and combines them with common features to reconstruct the fused image. Experiments on representative MMIF tasks show state-of-the-art (SOTA) performance. Code: github.com/Wangjiayu0512/SIDFusion.
Read the full abstract ▾
All authors Zeyu Wang, Jiayu Wang, Haiyu Song, Haoran Duan
Computation and Language
The Invisible Language Tax: Token Premiums of French and Regional Languages in 2026 LLM Tokenizers, and a French-Optimized Prototype
Thomas Serval
LLM services are billed per
token and context windows are measured in
tokens, yet the number of
tokens needed for the same content varies across
languages. We measure this
token premium on seven tokenizers of widely used 2026 models (OpenAI o200k, Llama 3, Qwen3, DeepSeek V3/V4, Gemma 3, Mistral Tekken, and the Claude generation-5 tokenizer via Anthropic's counting API) on NTREX-128 (124 non-English reference translations) and on the Universal Declaration of Human Rights for regional
languages. French requires 31% to 58% more
tokens than English, whereas Simplified Chinese ranges from 5% fewer to 40% more and is cheaper than French on six of the seven tokenizers. Regional and overseas
languages of France pay roughly 1.6 to 3.3 times the English count. We discuss how history re-sending, tiered pricing and fixed context windows amplify the absolute gap in agentic use. In a controlled experiment (BPE, Europarl, 50k vocabulary), adding French to tokenizer training data quickly reduces the premium, with diminishing returns and a growing cost for English. Finally, we present Baracoda FR v1.2, a byte-level BPE prototype with Tekken's vocabulary size. On a final test of six corpora never consulted during design, with a protocol declared fixed beforehand, it uses 11.5% fewer
tokens than Tekken on French and 3.7% fewer on English; results hold after removing test sentences overlapping the training data and with an equal ordinary-
token budget. It is worse on other
languages and, at comparable vocabulary size, does not outperform CroissantLLM. These are
segmentation results only; effects on model quality and task cost remain to be shown.
Read the full abstract ▾
Robotics
NEXUS: Perceptive Whole-Body Control for Terrain-Adaptive Teleoperation
Xiangyu Miao, Junsong Wu, Jiyuan Shi et al. (+6 more)
Whole-body teleoperation requires a
humanoid robot to reproduce a human operator's behavior even when their terrains differ. This demands that the
robot perceive local terrain and adapt its posture and contacts accordingly, rather than copy the operator's motion frame by frame. However, paired motion data linking the same behaviors across flat ground and different terrains remain scarce, limiting supervision for learning terrain-adaptive control. To enable whole-body teleoperation across mismatched terrains, we introduce NEXUS, a perceptive whole-body control framework that combines human motion commands with onboard sensory feedback. We first develop a scalable terrain-aware adaptation
algorithm that efficiently generates high-quality motion pairs across motions and terrains without per-motion or per-terrain tuning. Using a paired motion corpus totaling nearly 1,000 hours, we train a perceptive whole-body controller through teacher-student learning to reproduce commanded behaviors across terrains. Experiments demonstrate efficient, scalable generation of high-quality motion data and show that NEXUS combines broad behavioral coverage with terrain adaptability and tracking fidelity, outperforming existing whole-body controllers on the evaluated
benchmarks. Zero-shot real-world deployment enables real-time whole-body teleoperation on diverse unseen terrains, further validating the generalization of our method. Project website: https://nexus-
humanoid.github.io/
Read the full abstract ▾
All authors Xiangyu Miao, Junsong Wu, Jiyuan Shi, Weiji Xie, Jinrui Han, Xingyi Wang, Weinan Zhang, Chenjia Bai, Xuelong Li
Information Retrieval
When LLM-Inferred User Context Adds Value in Production Streaming Recommendation
Milad Sabouri, Neeraj Sharma, Sardar Hamidian et al. (+1 more)
Contextual information in recommender systems is shifting from static, predefined variables toward latent representations inferred from behavior. Large
language models support this shift by rendering an unstructured interaction history as a natural-
language summary, which yields a thematic user context that can be encoded and used in place of an aggregate profile. The conditions under which such generated profiles outperform aggregate
embeddings have received limited characterization mainly at the domain level. We evaluate semantic user-profiling strategies on a production streaming platform, ranking against the full catalog. The evaluation covers a 2*2 design space crossing representation type (aggregate or LLM-generated) with contextual scope (holistic history or
attention-fused short-term and long-term contexts). The relative ordering of the two representation types is conditional on the user's consumption regime. Aggregate profiles are consistently stronger under habitual consumption, which characterizes approximately four-fifths of the population, while LLM-generated profiles are stronger for exploratory users whose subsequent interactions diverge semantically from their history. We also observe a popularity-attractor effect in LLM-generated profiles, which modestly raises within-list diversity while substantially lowering catalog coverage and reducing novelty. These results indicate that a context-aware system can select a profiling strategy from the inferred consumption regime rather than applying one representation to all users.
Read the full abstract ▾
All authors Milad Sabouri, Neeraj Sharma, Sardar Hamidian, Shaghayegh Agah