Computation and Language
Hierarchical Wasserstein Merging for Multi-Domain Multi-Task Learning: From Specialists to a Generalist
Ming Cheng, Jiaying Gong and Hoda Eldardiry
Multi-domain multi-task learning (MD-MTL) aims to build a single generalist model that performs well across heterogeneous domains and tasks. However, joint training often suffers from interference under distribution shifts. Existing model merging methods mostly operate on model parameters while overlooking the
geometric structure of latent representation distributions across domains and tasks. To address these limitations, we propose Hierarchical Wasserstein Merging (HWM), a representation-level framework that models each domain-task specialist as a distribution of hidden representations on a shared support. HWM constructs task-level and global Wasserstein barycenters to capture within-task domain variation and cross-task structure, enabling either training-free specialist aggregation by Wasserstein-derived weights or training-based generalist learning through a hybrid Wasserstein
alignment loss. Experiments on four NLP tasks across four domains per task show that HWM achieves superior effectiveness and generalization capability in MD-MTL settings.
Read the full abstract ▾
Artificial Intelligence
From Concentration to Differentiation and Back: Routing Effective Rank in MoE Reasoning Cohorts
Kang Chen, Sihan Zhao, Yixin Cao et al. (+1 more)
Test-time scaling produces cohorts of
reasoning rollouts, yet there is no standard label-free account of how their internal computation reorganizes as inference unfolds. We introduce routing effective rank deff, the
entropy-effective dimensionality of a cross-rollout graph built from MoE expert-routing similarity. Across ten MoE configurations and five math/science
benchmarks, deff exhibits a reproducible low-high-low trajectory, with a prominent interior maximum in 98.5% of 3,105 model-question cohorts: routing similarity is concentrated early, maximally differentiated at intermediate budgets, and reconcentrated later, and the timing of this maximum varies systematically with architecture and
reasoning effort. An exact decomposition separates cohort-wide common-mode mass from residual spectral dimensionality: common-mode reallocation accounts for about two thirds of the trajectory, while the residual spectrum contributes about one quarter and retains substantial variation beyond the common mode. The decomposition further localizes behavior: among non-unanimous cohorts, increases in common-mode concentration strongly predict same-answer recoverability, and higher
reasoning effort delays the maximum by 2.59 octaves (doublings of the
token budget) and consistently expands the high-rank period across all four tested architectures, locating the effort effect in timing and duration rather than peak amplitude. Correctness comparisons separate structural monitoring from answer selection, positioning routing effective rank as a decomposable, label-free diagnostic of cohort organization - a principled spectral lens on how MoE
reasoning cohorts differentiate and reconcentrate over inference time.
Read the full abstract ▾
All authors Kang Chen, Sihan Zhao, Yixin Cao, Yu-Gang Jiang
Machine Learning
MetaRSI / RSI2: A Meta-Recursive Self-Improving System for Recursive Self-Improving Systems Themselves
Zihan Tan, Leixin Sun, Zitong Shi et al. (+28 more)
Recursive self-improvement (RSI) lets a system improve the model-building machinery from its own failures, so every later model inherits the gain. Yet RSI has been validated almost exclusively on coding and formal
benchmarks such as science QA and mathematics. This format bound limits RSI to improvement within a machine-checkable slice, not general capability where questions are open and correctness is settled by argument, replication, or measurement. We argue RSI must next operate across real, diverse scientific, engineering, and meta-scientific domains, not where formal evaluation is merely tractable. To that end we present MetaRSI-v1, where improvement is the scheduled composition of three typed operators over one unified paradigm. Data-RSI amplifies existing competence and marks its boundary; Harness-RSI edits a five-slot scaffold without touching weights; Model-RSI internalizes capability into parameters through bounded training. Sharing one loop kernel and artifact vocabulary, they make data, scaffold, and model changes composable rather than exclusive. A two-axis optimizer jointly decides operator order and each operator's proposal policy, while a meta-level policy revises the schedule across terms. We validate MetaRSI-v1 under the field's standard evaluations, on code and closed-form science, with no external teacher: the target model plays every role in its own loop. MetaRSI-v1 reframes self-improvement from a single-surface edit to a composition across the full model-production pipeline, opening two paths: a model route internalizing capability through training, and a harness route leaving weights untouched and thus extending self-improvement to any model reachable through an interface, with Data-RSI redefined as the shared substrate feeding both. The framework further yields refutable laws on where loops exist, how operators compose, and what supervision buys.
Read the full abstract ▾
All authors Zihan Tan, Leixin Sun, Zitong Shi, Yitao Liu, Jiajun Wu, Nathaniel Brooks, Jiaru Qian, Xiaoran Shang, Suyuan Huang, Yi Ding, Yangxu Liao, Mukai Li, Qiushi Sun, Shudong Liu, Xuankun Rong, Xiaohang Yu, Zhuo Chen, Hejia Geng, Chenxin Li, Aozhou Wang, Zengji Tu, Robert Tang, Yuxin Zhan, Eric Jiang, Yuxin Wu, Jianqing Zhang, Xiao Liang, Fang Wu, Haochi Zhang, Alexander Marlow, Guancheng Wan
Machine Learning · Cross-listed from stat.ML
Beyond Worst-Case Coreset Bounds for $k$-Clustering via Determinantal Sampling
Diptarka Chakraborty, Satyaki Mukherjee, Gaurav Vallabhdas Revankar et al. (+1 more)
Massive
datasets in modern machine learning have made data reduction a central challenge, particularly for clustering tasks where
memory and computational constraints demand compact yet faithful summaries. A standard approach is to construct an \textit{$\epsilon$-coreset}: a small weighted subset that approximately preserves the clustering cost for every plausible choice of centers. For the \textit{$(k,z)$-clustering problem}, existing worst-case bounds on coreset size are essentially tight, ruling out substantially smaller coresets in general. However, such worst-case instances are often unrepresentative of real-world data. In this work, we show that significantly smaller coresets are possible under mild and natural assumptions on the underlying data distribution. We introduce a new correlated sampling framework, called determinantal sampling, based on a novel application of determinantal point processes. Using this framework, we obtain an efficiently constructible $\varepsilon$-coreset for $(k,z)$-clustering in $\mathbb R^d$ whose dependence on $1/\varepsilon$ has exponent strictly smaller than $2$ when $d$ is fixed. This improves over the worst-case $\varepsilon^{-2}$ barrier under our beyond-worst-case assumptions. To the best of our knowledge, this is the first result that provably surpasses these lower bounds through beyond-worst-case assumptions. Finally, we validate our approach on synthetic and real-world
benchmark datasets, where it consistently achieves smaller coresets than existing state-of-the-art methods, even without explicitly enforcing the assumptions used in the analysis.
Read the full abstract ▾
All authors Diptarka Chakraborty, Satyaki Mukherjee, Gaurav Vallabhdas Revankar, Hoang-Son Tran
Artificial Intelligence
Building Trustworthy Graph-Agentic RAG for Social Good: Architectures, Failure Propagation, and Assurance by Construction
Vijay Bommireddy and Raviteja Bommireddy
Graph-agentic
retrieval-augmented generation combines structured evidence with adaptive controllers that can plan
retrieval, traverse relations, verify intermediate claims, delegate subtasks, and use tools. This combination is useful when answers depend on relations across documents, entities, time, or institutions, but it also creates coupled failure paths: a defect in graph construction can become retrieved evidence, alter later control decisions, and propagate toward a consequential outcome. We examine how such systems should be designed and evaluated for social-good settings in which freshness, authorization, traceability, oversight, and recourse matter alongside answer quality. We organize the literature by graph substrate, graph lifecycle,
agent function, coordination pattern, and authority boundary, and distinguish graph-based
retrieval from observation-dependent graph control. We then synthesize reported risks as an evidence-to-action failure chain and propose an assurance-by-construction blueprint comprising five interface contracts for evidence,
retrieval,
reasoning, capability and delegation, and outcome. These contracts make provenance, temporal validity, authorization, uncertainty, and recoverability explicit at system boundaries. An illustrative public-benefit information design shows how the framework constrains graph structure, permissions, abstention, and operating authority. Finally, we derive an evaluation agenda spanning graph assertions, trajectories, claims, coordination, and outcomes.
Read the full abstract ▾
Distributed Computing
Cops and Lethal Robber on Rings: A Distributed Perspective
Amanpreet Singh Saini, Ashish Saxena and Kaushik Mondal
The Cops and Robber game is extensively studied in the sequential setting where the main goal is to capture the robber. Capturing the robber means at least one cop, and the robber will be at the same vertex together at some time. There are several variants, including variants where the goal of the cops is to surround the robber. Surrounding the robber means there is at least one cop in each of the neighboring vertices of the robber's position. In this paper, we introduce it in the distributed setting while empowering the robber by saying it can even kill cops. Specifically, in our model, the robber moves in odd rounds and has unbounded speed, cops move in even rounds, and if one or more cops move into a vertex where the robber is currently residing, all these cops get killed. We call this lethal robber. This also connects our work to the Intruder Capture and Black Hole Search problems by introducing an entity which is dynamic as well as lethal, a setting that, to the best of our knowledge, has not been studied. In this work, we introduce the lethal robber, define the cops and lethal robber problem in the distributed setting and study it on a static ring of size $n$. We prove $n$ cops are not enough, even if all start from the same vertex, and provide an
algorithm starting from an arbitrary initial configuration that requires $n+\lfloor\log n \rfloor+4$ cops in the worst case.
Read the full abstract ▾
Machine Learning
Are Verifier Errors Independent Within a GRPO Group? Evidence from Qwen2.5 Rollouts
Esther Xin
Group-based reinforcement learning with verifiable rewards (RLVR) scoresmultiple completions per
prompt using automatic verifiers. Analysesbased on independent verifier errors may overlook dependence associatedwith shared answer formats. We investigate this dependence in24,998 groups of eight completions generated by Qwen2.5-1.5B onMATH, GSM8K, and DeepMath-103K. We estimate a pooled within-groupverifier-error correlation of 0.530 (95% confidence interval:0.500–0.560). Under an exchangeable-error model, this correspondsto a design-effect-adjusted effective sample size of 1.70 for aneight-completion group. Dependence varies substantially across answerforms: fractions, radicals, symbolic expressions, and intervals exhibitstronger clustering than unit annotations and percent signs. Replayinggroup-relative advantages across four rule-based verifier configurationsidentifies at least one advantage-sign disagreement in up to 0.83% ofgroups. Because a group is repeated sampling for one
prompt, thiswithin-group clustering may reflect shared
prompt difficulty as well asshared answer form, and we do not attempt to separate the two here.Unlike studies of correlated judgments across multiple evaluators, ouranalysis examines dependence across completions scored by the sameverifier. These findings motivate
prompt- and answer-form-aware analysesof verifier noise rather than characterizations based solely onaggregate error rates.
Read the full abstract ▾
Computer Vision
Scaling 3D Generative Priors to Large-Scale Scene Meshes from Multi-View Images
SangEun Lee, Wonseok Chae, Hoyoung Yoo et al. (+3 more)
Pretrained 3D generative models produce detailed geometry and appearance but are primarily designed for object-centric generation within a limited spatial extent. Recent approaches address this limitation by partitioning large scenes into smaller spatial regions and applying pretrained 3D generative priors to each region. However, scaling tiled generation to large multi-view scenes makes it challenging to maintain local
geometric continuity and global appearance consistency. We present a training-free framework for large-scale textured mesh generation from multi-view images. Our key idea is to scale tiled generation to large scenes with increased spatial detail while coordinating generation both locally and globally. We introduce local context tiled generation to improve
geometric continuity between neighboring regions and global appearance
alignment to reduce appearance discrepancies across distant regions. An adaptive scene decomposition further determines the number of tiles according to the input scene geometry. Experiments demonstrate improved
geometric and appearance fidelity over existing approaches while enabling fine-grained generation of large-scale scenes.
Read the full abstract ▾
All authors SangEun Lee, Wonseok Chae, Hoyoung Yoo, Geunyong Kim, NackWoo Kim, Hyeonjin Kim
Machine Learning
Parameterized and Streaming Algorithms for Euclidean Fair $k$-Center Clustering
Zeyu Lin, Chaoqi Jia, Longkun Guo et al. (+1 more)
Motivated by the growing importance of
fairness in machine learning, fair $k$-center clustering has attracted considerable research
attention as a fundamental problem. In this problem, a
dataset is partitioned into $m$ disjoint groups, and the objective is to select $k$ data points as centers, subject to upper bounds on the number of centers chosen from each group, aiming to minimize the maximum distance between any data point and its assigned center. Focusing on Euclidean spaces, which are ubiquitous in machine learning applications, we first develop a parameterized approximation
algorithm for Euclidean fair $k$-center with an approximation ratio of $2.732$. By incorporating this
algorithm as a post-processing stage into a one-pass streaming framework for large-scale data, we obtain an approximation ratio of $4.464$. These ratios can be further respectively improved to $2.414$ and $3.828$ with a runtime exponential on $k$. To ensure
polynomial-time complexity, we further design a one-pass streaming
algorithm with an approximation ratio of $4.732$, which can be further improved to $4.42$, outperforming the state-of-the-art ratio. Finally, extensive experiments show that our methods significantly outperform state-of-the-art approaches in terms of clustering accuracy.
Read the full abstract ▾
All authors Zeyu Lin, Chaoqi Jia, Longkun Guo, Chao Chen
Software Engineering
From Reading Code to Reading Spec: A Verified Layer for LLM-Driven Codebase Maintenance
Xinhao Zhang, Jingjie Lu, Kunpeng Liu et al. (+1 more)
The rapid growth of LLM-generated code increases software complexity and the maintenance burden on engineers. While LLMs offer a potential automated alternative, this structural complexity hinders their ability to manage codebases directly. We introduce the Provable Representation Of Original Functionality (PROOF), which manages codebases indirectly via structured specifications. To enable full-lifecycle codebase management strictly through these specifications, PROOF abstracts codebase
topology into a hierarchical natural-
language representation. To establish absolute trust, the system proves semantic equivalence by reconstructing source code exclusively from this specification. This verified foundation drives maintenance requests, executing code modifications while synchronously updating itself to prevent semantic drift. Experiments on real-world repositories confirm the effectiveness of these specifications.
Read the full abstract ▾
All authors Xinhao Zhang, Jingjie Lu, Kunpeng Liu, Fei Xie
Artificial Intelligence · Cross-listed from stat.ML
Recovering Weak Signals with Normalizing Flows
Sarod Yatawatta
In many scientific disciplines, weak signals of interest are obscured by dominant nuisance signals that are several orders of magnitude stronger. Recovering these weak signals requires subtracting the dominant ones; however, this calibration process inherently distorts or partially suppresses the underlying signal of interest. To address this problem, we propose the use of normalizing flow models to reconstruct calibration-affected weak signals. By leveraging the statistical invariance of the target signals and assuming minimal initial suppression, our framework effectively recovers the lost signal components. We provide a comprehensive theoretical overview of this normalizing flow-based recovery method and demonstrate its efficacy using simulated data.
Read the full abstract ▾
Computation and Language
Cross-Lingual Representation Alignment by Token-Level Optimal Transport in a Language-Agnostic Space
Taisei Yamamoto, Ryoma Kumon, Danushka Bollegala et al. (+1 more)
Cross-lingual
alignment (CLA) aims to align the representations of large
language models (LLMs) across
languages, enabling cross-lingual transfer to improve
multilingual capabilities. Previous CLA methods often ignore
language-specific information encoded in representations and only consider sentence-level
alignment, which may lead to suboptimal performance and input-output
language mismatch. We propose CAROT (Cross-Lingual
Alignment of Representations in a
Language-Agnostic Space via Optimal Transport), which consists of two steps: identifying
language-specific representations in LLMs' internal states and aligning
language-agnostic representations across
languages at the
token level by optimal transport, while explicitly preserving
language-specific representations. Inference-time steering experiments show that the representations computed by CAROT are effective
alignment targets, improving
multilingual performance by up to 11.2 points in accuracy while maintaining input-output
language consistency. We further use the representations obtained by CAROT as training targets, internalizing the aligned representations. The trained models outperform existing CLA methods in 11 of 18 evaluation settings (3 models $\times$ 3 tasks $\times$ ID/OOD
languages). Our work provides insights into what constitutes effective
alignment targets for CLA in LLMs. Code is available at https://github.com/ynklab/CAROT
Read the full abstract ▾
All authors Taisei Yamamoto, Ryoma Kumon, Danushka Bollegala, Hitomi Yanaka
Computer Vision
An Integrated Video-AI Platform for Action-Level Microanastomosis Training and Performance Feedback
Yan Meng and Daniel A. Donoho
Developing microanastomosis skill requires repeated practice with timely, action-specific feedback, yet expert review of lengthy microscope
videos does not scale to frequent or distributed training. We present an integrated
video-AI platform that turns a complete simulated procedure into inspectable, interactive feedback through three connected modules. First, a proposed
transformer segments the
video into six
surgical actions. Second, object detection and tracking localize instrument tips within each action; the resulting kinematic features and action statistics drive supervised classification of five NOMAT-aligned performance dimensions. Third, a grounded large
language model (LLM) uses these structured outputs to answer user questions about the current scene, actions, motion, and predicted performance through a unified interface. In a two-site study, 17 participants completed 72 procedures comprising 576 suture placements. The action-
segmentation module achieved 87.66% accuracy and 82.86% F1, increasing to 93.62% and 88.32% after workflow-aware refinement. The five performance classifiers achieved 76.0% mean accuracy, with Cohen's $\kappa$ from 0.63 to 0.93. Although the
language interface and educational benefit require prospective evaluation, these results establish the technical basis for an expert-supervised platform that can shorten review, expose the evidence behind performance estimates, and support scalable formative microsurgical training.
Read the full abstract ▾
Computer Vision
Multi-Grid Post-Training for Long-Form Multi-Shot Video Generation
Jiawei Mao, Haoqin Tu, Hardy Chen et al. (+8 more)
Generating long-form multi-shot
videos requires coherent within-shot motion and visually consistent narratives across shots. Existing
video generators favor continuous motion and struggle to present complete shot sets when an entire narrative is packed along one temporal axis. We propose MovieGrid, a Multi-Grid Post-Training paradigm that decomposes a long
video into shorter, temporally ordered chunks and arranges them on a spatial grid for joint modeling. This design reduces the number of shots handled by each temporal axis while enabling global information exchange across chunks. We construct the Multi-Grid Long
Video (MGLV)
dataset from 1,000 long-form
videos using source
video collection, hierarchical
segmentation, grid
video construction, and character-aware story annotation, producing 54K grid
videos paired with story
prompts. Our Noise-Free Random-Grid Training retains a random subset of chunks as clean visual context for denoising the remaining chunks. Grid
Embedding encodes grid structure, character-aware Story
Prompts link recurring entities, and Grid Boundary Loss stabilizes layouts. Under the same
token budget, MovieGrid generates 6.05 times more shots than Temporal Packing in a 1,616-frame
video. On a
benchmark spanning five real-world categories, it achieves state-of-the-art intra-shot consistency (0.9131 versus 0.8086 for HoloCine) and inter-shot consistency (0.5914 versus 0.5384 for StoryMem). MovieGrid can further scale
video length with minimal compromise through single or multiple generations.
Read the full abstract ▾
All authors Jiawei Mao, Haoqin Tu, Hardy Chen, Yuhan Wang, Keyang Xu, Jieru Mei, Hongliang Fei, Ruogu Fang, Wei Shao, Cihang Xie, Yuyin Zhou
Information Theory
Optimal-Access Cooperative MSR Codes: Parity-Check Matrix Construction And a Unified Transformation
Yaqian Zhang, Jingke Xu and Ya-Feng Liu
Cooperative MSR codes are a kind of storage codes which enable optimal-bandwidth repair of any $h\geq2$ node erasures in a cooperative way, while retaining the minimum storage as an $[n,k]$ MDS code. Each code coordinate (node) is assumed to store an array of $\ell$ symbols, where $\ell$ is termed as sub-packetization. To address the disk IO (input/output) capability, a cooperative MSR code is said to have optimal-access property, if during node repair, the amount of data accessed at each helper node meets a lower bound on this quantity. In this paper, we focus on reducing the sub-packetization level of optimal-access cooperative MSR codes. We propose new constructions of optimal-access cooperative MSR codes through two methods. At first, we propose a direct explicit construction by designing its parity-check
matrix. Such parity-check
matrix is built by repeatedly employing two crucial parity-check
matrices as building blocks. Secondly, we propose a generic transformation framework. Starting from an arbitrary $[n+d-k,d]$ MDS scalar code, one can derive a final cooperative MSR code by systematically applying two basic transformations. Both approaches yield $(n,k,\ell=\delta^m)$ optimal-access cooperative MSR codes with $\delta=d-k+h$ and $m=\binom{n}{h}-\lfloor\frac{n}{\delta}\rfloor(\binom{\delta}{h}-1)$. Compared with the state of the art (with $\ell=\delta^{\binom{n}{h}}$), the derived codes can reduce the sub-packetization $\ell$ by a fraction of $1/\delta^{\lfloor\frac{n}{\delta}\rfloor(\binom{\delta}{h}-1)}$, where $\delta=d-k+h$. Moreover, we also show that some previous code structures of optimal-access cooperative MSR codes and optimal-access MSR codes with $h=1$ are included as special cases of our transformation construction. At last, we note that all of the constructions are built over a finite field of linear size $\geq n+d-k$.
Read the full abstract ▾
Computational Complexity
Exponential Sampling Lower Bounds for Polynomial Sources
Yan Zhong
A degree-$d$
polynomial source is the output of a
polynomial map of degree at most $d$ over $\mathbb{F}_2$ on arbitrarily many uniform random bits. Khodabandeh and Shinkar (FOCS '26) proved that $\mathrm{Ber}(1/3)^{\otimes N}$ has statistical distance $1-o(1)$ from every constant-degree
polynomial source and conjectured exponentially small overlap. Independently of Khodabandeh and Shinkar, Byramji, Kane, Morris, and Ostuni (RANDOM '26) asked for an explicit target distribution at distance $1-\exp(-N^{\Omega_d(1)})$. We resolve both questions. For every fixed $d\geq1$, every degree-$d$
polynomial source has overlap at most $\exp(-c_dN)$ with $\mathrm{Ber}(1/3)^{\otimes N}$, where $c_d>0$ is independent of the seed length. For quadratics, $c_2=2^{-26}$ suffices. We amplify Khodabandeh and Shinkar's uniform separation of acceptance probabilities from non-dyadic parameters (numbers not of the form $a/2^b$ for integers $a$ and $b\geq0$). The result extends to other non-dyadic Bernoulli parameters and to coordinates that are Boolean functions of boundedly many bounded-degree
polynomials. We also give a uniform deterministic hierarchy between adjacent degrees. Appending the outputs of disjoint AND gates on $d+1$ inputs to uniform seed bits yields flat degree-$(d+1)$ target distributions of
entropy $k$ with overlap $\exp(-\Omega_d(\min\{k,N-k\}))$ against every degree-$d$ source, for $\min\{k,N-k\}\geq2(d+1)$. This
entropy dependence is optimal up to constants in the exponent among flat target distributions for fixed $d$. The construction has locality $d+1$ and uses $O(N)$ field operations to sample. At $k=\lfloor N/2\rfloor$, it handles $d\leq(1-\varepsilon)\log_2N/3$ with overlap $\exp(-N^{\varepsilon-o(1)})$ for fixed $0<\varepsilon<1$. The proof combines monotonicity of Gowers uniformity norms, pairwise independence of points in a random affine cube, and relative
entropy.
Read the full abstract ▾
Computer Vision
DualPathOcc: Dual-Resolution BEV Encoder for 3D Occupancy Prediction
Lihao Qiu, Jian Chen, Ruihao Wang et al. (+3 more)
Predicting 3D occupancy from multi-view images requires preserving
geometric detail during 2D-to-3D lifting while
reasoning over sparse, volumetric scene representations. We present DualPathOcc, a camera-based framework that combines a Spatial Enhancer for high-resolution feature aggregation before BEV compression, a SENet-augmented dual-path BEV encoder for local-global context modeling, and height-aware weighted cross-
entropy for near-ground occupancy. The final model is optimized with occupancy supervision and no explicit depth loss. On single-frame Occ3D-nuScenes, DualPathOcc achieves 37.37 mIoU. We further analyze how surface-centered depth targets interact with volumetric occupancy learning.
Read the full abstract ▾
All authors Lihao Qiu, Jian Chen, Ruihao Wang, Ramu Gautam, Mei Yang, Yingtao Jiang
Robotics
LANTERN: A Closed-Loop Benchmark for VLM-Based Cooperative Driving with Temporally Grounded Warnings
Yongshuo Liu, Xu Gao, Morui Zhu et al. (+5 more)
We present LANTERN, a closed-loop
benchmark for temporally grounded cooperative warnings. LANTERN separates warning onset, hazard onset, warning termination, and post-hazard recovery, and evaluates each physical event under matched warning and no-warning executions so that the warning's contribution is measured in isolation rather than confounded with onboard
vision. The
benchmark spans six safety-critical scenario families and provides 3,272 sequences with 236,309 frames for training, together with 120 matched route pairs for closed-loop evaluation. Each hazard route is evaluated under the warning and no-warning conditions, while its no-hazard control penalizes unconditional braking. We further introduce the Cooperative Unified Score (CUS), a safety-gated metric that jointly rewards route progress, anticipation, clearance, and recovery. Fine-tuning a representative VLM driving model raises CUS from 34.6 without warnings to 75.5 with them, demonstrating both the value of cooperative warnings and the discriminative power of the paired protocol. All resources will be made publicly available.
Read the full abstract ▾
All authors Yongshuo Liu, Xu Gao, Morui Zhu, Yongqi Zhu, Qi Chen, Deyuan Qu, Song Fu, Qing Yang
Machine Learning
Robust Conformal Consensus: Multi-Agent LLM-as-a-Judge Interval Evaluation with Conformal Prediction
Lihui Liu
LLM-as-a-Judge has emerged as a promising paradigm for evaluating natural
language generation. However, the uncertainty associated with such evaluations remains largely unexplored, which limits their reliability in real-world applications. Although conformal prediction offers a principled framework for uncertainty quantification, existing approaches typically apply it to a single LLM judge, overlooking the variability introduced by using different LLM evaluators. In this work, we propose a robust uncertainty estimation framework for multi-
agent LLM-as-a-Judge evaluation. Our approach constructs conformal prediction intervals for LLM-based scores from multiple LLMs. By considering intervals from different LLM judges, we obtain more stable and reliable uncertainty estimates. Extensive experiments demonstrate that our method produces valid prediction intervals with coverage guarantees, and that interval-based aggregation across multiple judges leads to more stable evaluation outcomes.
Read the full abstract ▾
Artificial Intelligence
AutoKD: Autonomous Knowledge Discovery
Qinwen Ge, Bo Ni, Haowei Fu et al. (+3 more)
Scientific discovery in data-rich domains is currently constrained by human bandwidth: the growth in the volume and complexity of real-world data far outpaces the rate at which researchers can read, reason, and synthesize. Recent LLM-based multi-
agent systems have begun to automate portions of the research cycle, but they target hypothesis generation in settings where validation cannot itself be automated, and each run is one-shot, with no mechanism for findings to accumulate or steer subsequent inquiry. This paper introduces AutoKD, a multi-
agent framework for autonomous knowledge discovery that is both computational and cumulative, allowing validated findings to persist and inform subsequent inquiry. Six coordinated LLM
agents collaborate in an open-ended discovery loop, where accepted findings are stored in a persistent insight graph that serves as both long-term
memory and an exploration-steering mechanism. We evaluate AutoKD on three diverse
datasets from two perspectives: Open-ended Quality against published findings, and Conditioned Quality via literature-derived queries. Across both evaluation perspectives, AutoKD covers known findings and surfaces substantive discoveries that complement human-driven research. Our code is available at https://github.com/GeQinwen/AutoKD.
Read the full abstract ▾
All authors Qinwen Ge, Bo Ni, Haowei Fu, Ngoc N. Tran, Erik Blasch, Tyler Derr
Emerging Technologies
multi-Stochastic Core Architecture for Scaling Probabilistic Ising Machines
Chirag Garg, Pratik Brahma, Saavan Patel et al. (+1 more)
Ising Machines offer vast potential to solve NP-hard optimization problems efficiently that are intractable to solve using conventional computing architecture. A lot of these optimization problems fall into statistical learnability and involve finding an optimal solution among many possible, near-analogous configurations, by searching in a non-convex energy landscape. In this context, the probabilistic Boltzmann machine architecture especially PASS (Parallel Asynchronous
Stochastic Sampler), explores and models the complex probability landscape pertaining to all possible configurations and excels in finding the ground-state energy solution of these intractable problems. Additionally, the noise-based
neuron architecture addresses the limitation of conventional annealing methods, which may get stuck around local minima. Here, we demonstrate a
stochastic sampling approach based on Block Gibbs Sampling to integrate multiple asynchronous PASS chips (four in this work), enabling improved scalability. Further, we demonstrate the scaling by mapping 784 nodes Max-Cut problem integrating 256 nodes PASS accelerator manufactured in 14 nm CMOS FinFET technology. PASS-enabled system with Block Gibbs Sampling protocol shows approximately 1000 times speedup for Max-Cut optimization compared to state-of-the-art methods implemented on CPUs and GPUs. The general applicability of this approach is further illustrated by solving a
quantum spin chain Transverse Ising system and accurately representing complex probability landscapes. Moreover, our results demonstrate the change in the scaling law to constant in the scaled-PASS accelerator as compared to exponential on GPUs enabling at least 4 orders of magnitude improvement in time-to-solution. Hence, the presented methodology enables the pathway for scaling of asynchronous
brain-like dynamics systems that do not follow any clock for its operation.
Read the full abstract ▾
All authors Chirag Garg, Pratik Brahma, Saavan Patel, Sayeef Salahuddin
Numerical Analysis
Vertex interpolation by bivariate $C^1$ cubic splines: counterexamples, geometric stability, and indecomposable defects
Junkai Qiu
We study vertex evaluation on the full space of continuously differentiable piecewise cubic
polynomials on a fixed planar triangulation. A complete dual description turns failure of interpolation into balanced edge weights with nonzero vertex loading. It leads to exact counterexamples with 17, 25, 31 and 41 vertices, each with one relation and the classical lower-bound dimension. The 31- and 41-vertex examples have interior graphs that are trees. We give a
geometric construction criterion for a sector-completion family and a certified implicit construction outside that family. With all boundary vertices fixed, the nearby bad configurations form a four-dimensional smooth locus in the 17-vertex case, two intersecting components of dimensions six and five in the 25-vertex case, and isolated transverse points in the two tree examples. A common Schur-complement estimate explains their different interpolation costs. We first realize arbitrary defect by decomposable chains of the 41-vertex example. We then construct obstructions from individually interpolatory blocks, prove that the capacity of one complete edge is exactly five, and build a fixed-square family with arbitrarily large strongly indecomposable defect. The latter excludes two triangle-disjoint connected normal bad submeshes even when those submeshes may have holes.
Read the full abstract ▾
Information Theory
A Graph Foundation Model for Large-Scale MIMO Detection
Xingyu Zhou, Le Liang, Hao Ye et al. (+5 more)
Large-scale multiple-input multiple-output (
MIMO) detection is fundamental to modern wireless networks but constrained by performance-complexity trade-offs. Existing detectors, whether classical or learning-based, often fall short in either scalability or generalizability across heterogeneous scenarios. To overcome these limitations, we introduce a wireless-native graph foundation model (GFM) tailored for large-scale
MIMO detection. The proposed GFM employs a physics-informed hybrid architecture, integrating the local correlation extraction of message passing neural networks with the global
attention of graph
Transformers, encoding the physical interference patterns from the expectation propagation
algorithm. Via extensive pre-training, this synergy enables the learning of a general-purpose detection mapping scalable across
antenna dimensions and channel conditions. For rapid downstream deployment, parameter-efficient fine-tuning is leveraged to adapt the GFM to specific non-ideal system regimes with minimal overhead. To enhance inference efficiency, a mixture-of-experts mechanism is embedded at downstream deployment to dynamically activate only the necessary sub-modules. Evaluations show that the proposed GFM consistently outperforms classical detectors and advanced data-driven baselines in accuracy, configuration generality, and cross-scenario transferability across various challenging zero-shot and few-shot conditions.
Read the full abstract ▾
All authors Xingyu Zhou, Le Liang, Hao Ye, Jing Zhang, Chao-Kai Wen, Xiao Li, Shi Jin, Wei Zhang
Computer Vision
NOVA: Normal-Side Modeling for Training-Free Zero-Shot Video Anomaly Detection
Wei-Chih Yin, Yun-Ching Kao, Cheng-Kuan Lin et al. (+1 more)
Training-free zero-shot
video anomaly detection (ZS-VAD) leverages
vision-
language models (VLMs) to localize anomaly instances from a predefined anomaly vocabulary, without providing any
video. Existing CLIP-based methods often emphasize anomaly-side semantics, while the competing normality side remains less carefully formulated. We identify two key limitations in existing solutions: (i) blurred decision boundary: normal
prompts may contain ambiguous verbs, such as running, that are semantically close to anomalies, reducing normal and abnormal separation in the VLM
embedding space; and (ii) modality gap: poor
alignment between features of textual normal anchors and visual frames. We propose NOVA, a training-free ZS-VAD framework that strengthens the normal side at both linguistic and visual levels. NOVA introduces Normality-Aware
Prompt Construction (NA), which excludes anomaly-adjacent verbs and biases normal descriptions toward static, low-motion scenes. To overcome the text-
vision modality gap, NOVA constructs a Visual Normality Anchor (VNA), which creates a weighted visual normal anchor from the initial frames of each test
video, providing a
video-specific normal reference without task-specific training or annotations. NOVA achieves 89.86 percent AUC on UCF-Crime and 95.07 percent AUC and 84.82 percent AP on XD-Violence, reaching state-of-the-art performance among comparable training-free zero-shot methods.
Read the full abstract ▾
All authors Wei-Chih Yin, Yun-Ching Kao, Cheng-Kuan Lin, Yu-Chee Tseng
Computer Vision
AGSA-Net: Abundance-Guided Self-Attention Network for Spectral Unmixing-Aware Hyperspectral Remote Sensing Image Classification
Nafisa Anjum, Satavisa Dey Borno, Ananna Saha et al. (+4 more)
Hyperspectral image (HSI) classification plays a vital role in remote sensing applications, including agriculture, environmental monitoring, and urban analysis. However, its performance remains challenged by high spectral redundancy, noise sensitivity, and the difficulty of jointly modeling local material composition and long-range spectral dependencies. To address this, we propose AGSA-Net, an abundance-guided self-
attention network that explicitly integrates spectral unmixing priors into the classification process. AGSA Net first estimates physically meaningful subpixel abundance maps subject to non-negativity and sum-to-one constraints, regularized by hybrid linear-nonlinear reconstruction decoder. The learned abundances are then used to construct an abundance affinity prior that guides a spectral
transformer to emphasize class-discriminative interactions, and the resulting
transformer features are fused with compact abundance descriptors for final prediction; in contrast to existing approaches that use abundance as auxiliary or concatenated features. Experiments on Indian Pines, Augsburg, and Berlin demonstrate the benefit of incorporating abundance- guided contextual modeling, particularly in heterogeneous urban scenes. The source code and trained models are available at: https://github.com/nnuvi/AGSA-Net
Read the full abstract ▾
All authors Nafisa Anjum, Satavisa Dey Borno, Ananna Saha, Mir Faiyaz Hossain, Sifat Momen, Nabeel Mohammed, Shafin Rahman
Computer Vision
MSCA-UNet: Multi-Scale Context and Attention U-Net for Image Segmentation
Sheng-Wei Chan
U-Net remains a practical baseline for image
segmentation because of its simple encoder-decoder structure and skip connections. However, the bottleneck representation is still dominated by a limited set of receptive fields, while decoder features are propagated without explicitly emphasizing the most informative channels and spatial locations. This paper presents MSCA-UNet, a U-Net-based
segmentation architecture that combines multi-scale contextual aggregation at the bottleneck with channel-spatial
attention refinement in the decoder. The multi-scale module uses parallel atrous convolutions to capture contextual features at different receptive fields, while Convolutional Block
Attention Modules (CBAMs) progressively recalibrate decoder features. Under identical experimental settings, the baseline U-Net achieves 96.9% mIoU on a held-out test set. Adding multi-scale context improves mIoU to 97.5%, while
attention alone reaches 98.4%. Combining both mechanisms yields 99.1% mIoU, a 2.2 percentage-point improvement over the baseline. Parameter analysis further shows that the
attention-only variant adds approximately 0.044M parameters, whereas the multi-scale module contributes most of the additional model capacity. The results support the view that multi-scale context enrichment and
attention-based feature refinement provide complementary benefits within a U-Net framework.
Read the full abstract ▾
Multiagent Systems
Adaptive stabilization of a leaderless bearing-constrained formation with disturbances
Minh Hoang Trinh, Chuong Van Nguyen, Quoc Van Tran et al. (+1 more)
In this paper, we consider the problem of regulating and maintaining a target formation characterized by a set of bidirectional bearing constraints under disturbances. The
agents in the formation are modeled by single integrators with deterministic bounded continuous disturbances of which both actual function and upper bound are unavailable for the control design. Due to the time-varying disturbances, the target formation is time-varying. We propose displacement/bearing-only based adaptive sliding mode control laws to uniformly asymptotically stabilize the time-varying target formation and reject the matched disturbances, and provide sufficient conditions to prevent possible collisions. A time-dependent adaptive design method is provided to convert the displacement-based control law to a bearing-only one. In addition, to alleviate chattering phenomena from sliding mode control, smooth adaptive control laws are introduced to guarantee uniform global boundedness of the desired formation. Finally, simulation results are given to support the analysis.
Read the full abstract ▾
All authors Minh Hoang Trinh, Chuong Van Nguyen, Quoc Van Tran, Tuynh Van Pham
Computer Vision
ChildGaze: A Benchmark Dataset for Collaborative Behavior Understanding in Children
Sindhuja Penchala, Saketh Reddy Kontham, Prachi Bhattacharjee et al. (+7 more)
Understanding collaborative behavior in children is important for analyzing social participation, peer interaction, shared
attention, and engagement during play and learning activities. Reliable recognition of these cues can support research in child development, educational analysis, and human-centered computer
vision. However, estimating where a child is looking does not necessarily reveal whether the child is actively participating in a shared activity. To support this higher-level analysis, we introduce ChildGaze, a child-centered behavioral annotation
dataset built on the ChildPlay
video collection [1]. ChildGaze introduces two behavioral labels, collaborative and non-collaborative, assigned independently to each child within a frame. The
dataset provides face, left-hand, and right-hand bounding boxes for children and adults and organizes the annotations at the row, person, and frame levels. The current release contains 27 annotated
video files, 10,641 frames, and 73,268 body-part annotation rows. Annotation reliability was evaluated on 1,187 frames using independent annotations from two annotators. The collaboration labels achieved 93.16% raw agreement and a Cohen's kappa of 0.8631, while bounding-box annotations achieved an overall mean IoU of 0.808. Baseline experiments with pretrained ViT and Swin
Transformer models achieved up to 97.44% child-person-level accuracy and 96.80% frame-level accuracy, respectively. These results show that ChildGaze provides a reliable
benchmark for studying collaborative behavior in naturalistic child-adult and peer interactions.
Read the full abstract ▾
All authors Sindhuja Penchala, Saketh Reddy Kontham, Prachi Bhattacharjee, S. Nima Mahmoodi, Daniel Fonseca, Sareh Karami, Mehdi Garemani, Sudip Mittal, Shahram Rahimi, Noorbakhsh Amiri Golilarz
Systems and Control
A Theory of Information Architecture for Networked Decisions: Freshness, Locality, and Coordination
Scott Moeller and Bhaskar Krishnamachari
Networked systems face a tradeoff between the scope of the information behind a decision and its freshness: a broader view of the system supports better coordination, but assembling and communicating it takes time, so it arrives older. We study this tradeoff for a team of
agents that repeatedly choose actions to minimize a shared quadratic cost driven by an environment that evolves on its own, unaffected by the
agents' actions. An information architecture specifies what each
agent observes, from where, and with what delay; we measure an architecture by the cost it loses relative to a decision made with complete, current information. We first compare fresh local observations with a complete but delayed global view. When every component of the environment decorrelates at a common exponential rate, this comparison reduces to a closed-form threshold on the ratio of delay to coherence time. We then study intermediate architectures in which each
agent acts on a time-aligned, and therefore older, snapshot of a wider neighborhood. The optimal neighborhood radius occurs where the marginal value of added scope equals the marginal cost of lost freshness. In a canonical spatial model, this radius is set by the spatial-correlation, decision-relevance, and temporal-propagation lengths. Throughout, architecture performance is governed by the predictability of the optimal decision rather than of the raw state.
Read the full abstract ▾
Machine Learning
Robust Dynamic Expansion for Continual Learning under Backdoor Attacks via Purification and Selective Recovery
Keyu Lin, Fei Ye, Qihe Liu et al. (+2 more)
Continual learning (CL) enables models to acquire new knowledge from sequentially arriving tasks while retaining previously learned knowledge. However, in practical scenarios, task streams collected from untrusted sources may contain
backdoor-poisoned samples, posing a critical challenge to the stability, plasticity, and security of continual learners. In this work, we investigate a challenging setting termed Continual Learning Under
Backdoor Attack (CLUBA), where each incremental task may involve a small proportion of maliciously manipulated training samples. Unlike conventional continual learning or
backdoor defense scenarios, CLUBA requires models to simultaneously mitigate catastrophic forgetting, preserve adaptation capability, and prevent the absorption of malicious supervision during sequential updates. To address this challenge, we propose a robust dynamic-expansion framework that integrates sample purification, selective recovery, and robust expert routing into a unified continual learning paradigm. Specifically, we introduce Bi-Prototype Purification (BPP) to identify suspicious samples by exploiting semantic discrepancies in feature space. Based on purified data, Gradient Discrepancy-based Robustness Optimization (GDBRO) selectively recovers informative poisoned samples through pseudo-label correction and gradient consistency evaluation, improving robustness while maintaining model plasticity. Furthermore, Robust Feature Consistency-based Expert Selection (RFCBES) constructs perturbation-aware class prototypes to enable reliable expert routing under corrupted or shifted inputs.
Read the full abstract ▾
All authors Keyu Lin, Fei Ye, Qihe Liu, Shijie Zhou, Jiguo Yu