Computer Vision
UniAfford: Token-Routed Multitask Learning for Generalizable 2D-3D Affordance Perception
Yuhao Liu, Yiming Zhong, Hanqing Wang et al. (+9 more)
Affordance perception aims to localize actionable regions supporting
embodied interaction, yet 2D and 3D affordance grounding have evolved as separate problems, with different task definitions, supervision formats,
datasets, and evaluation protocols. This fragmentation limits the learning of transferable object-affordance semantics across visual and
geometric spaces. We propose
Token Router for Tasks, a multitask training paradigm for MLLM-based systems that routes contextual hidden states to task-specific branches without requiring the
language head to generate predefined markers. Routed states are supervised directly by branch-specific objectives, enabling dense prediction losses to shape shared MLLM representations. We instantiate this paradigm as UniAfford, a unified framework for generalizable 2D-3D affordance perception, together with UniAfford-Data, a
dataset integrating pixel-level 2D annotations, point-level 3D annotations, and
language instructions under a shared object-affordance taxonomy, supporting heterogeneous supervision through semantic-level 2D-3D pairing. UniAfford adopts an MLLM as a shared semantic hub and a modality-aware
token router to produce image- and point-cloud-affordance queries. These queries respectively condition a SAM-style pixel decoder and a SONATA-based point decoder, enabling flexible 2D, 3D, and joint affordance inference from image-only, point-cloud-only, or paired
multimodal inputs. Experiments demonstrate strong zero-shot generalization across 2D and 3D affordance
benchmarks without target-specific fine-tuning, alongside state-of-the-art branch-wise performance under modality-isolated protocols. Ablations validate
token routing, joint 2D-3D supervision, and decoder coupling, while
language-head diagnostics show that routed latent states carry meaningful object-affordance semantics. Project page: https://4dvlab.github.io/UniAfford
Read the full abstract ▾
All authors Yuhao Liu, Yiming Zhong, Hanqing Wang, Shaocheng Yan, Yuhang Zhang, Wenzhou Lyu, Ziyang Ding, Wei Zhang, Xue Zhao, Jin Pan, Yuexin Ma, Xinge Zhu
Computer Vision
Beyond Attention Imbalance: Mitigating Hallucinations via Spectral Surgery
Siqi Lu, Suo Wei, Yongbin Zheng et al. (+3 more)
While Large
Vision-
Language Models (LVLMs) achieve remarkable success,
hallucinations remain a significant barrier to their reliable deployment. Recent studies primarily attribute these issues to cross-modal
attention imbalances; most solutions therefore focus on reweighting visual
tokens or suppressing
language priors. However, such approaches often overlook the spectral characteristics of the visual information flow and frequently rely on Contrastive Decoding (CD), which doubles inference time. Instead of following conventional approaches, we identify two distinct
hallucination patterns-Perceptual-Semantic Dissociation and Localized Fixation-and propose FLASH (Frequency-Localized
Attention SHaping), a training-free and CD-free framework. FLASH utilizes a Spectral
Vortex Score to detect
vision heads within multi-head
attention layers and applies adaptive spectral modulation to rectify the visual information flow during decoding. Empirical results demonstrate that FLASH achieves a superior balance between performance and efficiency compared to SOTA methods.
Read the full abstract ▾
All authors Siqi Lu, Suo Wei, Yongbin Zheng, Jianhang Yao, Wanying Xu, Peng Wang
Machine Learning
Efficiently Approximating Attention Is Hard
Lukas Haverbeck, Carmen Amo Alonso, Andres Felipe Posada-Moreno et al. (+2 more)
Softmax
attention is ubiquitous in modern machine learning, but its quadratic scaling with sequence length makes it costly. To reduce this cost,
attention is often approximated with fast
algorithms, which incur error but can still perform well in practice and on some inputs. At the same time, the growing diversity of
attention applications makes approximation guarantees that do not depend on particular input structure a compelling target. For such uniform guarantees over all inputs, known runtime lower bounds rule out fast
algorithms for near-exact
attention, but leave open the practically important regime: is there an efficient
algorithm with even a modest uniform approximation guarantee? We answer this question negatively. Under standard complexity-theoretic assumptions, no truly subquadratic
algorithm can approximate
attention with any nontrivial additive or relative guarantee uniformly over all inputs. This impossibility holds in the mildest parameter regime for which known
algorithms do not already achieve strong approximation guarantees in near-linear time, and extends to practically relevant relaxations: even after
polynomial preprocessing of the KV cache, no efficient
algorithm can obtain a nontrivial uniform approximation guarantee, or identify a small set of keys receiving substantial
attention under sparsity. Overall, our results settle the computational limits of uniform
attention approximation.
Read the full abstract ▾
All authors Lukas Haverbeck, Carmen Amo Alonso, Andres Felipe Posada-Moreno, Sebastian Trimpe, Marco Pavone
Computer Vision
Collision-Aware and Observation-Aligned Object-Centric Scene Reconstruction from Point Cloud
Yuxuan Xie, Xuan Yu, Rong Xiong et al. (+1 more)
Object-centric scene reconstruction requires completing partial object observations while preserving metric
alignment and avoiding collisions with the surrounding. Existing generation-based methods are often image-conditioned and suffer from scale ambiguity and insufficient
geometric constraints. We propose COOL, a framework for COllision-aware and Observation-aLigned reconstruction. Based on an object generation model, COOL conditions the generation on instance and background point clouds. Instance geometry anchors generation in scene coordinates, while background geometry provides local context for scene-consistent completion. We further introduce an explicit collision loss and use joint optimization and resampling to reduce collisions during inference. Experiments on 3D-Front and Scan2CAD demonstrate strong scene-level fidelity, observation
alignment, and collision reduction. Moreover, additional studies validate its robustness to mask errors and its applicability to real-world scene replicas.
Read the full abstract ▾
All authors Yuxuan Xie, Xuan Yu, Rong Xiong, Yue Wang
Machine Learning
Loss-Guided Pretraining Data Selection for Time-Series Foundation Models
Yike Li, Shaoxu Song and Jianmin Wang
Time series foundation models (TSFMs) are pretrained on heterogeneous collections containing billions of observations, yet their training windows are typically sampled without estimating whether they provide useful learning signal. We introduce a static data-selection framework that scores each window with a reference forecaster and retains an intermediate interval within every source
dataset. Specifically, we connect
forecasting loss to optimization difficulty by showing that normalized squared loss controls the per-sample gradient norm under a local Jacobian condition. We then define a reference loss score and apply
dataset-stratified selection to preserve the diversity of samples. Across various TSFM architectures, our method outperforms random selection by an absolute margin and even improves both relative MASE and CRPS over full-data pretraining by retaining fewer candidate pretraining windows. Further analyses show strong cross-scale and cross-architecture score correlations, indicating that a small reference model can often select data for larger targets, provided that the reference and target share compatible difficulty orderings.
Read the full abstract ▾
Social and Information Networks
Explicit objective functions in modularity-based community detection on multiplex networks
Elizaveta Evmenova and Petr Chunaev
Early, simultaneous, and late fusion combine network layers at different stages of community detection. Their modularity values consequently need not measure the same property of a partition. For normalized shared-node multiplexes, a unified comparison extends an existing two-layer identity: early fusion equals simultaneous fusion plus a weighted variance of community degree volumes. An elementary simplex argument explains simultaneous fusion's preference for single-layer weights. For a specified late-fusion construction, an additional transformation correction separates changes to the graph from changes to the objective. Exact small-network experiments and Louvain and Leiden experiments illustrate these distinctions. On label-free Cora, all objective-selected weights favor citations alone, while the fixed equal-weight mixtures achieve higher median adjusted Rand agreement with subject categories. The analysis provides a diagnostic for interpreting fusion objectives; higher objective values alone do not establish better recovery of externally defined communities.
Read the full abstract ▾
Computer Vision
V-JEPA Policy: Building Effective World-Action Models on Predictive Visual Latents
Yang Zhang, Jiangyuan Zhao, Chenyou Fan et al. (+4 more)
World-action models (WAMs) couple future visual-state prediction with action generation. By adapting
video generators or image-editing models pretrained at scale, a prominent line of recent WAMs inherits both predictive knowledge and the models in which it was learned. We ask whether a predictive visual latent space induced by large-scale predictive pretraining can instead provide a sufficient foundation for effective WAM learning without inheriting a complete pretrained visual generative model. To answer this question, we introduce V-JEPA Policy, a simple framework that builds a WAM on the latent space of a frozen V-JEPA 2.1 encoder. An instruction-conditioned future-latent predictor and a flow-matching action expert are jointly learned from scratch in a single downstream stage, with the predictor's future-informed context key–value states conditioning action generation. With 0.9B total parameters, of which 0.6B are trainable, V-JEPA Policy achieves competitive performance with representative WAM and
vision-
language-action baselines across LIBERO, LIBERO-Plus, and RoboCasa-GR1. Comparing visual foundations under the same downstream framework and training budget identifies V-JEPA latents as more effective than the discriminative, reconstructive, and
video-understanding-oriented alternatives, particularly under distribution shifts. Beyond task-specific learning, pretraining the predictor on DROID
video–instruction pairs without action labels and adapting it into a WAM yields substantial gains in downstream control and out-of-distribution generalization. Together, these findings establish predictive visual latents as a foundation for effective WAM learning from task-specific demonstrations and for transferring future-modeling knowledge acquired from broader in-the-wild
videos. Project page: https://breez3young.github.io/vjepa-policy/
Read the full abstract ▾
All authors Yang Zhang, Jiangyuan Zhao, Chenyou Fan, Jiayu Hu, Xiu Yuan, Chenjia Bai, Xiu Li
Computer Vision
Codebook-Guided Cross-Modal Knowledge Distillation for Structurally Heterogeneous Features
Dae Ung Jo, Jongin Lim, YoungJoon Yoo et al. (+1 more)
Cross-modal knowledge
distillation transfers knowledge from a teacher modality to a student modality. Existing feature-level
alignment methods typically assume that teacher and student features reside in structurally alignable representation spaces. However, this assumption does not hold when cross-modal features are structurally heterogeneous and lack clear unit-level correspondence, such as 2D spatial visual grids and 1D temporal audio sequences, thereby limiting the applicability of feature-level
alignment. To address this challenge, we propose a cross-modal
distillation framework that enables effective knowledge transfer across structurally heterogeneous feature spaces via a vector-quantized codebook. Specifically, teacher features are abstracted into a set of vector-form codes regardless of their original feature structure, and the selected codes serve as concept-level anchors for student learning. Code selection is guided by both task relevance and student compatibility, allowing the student to receive transferable teacher knowledge without requiring direct unit-level feature
alignment. Experimental results across diverse cross-modal
distillation scenarios demonstrate the effectiveness of the proposed framework on classification and semantic
segmentation tasks.
Read the full abstract ▾
All authors Dae Ung Jo, Jongin Lim, YoungJoon Yoo, Daeho Um
Machine Learning
Trident: Unifying Guarded Dispatch and Host Execution for PyTorch Triton Workloads
Jinjie Liu, Xiaoyan Liu, Shuhan Zhang et al. (+5 more)
User-written Triton kernels enable high-performance GPU computation within PyTorch, but their end-to-end latency can remain dominated by host-side orchestration, especially when device execution is short. Although torch.compile can generate native host wrappers for captured graphs, each invocation still passes through runtime-managed specialization lookup, guard evaluation, and preparation before reaching the wrapper. We present Trident, a compiler backend that removes this recurring overhead from the specialization cache-hit path. Trident introduces the Specialization Cache Module (SCM), which compiles guarded specialization selection, argument and execution-environment preparation, and host execution for multiple specializations into a single executable module. An invocation enters the SCM once, remains in compiled code when a specialization matches, and returns to Python only when a new specialization must be compiled. Built on Torch-MLIR, Trident lowers guards and host-side orchestration to native code while retaining calls to optimized runtime implementations of supported ATen operators. Our evalu- ation on two LLMs shows that Trident achieves up to a 1.47x speedup in model-level end-to-end latency over eager execution and up to 1.68x over torch.compile.
Read the full abstract ▾
All authors Jinjie Liu, Xiaoyan Liu, Shuhan Zhang, Wenjia Sun, Ruilin Yang, Chunlei Men, Yonghua Lin, Shaohua Li
Machine Learning
Differentiating Bisimulation Metrics: A Framework for Parametric Markov Chain Fitting via Bicausal Optimal Transport
Sergio Calo, Amy Zhang, Javier Segovia-Aguas et al. (+1 more)
Many problems in sequential decision-making, such as imitation learning from observations, state-space compression, world-model learning, and sim-to-real transfer, can be reduced to learning a model such that a notion of distance with respect to the target process is minimized. We consider this general framework and consider the bisimulation metric, equivalently Bicausal Optimal Transport (BOT), as the notion of distance to minimize. We show that BOT, since it can be formulated as a linear program (LP), is differentiable with respect to the model dynamics. We then derive an exact closed-form gradient via the envelope
theorem applied to the LP saddle point. The result is a general
algorithm, Differentiable Bicausal Optimal Transport (D-BOT), that can be applied to each of the problems above. The proposed
algorithm learns the best model by alternating between distance computation and gradient steps. We apply D-BOT for three different settings: state-space compression, parametric model learning, and imitation learning from observations (ILfO). We show empirical results that confirm the viability of all three instantiations.
Read the full abstract ▾
All authors Sergio Calo, Amy Zhang, Javier Segovia-Aguas, Anders Jonsson
Artificial Intelligence
Asking for What Was Never Requested: Horizontal and Vertical Proactivity in Agents
Ido Levy, Asaf Yehudai, Segev Shlomov et al. (+2 more)
An
agent that uses tools typically responds to what the user explicitly asks, yet completing the task may require information the user never requested. Work on proactive
agents mainly studies whether and when an
agent should act on its own, not what information it should pursue. We study a distinct axis of proactivity: its content. Horizontal proactivity pursues unstated information that the current context already identifies, and vertical proactivity pursues needs that only earlier evidence reveals. A need graph, recovered from a
benchmark's own decomposition, records which needs depend on which, so both forms, and whether the
agent stops at the right time, can be scored from a transcript without a model judge. To learn this behavior, we propose Q&D (questioner and drafter), which trains a questioner to prefer the question whose continuation retrieves more of the required evidence, with no reward model or judge. On held-out splits of three multi-hop question-answering
benchmarks, at equal
retrieval spend, the trained questioner improves both forms of proactivity over the same model, prompted, and outperforms a prompted model $15\times$ larger in the same role on two of the three, and the gain persists after controlling for question volume and length. Without further training, we place the questioner in an interactive customer-service
agent with a simulated customer, where it completes more tasks while asking fewer questions, and in retail it outperforms the $15\times$ larger model with fewer follow-up turns from the customer. These results show that proactivity depends not only on whether an
agent acts without being asked, but also on what it chooses to pursue and when it stops.
Read the full abstract ▾
All authors Ido Levy, Asaf Yehudai, Segev Shlomov, Asaf Adi, Leshem Choshen
Programming Languages
DatalogBench: Evaluating Large Language Models on Text-to-Datalog Synthesis
Yuan Li, Hanyun Jiang, Guowei Tian et al. (+2 more)
Datalog underpins
reasoning tasks such as program analysis, but its programs are hard to write. Existing synthesizers automate this task but require users to state their intent as input-output examples. Large
language models (LLMs) suggest a more natural route, text-to-Datalog synthesis from a natural-
language question, yet how well they do so has not been systematically evaluated. We present DatalogBench, a
benchmark of 136 text-to-Datalog synthesis tasks curated from existing Datalog-based artifacts. Synthesized programs are graded by execution on held-out inputs against an oracle validated by mutation analysis. Across six LLMs and four prompting configurations, exact match peaks at 68.4%, and relation descriptions or an input-output example have only modest, model-dependent effects. Under direct prompting, most failures occur at compile time, typically because a model invents auxiliary predicates that it never declares or types consistently. Two coding
agents reach up to 83.8% and eliminate nearly all such failures, leaving mostly semantic errors concentrated in recursive tasks. DatalogBench thus identifies recursive
reasoning and decomposition as open challenges for current LLMs and
agents, and offers a reliable, execution-grounded measure of both.
Read the full abstract ▾
All authors Yuan Li, Hanyun Jiang, Guowei Tian, Chengpeng Wang, Peisen Yao
Computer Vision
Seeing Is Not Addressing: Auditing Linguistic Access to Frozen Visual Geometry
Woosang Jeon, Jiwon Yang, Soo Chung et al. (+1 more)
Visual distinctions are often finer than those reflected in linguistic conceptualization.
Vision-
language models exhibit a similar asymmetry: a distinction can remain discriminable in frozen image geometry while being weakly addressable through the native text interface. We study this gap by separating visual discriminability from linguistic addressability in text-to-image
retrieval. Using FactorAtlas, a fully crossed testbed of 23,040 images spanning shape, hue, pattern, and nuisance variation, we compare both readouts on held-out images of the same distinctions. We then derive image-side contrasts that separate each value from its alternatives for matched visual grounding, and test whether this reduces the native-text access gap across factors and models. Direction-specific and visual-absence controls tie these gains to the relevant visual contrast; the gains persist after global
alignment and extend to compositional
retrieval and natural images. Together, these results show that visual discriminability and linguistic addressability need not coincide, and that matched visual grounding can probe and reduce the resulting access gap.
Read the full abstract ▾
All authors Woosang Jeon, Jiwon Yang, Soo Chung, Taehyeong Kim
Computer Vision
AESOP: Asymmetric Human-Camera Generation with Translation-Intensity Control
Jingzhong Lin, Zhanke Wang, Heng Li et al. (+9 more)
Human motion defines an action, while a camera trajectory determines how it is presented. Camera generation for a given human motion and joint human-camera generation are usually treated as separate tasks, although both share an asymmetric dependency: human motion can be generated independently, whereas the camera responds to the realized action. We introduce AESOP, a unified framework with an independent human pathway and a shared human-conditioned camera generator. Its asymmetric architecture serves both tasks while preserving the human output during camera generation. Although human context anchors the shot to the action and camera text describes its movement, translation intensity remains underspecified. We therefore construct trajectory pairs that differ in camera translation magnitude while sharing human motion and camera text, then use these pairs to learn an explicit intensity condition. Experiments on the PulpMotion
dataset demonstrate strong camera distributional and framing quality in both tasks and effective control over camera translation intensity. Project page is available at https://ripemangobox.github.io/AESOP.
Read the full abstract ▾
All authors Jingzhong Lin, Zhanke Wang, Heng Li, Wenxiang Liu, Zhao Zhang, Kecheng Tang, Dongdong Xiang, Changbo Wang, Di Kang, Chunchao Guo, Linchao Bao, Gaoqi He
Machine Learning
Interacting particle guidance for sampling reward-tilted generative priors
Adhithyan Kalaivanan, Zheng Zhao, Jens Sjölund et al. (+1 more)
Inference-time steering adapts pretrained
diffusion and flow-based models to new tasks, e.g., to generate samples from a conditional distribution or samples with desired properties, without retraining. This can be formalized as sampling from a reward-tilted generative prior. As exact sampling from this distribution is intractable, guidance-based methods rely on approximations producing biased samples, and sequential Monte Carlo (SMC) methods correct for this bias using importance weights. However, while exact in the large particle limit, SMC suffers from weight degeneracy and particle collapse in practice. We propose interacting particle guidance (IPG), which replaces reweighting with transport. The particles interact through an additional drift, derived from the Feynman–Kac PDE to cancel the reweighting term, and remain unweighted. Choosing the drift in a reproducing kernel
Hilbert space yields a closed-form solution that is cheap to compute, with negligible overhead compared to SMC. We demonstrate the method on Gaussian mixtures with known posteriors, and on high-dimensional image inpainting and
protein structure inference tasks.
Read the full abstract ▾
All authors Adhithyan Kalaivanan, Zheng Zhao, Jens Sjölund, Fredrik Lindsten
Computation and Language
Follow the Entities: A Corpus Map for Agentic Search
Soyeong Jeong, Sujay Kumar Jauhar, Sung Ju Hwang et al. (+1 more)
Answering questions and completing tasks over large document collections often requires connecting evidence spread across multiple documents, such as a project's approval recorded in one, its requirements in another, and its latest status in a third. Recent LLM
agents approach this by iteratively searching the full corpus rather than reading only a fixed set of top-ranked documents. However, when the corpus is exposed only as a flat collection of files, a relevant document gives no indication of how it relates to others, so the
agent must rediscover these relationships for every query, often missing complementary evidence while simultaneously consuming substantial additional
tokens. To address this, we introduce CorpusMap, a
navigation layer that organizes the corpus around its recurring entities, which are identifiable from the documents themselves and can link a single document to many others across sources. Specifically, CorpusMap represents each recurring entity as an Entity Page that aggregates information about it and links to every document that refers to it, forming a graph between entities and documents that the
agent can traverse to gather otherwise disconnected evidence. Moreover, since CorpusMap is constructed offline by resolving mentions of the same entity across documents, its links are shared across queries rather than rediscovered repeatedly at inference time. Using 7 different models with 3
benchmark datasets, we show that CorpusMap improves both evidence discovery and answer quality over raw-corpus agentic search while using fewer
tokens on average, and further outperforms 4 alternative
navigation layers, suggesting that entities serve as effective anchors for navigating large document collections.
Read the full abstract ▾
All authors Soyeong Jeong, Sujay Kumar Jauhar, Sung Ju Hwang, Andrew Joohun Nam
Computer Vision
ResComEmb: Effective and Efficient Multimodal Embedding via Residual Homogeneity Compression
Zijing Cai, Yuzhe Wang, Jingxian Zhu et al. (+2 more)
Multimodal large
language models (MLLMs) have shown strong potential for universal
multimodal representation learning. However, existing methods either compress each input into a single vector, limiting fine-grained expressiveness, or retain long sequences of visual-
token vectors, incurring substantial storage and interaction costs. To resolve this trade-off, we propose ResComEmb, a trainable framework for effective and efficient universal multi-vector
multimodal embedding. ResComEmb first encodes each input at native dynamic resolution into ordered global, intermediate, and fine-grained views. After MLLM contextualization and
embedding projection, a trainable Residual Homogeneity Compression (RHC) module reduces within-granularity redundancy and cross-granularity repetition under explicit visual
token budgets. Then, ResComEmb introduces a length-adaptive Bidirectional Late-Interaction Matching mechanism for robust query-document scoring, which averages the strongest
token-level matches in each direction and combines the two scores using a weight based on how many valid
tokens each side has. Extensive experiments on MMEB, ViDoRe V1, and ViDoRe V2 show that ResComEmb produces higher-quality universal
multimodal embeddings than VLM2Vec-V2, and outperforms ColQwen2.5 in visual document
retrieval using only 37.5% of its full visual
token budget, demonstrating a favorable effectiveness-efficiency trade-off.
Read the full abstract ▾
All authors Zijing Cai, Yuzhe Wang, Jingxian Zhu, Fengbin Zhu, Richang Hong
Computation and Language
CredWise: A Controlled Agentic Decision-Intelligence Framework for Explainable and Auditable Credit-Risk Assessment
Aakash Kumar Tiwari
Credit-risk prediction is important in banking, but a prediction alone does not explain why an applicant is risky or how it should be combined with other evidence. This paper presents CredWise, a decision-support framework that integrates credit-risk prediction, probability calibration, explainable artificial intelligence, policy
retrieval, SQL analytics, and controlled
agent-based workflows. An XGBoost model is trained on Lending Club data (1,345,310 loans, 18 features) using a temporal split: 2007–2016 for training, 2017 for validation, and 2018 for testing. On the 2018 test set, the calibrated model achieved a ROC-AUC of 0.7109, PR-AUC of 0.2993, F1-score of 0.3714, and accuracy of 65.44%. Calibration reduced the Brier score from 0.2157 to 0.1273 and the expected calibration error from 0.2862 to 0.0585. SHAP explanations were temporally stable, with a Spearman correlation of 0.9959 between 2017 and 2018 feature rankings. On 28 labeled queries covering nine policy sections, FAISS achieved the best Hit@1 (0.929) and MRR (0.964), while all three
retrieval methods reached Hit@5 = 1.0.
Agent routing achieved 95.6% accuracy (43 of 45 cases), and the SQL
benchmark scored 1.0 on exact-match, execution-success, and result-match across six cases. These results show that CredWise can combine predictions, explanations, policy evidence, and structured analytics in one controlled workflow. It is an academic research prototype, and final decisions remain with a human reviewer.
Read the full abstract ▾
Artificial Intelligence
OptiCom : A Unified Framework for State-Conditioned Composition in LLM-Driven Optimization
Chenxing Wei, Sichen Liu, Lizhao Liu et al. (+6 more)
Large
language models (LLMs) are increasingly deployed to solve complex scientific and practical problems via iterative optimization. However, dynamically coordinating diverse search mechanisms as candidate quality, failure modes, and resource budgets evolve remains a critical open challenge. Targeted empirical diagnostics reveal that mechanism effectiveness is highly state-dependent. Motivated by this, we analyze how individual decisions drive final outcomes, decomposing the expected terminal improvement under a shared budget into cumulative decision opportunities minus cumulative selection losses. Guided by this opportunity-loss theoretical foundation, we propose OptiCom, a unified framework that represents LLM-driven optimizers within a shared configuration space: C=(A,Q,O,E,M,S), corresponding to artifact, query, operator, evaluation,
memory, and strategy. Operating within this space, a fast LLM-based Optimization Controller dynamically composes immediate mechanisms through structured Action Packages, while a slower Strategy Adapter refines long-term selection preferences, operator weights, and templates based on accumulated trajectory feedback. Comprehensive evaluations across 32
benchmark groups demonstrate the superiority of framework: OptiCom achieves an average Max-score rank of 1.72 among 14 evaluated configurations, securing the top score in 23 groups. Ultimately, these results highlight the broad applicability and high extensibility of OptiCom as a general-purpose paradigm for robust LLM test-time scaling.
Read the full abstract ▾
All authors Chenxing Wei, Sichen Liu, Lizhao Liu, Ningyuan Sun, Chen Bingzhou, Ying He, Bo Jiang, Fei Yu, Yao Shu
Artificial Intelligence
Information Bottleneck-Guided Adaptive Hypergraph Transformer for Brain Disease Diagnosis
Jingxi Feng, Xudong Chen, Yifan Zhang et al. (+5 more)
Exploring high-order correlations and long-range dependencies in
brain networks holds significant value for both neuroscience research and clinical diagnosis. However, previous studies have lacked a unified integration of high-order and long-range dependency information in
brain networks, and there is substantial redundancy behind various types of information. These issues limit their effectiveness in the diagnosis of
brain diseases. To address this, we propose an Information Bottleneck-Guided Adaptive HyperGraph
Transformer (IBAHGT). By incorporating the information bottleneck (IB) principle, this approach enables adaptive learning of high-order correlations and both short- and long-range dependencies within a unified framework for
brain network analysis, achieving high-precision
brain disease diagnosis. IBAHGT consists of three key components: an information bottleneck-guided adaptive hypergraph convolution, which introduces a novel hypergraph information bottleneck (HIB) principle to adaptively learn hypergraph message-passing weights between nodes and hyperedges, optimizes information flow and captures high-order information in
brain networks that is maximally informative and minimally redundant (MIMR). The
Transformer encoder captures global information within
brain networks through the
attention mechanism, specifically modeling short- and long-range dependencies. An information bottleneck-guided node-level adaptive fusion employs the IB principle to learn independent weights for each node, facilitating the fine-grained integration of high-order information and global information to obtain an efficient representation for downstream tasks. Extensive experiments demonstrate that the proposed method outperforms current state-of-the-art methods and can identify biomarkers for clinical applications.
Read the full abstract ▾
All authors Jingxi Feng, Xudong Chen, Yifan Zhang, Heming Xu, Hongcheng Han, Xijing Wang, Dong Zhang, Shaoyi Du
Cryptography and Security
Beyond Semantic Narrowing: Robust and Efficient LLM Watermarking with Hamming Neighborhoods
Zewen Sun, Tongyang Zhao, Liyao Xiang et al. (+3 more)
Semantic watermarking improves robustness against watermark removal attacks by
embedding detectable signals into sentence-level representations. However, existing watermarking methods typically impose watermark-specific semantic preferences on generated sentences without explicitly accounting for the highly non-uniform and context-dependent semantic preference of LLM generation. When these two preferences are poorly aligned, many natural continuations become incompatible with the watermark, causing semantic narrowing: reduced semantic freedom, increased resampling cost, and potential degradation on tasks with strict semantic requirements. To alleviate this problem, we propose HammingMark, which uses the semantic hash of the preceding sentence as a dynamic center and accepts candidates whose hashes fall within its Hamming neighborhood. Defining watermark validity over a Hamming neighborhood in compact hash space retains a larger fraction of naturally likely semantic continuations. The coarse many-to-one hash mapping further allows diverse semantic realizations to remain watermark-valid. Experiments on C4 and BookSum show that HammingMark achieves strong robustness, high detectability, and near-unwatermarked generation quality, requiring only 2.2 sampled candidates per accepted sentence,a 72.8% reduction compared with the most sampling-efficient existing method. On more complex tasks with strict semantic constraints, HammingMark achieves the highest detection rates with the highest or tied-highest ROUGE-L scores, demonstrating its effectiveness in balancing watermark detectability and generation quality under constrained generation settings.
Read the full abstract ▾
All authors Zewen Sun, Tongyang Zhao, Liyao Xiang, Mingxuan Ma, Lingzhe Wang, Zhiyuan Li
Cryptography and Security
When Cyber Scoring Systems Diverge: An Empirical Comparison
Kirsi Hellsten, Joni Herttuainen, Ambrose Kam et al. (+3 more)
Vulnerability scoring systems underpin cyber patch prioritization and risk management, but their comparative behavior is almost always assessed in the abstract, through correlation studies in IT vulnerability databases, rather than by the operational consequences they produce when embedded in a system-level risk model. Here we present an empirical comparison of four vulnerability scoring systems, namely CVSS (Common Vulnerability Scoring System), EPSS (Exploit Prediction Scoring System), SSVC (Stakeholder-Specific-Vulnerability Categorization), and IronMiner (operationally calibrated proprietary scoring system). As a substrate for comparison, we use a reconstruction of the 2015 Ukraine Power Grid operational-technology (OT) network that provides a documented incident
topology. The results show a high degree of disagreement between the scoring systems. This suggests that the choice of the scoring system could significantly influence mitigation strategies and vulnerability prioritization, implying that a composite or hybrid scoring approach could offer a more suitable solution.
Read the full abstract ▾
All authors Kirsi Hellsten, Joni Herttuainen, Ambrose Kam, Arlanda Johnson, David Welsh, Kimmo Kaski
Software Engineering
CRJudgeBench: Can AI Detect Plausible but Invalid Code Reviews?
Yue Pan, Jiawei Li, Ziyuan Zhang et al. (+2 more)
Large
language models can generate plausible code-review comments, but such comments may contain technically incorrect claims that mislead developers. We study technical trustworthiness judgment: determining whether a review comment's core technical claims are correct and applicable to the reviewed code in its repository context. Existing code-review
benchmarks primarily evaluate review generation, issue discovery, or general comment quality, but do not directly assess whether an
agent can determine the technical trustworthy of an individual review comment. To fill this gap, we introduce CRJudgeBench, a
benchmark of 1199 instances constructed from real pull requests and expert-verified perturbations, covering both trustworthy and plausible but untrustworthy comments. We further present Sentinel, a repository-grounded agentic judge that actively gathers code evidence to verify review comments before making judgments. Starting from Qwen3-Coder-30B-A3B-Instruct, Sentinel is trained on the CRJudgeBench training split through iterative action-level learning from a privileged teacher. On the 359-instance CRJudgeBench test set, Sentinel achieves 76.60% accuracy, outperforming GLM-5.3 by 6.13 percentage points and its base model by 19.78 points. These results show that even state-of-the-art general-purpose LLMs struggle to identify untrustworthy comments, while iterative action-level learning substantially improves the accuracy of repository-grounded trustworthiness judgments. Our
dataset is available at https://huggingface.co/
datasets/dcloud347/CRJudgeBenchmark
Read the full abstract ▾
All authors Yue Pan, Jiawei Li, Ziyuan Zhang, Xiangxin Zhao, He Ye
Systems and Control
Ancillary Services in High-Renewable Power Systems: Comparing Market Design, Emerging Trends, and Future Challenges
Andreas Makrides, Andrey Churkin, Fei Teng et al. (+1 more)
Rapid growth in renewable generation is changing power-system operation and increasing the importance of ancillary services for security and reliability. As inverter-based resources displace conventional synchronous generation, system operators must procure a broader set of services spanning five categories: frequency control and reserves, voltage and reactive power support, system stability, restoration, and congestion management. This paper compares ancillary-service
market design in Great Britain, Germany, Denmark, Italy, California, Texas, and Australia. It examines how these systems define, procure, remunerate, and coordinate services as variable renewable generation increases. The review develops a consistent product-level classification, provides comparable timing visualisations of frequency-control and reserve products, and maps implementation modalities across services and systems. Four trends emerge: faster and more granular frequency-response products, more explicit procurement of stability capabilities including inertia, system strength, and dynamic voltage support, broader participation by storage, demand-side resources, and other inverter-based resources, and greater use of locational, targeted, and technology-neutral procurement. Challenges include limited harmonisation, incomplete valuation of flexibility and stability capabilities whose value depends on location and operating conditions, barriers to participation by distributed and emerging resources, and insufficient coordination between
market and operational arrangements. The comparison finds no convergence towards a single
market design and supports differentiated but coordinated ancillary-service frameworks reflecting each service's technical, temporal, and locational characteristics.
Read the full abstract ▾
All authors Andreas Makrides, Andrey Churkin, Fei Teng, Pierre Pinson
Computational Engineering
Hybrid GA/MSDLO Approach to Solve a Greenfield Robotized Machine Tending Layout
Ramez Awad and Joshua Beck
Meta-heuristics like genetic
algorithms (GAs) effectively explore solution spaces but often yield suboptimal results and are sensitive to parameter tuning. In contrast, the mass-spring-damper layout optimization (MSDLO) method is fast and excels in locally optimizing resource arrangements, though its effectiveness depends on the initial resource placement. This paper first employs genetic
algorithms to establish an optimal resource placement in a greenfield layout. We then apply MSDLO to fine-tune the positions and orientations of these resources. The results are presented and discussed, highlighting this approach's practicality in effectively addressing industry needs.
Read the full abstract ▾
Machine Learning
Explainable Machine Learning for Multilayer Planar Winding Inductance Estimation
Spyros Rigas, Theofilos Papadopoulos, Georgios Alexandridis et al. (+1 more)
Rapid and accurate self-inductance estimation for multilayer rectangle-shaped planar windings is essential for modern high-frequency power converters, yet traditional workflows rely on complex mathematical equations, rigid monomial formulas or unexplainable black-box machine learning (ML) models that degrade severely outside their training domain. This paper introduces an explainable ML framework unifying post-hoc feature attribution (SHAP and permutation importance) with Kolmogorov-Arnold Network-guided symbolic regression via the SR-KAN framework to discover closed-form analytical equations without prior structural assumptions. Evaluated on a new open-source
dataset of over 10,000 Finite Element Analysis (FEA) simulations across seven out-of-distribution (OOD) classes, standard tree-based ensembles exhibit severe extrapolation errors (> 36%), whereas the unconstrained SR-KAN expression achieves a robust OOD relative error of 8.22%. Experimental verification across 55 physical printed
circuit board prototypes (up to 8 layers, with inductances from 4.11 {\mu}H to 559.27 {\mu}H) confirms that the KAN-discovered expression translates effectively to real-world hardware, predicting inductance with a mean absolute relative error of 6.26%. To support reproducible research, the complete FEA simulation
dataset and prototype measurements are released open-source.
Read the full abstract ▾
All authors Spyros Rigas, Theofilos Papadopoulos, Georgios Alexandridis, Antonios Antonopoulos
Distributed Computing · Cross-listed from quant-ph
Encoding and Node Choices in Transversal Fault-Tolerant Distributed Quantum Computations: An Initial Study
Seng W. Loke
We compare and study different Bivariate-Bicycle (BB) encodings and node choices for distributed
quantum operations such as transversal non-local CNOTs. We observe that while some encodings have more physical
qubits requiring more ebits for a distributed computation, reducing ebit consumption alone might not be the best criterion for selecting an encoding for the logical
qubits, if the goal is to reduce the logical error rate of the distributed computation; for example, one should also consider encodings with a larger distance, which using more physical
qubits can provide. We consider distributed, or non-local, CNOTs and computation of the global gate (GCZ) over distributed logical
qubits as examples. The choice of encoding enables particular concurrent operations; e.g., we show that a transversal physical GCZ on a self-dual $[[120,8,12]] BB$ code can realize eight concurrent logical GCZ operations after accounting for the logical permutation induced by transversal Hadamard.
Read the full abstract ▾
Machine Learning
Pointwise or Pairwise: When Do Pairwise Losses Help Reward Learning, Provably?
Junghyun Lee, Minsoo Ha, Sanghwa Kim et al. (+4 more)
Pairwise losses are increasingly used for reward learning even when pointwise rewards are observed, with mixed empirical results. When and why do pairwise losses outperform pointwise losses? We study this question in a grouped offline contextual-bandit setting allowing multiple actions per context, capturing many reward learning scenarios. We compare Value Regression (VR), which regresses observed rewards pointwise, with Value Difference Regression (VDR), which regresses reward differences between a pair of actions sampled under the same context. We consider a semiparametric model where the mean reward is the sum of a learnable action-dependent component and an arbitrary context-dependent yet action-independent nuisance, capturing context-specific disturbances. Using a unified localized analysis, we prove finite-sample regression guarantees for finite and linear function classes and translate them into offline-regret bounds. For finite classes, VDR eliminates the misspecification term in the VR bound and improves a reward-scale-dependent error term by averaging over actions within each context, a benefit absent from the corresponding VR term. For linear classes, neither method uniformly dominates: within-context differencing removes nuisance-induced bias but may increase estimation variance relative to using absolute rewards when the misspecification is sufficiently low. This yields a feature geometry-dependent bias-variance tradeoff, which we corroborate with numerical experiments.
Read the full abstract ▾
All authors Junghyun Lee, Minsoo Ha, Sanghwa Kim, Yeongjong Kim, Eunjee Lee, Seiyun Shin, Kwang-Sung Jun
Networking · Cross-listed from quant-ph
Optimal Entanglement Routing in Quantum Repeater Chains: Beyond Fixed Operation Order and Purification Schedule
Aikaterini Mandilara, Antonia Tsili, Dimitris Syvridis et al. (+1 more)
Entanglement routing establishes entangled pairs between distant nodes of a
quantum network by purifying and swapping pairs generated on elementary links. Existing methods typically restrict the decision space along two axes: the operation order, often fixed to purify-then-swap (PtS), and the purification schedule of each link, often restricted to pumping. Focusing on linear repeater chains with finite link capacities, we relax both restrictions and study the maximization of the expected end-to-end throughput subject to a fidelity threshold under two
quantum-noise models. We develop a unified capacity-aware optimization framework comprising an exact mixed-integer linear program (MILP) under PtS, instantiated with either pumping or general tree purification schedules, and an exact dynamic program (DP) over arbitrary operation orders. Under symmetric Pauli noise, we prove that pumping converges to a fidelity strictly below unity, imposing a capacity-independent feasibility bound and a maximum chain length on every pumping-based PtS method, whereas general tree schedules yield a capacity-dependent bound. We further prove that post-swap purification never increases the throughput, so a free operation order can only increase feasibility. Numerical evaluations confirm the bounds: tree schedules serve over 90% of the requests that pumping cannot at moderate fidelity thresholds; within the pumping class, a free operation order recovers much of this advantage; but once links use tree schedules, the tree-based MILP and the order-exact DP serve identical request sets throughout. Operation order and purification schedule are thus substitutes, with the purification schedule the dominant factor governing feasibility under symmetric Pauli noise.
Read the full abstract ▾
All authors Aikaterini Mandilara, Antonia Tsili, Dimitris Syvridis, Konstantinos Christodoulopoulos
Artificial Intelligence
Learning to Prove, Not Just to Answer: Reinforcement Learning from Formal Verification for Natural-Language Logical Reasoning
Qili Zhang, Qianren Mao, Hanze Cai et al. (+11 more)
Large
language models (LLMs) are increasingly deployed for natural-
language logical
reasoning, where the final answer is easy to check but the proof behind it is not. In natural-
language logical
reasoning, an intermediate conclusion should follow from its premises, and the resulting derivation should support the final answer. Existing methods lack machine-checkable verification of intermediate conclusions and answer-supporting proof dependencies, so they may assign credit to invalid or answer-irrelevant steps. We propose Proof-R1, an RL framework from formal verification that trains LLMs to construct verifiable proofs for natural-
language logical
reasoning. Proof-R1 admits a generated conclusion into the verified proof state only when the corresponding
reasoning action satisfies the proof obligations through UNSAT-based machine-checkable formal verification. Proof-R1 also recovers the answer-supporting dependency closure to trace the proof structure of the final answer and align outcome credit with the proof dependencies. Experiments demonstrate that Proof-R1 improves answer accuracy across three logical
reasoning benchmarks and four backbone models and outperforms training-free
agents and training-based methods in terms of
reasoning-process verifiability.
Read the full abstract ▾
All authors Qili Zhang, Qianren Mao, Hanze Cai, Kaiming Zhao, Yuening He, Xihan Lei, Yashuo Luo, Hanwen Hao, Yutong Gu, Likang Xiao, Zhijun Chen, Weifeng Jiang, Haoyi Zhou, Jianxin Li