Computational Complexity · Cross-listed from quant-ph
Near-Optimal Bounds on the Density of Low-Energy States of $k$-Local Hamiltonians and Faster Quantum Algorithms
Sevag Gharibian, François Le Gall, Ranitha Mataraarachchi et al. (+1 more)
Low-energy estimation and state preparation for general $k$-local
Hamiltonians are fundamental challenges in
quantum complexity theory. Buhrman et al.~ [BGLGST, PRL 2025] recently broke the natural Grover bound $O^\ast(2^{n/2})$ for both problems, with the improvement depending on the relative accuracy $\varepsilon$ and the locality $k$. In this work, we present faster exponential
quantum algorithms for these problems, where the binary
entropy function governs the runtime exponent. For sufficiently small $\varepsilon/k$, our
algorithms improve the exponent by a factor of $\log(k/\varepsilon)$ over [BGLGST, PRL 2025]. Our main technical result is an
entropy-governed lower bound on the dimension of the
Hamiltonian's low-energy subspace, obtained by depolarizing its ground state. For fixed $k$, this bound is optimal up to constant factors in the exponent. The same framework yields tighter bounds for Heisenberg, $XY$, and Ising models on arbitrary interaction graphs.
Read the full abstract ▾
All authors Sevag Gharibian, François Le Gall, Ranitha Mataraarachchi, Suguru Tamaki
Systems and Control
Frequency Measurement Practices for Inertia Assessment in Inverter Based Resources Dominated Power Systems
Christos M. Nikolakakos, Hassan Haes Alhelou and Nikos Hatziargyriou
Transmission system operators and protective relays compute the rate of change of frequency (RoCoF) from frequency averaged over tens to hundreds of milliseconds, as standards and grid codes specify. Any response delivered inside that window lowers the measured RoCoF, so the inferred inertia depends on the window and the responses in service. This paper defines the windowed inertia estimate and derives an exact identity the system inertia divided by one minus the fraction of the disturbance energy delivered inside the window and a closed-form prediction that applies the same
estimator to the trajectory of a linear response model. Eleven IEEE 9-bus RMS runs synchronous, grid-following and grid-forming configurations, disturbance sizes and parameter sweeps are reproduced by that model, and the identity closes on the measured response powers. Fast frequency response inflates the estimate most: at 500 ms a grid-following system with 20 % less synchronous inertia reports the same value as the all-synchronous system, the grid-forming system a higher one. On a reduced Greek transmission system the 500ms estimate exceeds the inertia by 17-26%, and a scenario with 10% less synchronous inertia reports more than the all-synchronous scenario's inertia. Operators can thus compute what their measurement reports.
Read the full abstract ▾
Computer Vision
Preference-Guided Adaptation for Open-Vocabulary Semantic Segmentation via Prompt Disagreement
Hyun-Kurl Jang, Jihun Kim and Kuk-Jin Yoon
Open-vocabulary semantic
segmentation (OVSS) enables pixel-level prediction over arbitrary text-specified vocabularies and has shown strong generalization on common
benchmarks. However, OVSS performance often degrades in specialized domains such as medical imaging, remote sensing, and industrial inspection, where dense pixel-level masks for adaptation are costly to obtain and require domain-specific expertise. We propose a preference-guided adaptation framework that replaces dense mask supervision with binary preferences. We observe that different
prompt templates produce systematically different
segmentations for the same image, a phenomenon we call
prompt disagreement, and we repurpose it as a built-in source of preference supervision. Building on this, we mine localized preference queries from regions of high cross-template uncertainty, and adapt the OVSS model with Region-Localized Preference Optimization (RLPO) together with consistency regularization that stabilizes updates outside the queried region. Across extensive experiments on the MESS
benchmark, the proposed method achieves consistent gains across diverse OVSS backbones without any pixel-level annotation, and remains effective under noisy preferences. Our code is available at https://github.com/blue-531/pref-ovss.
Read the full abstract ▾
Computer Vision
RRG-SLAM: Real-time Reflection-aware Gaussian SLAM for Indoor Scenes
Yong Liu, Keyang Ye, Zhexi Peng et al. (+3 more)
We introduce the first real-time reflection-aware Gaussian SLAM system for indoor scenes. The system features a reflection-aware TSDF-Gaussian hybrid representation that explicitly separates diffuse scene appearance from reflection components. The base scene is modeled by a TSDF volume and a set of base Gaussians capturing geometry and diffuse appearance, while planar reflections are represented by reflection Gaussian groups associated with detected reflective planes. The rendering is performed in three passes: TSDF raycasting first yields surface color, depth, plane IDs and reflection masks; base Gaussians are then rendered order-independently with depth culling and combined with the TSDF output to form the base image; finally, under the guidance of the plane ID map, reflection Gaussians from different reflection groups are rasterized only into their corresponding planar regions to generate the reflection image, which is subsequently composited with the base image via the reflection mask to produce the final output. For online reconstruction, our system first estimates the camera pose through reflection-aware tracking to suppress interference of reflection-dominated regions. It then identifies reflective planes using
geometric, semantic, and temporal cues, and fuses the observations into the augmented TSDF volume with reflection-aware attributes. Afterwards the base and reflection Gaussians are initialized, optimized, and pruned online to maintain both reconstruction quality and efficiency. Experiments on a variety of
datasets show that our method outperforms existing SLAM systems in reconstruction quality, tracking robustness, and novel-view rendering for indoor environments with reflections, while preserving real-time performance.
Read the full abstract ▾
All authors Yong Liu, Keyang Ye, Zhexi Peng, Ruixian Mei, Kun Zhou, Tianjia Shao
Artificial Intelligence
PairPref: When Should Memory Guide the Answer? A Benchmark for Contextual Preference Use
Mingfei Lu, Mengjia Wu and Yi Zhang
Memory-augmented assistants use retrieved preferences to guide their responses. A small change in the situation can change whether a preference is appropriate while barely affecting its
retrieval similarity.
Memory benchmarks typically test whether systems store and retrieve preferences, with less
attention to when those preferences should apply. We introduce PairPref, a
benchmark of contextual preference use. Each pair changes only the situation, keeping the preference, request, and four candidate replies fixed. The preference remains valid in both situations. In the selection track, models must choose the reply that applies the preference only where appropriate. In the free-generation track, they must decide when to apply it without seeing candidate replies. Both tracks use the same 1,227 pairs across 45 preferences and eight situation categories. We evaluate eight models, most of which achieve selection scores ($\Delta$) of 51 to 65 points. In free generation, however, both responses are appropriate for their respective situations in only 3.6% to 18.3% of pairs. Models continue to apply the preference in both situations even with fewer retrieved
memories, alternative presentation formats, and a stricter
prompt. These results show that models still struggle to judge when user preferences apply and respond accordingly.
Read the full abstract ▾
Computer Vision
SAGE: Subspace Alignment for Classifier-Free Guidance in Mixture-of-Experts Diffusion Models
Boyu Zhang, Yangming Cheng, Ning Zhang et al. (+5 more)
Diffusion Transformers with Mixture-of-Experts (MoE) routing are a leading recipe for scaling generative models. Classifier-Free Guidance (CFG) is essential for generation quality, yet excessively high guidance scales trigger collapse. We identify a previously unreported failure mode in their combination: the two CFG branches route independently, so their realized activations occupy different subspaces. The unconditional write then leaves the conditional subspace, and CFG amplifies that residual linearly in the guidance scale. We propose SAGE, a training-time regularizer that aligns unconditional MoE activations to the conditional subspace without restricting routing diversity, at zero inference cost. Toy experiments show that SAGE dramatically suppresses extreme drift by 9.2x. When scaled to a 1B-parameter text-to-image model, SAGE significantly improves generation quality, delivering a 9.3% boost in peak DPG-Bench performance. Extensive experiments demonstrate that SAGE consistently outperforms the baseline.
Read the full abstract ▾
All authors Boyu Zhang, Yangming Cheng, Ning Zhang, Pengfei Liu, Weijie Li, Yifan Gao, Hangyu Li, Litong Gong
Computer Vision
Evidence Before Accuracy: A MRI-PET Fusion Network for Alzheimer Disease Classification with Causal Regional Validation
Saeid Firouzi Daghigh and Saeed Ayat
Deep learning models for Alzheimer disease (AD) classification routinely report near-perfect discrimination, yet few are shown to rest on AD-relevant neurobiology rather than on
dataset artifacts, subject-level leakage, or non-
brain image content. We present a fusion network combining T1 MRI and FDG PET across axial, coronal, and sagittal planes, trained on ADNI consists of 554 paired subjects. The fusion model reaches AUC 0.962, accuracy 0.909, and F1 0.891, competitive with recent 3D CNN and
multimodal transformer systems at substantially lower cost. We first quantify how much modality, plane and slice geometry matter. A validation-only search over slice centres and neighbour spacings moves AUC by 0.180 for MRI and 0.078 for PET, selecting narrow spacing for MRI and wide spacing for PET, with the chosen coronal centres falling on the hippocampal body and on the posterior cingulate respectively. The contribution, however, is the evidence layer built around that number. Shortcut controls collapse the model to AUC 0.622 (silhouette), 0.608 (exterior), and 0.500 (blank), and a label-permutation null yields 0.456. Forward region-of-interest (ROI) ablation shows that masking medial temporal cortex in MRI and the posterior default-mode network (DMN) in PET produces the largest shift in the AD logit, while area-matched controls remain indistinguishable from that null. Reverse ROI ablation shows that the medial temporal lobe alone retains 89.2% of above-chance discrimination in MRI and the posterior DMN alone retains 79.0% in PET. A quantitative comparison of attribution methods shows occlusion sensitivity reaching 3.5-5.0* enrichment inside a priori AD regions against 0.10-0.43* in controls. Ablation and attribution independently establish a biologically correct double dissociation: hippocampal evidence is carried by MRI, posterior cingulate evidence by PET.
Read the full abstract ▾
Artificial Intelligence
EOPSA: Efficient On-Policy Self-Distilled Safety Alignment
Qirui Liu, Yichen Sun, Yan Wang et al. (+5 more)
On-Policy Self-
Distillation (OPSD) has emerged as a promising paradigm for safety
alignment, delivering dense,
token-level supervision by distilling from a teacher conditioned on refusal-oriented privileged
prompts. However, we reveal that this paradigm suffers from critical inefficiencies that degrade both training efficiency and general
reasoning capabilities. Specifically, we diagnose two fundamental bottlenecks: (1) supervisory collapse over extended rollouts, where the teacher's corrective efficacy degrades precipitously as the student's generation prefix lengthens, injecting noisy gradients into late-stage
tokens; and (2) gradient dilution from stylistic shifts, where the
distillation objective is dominated by safety-irrelevant stylistic discrepancies induced by privileged prompting, washing out genuine safety signals and impairing base
reasoning. To resolve these issues, we propose Efficient On-Policy Self-Distilled Safety
Alignment (EOPSA), which concentrates computational and gradient budgets exclusively on reliably supervised, safety-critical
tokens. EOPSA incorporates two coordinated mechanisms: (i) Adaptive Rollout Scheduling, which dynamically bounds the generation horizon guided by a novel Teacher Rescue Rate (TRR) metric to operate strictly within reliable supervision regimes; and (ii) Selective
Distillation, which filters out safety-neutral
tokens to restrict gradient updates exclusively to safety-pivotal transitions. Extensive evaluations across
reasoning models up to 32B parameters demonstrate that EOPSA slashes rollout computation by $\sim$50% and backpropagates through merely $\sim$2% of
tokens, consistently outperforming full-
token distillation baselines in both safety compliance and
reasoning retention.
Read the full abstract ▾
All authors Qirui Liu, Yichen Sun, Yan Wang, Yu Mi, Wei Cao, Yue Shen, Zhixuan Chu, Kui Ren
Cryptography and Security
SEAD: A State-Based Perspective on Attack and Defense in Tool-Using Agents
Xinjie Shen, Junran Wang, Rongzhe Wei et al. (+1 more)
Language-model
agents increasingly use tools to act on external systems. Earlier actions can alter files, permissions, database records, or other state, making a later routine-looking action harmful. Yet the visible interaction may not reveal the underlying state needed to assess that action. We formulate attack and defense as partially observed state control in SEAD, deriving their design requirements from this shared execution process. Because attackers supply instructions while the target chooses concrete actions, DART decomposes harmful goals into locally plausible steps and uses feedback from actual tool execution to guide trajectory search. The defender must decide before execution with incomplete state evidence. SAGE can therefore investigate relevant state through read-only queries before allowing or blocking each action, including those proposed after a block. We construct an environment-verifiable
dataset integrating controlled initial states, replayable tool environments, and task-specific executable checks. Across four target models, DART improves semantic attack success by 18.8–35.9 percentage points over the competing baseline, with consistent gains under executable verification. On recorded trajectories, SAGE preserves 95.79% of benign trajectories while intercepting 92.73% of harmful paths by the harm-enabling boundary. In online attack-defense evaluation, it reduces DART's executable attack success from 48.0% to 4.0%. SAGE remains effective across four attack methods and generalizes to out-of-domain environments. Our code and data is available at https://github.com/EverywhereSafety/SEAD.
Read the full abstract ▾
All authors Xinjie Shen, Junran Wang, Rongzhe Wei, Pan Li
Game Theory
Nash Equilibria in Auctions with Pacing Strategies: Complexity and Inefficiency
Aris Filos-Ratsikas, Charalampos Kokkalis and Mohamad Latifian
We introduce and study Auctions with Pacing Strategies (APS) games, a full-information model in which utility-maximizing bidders compete across many simultaneous first-price auctions, each choosing a single pacing multiplier that uniformly scales their values into bids. We settle three central questions. First, we show that there are instances that admit no approximate pure Nash
equilibria. Then, we prove that the problem of deciding whether an APS game admits an (approximate)
equilibrium is NP-complete in general, but can be solved in
polynomial time if either the number of bidders or the number of items is fixed. Finally, when an
equilibrium does exist, we characterize its inefficiency exactly, showing that both the Price of Anarchy and the Price of Stability equal $\frac{e}{e-1}$.
Read the full abstract ▾
Cryptography and Security
How to Tame a Multi-Headed Hydra? Adaptive Multi-Category Safety Steering for Large Language Models
Chenxi Wang, Ruiyang Huang, Li Huang et al. (+1 more)
As large
language models (LLMs) become increasingly widespread, preventing unsafe responses to harmful
prompts is essential for their safe deployment. Activation steering offers an approach to improving LLM safety by modifying internal activations during inference without updating model parameters. However, a single
prompt can involve multiple harm categories, and steering toward safety in one category may leave harmful content from another unaddressed. Despite advances in adaptive steering, existing methods do not explicitly coordinate steering direction and strength when multiple harm categories co-occur within a single
prompt. To address this problem, we propose CAM-Steer, a Category-Adaptive Multi-category Safety Steering framework. Specifically, it estimates the risk associated with each harm category by comparing the current hidden state with safe and unsafe prototypes. The estimated risks are then used to combine the safety directions for different harm categories into a single steering direction and to determine the strength of the intervention. Finally, it rotates the hidden state along the composed steering direction, with the rotation angle determined by the estimated risks, while preserving the hidden-state norm. Experiments across three LLM backbones and seven harm categories show that CAM-Steer outperforms the evaluated baselines in average defense success rate, including when categories co-occur. Further analyses support its component designs and informative risk scores, with negligible inference overhead.
Read the full abstract ▾
All authors Chenxi Wang, Ruiyang Huang, Li Huang, Yifan Wu
Computer Vision
XFlow: A Workflow Model for Instruction-Guided Lesion Segmentation in Chest X-rays
Geon Choi, Hangyul Yoon, Hyunki Park et al. (+2 more)
Existing text-guided
segmentation models in the medical domain cover only a narrow set of anatomical structures and lesions in chest X-rays (CXRs), and most of them assume that the queried target is always present in the image. Instruction-guided lesion
segmentation (ILS) was introduced to overcome these limitations by segmenting diverse lesion types from simple user instructions while also recognizing when the queried lesion is absent, and ROSALIA was proposed as the first model for this task. However, the masks produced by ROSALIA remain of limited quality, often carrying scattered noise. Moreover, ROSALIA predicts the mask in a single shot, which differs fundamentally from how radiologists perceive and delineate lesions in practice. A radiologist first surveys the entire thorax, then localizes the approximate region of abnormality, and only then refines the lesion contour. Motivated by this coarse-to-fine, multi-level perception process, we present XFlow, a workflow model for ILS that combines box-based localization with multi-turn point refinement. XFlow detects the lungs, decides whether the queried finding is present in each of them, and
prompts a fine-tuned SAM with the lesion box for an initial mask. It then corrects that mask through point
prompts until its boundary follows the lesion, leaving every intermediate decision visible. Our experiments show that XFlow achieves the best
segmentation quality on both internal and external evaluation. Notably, it surpasses ROSALIA in
segmentation quality even when the two are trained on the same lesion annotations. Code and model weights will be made publicly available.
Read the full abstract ▾
All authors Geon Choi, Hangyul Yoon, Hyunki Park, Sang Hoon Seo, Edward Choi
Robotics
MonoEgo: Monocular Metric Egocentric Demonstration Capture with Passive Wrist Constellations and Sparse Workstation Anchors
Jie Xu, Kangjin Yu, Ziyi Jin et al. (+2 more)
Image-aligned metric demonstrations often require dedicated tracking hardware and synchronization across devices. We present MonoEgo, a capture system that replaces active wrist instrumentation with offline
monocular reconstruction. One 90-FPS global-shutter camera observes calibrated passive wrist constellations, sparse workstation anchors, and the scene on a shared image clock. MonoTag SLAM combines marker corners with ORB geometry and uses visual evidence to reject ambiguous planar-marker poses. Its metric Atlas supports interval scale re-anchoring, verified map merging, and retrospective localization of earlier frames supported by the final map. Camera and wrist-constellation outputs retain validity and map provenance, and unsupported motion is left missing. Experiments show metric tracking beyond continuous anchor visibility, reconnection of supported map components, and recovery of some missing camera poses. Comparisons against a multisensor camera reference and separate stationary-constellation tests characterize trajectory agreement and precision while revealing incomplete coverage and residual
geometric uncertainty. The results indicate that passive fixtures and offline reconstruction can reduce capture-side requirements. Dynamic accuracy, deployment, and downstream policy benefits require further study.
Read the full abstract ▾
All authors Jie Xu, Kangjin Yu, Ziyi Jin, Beichen Wang, Zhongpu Xia
Machine Learning
HALO: Enhancing Time Series Generation via Hyperspherical Latents and Masked AutoregRessive Modeling
Chunyi Hou, Xiangfei Qiu, Hanyin Cheng et al. (+2 more)
Most existing time series generators rely on a two-stage modeling paradigm: the first stage learns discrete latent representations of time series; the second stage performs autoregressive modeling on these discrete latents through next
token prediction. However, this paradigm suffers from two stage-specific limitations: the first stage can lead to information loss when discretizing continuous time series, while the second stage is prone to error accumulation during autoregressive generation. To address these limitations, our core idea is to perform generative modeling in a continuous latent space with a more efficient autoregressive framework. We propose
HALO, which enhances time series generation via Hyperspherical Latents and Masked Autoregressive modeling to achieve this goal by tackling two key bottlenecks: (1) variance and scale heterogeneity of continuous latent representations; (2) the difficulty of balancing generation efficiency with temporal correlation modeling.
HALO first introduces a hyperspherical VAE that constrains continuous latents to a fixed-radius hyperspherical shell, effectively stabilizing the numerical fluctuations of continuous latent representations. Secondly, we develop a masked autoregressive model that balances parallel decoding and temporal correlation learning, substantially reducing the number of inference steps required for generation and improving generation stability. Our extensive experiments demonstrate that
HALO achieves state-of-the-art generation performance while offering significantly improved inference efficiency over existing advanced baselines.
Read the full abstract ▾
All authors Chunyi Hou, Xiangfei Qiu, Hanyin Cheng, Yutong Li, Bin Yang
Artificial Intelligence
Can AI Make Money in Crypto? Measuring the Gap from Backtests to Real Markets
Xingtong Yu, Jiarun Zhou, Guanlin Ding et al. (+12 more)
AI-based trading methods have rapidly evolved from machine learning and reinforcement learning to large
language models (LLMs) and trading
agents, yet their performance is still predominantly assessed through historical backtesting. Such evaluations provide limited evidence of whether a method can generalize to unseen future
markets or whether its backtested performance can be sustained in realistic trading frictions (e.g., latency, slippage, liquidity constraints, and
market impact). We present a unified
benchmark that evaluates representative machine learning, reinforcement learning, LLM-based, and
agent-based trading methods in cryptocurrency
markets through three progressively more realistic stages: historical backtesting, prospective exchange-based paper trading, and real-money live trading. These stages jointly increase temporal realism by moving from historical to unseen future
markets, and execution realism by moving from offline simulation toward live trading. This protocol enables us to quantify the backtest-to-realization gap, identify when performance begins to deteriorate, and compare how this gap differs across major classes of AI trading methods. We further provide a unified open-source system supporting all three evaluation stages, together with a public platform that continuously updates
benchmark results. Code is available at https://github.com/Starlien95/Awesome-TradingAI.
Read the full abstract ▾
All authors Xingtong Yu, Jiarun Zhou, Guanlin Ding, Wenkang Wei, Jiarui Liu, Chang Zhou, Fangzhou Ge, Chenyi Xu, Xikun Zhang, Renqiang Luo, Jie Zhang, Hong Cheng, Xinming Zhang, Hui Zhang, Yuan Fang
Machine Learning
Low-Confidence Remasking Traps Flexibility: Realizing Arbitrary-Order Potential for Diverse Rollouts in Diffusion LLMs
Moongyu Jeon, Dongjae Jeon, Bumjun Kim et al. (+2 more)
Masked
diffusion language models support arbitrary-order generation, suggesting a natural way to produce diverse outputs. However, recent work argues that this flexibility reduces diversity by delaying high-uncertainty
tokens that can lead to different generation paths. We trace this diversity loss not to arbitrary-order generation itself, but largely to low-confidence remasking (LCR), a widely used decoding rule. At each step, LCR samples a
token at every masked position but commits only the sampled
token with the highest probability, filtering out the rest. We show that this mechanism can exponentially suppress lower-probability
tokens as more positions compete, and observe the same suppression in LLaDA. In contrast, top-probability position selection (TPP), which has often been conflated with LCR under the shared label confidence-based decoding, avoids this diversity loss. TPP first selects the position whose most likely
token has the highest probability, then samples directly from that position's distribution. Replacing LCR with TPP restores diversity and yields Pass@$k$ comparable to left-to-right decoding, suggesting that the reported diversity loss stems largely from LCR's filtering rather than from generating high-confidence positions first. To further exploit order flexibility, we introduce
Entropy-Guided Initialization (EGI), which samples the first
token at the highest-
entropy position and then follows TPP. This simple modification further improves rollout diversity and solution coverage beyond left-to-right decoding, with gains extending to downstream policy optimization, highlighting the potential of arbitrary-order generation for diverse rollouts.
Read the full abstract ▾
All authors Moongyu Jeon, Dongjae Jeon, Bumjun Kim, Mingyu Kim, Albert No
Machine Learning
KiT: A Foundation Model for Financial Time-Series Forecasting using DiffusionTransformers
Boyu Zhang and Haorui Li
Financial candlestick
forecasting is fundamental to quantitative investment, yet it remains exceptionally challenging due to extremely low signal-to-noise ratios and vast heterogeneity across
markets and instruments. Existing approaches have largely attempted to introduce deep learning to capture hidden temporal features, but most adopt an auto-regressive formulation, which leads to error accumulation during inference. Meanwhile, general-purpose time-series foundation models are not tailored to the unique structure of k-line data and yield unsatisfactory performance on downstream candlestick
forecasting tasks. To tackle these problems, we introduce KiT, a K-line
Diffusion Transformer foundation model, and reformulate future prediction as conditional path generation via flow matching: given a historical context window, the model generates an ensemble of plausible future OHLCV trajectories. We pre-train KiT at multiple parameter scales on billions of candlestick bars spanning multiple
markets and timescales. Across three
markets and seven resolutions, KiT attains a mean return RankIC of 0.057 and a mean
volatility RankIC of 0.66, leading at every timescale and outperforming both task-specific financial forecasters and general time-series foundation models. Code will be available at: https://github.com/Luciferbobo/KiT.
Read the full abstract ▾
Artificial Intelligence
Does Model Uncertainty Track Human Ambiguity? Evidence from Multi-Annotator Vision Benchmarks
Manya Singh and Arjun Pakrashi
Human-model
alignment is critical for trustworthy AI-assisted decision-making systems. Yet, most work evaluates model predictions against single ground-truth labels, overlooking that humans themselves often disagree on labels, a signal of genuine ambiguity. We investigate whether models struggle on the same instances that humans find difficult. We measure this on two
vision datasets (FER+ and CIFAR-10H) where multiple human annotations per image capture human disagreement patterns. We evaluate eight pretrained models across three architectures (ResNet, EfficientNet, MobileNetV3) in two parts: first, whether model uncertainty (softmax confidence,
entropy) correlates with human disagreement, and second, whether predictive multiplicity measures (inter-model disagreement, Jensen-Shannon divergence) do. We find that it does not:
alignment is weak in both dimensions. At the discrete label level, 50.4% of CIFAR-10H images and 33.5% of FER+ images receive multiple valid classifications from humans, while the models converge on only one. These instances represent a critical failure case where humans perceive ambiguity and would request expert review, yet models decide confidently. At the continuous score level, single-model uncertainty correlates weakly with human disagreement ($\rho = 0.24--0.55$), and predictive multiplicity provides only modest improvement. Widely-used uncertainty quantification methods do not reliably identify instances humans find ambiguous. Model uncertainty should not be treated as a trustworthy signal by default for decision-making in high-stakes scenarios.
Read the full abstract ▾
Machine Learning
Distribution-Conditioned Task Routing for Class-Incremental Learning
Longhuan Xu, Zhipeng Zhou, Wei Ji et al. (+3 more)
Parameter-efficient adaptation enables continual learners to acquire task-specific knowledge through compact model updates while maintaining strong within-task performance. However, class-incremental inference requires each input to be classified among all classes seen so far without access to its task identity. For learners equipped with task-specific parameter-efficient modules, this introduces a critical task-routing challenge beyond catastrophic forgetting. We study post-hoc task routing without retraining the learner or introducing a separately trained router. Such training-free inference-time calibration remains comparatively underexplored in parameter-efficient class-incremental learning. We identify three sources of routing error (feature-level, task-level, and class-level misalignment) and propose Feature Distribution Calibration (FDC). Its three components address these misalignments: Task Subspace Filtering (TSF) suppresses feature components outside each task's principal subspace, Residual Likelihood Calibration (RLC) evaluates the typicality of its subspace residual, and Prototype Affinity Calibration (PAC) measures compatibility with the task's class prototypes. Experiments demonstrate plug-and-play applicability to eight parameter-efficient class-incremental methods using a shared encoder. With one component configuration selected per method across all five
benchmarks, FDC improves final accuracy in all 40 method-
dataset pairs by 4.39 percentage points on average. Enabling all components improves 35 of the 40 pairs, with an average gain of 4.45 points. When applied to a simple baseline, FDC achieves strong overall performance.
Read the full abstract ▾
All authors Longhuan Xu, Zhipeng Zhou, Wei Ji, Chunyan Miao, Peilin Zhao, Lijun Zhang
Computer Vision
SubjectAnchor: Subject-Aware Memory-to-Video for Multi-Shot Storytelling
Xinyu Wang, Huafeng Shi, Zian Li et al. (+4 more)
We present SubjectAnchor, a Subject-Aware
Memory-to-
Video paradigm for multi-shot storytelling in which the current shot is generated by conditioning on explicit visual
memories extracted from previous shots. The objective is to preserve subject identity and scene consistency across cuts while retaining the controllability of shot-wise prompting. Built on Wan2.2-I2V-A14B, SubjectAnchor contains three key components: subject-related
memory construction, subject-aware temporal rotary position encoding, and
memory-aware
attention partition. For each target shot, the method constructs a compact
memory bank by tracing each required subject to its historical appearance and retrieving the most relevant precomputed keyframes. These
memory frames are encoded into the model input as explicit visual conditions, while different subjects are assigned to separated negative temporal slots to reduce identity interference. In addition,
memory-aware
attention partition regulates the interaction between
memory tokens and generated content within a shared backbone. This formulation preserves the appearance anchoring of explicit visual
memory while remaining compatible with script-driven shot-by-shot generation. Experiments show that SubjectAnchor improves cross-shot identity consistency over representative
memory-based and holistic baselines while maintaining competitive visual quality.
Read the full abstract ▾
All authors Xinyu Wang, Huafeng Shi, Zian Li, Yan Zhou, Xiaoqiang Liu, Yue Ma, Pengfei Wan
Computer Vision
Can Attack Difficulty Be Characterized Before Optimization? A Study of Pre-optimization Difficulty in Person-Vanishing Attacks
Jingyao Xu, Dongdong Wang and Siyang Lu
Adversarial attacks against object detectors are traditionally studied from an optimization perspective, where attack difficulty is regarded as an outcome observed only after
adversarial optimization. This raises a fundamental question: can the relative attack difficulty of different inputs be characterized before optimization begins? In this paper, we investigate this question for person-vanishing attacks by introducing the concept of pre-optimization attack difficulty, which captures intrinsic differences in optimization effort across input images. To estimate this latent difficulty before optimization, we propose Quad-CLEVER, an efficient geometry-based
estimator derived from a quadratic approximation of the local person-vanishing margin along the most attack-relevant direction. Extensive experiments across multiple attack
algorithms demonstrate that Quad-CLEVER consistently correlates with the observed optimization cost, providing empirical evidence that attack difficulty exhibits a predictable pre-optimization structure. Building upon this finding, we further propose a difficulty-aware attack framework that leverages the estimated difficulty to adaptively allocate optimization budgets for a base attack under a fixed computational budget. On BDD100K, the proposed framework improves the image-level attack success rate by up to 5.78$\%$ while reducing the average optimization cost by up to 11.42 iterations. On the more challenging EventPed
dataset, it saves 2.25 optimization iterations while maintaining comparable attack performance. These results demonstrate that attack difficulty can be meaningfully estimated before optimization and that exploiting such estimates enables more computationally efficient
adversarial attacks.
Read the full abstract ▾
Machine Learning
Scalable GNN-based Knowledge Graph Representation Learning with Efficient Message Passing
Huu Tan Mai, Cuong Xuan Chu, Heiko Paulheim et al. (+1 more)
Graph neural networks (GNNs) excel at representation learning on Knowledge Graphs (KGs), achieving stateof-the-art performance on tasks like link prediction or entity classification. However, their high computational complexity, inherent to their user-defined message passing (MP)
algorithm, still prohibits their widespread adoption, especially for large KGs. Current efforts to mitigate the scalability bottlenecks of GNNs on KGs, such as subgraph sampling, are often task- and model-specific, and do not reliably guarantee lossless (if applicable) runtime/space reductions. To address this, we extend Relational Sparse
Matrix Multiplication (RSPMM), originally designed to losslessly lower the space complexity of composition-based MP with pointwise composition functions, to support more expressive functions (e.g., 2x2 block-diagonal
matrix multiplication, Givens rotation, circular correlation). Our method delivers significant task-independent reductions in runtime and space for current GNNs on KGs and facilitates efficient re-implementations of GNNs that maintain near state-of-the-art performance on challenging KG tasks, for a fraction of computational costs.
Read the full abstract ▾
All authors Huu Tan Mai, Cuong Xuan Chu, Heiko Paulheim, Daria Stepanova
Robotics
Robot-Assisted Deployment and Maintenance of Inflatable Modules for Lunar Habitation: A Field Demonstration
Kentaro Uno, Shamistan Karimov, Ashutosh Mishra et al. (+5 more)
Long-term human habitation and in-situ development on the Moon open a new era of space utilization. In this context,
robots are a key technology for facilitating the construction of future human outposts. Toward the deployment and establishment of human habitation modules on the lunar surface, we propose a combined system consisting of inflatable modules and a modular, reconfigurable robotic system. This paper presents a report demonstrating various
robot-assisted task executions using real hardware, namely the modular and reconfigurable
robot MoonBot and the inflatable module HIDAS, to enhance the reliability of their deployment and maintenance. The demonstrated tasks include robotic inspection during inflation, module position
alignment, final safety locking, and three-dimensional mapping for post-deployment maintenance. All demonstrations were conducted either in a laboratory environment or at a lunar analogue test site. Finally, lessons learned are discussed to provide essential insights for this robotic application to future lunar habitation.
Read the full abstract ▾
All authors Kentaro Uno, Shamistan Karimov, Ashutosh Mishra, Elian Neppel, Hazal Gozbasi, Shreya Santra, Shinichi Kimura, Kazuya Yoshida
Machine Learning
QAMM: Adjoint MeanFlow Matching for Few-Step Offline Reinforcement Learning
Yuehu Gong, Shutong Ding, Mokai Pan et al. (+4 more)
Flow policies can model rich action distributions, but their iterative sampling limits decision speed. Adjoint matching uses the critic's action gradient to improve a flow policy without backpropagating through its sampling trajectory, yet its supervision is defined for instantaneous velocities. We propose QAMM, a method that turns the critic-derived adjoint signal into supervision for MeanFlow's average velocity. The resulting policy learns finite-interval transport directly and generates actions with few network evaluations. We derive the adjoint MeanFlow target, specify its gradient boundaries, and train it with an offline actor-critic. On ten HumanoidMaze tasks, QAMM produces effective two-call policies and achieves competitive performance against strong flow-policy baselines. These results show that adjoint-based Q optimization can be combined with average-velocity learning to obtain expressive offline policies with few-step action generation.
Read the full abstract ▾
All authors Yuehu Gong, Shutong Ding, Mokai Pan, Yimiao Zhou, Jiashu Hou, Ye Shi, Yanwei Fu
Multiagent Systems
MASTraceBench: Diagnosing Collaboration Gains through Proposal Trajectories in LLM-Based Multi-Agent Systems
Yapeng Li, Songze Li, Shuang Yu et al. (+4 more)
LLM-based multi-
agent systems (MAS) have shown promise in complex problem solving. As MAS methods diversify, systematic evaluation becomes increasingly challenging. However, existing
benchmarks largely focus on final outcomes, leaving unclear how collaboration gains arise, are preserved, or are lost. To address this limitation, we introduce MASTraceBench, a
benchmark for diagnosing collaboration gains through proposal trajectories in MAS. Across six cooperative and competitive tasks, MASTraceBench tracks and grades proposal trajectories and provides a multi-layer metric suite covering Task Score, Collaboration Gain, proposal-trajectory indicators, and
Token Cost. Using MASTraceBench, we systematically compare representative MAS methods not only by final performance, but also by how
agent proposals evolve and are aggregated into the final answer. This analysis reveals a recurring pattern: final MAS answers rarely surpass the strongest initial proposal; interaction often lifts initially weaker proposals toward it, while strong initial proposals are seldom further improved and may regress. To reduce this risk, we propose CLEARS, which replaces whole-proposal exchange with claim-level evaluation across
agents to guide reliable synthesis. CLEARS more often preserves or improves upon the strongest initial proposal and achieves the highest Collaboration Gain on five of the six tasks.
Read the full abstract ▾
All authors Yapeng Li, Songze Li, Shuang Yu, Jing Yu, Zhixin Liu, Liqiang Wen, Tonghua Su
Computer Vision
ConCAD: Constraint-Aware Image-to-CAD Generation with Dual-Granularity Rewards
Chenxi Zhai, Xi Cheng, Hang Cheng et al. (+5 more)
Image-to-CAD generation seeks executable parametric programs that recover both the geometry and design intent of a reference object. Existing systems are commonly evaluated by validity and shape overlap, although two solids with similar volume can encode different CAD relations. We introduce ConCAD, a constraint-aware image-to-CAD framework optimized via Group Relative Policy Optimization (GRPO) with rewards at two complementary granularities: a code-level constraint reward and an execution-level
geometric reward. This complementary design disambiguates structurally distinct yet volumetrically similar shapes while ensuring valid 3D geometry. To verify that these rewards recover geometry and design intent, we introduce a B-rep
geometric constraint satisfaction rate (G-CSR), which analytically extracts and evaluates
geometric constraints from boundary representations. Experiments on the DeepCAD and Zero2CAD demonstrate that ConCAD achieves the best IoU and Chamfer Distance over competitive baselines, while also outperforming them on G-CSR, validating its superior recovery of both
geometric fidelity and parametric design intent.
Read the full abstract ▾
All authors Chenxi Zhai, Xi Cheng, Hang Cheng, Zhicheng Guan, Mingyu Fan, Yanzhe Tang, Pingfa Feng, Long Zeng
Machine Learning
LLN: Learnable Lens Networks for Parameter-Efficient Long-Horizon Dynamical Prediction
Binbin Yong, Zhao Su, Lan Guo et al. (+3 more)
Explicit residual connections of the form (x+f(x)), often combined with normalization layers, have become a standard strategy for training very deep neural networks. However, residual addition primarily provides an algebraic shortcut for gradient propagation, while leaving the
evolution of feature geometry across layers largely unconstrained. We introduce Learnable Lens Networks (LLN), a physics-inspired architecture that replaces direct feature-space residual accumulation with learnable optical transport in an augmented position-angle phase space. Each layer alternates between free propagation, which provides an implicit transport path, and a learnable lens field that performs nonlinear trajectory transformation and focusing. Theoretically, we establish that LLN transport is globally invertible and volume-preserving for any differentiable lens field, with the implemented coordinate-wise Gaussian transport further satisfying symplecticity. Importantly, these structural constraints do not limit expressivity: with unrestricted
embeddings and readouts, LLN retain universal approximation of continuous end-to-end maps. Experiments across diverse dynamical systems demonstrate that LLN improves long-horizon prediction while using substantially fewer parameters than same-depth comparators. Further analysis reveals stable depth-wise gradient transport and interpretable learned dynamics under the coupled propagation and refraction design.
Read the full abstract ▾
All authors Binbin Yong, Zhao Su, Lan Guo, Haoran Li, Jun Shen, Qingguo Zhou
Artificial Intelligence
Xijing Wang, Yinsheng Yao, Jinru Ding et al. (+5 more)
Large
language model (LLM)
agents offer new opportunities for automated analysis in industry. However, rigorous evaluation of such
agents-for example, within power system scenarios-remains hindered: real operational data are confidential, and existing public resources fail to fully capture the chained dependencies and heterogeneous evidence. To address this gap, we propose PowerBench, comprising (1) a generation framework that derives interconnected heterogeneous operational data through a common dependency chain, and (2) a synthetic
dataset generated by this framework. The
dataset covers 761 devices across 100 device types, with 13.35 million hourly telemetry records spanning two years and 24,939 operational documents. Building on this
dataset, we construct 300 questions across three task families that evaluate frontier LLMs' ability to complete analysis tasks that require autonomous evidence
retrieval and
reasoning across interconnected and heterogeneous data under restricted tool calls and time budgets. Results demonstrate that the evaluated frontier LLMs remain challenged on these tasks: the best model reaches only 74.2% joint accuracy. Our trace analysis further reveals that model performance varies across evidence discovery, content
retrieval, tool use,
reasoning over evidence, and answer submission. These findings provide detailed insights for evaluating LLM
agents and guiding their reliable deployment in industry. The framework,
dataset, and
benchmark tasks are available at https://github.com/open-compass/PowerBench.
Read the full abstract ▾
All authors Xijing Wang, Yinsheng Yao, Jinru Ding, Yidong Jiang, Ziwen Xu, Yiwen Jiang, Jie Xu, Dawei Cheng
Machine Learning
M3OS: A Monte Carlo Graph Search-Orchestrated Multi-Agent LLM System for Evidence-Traced Molecular Optimization
Junjie Wang, Yaowei Jin, Ruohui Tang et al. (+7 more)
Small-molecule optimization integrates medicinal-chemistry
reasoning and computational evidence through iterative, multi-objective decisions. When large
language models (LLMs) reason over optimization histories stored primarily in conversational context, they must recover candidate identities, prior evaluations, and task constraints to guide subsequent decisions. We present M3OS, a multi-
agent LLM system that decouples molecular-design
reasoning from optimization-state management through Monte Carlo graph search. A persistent graph links evaluated candidates, parent-child transformations and evaluation evidence, while rewards and visit statistics guide LLM-assisted parent selection. Two branches combine tool-driven candidate generation with knowledge- and case-guided medicinal-chemistry editing. An execution harness controls graph updates through structured output extraction, molecular validation and task-bound evaluation.
Agents receive role-specific contexts, while the graph preserves optimization trajectories beyond their active contexts. Across three molecular optimization
benchmarks, M3OS achieves higher success rates than baselines, supporting the integration of persistent search state, specialized
agents and controlled execution for multi-constraint optimization.
Read the full abstract ▾
All authors Junjie Wang, Yaowei Jin, Ruohui Tang, Guonan Cui, Haojie Wang, Penglei Wang, Dingyan Wang, Duo An, Shuangjia Zheng, Qian Shi
Computer Vision
HPMD: A Historical Persian Manuscript Dataset for Word Spotting with Line-Level Annotation
Saeid Firouzi Daghigh and Majid Iranpour Mobarakeh
Large collections of historical Persian manuscripts have been digitized, but searching them is still slow and mostly manual. Historians usually want to find where a specific name, date, event, or topic appears, which is a word spotting problem. Progress on this task is limited by two things. First, there is almost no public
dataset of historical Persian handwriting; the only notable resource, OpenITI MAKHZAN, contains a relatively small Persian portion. Second, word spotting models usually need word-level bounding boxes, which are very expensive to annotate. In this paper we introduce a new
dataset of 223 pages, 3,678 lines, 37,631 words, and 130,630 characters, collected from diverse historical Persian books of poetry and prose and annotated at the region, line, and text level. We also propose a baseline that is trained only with line-level annotations but returns word-level locations. A fine-tuned line detector finds text lines, and a fine-tuned CRNN recognizer trained with CTC produces a frame-by-character posterior
matrix for each line. Instead of decoding the most probable character at each frame, the query is scored directly against this
matrix, so visually similar characters in Persian such as be and pe no longer cause hard failures. The frame
alignment also gives the horizontal position of the word inside the line. On the test set, the fine-tuned line detector reaches an F1 of 0.892, and posterior-based search raises the word spotting F1 from 0.487 to 0.558 compared with exact matching on the decoded text, with the decision threshold selected on a held-out validation set. A PHOC attribute-
embedding baseline that additionally receives oracle word boundaries at test time reaches an F1 of 0.449, below the proposed method. We also report a distributional analysis of the
dataset, a taxonomy of
retrieval errors, and a per-conditionbreakdown of performance.
Read the full abstract ▾