Searcharxiv⌕ Search

arXiv subjects

Ke Liu

Publications and source records attributed to Ke Liu.

At least 19 recordsLinked to original sources
arXiv2026

Taming Spacetime Overhead and Design Complexity in Distributed Fault-Tolerant Superconducting Quantum Computation

Scaling fault-tolerant superconducting quantum computers will likely require distributed architectures built from multiple manufacturable quantum processing units. A central question is whether noisy and slow inter-chip operations impose substantial spacetime overhead or orchestration burdens compared with monolithic architectures. To answer this question, we present a hardware-grounded architectural co-design together with a comprehensive resource-estimation protocol for surface-code-based modular processors. The design confines inter-chip latency and noise to module boundaries, preventing slow, noisy links from inducing prohibitive spacetime overhead or becoming a global orchestration bottleneck. The resource-estimation protocol integrates hardware constraints and circuit-level error-correction performance into utility-scale algorithmic cost estimates, enabling a controlled assessment of different architectures. Using RSA-2048 factorization as a demanding benchmark, we estimate resources under experimentally anchored parameters and realistic superconducting hardware constraints. Compared with a large, ideal monolithic baseline, the resulting distributed architecture requires only modest additional resource overhead in both qubit count and execution time. More importantly, the overhead is nearly scale-invariant across a broad module-capacity window, decoupling chip size from global performance. This decoupling turns module capacity from a finely tuned architectural parameter into a flexible engineering degree of freedom, allowing chip sizes to be set by manufacturability and control-packaging constraints rather than architectural fine-tuning. These results establish a viable route to distributed fault-tolerant superconducting quantum computation that scales without prohibitive resource growth or heavy orchestration burden.

quant-ph↗
arXiv2026

Scalable Adaptation of 3D Geometric Foundation Models via Weak Supervision from Internet Video

Geometric foundation models show promise in 3D reconstruction. However, their progress is severely constrained by the scarcity of diverse, large-scale 3D annotations. While static-scene Internet videos are abundant and diverse, utilizing them as a scaling source for geometric learning is challenging due to the absence of ground-truth geometry and the presence of observational noise. To address this, we propose SAGE, a framework for Scalable Adaptation of GEometric foundation models from raw video streams. SAGE leverages a hierarchical mining pipeline to transform videos into training trajectories and hybrid supervisions: (1) Informative training trajectory selection; (2) Sparse Geometric Anchoring via SfM point clouds for global structural guidance; and (3) Dense Differentiable Consistency via 3D Gaussian rendering for multi-view constraints. Besides, we also introduce a regularization strategy that replays a small fraction of supervised data to prevent catastrophic forgetting. Applied to two architecturally distinct backbones, SAGE reduces Chamfer Distance on unseen benchmarks (7Scenes, TUM-RGBD, Matterport3D) by 20-42% with MV-DUSt3R and consistently improves VGGT. SAGE establishes Internet video as a viable and scalable adaptation source for geometric foundation models. Code is available at https://github.com/aim-uofa/SAGE.

cs.CV↗
arXiv2026

pymatgen: 15 years of community growth, new functionality, and future prospects

We present a retrospective on the Python Materials Genomics (pymatgen) library, reflecting on 15 years of community growth and established best practices. The current version of pymatgen builds on its robust, open-source foundation, emphasising its collaborative nature. Over the past decade, pymatgen has thrived as one of the largest open-source materials science codebases. We detail how pymatgen supports advanced computational materials science workflows, how it adapts to changing demands, and the lessons learned from its growing community, providing guidance beyond pymatgen's open-source community. Pymatgen will continue to evolve in response to the current rapidly changing landscape of computational materials science and materials informatics. We discuss the challenges and potential solutions to managing the community-driven evolution of pymatgen and provide an outlook on its future development.

cond-mat.mtrl-sci↗
arXiv2026

Decoding Neural Population Dynamics through Robotic Analog

Animal evidence shows that precise voluntary movements arise from rotational neural population dynamics in motor cortex, but their physical effects remain unknown. We developed a robotic analog of biological motor systems with artificial muscles, multimodal sensors, and a neural network controller trained via reinforcement learning. The robotic analog exhibited accurate movements, robustness to damage, and neural population dynamics akin to animals. This task-driven, embodied model illuminates the causal link between neural population dynamics and motor outcomes. We discovered that neural rotations generate oscillatory maneuvers orthogonal to the reaching direction, optimizing trajectory adjustments, which is confirmed by primate neural data. The model also revealed counterintuitive neural energy principles under sensor and motor redundancies, and striking Eureka moments during motor learning, bridging biological and artificial systems. These findings provide new perspectives on how neural dynamics contribute to accurate and flexible movement, inspiring future intelligent robots with animal-like mobility.

cs.RO↗
arXiv2026

CoEvoWhen: Policy-Tool Coevolution for Ultra-Long Video Temporal Grounding

Ultra-long video temporal grounding requires balancing long-range evidence search with fine-grained event understanding under a limited visual budget, yet existing agentic methods still rely largely on predefined policies and tool capabilities. Motivated by this, we propose a novel policy-tool coevolution framework that jointly evolves high-level policies and executable media tools from the agentic reasoning trajectories of a VLM, forming a reusable skill without updating model parameters. During evolution, an external skill updater distills transferable task experience in long-video temporal grounding, accordingly refining the orchestration of long-range image-based and fine-grained video-based observations. Alongside these policy updates, the updater employs its coding capabilities to upgrade existing tools or create new ones, adapting the tools to long-video evidence acquisition. Equipped with the evolved skill, the VLM autonomously orchestrates tools under the guidance of the evolved policy, coordinating image and video observations for agentic inference without relying on a separate, stronger planning model. Extensive experiments spanning five benchmarks and three VLMs show that policy-tool coevolution consistently improves temporal grounding accuracy in ultra-long videos while reducing visual token cost at inference, and that the evolved skill yields substantial performance gains on general long-video QA without additional task-specific evolution, demonstrating the effectiveness and generalizability of our framework for long-video understanding.

cs.CV↗
arXiv2026

The Visual Target Matters: Learning across the Visual Hierarchy for Brain-to-Image Retrieval

Brain-to-image retrieval seeks to identify the visual stimulus that elicited a non-invasive neural response. Candidate images are typically represented by pretrained vision models, whose internal representations vary in abstraction across depth. Existing methods usually train the neural encoder to recover a fixed final-layer visual target. Under this formulation, the visual hierarchy is reduced to a single prescribed endpoint, preventing representations at other depths from directly shaping the visual target. This limitation motivates learning how information across visual depths should contribute to the retrieval target. To this end, we introduce NeuroGlyph, which learns a trial-independent visual target from multiple depths of a frozen visual backbone. NeuroGlyph decomposes the target into factor-specific subspaces. Each subspace learns an image-conditioned allocation over visual depth. The resulting subspaces are fused into a single embedding for retrieval. Across THINGS-EEG and THINGS-MEG, NeuroGlyph outperforms final-layer supervision in all controlled comparisons. It also surpasses the post hoc best fixed-layer oracle in three of four comparisons. Parameter-matched ablations support both factorized target construction and image-conditioned depth allocation. Under comparable 200-way retrieval protocols, NeuroGlyph achieves the strongest system-level performance in six of eight reported metrics. These results support learning retrieval targets across the visual hierarchy rather than prescribing one visual depth.

cs.CV↗
arXiv2026

SheetMind: Actions Set Accuracy, Agents Set the Failure Mode

Spreadsheet agents are converging on elaborate multi-agent designs, yet it is unclear how much of their performance comes from the agents rather than from the action interface they share. We answer this with SheetMind, a Manager-Action-Reflection framework, in a controlled study over all 221 tasks of the SheetCopilot Benchmark: five architectural variants, four backbones, exact McNemar tests on paired outcomes, and a checker reproducing the official chart and pivot comparisons. Replacing the high-level action API with primitive cell operations costs 47.1 points (p < 0.0001) and leaves the agent below a do-nothing baseline, whereas both extra agents together are worth 3.2 points: the Reflection Agent adds +4.5 (p = 0.013), the Manager +1.4 (p = 0.68). Decomposition instead changes how the system fails, cutting silently wrong outputs from 33% to 25% of tasks (p = 0.010). Capability saturates: GPT-5 and the five-times-cheaper GPT-5-mini are not significantly different (61.1% vs. 58.4%, p = 0.15), while GPT-3.5 loses 16.3 points and fails differently. A reflector must judge the step it just took, not the subtask. SheetMind reaches 61.1% Pass@1 with GPT-5 on the full SCB-221, against a do-nothing baseline of 9.0%. Accuracy comes from the operations an agent can name; the agents decide how it fails.

cs.HC↗
arXiv2026

Adaptive Cortically Constrained EEG-Vision Alignment for Zero-Shot Brain-to-Image Retrieval

Zero-shot brain-to-image retrieval requires robust alignment between noisy EEG responses and visual representations. Existing EEG-vision alignment methods often operate in sensor space and apply fixed visual supervision to all responses, ignoring both spatial mixing in scalp EEG and response-wise variability in alignment reliability. We propose an adaptive cortically constrained EEG-vision alignment method for zero-shot brain-to-image retrieval. The method reconstructs EEG responses into predefined ROI-level source-pattern representations and encodes them with a Neuro-ROI Attention Encoder. To handle response-wise variability, we introduce an evidence-based adaptive visual supervision strategy that weights detail-controlled visual targets using model-based alignment evidence. On THINGS-EEG, the proposed method achieves strong 200-way zero-shot retrieval performance, with ROI-level attribution providing post hoc interpretability of the learned source-pattern representations. These results show that cortically constrained representation learning and adaptive supervision can jointly support EEG-vision alignment for zero-shot brain-to-image retrieval.

cs.CV↗
arXiv2026

SkelWAM: A Skeleton-Guided World-Action Model for Zero-Shot Cross-Embodiment Manipulation

Reusing manipulation experience across robot embodiments is important for scaling robot learning and reducing repeated task-specific data collection. However, changes in embodiment alter visual appearance, action dimensionality and semantics, and the whole-body configurations that can realize the same tool pose. We present SkelWAM, a skeleton-guided world-action model that couples perception and control through one explicit geometric representation for single-source cross-embodiment manipulation. Arm centerline geometry, tool-center-point (TCP) pose, and parallel-jaw commands form a shared 25-D state. The same definition underlies canonical third-person and wrist observations and future whole-body action targets. Trained with predictive visual supervision, a video-action mixture of transformers predicts canonical skeleton action chunks, which embodiment-specific constrained decoders convert into joint or continuum-robot controls. This formulation requires no one-to-one joint correspondence and uses no target-task demonstrations or target policy updates. We introduce LIBERO-Cross10, a source-only cross-embodiment transfer benchmark covering ten tasks and ten target embodiments across four morphological groups. On this benchmark, Franka-trained SkelWAM achieves 43.3% success over 1,000 episodes, exceeding the best-performing evaluated baseline by 36.2 percentage points. We further deploy a JAKA mini2-trained policy on the Feagine A03 continuum robot for three tabletop manipulation tasks, illustrating the approach's potential for real-world cross-embodiment manipulation. Project page: http://www.liukepku.com/skelwam/index.html

cs.RO↗
arXiv2026

Beyond Classification: Structured Supervision Aligns Visual Evidence with Medical Semantics

Vision Transformers (ViTs) have shown immense potential in medical image analysis. However, standard pre-training via global image classification suffers from spatial collapse, where models rely heavily on background shortcuts rather than localising critical foreground lesions. To overcome this limitation and align visual evidence with precise medical semantics, we systematically investigate alternative pre-training paradigms.Specifically, we evaluate three independent forms of structured supervision: topological priors via graph self-supervision, dense pixel-level constraints via segmentation, and cross-modal semantic grounding via image-text pairs. Notably, our empirical analysis reveals that while all three forms of structured supervision successfully alleviate the global pooling bottleneck and steer visual attention towards foreground regions, image-text alignment achieves the most superior performance. By embedding high-dimensional diagnostic logic, the cross-modal approach not only anchors attention on precise visual evidence but also enables profound abstract reasoning. Extensive experiments demonstrate that this semantically enriched pre-training fundamentally enhances the model's feature representation. Consequently, when fine-tuned for downstream clinical classification tasks, our models achieve superior accuracy and yield highly interpretable attention maps focused on true pathological features, vastly outperforming vanilla classification baselines.

cs.CV↗
arXiv2026

Anatomy of a Decision: Uncertainty-aware Hierarchical Intent Learning via Flow Matching for Multimodal Recommendation

Modeling the underlying user intent is crucial for recommendation, but existing methods struggle with the inherent uncertainty and the dynamic, hierarchical nature of user interests. Current approaches often rely on clustering or prototype learning to discover a static set of intents. However, they face two critical challenges: (1) they overlook the uncertainty inherent in multimodal features; and (2) they assume a static and flat intent structure, failing to adapt to a user's varying decision certainty. To address these limitations, we propose UHIFlow, an Uncertainty-aware Hierarchical Intent learning framework via Flow matching. First, our Cross-modal Uncertainty Synergistic Modeling (CUSM) module leverages conditional flow matching to quantify uncertainty from visual and textual modalities and synergistically align them. Subsequently, the Uncertainty-guided Hierarchical Intent Generation (UHIG) module uses this quantified uncertainty to dynamically construct a personalized intent hierarchy, generating coarse-grained intents for uncertain users and fine-grained ones for users with clear preferences. Extensive experiments on three real-world datasets demonstrate that UHIFlow significantly outperforms state-of-the-art baselines.

cs.IR↗
arXiv2026

IMEX-FND: A Traceable Interaction-Aware Mixture-of-Experts Framework for Multimodal Fake News Detection

Multimodal fake news detection (FND) increasingly demands verdicts that are not only accurate but traceable, revealing how cross-modal evidence is combined, yet two coupled difficulties remain. First, text-image relations are heterogeneous: uniqueness, redundancy, and synergy coexist and vary from post to post, so a single global fusion rule is brittle and opaque. Second, the dominant modality shifts across instances, which static encoders and a fixed fusion pathway handle poorly. We present IMEX-FND, an interaction-aware mixture-of-experts framework that couples adaptive routing with explicit interaction decomposition. A Multi-Modal Expert Gateway (MMEG) performs instance-wise, within-modality routing over specialized and shared experts and builds a CLIP-grounded cross-modal stream, yielding three refined, interaction-ready representations that adapt to the dominant modality of each post. An Interaction-aware Multi-Modal Expert Fusion (IMEF) module then decomposes the interactions among these streams into uniqueness, redundancy, and synergy, producing transparent, sample-wise weights via a modality-replacement training signal. The two stages form a single route-then-decompose pipeline whose routing and interaction weights are both inspectable, offering instance- and dataset-level traceability for misinformation diagnosis. Extensive experiments on the Weibo, Weibo-21, and Gossip benchmarks show that IMEX-FND achieves state-of-the-art performance, surpassing competitive baselines by 0.4-1.2% while offering superior traceability with fewer parameters.

cs.SI↗
arXiv2026

CoANeRV: Coordinate-Aware Token-Space Neural Video Representation

Neural representations for videos (NeRV) have shown strong reconstruction fidelity by storing video-specific information in network weights. However, existing formulations typically require either costly per-video optimization or video-specific weight generation, making it difficult to scale to efficient amortized video representation. We propose CoANeRV, a coordinate-aware token-space framework that adapts the broader token-conditioned neural-field paradigm to amortized video representation. CoANeRV forms compact video tokens in one feed-forward pass and uses a shared coordinate-conditioned decoder to reconstruct continuous spatio-temporal queries, avoiding per-video decoder optimization or generation while retaining coordinate-level reconstruction flexibility. To make token-space reconstruction effective, CoANeRV introduces a coordinate-aware decoding architecture that aligns spatio-temporal queries with video tokens through axis-adaptive positional encoding and temperature-modulated cross-attention. Block-wise coordinate querying further reduces peak attention memory, making high-resolution reconstruction practical. Experiments on diverse video datasets show that CoANeRV consistently improves reconstruction quality over prior feed-forward NeRV and INR baselines, reduces peak memory compared with attention-based coordinate decoders, and provides efficient amortized encoding without per-video optimization. These results support the proposed video-specific combination of feed-forward token formation, spatio-temporal coordinate retrieval, and memory-bounded dense querying. The code is available at https://github.com/jialong2023/CoANeRV.

cs.CV↗
arXiv2026

From Talking to Singing: A New Challenge for Audio-Visual Deepfake Detection

With rapid advances in audio-visual generative models, reliable forgery detection becomes increasingly critical. Existing methods for audio-visual deepfake detection typically rely on cross-modal inconsistencies. In singing, rhythmic vocalization weakens this coupling and introduces a nontrivial domain shift, substantially degrading detection performance. We construct the Singing Head DeepFake (SHDF) dataset using rhythm-aware generative models to fill the gap in singing benchmarks. To cope with cross-scenario domain shifts, we propose a Text-guided Audio-Visual Forgery Detection (T-AVFD) framework that generalizes across both talking and singing scenarios. T-AVFD comprises a facial authenticity pattern learner and a multi-modal differential weight learning module. The pattern learner aligns facial features with multi-granularity textual descriptions to learn generalizable authenticity patterns. The weight learning module preserves intrinsic audio-visual consistency and adaptively integrates it with authenticity patterns via differential weighting. Extensive experiments on multiple talking head deepfake datasets and SHDF show consistent improvements over existing baselines and strong robustness under diverse perturbations.

cs.AI↗
arXiv2026

StrataCL: Fabric-Native Communication Library for Production Supernodes

Modern distributed AI workloads run across hundreds of accelerators, making communication a major bottleneck. Existing communication libraries remain largely buffer-centric because user and communication buffers are managed separately, causing redundant data copies or costly user-buffer registration. This paper presents StrataCL, a zero-redundancy and fabric-native communication library for production supernodes. StrataCL introduces registration-on-allocation to realize user-buffer direct communication, and designs communication operators with workload-balanced NPU-core partitioning and NPU-driven SDMA offloading to exploit supernode architecture features. On the Huawei CloudMatrix384, StrataCL improves collective bus bandwidth by up to 1.6x and improves MoE dispatch/combine bus bandwidth by up to 1.4x. Across three production workloads, StrataCL improves LLM inference throughput by 1.9x, reduces P99 TTFT by 2.2x, and reduces LLM and Recsys training iteration time by 1.4x and 1.3x, respectively.

cs.DC↗
arXiv2026

Quark matter at finite temperature and proto-quark stars with the axion effects in SU(3) Nambu-Jona-Lasinio model

We investigate the thermodynamical properties of strange quark matter (SQM) and proto-quark stars (PQSs) within the SU(3) Nambu-Jona-Lasinio (NJL) model at finite temperature, specifically incorporating the effects of axion fields and vector interactions. Our results demonstrate that these interactions significantly influence the equation of state (EoS), constituent quark masses, entropy density, and the maximum star mass of PQSs at the isentropic stages along the star evolution line. Furthermore, we reveal a distinct thermodynamic signature in the early evolution: the presence of trapped neutrinos leads to a substantial increase in electron number density while simultaneously suppressing the core temperature compared to the neutrino-free case. These findings may highlight the crucial role of the axion effects, flavor-dependent vector interactions, and particle composition in determining the observable properties of compact stars at finite temperature.

nucl-th↗
arXiv2026

Spacetime Layout and Logical Compilation of Color Code

Fault-tolerant quantum computing requires system-level coordination of logical primitives. Here, we establish a logical compilation framework for the color code, grounded in its topological structure and supporting universal logical operations. Based on its anyon-condensation and domain-wall structure, we introduce a spacetime block-diagram representation capturing logical patches and operations and derive the rules governing block assembly. A correspondence with ZX diagrams further identifies the logical semantics of this representation and enables transformations that preserve the represented computation. Moreover, we develop a code-derived compilation strategy that converts ZX representations of logical computations into valid color-code spacetime layouts. In this strategy, edge-decorated ZX diagrams tailor the logical representation to the color code under the block-assembly constraints, and fusion-region-aware routing exploits semantic equivalence during geometric embedding. We automate the complete logical compilation process and demonstrate successful compilation across a broad range of algorithms. Our work advances color-code architecture from individual primitives to the automated synthesis of logical computations, marking a significant step toward its full-stack quantum computing.

quant-ph↗
arXiv2026

PhysioBench: A Unified Benchmark for Physiological Signal Question Answering

Physiological signals support diverse clinical and monitoring tasks, yet existing physiological signal foundation models typically require task-specific adaptation for each task. Natural language provides a common interface for specifying different prediction objectives, but the ability of current models to follow such instructions across physiological signal modalities remains insufficiently evaluated. To address this gap, we introduce PhysioBench, a unified benchmark for physiological signal question answering. PhysioBench harmonizes annotations from 22 public datasets into 61.4 million questions across 30 tasks. Each question-answer pair is grounded in a signal segment and traceable to its source annotation. We evaluate 21 representative models, including large language models, vision-language models, time-series language models, and physiological signal foundation models under three complementary settings. The results show that none of the evaluated models achieves consistently strong performance across physiological signal modalities and tasks. The incorporation of natural language supports unified prediction across tasks, although performance remains sensitive to question formulation. Beyond these findings, PhysioBench offers an extensible platform for fine-grained analysis and future research on physiological signal understanding. Our codes are available at https://github.com/Leanna97/PhysioBench.

cs.CL↗