Computation and Language
LatCom: Cross-Agent Latent Compression for Efficient Multi-Agent Collaboration
Shinan Zhang, Tao Zhang, Qihui Zhu et al. (+7 more)
LLM-based multi-
agent systems (MAS) increasingly use latent collaboration to avoid the information loss and repeated encoding-decoding overhead of natural-
language communication. However, directly forwarding all sender latents makes the receiver-side context scale with both the number of
agents and the
reasoning length, increasing computation,
memory usage, and collaboration latency. A natural solution is latent compression. But we find that cross-
agent redundancy remains unresolved in existing latent compression approaches, which typically compress each sender independently and then concatenate the results. We propose LatCom, a cross-
agent latent compression framework for efficient multi-
agent latent collaboration. LatCom maps multiple sender latents into a fixed number of receiver-readable and task-relevant slots. Rather than reconstructing all sender hidden states, it optimizes the compressed latents for receiver-side task utility. LatCom trains the compressor in two stages: single-sender readability learning first establishes a latent interface interpretable by the frozen receiver, and multi-sender fusion learning then trains the compressor to fuse complementary evidence and remove redundancy across
agents. Experiments on multiple
benchmarks with Qwen3-4B show that LatCom achieves an average 2.46x inference speed-up over LatentMAS and reduces output
token usage by 70.3% while maintaining comparable average accuracy.
Read the full abstract ▾
All authors Shinan Zhang, Tao Zhang, Qihui Zhu, Mengjie Zhang, Dong Jin, Yunpeng Hou, Shuangwu Chen, Xiaobin Tan, Quan Zheng, Jian Yang
Computer Vision
Back2Struct: Making Structured Images Editable Again
Pengyu Yan, Yixin Wu, Yunjie Tian et al. (+1 more)
Structured images, such as diagrams, charts, and flowcharts, are inherently symbolic and can be compactly represented in an editable format, yet in practice, they are often rendered as images, and therefore not graphically editable. This mismatch presents a significant challenge for researchers, engineers, and designers who wish to incorporate modified versions of existing graphic content into new materials without manually reconstructing it. In this study, we presentBack2Struct, which "makes structured images editable again" by directly recovering vector graphics code (SVG / XML) from image representations. Given an image of a structured graphic, Back2Struct predicts semantically object-level SVG / XML code that explicitly encodes text, shapes,
topology, and layout, rather than performing low-level pixel vectorization. The generated code can be seamlessly imported into tools such as PowerPoint, allowing users to edit, refine, restyle, and reuse graphic content while preserving structural fidelity. Beyond supervised fine-tuning on ground-truth SVG
token sequences, we further optimize Back2Struct with reward-based learning to better match deployment-time requirements: the output should be syntactically valid, properly concise, and visually faithful to the input diagram. Specifically, we design a composite reward that jointly encourages SVG / XML compilability, length consistency with the reference code, and structural or semantic similarity between the generated and ground-truth graphics. These complementary signals guide the model to produce SVGs that are not only closer to the training distribution, but also more complete, editable, and renderable in practice. Experiments show that Back2Struct improves accuracy, editability, validity, and user
alignment over baselines.
Dataset and code are available at: pengyu965.github.io/Back2Struct.github.io
Read the full abstract ▾
All authors Pengyu Yan, Yixin Wu, Yunjie Tian, David Doermann
Computer Vision
RBF-GNN: Rational Basis Functions for Pseudo-Coordinate based Graph Convolutions
Paweł Batorski, Abtin Pourhadi and Paul Swoboda
We propose RBF-GNN, a new pseudo-coordinate based graph neural network architecture that takes into account Euclidean, spherical or angular coordinates and uses them to induce a powerful spatial inductive bias. Similar in architecture to SplineCNN, we improve upon the latter by replacing the less efficient sparse-activation based B-splines whose number grows exponentially with dimension by rational Padé basis functions. For effective training we propose a spline-subspace initialization and a variance-preserving weight rescaling. Experimentally, we evaluate on a number of popular neural network architectures that use SplineCNNs. We replace only the SplineCNNs with RBF-GNN. We achieve improved results, including on semantic keypoint matching, shape matching, event based camera computer
vision tasks. Code is available at https://github.com/pawelswoboda/RationalBasisCNN.
Read the full abstract ▾
Sound
ReDimNet2+: Multi-Corpus Data Scaling for Robust Speaker Verification
Kirill Borodin, Vasilii Kudryavtsev, Maxim Maslov et al. (+1 more)
Automatic speaker verification must remain reliable across devices, rooms, and compression pipelines. We present ReDimNet2+, which scales training of the compact ReDimNet2 backbone across seven public corpora (63,934 speakers, about 8,675 hours). Analysis of a VoxBlink2 subset reveals a shift in predicted spectral coloration, motivating codec and waveform augmentation alongside this multi-corpus training, large-margin fine-tuning (LMFT), and graph-based
retrieval reranking. With random 4-second evaluation windows for all models, ReDimNet2+ LMFT reduces pooled VoxCeleb1 EER from 2.42% to 0.82% and a 26-condition robustness stress-test EER from 7.21% to 1.99%. Under this shared local protocol, it reaches 0.35% EER on VoxCeleb1-O versus 0.787% for the best evaluated WeSpeaker checkpoint. On a VoxBlink2
retrieval subset, reranking improves the final model's Pr@k from 0.7413 to 0.7687.
Read the full abstract ▾
All authors Kirill Borodin, Vasilii Kudryavtsev, Maxim Maslov, Grach Mkrtchian
Computer Vision
Embedded Bi-Temporal Building Damage Assessment for On-Board Data Reduction
Thomas Goudemant, Benjamin Francesconi, Marjorie Bellizzi et al. (+1 more)
Rapid assessment of building damage after natural disasters is essential to support emergency response. Earth Observation satellites can acquire relevant imagery shortly after an event, but exploitation is limited by uplink and downlink capacity and by ground-processing latency. We address this with a bi-temporal building damage assessment pipeline built on a siamese detector derived from YOLOX, designed to compress information at both ends of the ground/space link. On the ground, pre-disaster reference images are encoded into a compact latent space – compressed by up to a factor of 64 – and uplinked to the satellite. On board, this reference is compared with a fresh post-disaster acquisition so that the downlink carries only actionable object-level products, bounding boxes and damage classes, instead of full scenes. This cuts the data exchanged in both directions, while on xBD the strongly compressed reference still preserves most of the detection performance. Because on-board acquisitions suffer from residual pre/post co-registration errors, we introduce a latent-space shift estimation and correction module that regresses the global offset from the coarse feature level and realigns the post-disaster features before fusion. It substantially improves robustness to de-registration – especially under large shifts, where fusion-only variants collapse – while also raising nominal accuracy and remaining compatible with the strongest compression. We finally port the pipeline to two embedded targets, a Xilinx Versal VCK190 and an NVIDIA Jetson AGX Orin, and report hardware performance (latency, throughput, power efficiency). The core detector and its compression port cleanly to both, but the operators needed for long-range robustness survive only on the Jetson GPU, whereas the Versal DPU does not.
Read the full abstract ▾
All authors Thomas Goudemant, Benjamin Francesconi, Marjorie Bellizzi, Adrien Dorise
Artificial Intelligence
CADOC: Cache-Aware Dynamic Object Context for Long-Horizon Agents
Junjie Yao, Zhangchen Zhou and Zhi-Qin John Xu
For a long-horizon
agent, context is the bottleneck: the history is resent with every request, the window caps task length, and
reasoning degrades as the history grows. Replacing structured objects with compact
retrieval Cards shortens the
prompt and keeps the exact originals retrievable, but editing the history can break prefix-cache reuse, and prior recoverable methods time their edits by forecasts of future reuse or by preset intervals. We propose CADOC (Cache-Aware Dynamic Object Context), an online
algorithm that replaces structured objects with compact Cards while preserving exact, on-demand
retrieval of their original contents. CADOC schedules replacements in batches by balancing accumulated waiting cost against shared cache-reconstruction cost. Its scheduling rule follows from an economic order quantity trade-off, recovers the optimal integer batch under stationary assumptions. Across evaluation, CADOC consistently achieves the lowest aggregate input cost among the compared configurations, which reduces input cost by approximately 40% on average while maintaining task performance close to full context. CADOC thus provides a cost-derived approach to compressible context management, demonstrating that efficient compression depends not only on shortening
prompts but also on scheduling edits to preserve cache reuse.
Read the full abstract ▾
Cryptography and Security
OPFL: Optimistic Verification of Federated Learning via Empirical Boundary
Hongxu Su, Jianzhu Yao, Xuechao Wang et al. (+1 more)
Federated learning enables multiple clients to collaboratively train models without sharing their private data. However, the lack of visibility into local training makes it difficult to verify whether clients follow the prescribed training procedure or submit malicious updates, such as model poisoning. A natural approach is to replay client training for verification. However,
privacy-preserving replay produces numerical results that cannot be directly matched with local client execution because the two run in different environments. We present OPFL, an optimistic verification framework for
privacy-preserving
federated learning. To protect data
privacy, OPFL performs replay inside secure multi-party computation (MPC). Although gradients computed on MPC and local GPUs are not bitwise identical, we observe that their absolute differences are stable and bounded. OPFL therefore calibrates an empirical boundary offline and uses it to distinguish benign numerical deviations from malicious manipulation. To reduce the cost of expensive MPC replay, OPFL adopts optimistic verification by post
auditing only sampled training steps. Experiments on LeNet, BERT, and Qwen show that the boundary generalizes across
datasets, input lengths, and GPUs, while achieving $0$% ASR against model poisoning and PGD-based attacks. On a LeNet workload, at $p=0.01$, OPFL is approximately $98.6\times$ faster than full MPC-based FL and $625.5\times$ faster than ZK-based approach.
Read the full abstract ▾
All authors Hongxu Su, Jianzhu Yao, Xuechao Wang, Pramod Viswanath
Multiagent Systems · Cross-listed from physics.soc-ph
An LLM-powered Agent Framework for Heterogeneous Evacuation Behavior Modeling under a Moving Threat in a Public Plaza
Jian Ma, Runxin Yu, Tianyu Tang et al. (+1 more)
Modeling heterogeneous evacuation behavior under a moving threat is difficult because human perception,
memory, and evidence evaluation are not well captured by fixed rules. We propose a novel LLM-powered
agent-based framework to represent these internal decision processes. Each pedestrian
agent perceives a private symbolic ASCII view, maintains a
Memory-based Knowledge Graph derived solely from individual observations, and makes decisions through persona-conditioned
prompts under a common sampling configuration. A compressed decision context with stateless
memory preserves trial-and-error experience across turns while excluding
reasoning traces, and a validation engine separates behavioral choice from physical feasibility by executing routes only over observed terrain. We evaluated eight personality compositions in eight paired randomized blocks within a simulated public plaza. Usable-exit knowledge was strongly associated with evacuation success: 89.5% of
agents possessing such knowledge evacuated, compared with 1.05% of those without it. Personality compositions also differed in their evaluation of remembered threat evidence: the proportion of danger assessments varied by 0.265, while high-urgency, low-directness decisions ranged from 11.41% to 34.33%. After direct threat sightings, responses converged, with 99.6% of assessments classifying the situation as dangerous. Movement was selected in 99.8% of decisions. Overall, evacuation outcomes were strongly associated with information access, while evacuation time was jointly associated with spatial geometry, information, and affect. The framework provides an auditable approach to generating endogenous behavioral heterogeneity through persona-conditioned LLM
agents in crowd-evacuation simulations.
Read the full abstract ▾
All authors Jian Ma, Runxin Yu, Tianyu Tang, Xiaolian Li
Sound
RVQ Position Aware Speculative Decoding for On Device Text to Speech
Berkin Durmus, Eduardo Pacheco, Zach Nagengast et al. (+1 more)
Autoregressive decoding (AR) with
Transformer models is
memory bandwidth bound at single stream inference, the typical deployment regime for on device text to
speech (TTS). Real time streaming with Qwen3-TTS requires more than 200 sequential model calls per second, dominated by the inner loop MultiCodeDecoder that emits the 15 residual vector quantization (RVQ) codes per 80 ms audio frame. We propose RVQ position aware speculative decoding for the MultiCodeDecoder, attaining 2.47 accepted
tokens per model call at $5\times10^{-4}$ percent added parameters and 10 to 20 percent per round speculation/verification overhead, reducing real time synthesis from 200 to 88 sequential model calls per second. The scheme is distributionally lossless under the deployed top-k sampling, and WER parity with the original system is consistent with this guarantee. We deliver 2 to 2.2x speedup for RVQ
token generation with Qwen3-TTS 0.6B on recent iPhone and Apple Silicon Mac devices.
Read the full abstract ▾
All authors Berkin Durmus, Eduardo Pacheco, Zach Nagengast, Atila Orhon
Cryptography and Security
One Pipeline Does Not Fit All: TAILOR, a Type- and State-Aware Framework for CVE Reproduction
Ji He, Huang Zhang, Lijie Zheng et al. (+2 more)
Growing vulnerability disclosure and widespread software reuse increase security teams' need for reproducible evidence to diagnose vulnerabilities, validate patches, and build regression tests. Producing such evidence at scale requires automated end-to-end CVE reproduction. Existing methods typically process different CVEs through a uniform pipeline, but differences in runtime form, trigger interfaces, and prerequisite state impose different execution requirements on individual stages, making fixed workflows difficult to adapt to diverse reproduction needs. To address this problem, we present TAILOR, a type- and state-aware multi-
agent framework specialized for complex vulnerability reproduction. TAILOR converts static vulnerability information into auditable reproduction evidence and packages reconstructed environments and trigger evidence into reproduction artifacts. Its first-level type-aware mechanism adaptively matches each vulnerability to an execution path. Within the Web path, its second-level state-aware mechanism constructs the required prerequisite state before exploitation, decouples prerequisite-state construction from core vulnerability triggering, and shares execution constraints across exploitation and verification. We construct a
dataset of 200 CVEs with an emphasis on cases with complex execution requirements. TAILOR successfully reproduces 59.24% of Web vulnerabilities and 44.19% of traditional vulnerabilities. Further ablation experiments show that the two control levels respectively mitigate execution-path mismatch and missing Web prerequisite state. Overall, TAILOR broadens the coverage of automated CVE reproduction and provides auditable evidence for vulnerability diagnosis and defense.
Read the full abstract ▾
All authors Ji He, Huang Zhang, Lijie Zheng, Lele Zheng, Yulong Shen
Computer Vision
World2Motion: Turning Video World Models into 3D Human Motion Generators
Fangyuan Tu, Xiangyue Zhang, Yiyi Cai et al. (+8 more)
We present World2Motion, a framework that generates scene-aware 3D human motion and corresponding
video from a single image and a text
prompt. While existing 3D motion generators learn from motion
datasets, their generalization is constrained by limited coverage of environments. In contrast,
video world models such as Cosmos 3 offer broader environmental priors but are not designed for full-body motion generation; recovering motion from their generated
videos requires costly two-stage inference. To address these, we turn Cosmos 3 into a single-stage 3D motion generator. This adaptation has two challenges: the scarcity of paired
video–motion data and temporal instability in the generated motion. First, we construct a training
dataset combining synthetic
video–motion pairs with real
videos paired with estimated 3D motion. Second, we propose a shift-decoupled noise schedule that assigns different noise levels to
video and motion through shared denoising progress. This design accommodates the different denoising requirements of the two modalities, reducing motion jitter. Experiments on a multi-source interaction
benchmark show that World2Motion has better motion–text
alignment and scene interaction compared with the evaluated 3D motion generators. It also matches the interaction success rate of the two-stage baseline while achieving approximately 3.3$\times$ faster inference. Our project page is available at https://fyantu.github.io/World2Motion/.
Read the full abstract ▾
All authors Fangyuan Tu, Xiangyue Zhang, Yiyi Cai, Yichen Peng, Kunhang Li, Bo Zheng, Zhixiang Wang, Kaipeng Zhang, Erwin Wu, Haoran Xie, Haiyang Liu
Computer Vision
VesselBench-800K: A Large-scale Perception Benchmark for Multimodal Vessel Detection, Counting, and Density Estimation
Danfeng Hong, Chenyu Li and Jocelyn Chanussot
Vessel perception from space is crucial for a wide range of maritime applications, from traffic monitoring to environmental protection. However, most existing
datasets predominantly focus on general object detection tasks in optical remote sensing (RS) images. Relying solely on single-modality optical RS images proves inadequate for effectively perceiving vessel objects in complex maritime scenarios, where ever-changing weather conditions (e.g., clouds and rain), the need for day-and-night coverage, and the inherent limitations of a single imaging modality pose significant challenges. To fill this gap, we introduce VesselBench-800K, the largest-to-date
benchmark dataset on a global scale for vessel perception in
multimodal RS images. As its name suggests, VesselBench-800K comprises 800,000 images, each at a resolution of 512x512 pixels, specifically curated for vessel perception tasks such as detection, counting, and density estimation. These
multimodal image pairs (i.e., optical, SAR) are collected from diverse platforms, sensors, scenes, shooting heights, and synthetic sources, spanning spatial resolutions from 4.5m to 0.1m. Furthermore, we evaluate numerous state-of-the-art detection, counting, and density estimation models on VesselBench-800K through both qualitative and quantitative comparisons. By revealing previously unrecognized cues, this
dataset holds immense potential to significantly advance our understanding of marine traffic. Our VesselBench
dataset will be publicly available at https://github.com/danfenghong/IEEE_TGRS_VesselBench to support and contribute to community development.
Read the full abstract ▾
Computer Vision
Visual Parallel Search: Learning to Search High-Resolution Images with Parallel Tile Inspection and Adaptive Zoom
Xijia Tao, Yihua Teng, Xinyu Fu et al. (+5 more)
High-resolution visual question answering often fails because a
multimodal model does not acquire the small, spatially localized evidence needed to answer a question. Sequential zooming can recover detail, but it asks the main model to choose a region before obtaining a reliable overview. We introduce VPS, a visual parallel-search framework in which a main
agent first invokes grid_search to inspect image tiles in parallel with question-conditioned sub-
agents, and then adaptively invokes zoom_in on a precise or merged region. The same interface supports both training-free inference and post-training of the main and sub-
agents. Across five
benchmark splits and three model sizes, VPS improves mean accuracy over dedicated zoom-only search in 14 of 15 same-model comparisons, with gains up to 8.0 points and especially strong improvements for smaller main models. ZoomBench retains an approximately 3.2-point gain at every tested size. We further develop a supervision pipeline with hint-free verification and a paired role-specific GRPO surrogate for learning the controller and tile-reader roles. SFT improves observed accuracy on all five
benchmark splits, including a 4.17-point gain on HR-Bench 4K. Role-specific RL further reshapes search behavior: main-only RL reduces mean tool use from 2.65 to 2.11 with similar pass@1 in an internal four-response evaluation, while external accuracy changes are mixed. Joint training reveals an asymmetry between local evidence reading and global search control. Together, these results support VPS as an effective inference-time scaffold and a trainable decomposition for visual evidence acquisition.
Read the full abstract ▾
All authors Xijia Tao, Yihua Teng, Xinyu Fu, Cheng Gong, Ziru Liu, Xudong Xie, Rui Liu, Lingpeng Kong
Computer Vision
Parameterized Stripe Attention for Efficient Video Generation
Xingyu Jia, Baole Ai, Ang Wang et al. (+2 more)
Diffusion Transformers (DiTs) enable high-quality
video generation but suffer from substantial inference latency, primarily attributable to the computationally expensive full spatio-temporal
attention. While sparse
attention methods offer potential solutions, existing approaches face an inherent flexibility–efficiency dilemma: predefined masks lack the flexibility to capture diverse
attention patterns, while runtime-determined masks introduce overheads and sacrifice hardware efficiency. We identify the lack of a unified structural characterization of DiT
attention as a key limitation of existing methods, and establish that
video DiT
attention exhibits periodic diagonal stripe structures along both temporal and spatial dimensions. To formally encode these structured patterns within a single efficient kernel, we present PSA, a parameterized stripe
attention that formalizes the observed stripe regularity, unifying diverse
attention patterns for efficient mask generation. This unified representation enables a single hardware-efficient CUDA kernel to process all sparse patterns, achieving FlashAttention-3-level Model FLOPs Utilization. To determine optimal sparsity configurations, we propose a training-free offline search
algorithm that automatically maximizes sparsity under a specified error tolerance for each
attention head. Experiments on HunyuanVideo and Wan~2.1 demonstrate that PSA achieves 1.57$\times$ and 1.37$\times$ end-to-end speedups over FlashAttention-3 baselines, with acceptable visual quality degradation.
Read the full abstract ▾
All authors Xingyu Jia, Baole Ai, Ang Wang, Kang Zhao, Yong Li
Software Engineering
Cross-Organizational SysML Model Integration: A Survey of Challenges and AI-Supported Tasks
Zirui Li, Torsten Brix and Stephan Husung
Cross-organizational collaboration is widely regarded as a key promise of SysML-based Model-Based Systems Engineering (MBSE), yet practitioners still face persistent challenges when exchanging and integrating system models. In parallel, Large
Language Models (LLMs) raise expectations for AI-assisted model understanding and integration, while reliability and required human oversight continue to pose challenges. This paper reports the results of an online questionnaire survey with 29 MBSE stakeholders involved in cross-organizational collaboration. Respondents rated eight predefined integration challenge categories and six AI-supported task types on five-point Likert scales. The results indicate that stakeholders perceive model integration as a multi-dimensional
alignment problem across semantics, behavior, traceability, and exchange interoperability. These perceptions vary by organizational role and frequency of integration involvement. AI is rated highly useful for analysis tasks such as semantic structure analysis and inconsistency detection, and respondents predominantly prefer human-in-the-loop use with mandatory verification. These findings motivate AI support that enhances, rather than replaces, engineering responsibility in SysML-based integration.
Read the full abstract ▾
Systems and Control · Cross-listed from quant-ph
Towards Scalable Quantum Unit Commitment in Power Systems: Encoding and Complexity Reduction Techniques
Marc Carrillo-MuÑoz, Sergio MartÍnez-Hermida, Sara Barja-MartÍnez et al. (+2 more)
This paper develops a
Quantum optimisation Unit Commitment (UC) framework that benefits from Pauli Correlation Encoding (PCE) as a
qubit reduction preprocessing technique and Sample-based
Quantum Diagonalisation (SQD) as a hybrid post-processing refinement method. The UC problem is formulated in binary form, then transformed into a QUBO problem and mapped onto an Ising representation suitable for adiabatic
quantum evolution within the Qibo framework. This study analyses how PCE and SQD techniques affect
qubit scalability, computational effort, feasibility, and probability of recovering the optimal solution as the number of generators increases. The results show that PCE reduces the effective size of the encoded problem, SQD improves the concentration of probability on feasible and optimal solutions, and their combined application provides the best overall behaviour in several scalable case studies, achieving more reliable solutions with lower effective computational cost than the unreduced formulation. The repository is available open source in Github (link is not yet available until work is published. However, if requested by the reviewers, we can make it open for a scific time window, if requested).
Read the full abstract ▾
All authors Marc Carrillo-MuÑoz, Sergio MartÍnez-Hermida, Sara Barja-MartÍnez, Antonio E. SaldaÑa GonzÁlez, MÒnica AragÜÉs-PeÑalba
Social and Information Networks
Constrained Enumeration Reveals Hidden Optima and Precision-Dependent Degeneracy in Modularity-Based Community Detection
Fabio Morea
Modularity landscapes are often flat near the top: many distinct partitions achieve indistinguishable scores, and repeated runs of heuristic
algorithms can still miss accessible optima. We introduce a two-phase workflow that (i) samples partitions until novelty saturates, then (ii) localises instability to a small subset of nodes and enumerates only that residual ambiguity under a locked stable core. Across a simple 50-nodes
benchmark network, and a real weighted collaboration network, constrained enumeration systematically expands plateau coverage and can improve modularity beyond extensive Louvain restarts. Finally, we show that edge-weight rounding qualitatively reshapes plateau structure, making precision sensitivity an essential part of solution-space reporting.
Read the full abstract ▾
Artificial Intelligence
ImbalancE: Inference-Time Latent Search Against Degree Imbalance in Link Prediction
Alberto Bernardi, Luca Costabello and Christophe Gueret
Knowledge Graph
Embedding models have been extensively used to learn representations of entities and relations in Knowledge Graphs for predicting missing links. However, the quality of the learned representations varies a lot across different areas of the graph. If previous research has loosely linked the problem to relation types or degree bias, we show that it is more widespread and it correlates with the degree imbalance of the entities in test triples. In particular, the prediction of a target entity that has a degree much smaller than the degree of the anchor entity is extremely problematic. This is critical in recommender systems and other use cases, where these triples represent important corner cases. To address this issue, we propose an inference-time latent search optimization method capable of significantly improving model predictions on the most imbalanced triples. Built on top of a pre-trained model, it explores the
embedding space at evaluation time, blending known and out-of-band information to mitigate the degree imbalance bias. We show the value of our approach on imbalanced triples from common
benchmark datasets, where we outperform conventional methods, opening the door to the successful adoption of Knowledge Graph
Embedding models on these critical corner cases.
Read the full abstract ▾
Computer Vision
Salt++: Context-Aligned Post-Training for Few-Step Streaming Multimodal Generation
Xingtong Ge, Yutong Wang, Lunjie Zhu et al. (+7 more)
Few-step streaming audio–
video generation requires both causal modeling and step
distillation, yet standard training recipes face two context-related challenges. Teacher forcing pairs clean history with a noisy target, but supervises predictive contextual representations only indirectly through velocity prediction. Meanwhile, directly reusing bidirectional score models in causal Distribution Matching
Distillation (DMD) creates a mismatch between generation and scoring contexts. We address these challenges with Salt++, a two-stage post-training framework comprising Causal Self-Flow (CSF) and context-aligned autoregressive DMD. CSF exploits contextual information asymmetry by varying the history while keeping the noisy target fixed: a noise-mixed-history student aligns its intermediate representations with those of a clean-history exponential-moving-average teacher. This self-supervised signal encourages the student to extract semantic information and improves cross-modal
alignment. Context-aligned AR DMD shares the causal mask and prefix across generator sampling, fake-score training, and real-score evaluation to match generated and reference distributions under a block-conditional KL objective. With calibrated teacher guidance, it performs clean-prefix few-step
distillation and then adapts to generated histories without switching objectives or requiring separate consistency
distillation. At 480p, Salt++ improves visual and motion quality by 57% and 45% over OmniForcing on JavisBench under the same 4-step causal setting. A separate scale-wise post-training stage extends Salt++ to 4-step $1664\times960$ generation, outperforming bidirectional LTX-2 on six of seven reported metrics. Project page: https://xingtongge.github.io/Saltpp
Read the full abstract ▾
All authors Xingtong Ge, Yutong Wang, Lunjie Zhu, Haitao Lin, Fangyu Lin, Yushi Huang, Xin Zhang, Yi Zhang, Yu Liu, Jun Zhang
Robotics
All You Need Is Low Fidelity: Zero-Shot Sim-to-Real of Learned Robotic Fish Control
Liam Maloney, Simon Ramchandani, Mike Y. Michelis et al. (+2 more)
Complex tasks for
underwater robots remain limited by the capabilities of their controllers. Learning a better one for a soft, underactuated robotic fish trades simulator cost against fidelity. We show that an intentionally low-fidelity simulator is enough: a stateless, quasi-steady fluid model with no wake and no added-mass history suffices to learn a general, closed-loop controller that transfers to hardware without tuning. Our platform is a soft, single-motor, tendon-driven fish whose policy observes only what the hardware can measure. A staged pipeline grounds the simulator in two independent identifications, fixing the tail dynamics and a stateless fluid model; the policy then acts through a band-limited rhythmic trajectory generator rather than commanding the tail directly. Deployed unchanged in an outdoor pool, a single policy performs closed-loop target reaching, disturbance rejection, and out-of-distribution target acquisition and tracking. The transfer rests on the constraint rather than the fidelity: the generator cannot leave the band over which the fluid was identified. This raises the question of how much of the physics can reside in the controller rather than in the simulator.
Read the full abstract ▾
All authors Liam Maloney, Simon Ramchandani, Mike Y. Michelis, Ronan Hinchet, Robert K. Katzschmann
Computation and Language
CypherTurn: A Multi-Turn Benchmark for Conversational Text-to-Cypher Evaluation and the Autonomy Divergence
Yuzhe Zhang, Weijie Zhu, Haolin Yang et al. (+5 more)
Graph databases are increasingly queried through natural
language, yet every existing
benchmark evaluates isolated single-turn queries rather than the multi-turn sessions through which analysts actually work. We introduce CypherTurn, the first
benchmark for conversational Text-to-Cypher evaluation, comprising 721 sessions and 5,927 turns across 7 knowledge graphs and 13 conversational phenomena. We evaluate 15 models under a guided oracle protocol and a fully autonomous agentic protocol, yielding four findings. First, the best model reaches only 64.7% execution accuracy, and session-level correctness remains below 5%. Second, despite strong overall rank correlation, frontier models exhibit a consequential reordering of the top of the leaderboard under autonomous operation, a phenomenon we term the Autonomy Divergence, which reveals error-management as a partially independent capability from raw generation skill. Third, scaling action budgets from x3 to x10 fails to close the autonomy gap, as the strongest frontier models self-limit to approximately two actions per turn regardless of available budget. Fourth, single-turn Cypher fine-tuning degrades multi-turn instruction following, while architecture-appropriate specialization outperforms several frontier models. These results establish CypherTurn as an open challenge for conversational graph database
reasoning. Code and data are available at https://github.com/BarryQ/CypherTurn.
Read the full abstract ▾
All authors Yuzhe Zhang, Weijie Zhu, Haolin Yang, Ziyun Zhang, Xianwei Xue, Mengke Chen, Qiutong Pan, Huaqian Cai
Artificial Intelligence
CF-LoRA: Decoupled Factor Aggregation and Adaptation-Aware Client Clustering for Federated LoRA Fine-Tuning
Mengjun Yi, Langxing Yang, Suhan Guo et al. (+2 more)
Federated LoRA fine-tuning enables parameter-efficient adaptation of pre-trained models without sharing private data, but suffers from two fundamental mismatches under heterogeneous client data: a structural aggregation mismatch caused by independently averaging LoRA factors, and a statistical collaboration mismatch caused by enforcing a single global adapter across divergent clients. To address these issues, we propose CF-LoRA, a clustered
federated LoRA fine-tuning framework that combines decoupled factor aggregation with adaptation-aware client clustering. CF-LoRA first learns a globally shared $A$ factor while retaining personalized $B_i$ factors, then identifies clients with similar adaptation patterns based on the cosine similarity of their learned $B_i$ factors, and finally performs intra-cluster $B$-factor aggregation with a frozen $A$ factor. By decoupling LoRA factor aggregation, CF-LoRA preserves the low-rank structure and mitigates the structural aggregation mismatch, while adaptation-aware clustering promotes collaboration among clients with similar adaptation patterns and reduces negative transfer caused by statistical heterogeneity. Experiments on four
language tasks and four
vision datasets with RoBERTa and ViT show that CF-LoRA achieves the highest average accuracy in both modalities while communicating only one LoRA factor per optimization round.
Read the full abstract ▾
All authors Mengjun Yi, Langxing Yang, Suhan Guo, Furao Shen, Jian Zhao
Machine Learning
Abductive World Modeling via Causal Representation Learning
Ziqi Liu, Songhan Yang, Linfan Zhou et al. (+4 more)
The central challenge of world modeling is to learn representations that capture how the world evolves. However, existing world models predominantly represent future states without explicitly capturing the latent causes underlying their
evolution, limiting their ability to reason about why and how the world changes. To address this limitation, we propose Abductive World Modeling (AWM), a framework that learns structured causal representations by abductively inferring latent causes from predicted futures. Specifically, we realize AWM through the Hierarchical Abductive State Pyramid (HASP), which organizes the inferred world state into three complementary components - Entity, Dynamic, and Relation - capturing what exists, how it changes, and how entities interact, respectively. By jointly
reasoning over the current observation and its predicted future, HASP abductively infers these latent factors and integrates them into a structured state representation for downstream
reasoning. To the best of our knowledge, AWM is the first framework to introduce abductive state inference into latent-space world modeling for learning structured representations of world dynamics. Experiments across physical prediction, causal
reasoning, and action understanding demonstrate the effectiveness of our approach. Compared with V-JEPA, a state-of-the-art latent-space world model, AWM improves physical prediction AUROC by 10.7%, causal
reasoning accuracy by 16.8%, and action Top-1 accuracy by 68.0%.
Read the full abstract ▾
All authors Ziqi Liu, Songhan Yang, Linfan Zhou, Jiatong Liu, Lijun Peng, Long Wan, Yinqi Bai
Artificial Intelligence
REALHOP: Rethinking Multi-Hop Reasoning Evaluation via Behavioral Auditing
Jiawen Tao, Xiaokun Yuan, Yaoming Li et al. (+4 more)
Complex questions often require multi-hop
reasoning that connects facts distributed across sources or distant regions of a long context through intermediate steps.
Benchmarks commonly evaluate this ability with questions built around predefined
reasoning chains, treating a correct answer as evidence that the intended composition was used. Yet answer correctness alone leaves open whether success depends on the evidence associated with each intended step: models may instead rely on memorized associations, shorter paths, or partial evidence. We examine this dependence using the Behavioral Necessity Rate (BNR), which measures how often targeted evidence removal prevents answer recovery on initially correct instances. Across five existing
benchmarks, panel-mean BNR ranges from 16.6% to 48.9%, exposing a substantial gap between annotated structure and observed dependence. Guided by this diagnosis, we introduce REALHOP, a diagnose-construct-verify framework that rebinds entities, factorizes selected relations, adds complete competing paths, and places evidence at traceable locations. Structural and semantic checks precede freezing; behavioral interventions follow. On 790 paired MuSiQue questions, REALHOP raises panel-mean BNR from 27.4% to 94.4% while retaining high Full accuracy. It also yields high BNR on REALHOP-FRAMES and REALHOP-LONGBENCH. On 216 long-context questions, the matched multiple-choice spread across 16 models grows from 13.9 to 59.2 points and persists under repeated open-ended evaluation. Together, these results show that a conceptually coherent chain and a correct final answer do not by themselves establish multi-hop
reasoning. Verifying that success depends on every intended hop is therefore as fundamental to multi-hop evaluation as measuring answer accuracy itself.
Read the full abstract ▾
All authors Jiawen Tao, Xiaokun Yuan, Yaoming Li, Chenxu Liu, Mengzhou Wu, Tong Yang, Maxm Pan
Computation and Language
SRJudge: Empowering Large Language Models with Selective Reasoning for Fine-Grained Knowledge Concept Tagging
Zhiwei Yang, Jiahua Yang, Huiru Lin et al. (+2 more)
Knowledge concept tagging aims to assign specific concept or topic labels to educational content, which is essential for both educators and learners in traditional and online teaching practices. Recent work has explored large
language models (LLMs) for this task, achieving promising performance. However, LLMs still struggle to select the correct concept from a large-scale candidate set due to the high dimensionality of the decision space. In this paper, we propose a novel three-stage Select-Reason-Judge (SRJudge) framework, which empowers LLMs with selective
reasoning capability for fine-grained knowledge concept tagging. Specifically, the Selector in Stage 1 first narrows the candidate concepts to a top-K shortlist by fine-tuning a small
language model (SLM), e.g., BERT, since the top-$K$ predictions hit the correct concept in most cases, thereby reducing the decision space of correct candidates. Next, the Stage 2 Reasoner employs a lightweight LLM for refined
reasoning over the shortlisted candidates. It further integrates an improved reinforcement learning strategy with a dynamic task-specific reward function and a
pruning mechanism to better align with human
reasoning preferences. Finally, a larger LLM acts as a judger that evaluates the overall rationality of the
reasoning process and its explanations to determine the final output. In addition, we construct two high-quality
datasets for further validation, i.e., the biology
dataset S_Bio and the physics
dataset S_Phy. Experimental results demonstrate that our method consistently outperforms state-of-the-art baselines across
benchmark datasets, verifying its effectiveness and superiority. Resources are available at: https://github.com/Nicozwy/SRJudge.
Read the full abstract ▾
All authors Zhiwei Yang, Jiahua Yang, Huiru Lin, Xing Chen, Quanlong Guan
Computer Vision
UltraMatch: Transport Path Routing for Ultra-Fast and Memory-Efficient Image Matching
Jiajun Le, Yifan Lu, Zizhuo Li et al. (+3 more)
Despite recent advances in accuracy and efficiency, coarse matching remains an indispensable yet costly stage in existing semi-dense matchers due to dense
token-level matching. We present UltraMatch, an ultra-efficient and scalable semi-dense matching framework that bypasses the quadratic computation and
memory cost of dense
token-level matching by routing only a small fraction of candidate matching paths. At its core, a lightweight Transport Path Router operates on coarse block representations to rank candidate target blocks for each source block and retain only a small set, restricting subsequent
token-level matching to the selected paths and avoiding the construction of the full
token-to-
token matching
matrix. We further design a sparse global Dual-Softmax that performs matching only over the routed block candidates while retaining global competition across the sparse matching space. Beyond matching acceleration, UltraMatch employs deployment-oriented structural reparameterization for feature extraction and a tiny fine matching head with shared parameters, further reducing inference cost and
memory consumption. UltraMatch achieves competitive accuracy among semi-dense matchers, while running 1.67$\times$ faster than SuperPoint+LightGlue with only 0.44 GiB peak inference
memory. Its scalability enables inference at up to 6K resolution on a single RTX 3090, whereas existing semi-dense matchers run out of
memory before reaching 2K. Our routing strategy is also transferable, delivering about 2$\times$ end-to-end speedup in EDM and ELoFTR without accuracy loss. The project repository is available at https://github.com/JiajunLe/UltraMatch.
Read the full abstract ▾
All authors Jiajun Le, Yifan Lu, Zizhuo Li, Lei Cao, Junjun Jiang, Jiayi Ma
Sound · Cross-listed from eess.AS
Louder, Longer, Livelier: Acoustic Shortcuts and Underspecified Rationales in Speech LLM Judges
Mingyue Huo, Shivam Mehta, Bhavin Jawade et al. (+2 more)
LLM-as-a-judge is widely used for evaluating text, but extending this paradigm to
speech requires models to interpret acoustic as well as linguistic evidence. This introduces a modality-specific risk: a
speech judge may treat a perceptually salient cue as evidence of quality even when that cue is irrelevant to the target criterion or receives more weight than human listeners give it. We call this behavior an acoustic shortcut. To study it, we audit six
speech LLM judges using controlled manipulations of intensity, content richness, and emotional delivery. We evaluate both pointwise scoring and pairwise comparison, using human preference calibration to interpret the results. The judges consistently reward louder audio, prefer content-rich
speech more strongly than human listeners do, and map emotional delivery into quality preferences. These effects are most visible in pairwise comparison, while pointwise scores often obscure them. More concerningly, the accompanying rationales rarely identify the acoustic cue that changes a judgment and instead repeatedly rely on a limited vocabulary, leaving them acoustically underspecified. Together, these findings show that reliable
speech judges must both resist acoustic shortcuts and ground their rationales in the acoustic evidence behind their decisions. To support reproducibility and future audits, we also release SpeechJudgeAudit, the controlled stimuli and evaluation tools used in this study.
Read the full abstract ▾
All authors Mingyue Huo, Shivam Mehta, Bhavin Jawade, Yinghong Lan, Haoqi Li
Systems and Control
An Energy-Based Framework for Transient Stability of Grid-Forming Converter Networks With Current Limiting
Wei Zhou and Yunjie Gu
Existing analyses for the transient stability of grid-forming (GFM) converters under current limiting mainly address single-converter systems, while network-level transient stability analysis remains challenging. This paper develops a network energy construction that incorporates current limiting while retaining a provable dissipation property. This structure enables Lyapunov-based analysis consistent with classical direct method for synchronous-machine based systems, without switching between mode-dependent energy functions. A two-GFM example using a reactive circular current limiter and impedance insertion illustrates the proposed framework. Electromagnetic transient simulations support the theoretical results.
Read the full abstract ▾
Social and Information Networks
Partition Space Maps for Community Detection: Visualizing Algorithmic Behaviour and Guiding Search
Fabio Morea
Community-detection methods search over possible partitions of a network, but the structure of this partition space is rarely examined directly. This paper introduces two complementary tools that make~$\mathcal{P}$ analytically and visually accessible. First, a canonical labelling scheme based on the Restricted Growth Sequence~(RGS) is adopted, assigning each partition a unique, permutation-invariant identifier and eliminating the need for pairwise similarity measures such as the Normalized Mutual Information. Second, granularity~$\Gamma$ is defined and combined with modularity~$Q$ to produce a two-dimensional projection: the Partition Space Map~(PSM). Within the $(\Gamma,Q)$ plane, only a discrete set of integer values of~$\Gamma$ is attainable, and upper and lower bounds on~$Q$ are derived directly from the deviation
matrix. These tools are demonstrated through complete enumeration of~$\mathcal{P}$ for small
benchmark graphs, revealing the fine structure of modularity degeneracy and the combinatorial constraints that shape the feasible region. The framework provides an exact, assumption-free reference for evaluating heuristic community detection
algorithms and lays the groundwork for geometry-aware exploration of partition space in larger networks.
Read the full abstract ▾
Computation and Language
AMU:Admission and Memory Update for Personalized Conversations—Structured Memory with SLM Guided Control
Tao Hwang and Yishi Diao
Large
language models (LLMs) have become the foundation of personalized assistants, but maintaining persistent user
memory across long-term interactions remains challenging. Existing
memory systems often focus on storage,
retrieval, or consolidation, while
memory writing remains less controlled: transient requests, duplicate statements, and outdated user states may enter
memory and later be retrieved for personalization. In this paper, we present AMU: Admission and
Memory Update for Personalized Conversations, an SLM-guided (Small
language model guided) structured framework for writing-time
memory control. AMU uses structured
memory filtering to decide what should enter
memory and SLM-guided storage management to determine whether an admitted record should be stored separately, discarded as a duplicate, or fused as an update. We evaluate AMU in a controlled
memory writing and
retrieval setting. Experimental results show that AMU maintains cleaner and more retrievable personalized
memories.
Read the full abstract ▾