Peer Revenue Fully funded

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science

cs Watch Computer Science

Monday 24 August

Machine Learning

SplitLite: Low-Rank Residual Compression for Split Learning

Tao Li, Yulin Tang, Qi Guo et al. (+1 more)

Federated fine-tuning of on-device large language models (LLMs) faces a significant computing burden. To overcome this limitation, split learning (SL) has emerged as a promising solution, which offloads the primary training workload to a powerful server. However, SL requires exchanging high-dimensional activations and gradients between clients and the server, resulting in prohibitive communication costs. To overcome this challenge, we propose SplitLite, a communication-efficient split federated LoRA fine-tuning method that exploits the low effective rank structure of consecutive-epoch activation and gradient residuals. Our key finding is that, under low-rank LoRA updates with the pretrained backbone frozen, the activation and gradient residuals of the same data sample between adjacent epochs exhibit low effective ranks, with most of their energy concentrated in a small number of singular directions. By exploiting this property, SplitLite transmits only quantized truncated singular value decomposition (SVD) residual factors, thereby significantly reducing both activation uplink and gradient downlink traffic. Extensive experiments on the GLUE benchmark across a series of advanced on-device LLMs demonstrate that our method reduces activation uplink communication costs by up to 93.5% and total communication costs by up to 88.6%, without sacrificing model performance.
Read the full abstract

All authors Tao Li, Yulin Tang, Qi Guo, Xianhao Chen

Computer Vision

AnaDiffusion: Anatomically Compositional Latent Diffusion for Controllable 3D Brain MRI Generation

Huiwen Han, Lulin Liu, Bangya Liu et al. (+8 more)

3D brain MRI generation has made significant advances in medical imaging, simulation, and controllable anatomical analysis. However, existing generative models typically synthesize 3D volumes monolithically, often overlooking regional anatomical structures and limiting local controllability. To address these limitations, we introduce AnaDiffusion, an anatomically compositional latent diffusion framework that factorizes the generation process into distinct, anatomically meaningful regions, followed by part-to-whole assembly and global refinement. Our approach first trains part diffusion models to capture local structural priors. We then inject an assembled anatomical composite of the parts into the whole-brain latent representation and continue denoising. This mechanism enables the model to resolve global context while preserving the injected anatomy. As a result, AnaDiffusion produces both explicit part assets and a globally coherent volume, thereby enabling controllable part editing without requiring subject-specific dense segmentation maps at inference time while maintaining consistent part-to-whole brain structure. On the subject-disjoint ADNI test split, AnaDiffusion achieves the lowest FID across the whole brain, left and right hemispheres, cerebellar-brainstem complex, and seam regions. It also achieves the best cerebellar and second-best ventricular and brainstem absolute Cohen's d values among the evaluated methods. In localized editing experiments, paired MS-SSIM demonstrates high target transfer and off-target preservation, supporting controllable part replacement with minimal unintended anatomical alterations.
Read the full abstract

All authors Huiwen Han, Lulin Liu, Bangya Liu, Yuanhao Cai, Nuo Chen, Xiaoqing Wang, Ziqian Xie, Chenyu You, Shuiwang Ji, Degui Zhi, Zhiwen Fan

Distributed Computing · Cross-listed from math.OC

CED-EF: Compressed Exact Diffusion with Error Feedback for Multi-Agent Learning

Sulaiman A. Alghunaim and Kun Yuan

We study decentralized stochastic optimization over a network of $N$ agents under compressed communication. We propose CED-EF, an exact diffusion-based method with error feedback that directly accommodates biased $\delta$-contractive compressors while communicating one compressed model-sized vector per node per iteration. For smooth nonconvex objectives with unbiased stochastic gradients whose variance is bounded by $\sigma^2$, where $\sigma\geq0$, we establish a convergence rate whose leading stochastic term is $\mathcal O(\sigma/\sqrt{NK})$. For $\sigma>0$, the dominant dependence of the corresponding transient time on the number of agents, compression level, and spectral gap $\Delta_\lambda$ is $\mathcal O(N^3/(\delta^4\Delta_\lambda^4))$, with fixed problem-dependent factors suppressed. Under the Polyak–Łojasiewicz condition, CED-EF attains a leading stochastic term $\widetilde{\mathcal O}(\sigma^2/(NK))$ with transient time on the order of $\widetilde{\mathcal O}(N/(\delta^2\Delta_\lambda^2))$. These dependencies improve the compression and/or network dependence of existing results. Numerical experiments on least-squares and logistic-regression problems illustrate the performance advantages of CED-EF.
Read the full abstract

Computer Vision

Misanthrope: A Privacy-Preserving Keypoint Detector

Francesco Vultaggio, Predrag Djindjic, Markus Gerke et al. (+2 more)

Image matching is a core component of applications such as Simultaneous Localization and Mapping (SLAM), Visual Localization, and Structure from Motion (SfM). However, the local image features central to this task are vulnerable to inversion attacks, which enable adversaries to reconstruct privacy-sensitive scene content from local features. These attacks pose a particular threat in distributed computing scenarios where the pre-computed features leave edge devices to be processed by remote servers. In this work, we introduce Misanthrope, a novel privacy-preserving keypoint detector trained through self-distillation to avoid detecting keypoints on people—a predominant source of privacy-sensitive content in most localization scenarios—thus mitigating inversion attacks at the source rather than through post-hoc obfuscation. We demonstrate how inverted images from traditional feature detection pipelines can be used to detect and re-identify people in the scene, while Misanthrope is able to mitigate these attacks. Furthermore, Misanthrope maintains image matching performance on par with the state of the art and even surpasses it in challenging settings where people act as distractors, such as phototourism and in-the-wild odometry. On the Image Matching Challenge 2021 Phototourism test set, Misanthrope is the top-performing sparse feature extractor in 7 out of 9 scenes. We make our model and its evaluation script available here: https://github.com/fratopa/misanthrope
Read the full abstract

All authors Francesco Vultaggio, Predrag Djindjic, Markus Gerke, Sebastian Tschiatschek, Phillipp Fanta-Jende

Computer Vision

Coarse Indexing, Fine Evidence: Decoupling Temporal Granularity in Long-Video RAG

Zhe Jin, Zhimin Lin, Bin Zheng et al. (+2 more)

Graph-based retrieval-augmented generation (RAG) provides a scalable paradigm for long-video understanding, but existing systems typically inherit a fixed temporal granularity from video segmentation when constructing their retrieval index. We argue that this design unnecessarily couples indexing granularity with evidence granularity: coarse representations can often suffice for locating relevant temporal regions, while fine-grained evidence remains important for downstream reasoning. We propose Density-Aware Graph Construction (DAGC), a training-free approach that decouples a query-independent coarse retrieval index from the original fine-grained evidence space. DAGC constructs a compact, density-adaptive graph index by merging visually redundant neighboring chunks, while preserving mappings to the original temporal units. Retrieved coarse regions are subsequently expanded back to the original chunk granularity for fine-grained evidence refinement and answer generation. Experiments on MLVU, VideoMME, and LongVideoBench show that DAGC retains only about 40–50% of the original graph nodes and achieves $1.3$–$1.7\times$ end-to-end wall-clock acceleration while preserving approximately 99% of the original QA performance. The gains transfer across different LVLM backbones and video RAG pipelines, suggesting that long-video RAG need not maintain the same temporal granularity for indexing and evidence reasoning.
Read the full abstract

All authors Zhe Jin, Zhimin Lin, Bin Zheng, Junhua Fang, Huihua Yang

Information Theory · Cross-listed from physics.optics

Sensitivity Limits for $\phi$-OTDR

Juan M. Marin, Roman Ermakov, Huwei Wang et al. (+2 more)

We demonstrate a new lower bound on the sensitivity of $\phi$-OTDR by estimating phase using Kalman filtering. Numerical analysis shows a $\sim$35-dB reduction in the minimum detectable SNR, compared to when using conventional phase estimation.
Read the full abstract

All authors Juan M. Marin, Roman Ermakov, Huwei Wang, Francesco Da Ros, Darko Zibar

Computers and Society

Large language models simulate intersectional synthetic identities with a budget of one to two dimensions

Virgile Rennard and Christos Xypolopoulos

Large language models are increasingly used as synthetic survey respondents, promising cheap access to rare intersectional populations. We test standard demographic-persona methods against every real intersectional subgroup across 15 waves of Pew's American Trends Panel – 21 million simulated response distributions from eight models. In real respondents, subgroup opinion is approximately the additive sum of its single-identity components, yet grows 2.5x more distinctive as identities intersect. Simulated respondents show no such composition: a single feature explains a two-feature persona's responses better than the additive combination in 75-82% of subgroups, and a third feature adds almost nothing. This collapse survives every prompting strategy we test. Additionally, the feature models retain is chosen nearly blindly – except that they systematically discard race and religion, the strongest real drivers of opinion. Synthetic samples offer intersectional personas but represent one identity at a time.
Read the full abstract

Data Structures and Algorithms · Cross-listed from quant-ph

Exact and Optimal Recursive Quantum Search via Hilbert-Space Decomposition

John Burke and Ciaran McGoldrick

Current approaches to quantum search fail to deeply exploit extant structure in the underlying Hilbert space. Decomposing the search by this structure empowers new strategies and formulations for quantum search and algorithm design. We present a new decomposition technique acting directly on this structure by recursively decomposing the Hilbert space and constructing the search operator from reflections over the resulting partition. When initial and target states factorise over this partition, dynamics reduce to a single rotation in a two-dimensional plane at each level, with angle given by a scalar recurrence. This recurrence avoids error accumulation from separately bounding success probabilities at each level, yielding an exact state description enabling treatment of the recursion as a whole. We obtain the target state deterministically and derive oracle and non-oracle costs independently of the search setting. For unstructured search, our approach attains the simultaneously optimal $\Theta(\sqrt{N})$ oracle and non-oracle gate counts. For spatial search on $d$-dimension grids, it recovers the $O(\sqrt{N})$ time for $d\geq3$ and the $O\bigl(\sqrt{N}(\log N)^{3/2}\bigr)$ bound of Aaronson and Ambainis for $d=2$. The exact description of the recursion extends over our decomposition to new subdivision structures and provides a new approach for applying and analysing recursion in quantum algorithm design.
Read the full abstract

Artificial Intelligence

PatchWrite: One Line, Not One Section – Compile-Gated, Validity-Preserving Editing for AI-Drafted Manuscripts

Weiwei Yang

Automated manuscript pipelines often regenerate an entire section to repair a local defect, allowing unrelated metrics and citations to change even when the resulting PDF still builds. PatchWrite instead constrains how candidate edits become committed manuscript states: it reuses bounded EDIT N M editing and rollback, but tightens compilation acceptance with fatal-log checks and adds evidence locks that require every cited key and experimental numeric token to be attested by a reference registry or experimental log. Candidates that fail either check are rejected and the previous HEAD is retained. On a 24-manuscript x 8-fault oracle stress test (768 jobs, evenly split between compile-breaking and content-only faults), whole-slot rewriting mutated an unrelated "12-layer" line in every case (0/192 preserved; numeric Jaccard 0.6667), whereas PatchWrite preserved it in 192/192 cases. Removing the compile gate reduced acceptance to 0, while removing the evidence gate allowed a hallucinated citation to pass. The same pattern held across all eight faults. To test the protocol with generation rather than oracle edits, we reran the 192 jobs with the writer model proposing the edits. The model's candidates were accepted in 75% of cases; nearly all rejections came from one reproducible failure mode in which the model attempted to delete a line using an empty replacement unsupported by the current grammar. Every accepted candidate passed both gates, and 93.75% fixed the injected fault; the remaining cases involved a technically valid but sentence-inappropriate citation and one markup-changing near-miss. In a blind evaluation of sixteen PDF pairs, both raters preferred PatchWrite for preserving lab-grounded facts (C1 Likert 5.0 vs. 2.0), while rating prose quality nearly identically. Logs from 193 in-product drafting tasks show the same classes of failures occurring in practice.
Read the full abstract

Robotics

Free-Energy-Gated Plasticity for Real-Time Online Motor Learning in Physical Human-Robot Interaction

Hiroki Sawada and Jun Tani

Fully online embodied learning requires synaptic adaptation to acquire new behaviors while preserving previously learned dynamics during ongoing interaction. We extend the Predictive-Coding-inspired Variational Recurrent Neural Network (PV-RNN) to continuously adapt its synaptic weights and propose Free-Energy-Gated Plasticity (FEGP), which regulates the effective learning rate according to variational free energy. In real-time physical human-robot interaction, a randomly initialized network acquired three cyclic motor patterns without offline pretraining, replay, or task-boundary signals, with all three patterns emerging in autonomous rollouts. Controlled experiments over ten randomized teaching streams and five network initializations per stream showed that FEGP substantially improved repertoire coverage and retention of previously acquired patterns after they left the recent observation window. Neither a constant learning rate matched to the gate's time-averaged effective rate nor replay of the same gain values with disrupted temporal organization reproduced these improvements. These results indicate that the temporal allocation of plasticity relative to model-environment mismatch, rather than simply its average magnitude or distribution, is critical for maintaining previously acquired behaviors during continued online learning.
Read the full abstract

Logic in Computer Science

Nonstandard Axiomatic Semantics

Patrick Cousot

Similar to Skolem's nonstandard models of Peano's naturals, we show that axiomatic semantics based on Hoare logic has nonstandard models and so does not specify a unique, well-defined, and formal operational semantics of programming languages. We propose to enrich axiomatic semantics with additional proof obligations to solve this ambiguity problem. These proof obligations are always satisfied for standard trace models so that Hoare logic proofs are unchanged for these standard models.
Read the full abstract

Computer Vision

ENCORE: Entropy-Guided Cropping and Attention Regularization for Robust Vision–Language Understanding

Yuanhao Sun, Huawei Ji, Jiaxin Ding et al. (+2 more)

Vision-Language Models (VLMs) perform well on diverse vision-language tasks, but transformer-based visual encoders split images into fixed-resolution sub-images, compromising object integrity in lightweight VLMs. Existing methods only focus on the visual modality and fail to dynamically preserve the integrity of prompt-relevant regions, limiting performance. In this work, we observe that the early-layer image-text entropy of cross-modal attention strongly correlates with answer grounding quality and task accuracy. Building on this finding, we propose ENCORE, an entropy-guided framework with two components: At inference, an Entropy-based Cropping Strategy (ECS) evaluates a small set of candidate crops and selects the one with minimal entropy, preserving contiguous regions relevant to the prompt. At training, Entropy Regularization Training (ERT) augments next-token prediction with an entropy term that sharpens attention on key visual tokens while down-weighting irrelevant ones. Experiments on ten VQA benchmarks show that ENCORE, fine-tuning only 0.14% of parameters, achieves an average 1.43% accuracy gain and state-of-the-art performance among recent 2B-parameter VLMs. Our code is released in https://github.com/baokou-fw2/ENCORE.
Read the full abstract

All authors Yuanhao Sun, Huawei Ji, Jiaxin Ding, Luoyi Fu, Xinbing Wang

Machine Learning

A Physical Response-and-Memory Model for Muon Optimization

Yinze Hu, Hongjun Xiang, Xingao Gong et al. (+1 more)

Training large language models is costly. How low a loss the same compute can ultimately reach depends on how each step's gradient is converted into a weight update; the rule that performs this conversion is the optimizer. From SGD and AdamW to the recent Muon, effective update rules have mostly been shaped by engineering intuition and then selected on benchmarks. Muon semi-orthogonalizes the momentum matrix before applying the update and has kept breaking records on public training benchmarks; yet why the semi-orthogonalized direction works, and over how long a history the momentum should average, are two questions at present answered mainly by experience. Here we treat the weight matrix during training as a responsive medium with memory and build a physical model for it, in which both questions find answers: the semi-orthogonalized direction is the maximally dissipative response under an output-side safety budget, which explains why it works; momentum is the internal stress accumulated by the medium; how long it should average is set by the relaxation of this stress, and a real medium relaxes on more than one timescale, the simplest form being one fast and one slow. On this basis we propose the Bi-Maxwell optimizer. The framework further yields a testable consequence: gradient directions change fast early in training and more slowly later, so the optimal memory length should grow with training stage; step-by-step measurements of a proxy for it by a read-only probe across 8 independent training trajectories are consistent with this consequence. Replacing the memory kernel alone, from a single timescale to two, brings training to the target loss in noticeably fewer steps on a public large-language-model optimizer benchmark.
Read the full abstract

All authors Yinze Hu, Hongjun Xiang, Xingao Gong, Hongyu Yu

Computation and Language

LLM Pedagogical Behavior in AI Tutoring Interactions

Suhyeon Lee, Juneha Baek, Jaehyeong Park et al. (+1 more)

Students increasingly use LLMs as tutors for coursework and problem solving. Little is known about the level of assistance LLMs provide when students use them as tutors in authentic learning interactions. This matters because tutoring responses can differ substantially in how directly they help students complete a task. We operationalize this dimension as scaffolding level and develop a five-level scale, validated against human annotations, that characterizes responses according to the degree of direct assistance they provide. We apply the scale to 14,637 LLM responses from 203 students in a university AI course. Responses are overwhelmingly concentrated at high levels of assistance, with more than 95% classified as either Explaining or Solving. Scaffolding level is systematically associated with students' subsequent conversational behavior, but provides little additional predictive information about performance on three subsequent exams beyond prior achievement and dialogue behavior. These findings provide an empirical baseline for LLM assistance in tutoring interactions and a measurement framework for evaluating how alternative tutoring designs change that assistance.
Read the full abstract

All authors Suhyeon Lee, Juneha Baek, Jaehyeong Park, Donghyuk Shin

Networking

Channel-Token Attention for Reliable Dynamic Spectrum Access under Bursty Primary-User Traffic

Krishna Acharya, Dinanath Padhya, Utsab Dahal et al. (+2 more)

Dynamic spectrum access must coordinate secondary users under bursty primary-user activity while preserving packet reliability and delay. We present TACAN, a centralized policy that represents each channel as a token containing occupancy history and automatic-modulation-classification entropy; a context token supplies queue class, delay and user identity. A Transformer encoder is warm-started from an occupancy-greedy policy and refined with proximal policy optimization. The frozen policies were trained to maintain a channel assignment in every slot, including when queues were empty. We therefore replay them on held-out trajectories and distinguish standby assignment success from packet-present access and packet delivery. In a 20-channel network with 60 primary devices and 4 secondary users, TACAN achieves 92.53% +/- 0.47 packet-present access success, compared with 89.94% for Greedy and 83.53% for PPO+MLP. Its paired gain over Greedy is 2.59 points (parametric 95% CI 1.89-3.29), with wins in all five seeds; the exact two-sided sign-test value is 0.0625. The gain rises from 0.57 points at normal primary-user load to 7.67 points at extreme load. TACAN also reduces mean delivery delay from 1.208 to 1.123 slots and the conditional user-reliability gap from 9.69 to 3.15 points. Delivered packets per SU-slot remain arrival-limited (30.12% versus 30.11%), so no packet-throughput gain is claimed.
Read the full abstract

All authors Krishna Acharya, Dinanath Padhya, Utsab Dahal, Ashish Kandel, Binod Sapkota

Numerical Analysis

Why the Kellogg Mesh Is Radial: A Mathematical Explanation of a Classical Computational Benchmark

Shun Zhang

Kellogg's checkerboard interface problem is a classical benchmark for robust adaptive finite element methods. Its successful adaptive meshes are radial: they refine strongly toward the interface crossing but show no angular structure, despite the large contrast and the asymmetric solution. We explain this by proving that the singular solution $u(r,\theta)=r^\gamma\mu(\theta)$ satisfies the exact identities $\kappa|\nabla u|^2=\Lambda r^{2\gamma-2}$ and $\kappa|\nabla^2 u|_F^2=2(1-\gamma)^2\Lambda r^{2\gamma-4}$, with $\Lambda=\gamma^2\cos^2(\pi\gamma/4)$ and the Hessian taken separately in each quadrant. The point is what has disappeared: the right-hand sides depend on $r$ alone, although $\kappa$ and $u$ each depend on the angle as well. Combined with equal discretization-error distribution, this shows that the target element density is radial, so a correct mesh should display nothing but refinement toward the center, and a Kellogg mesh that is not radial is visible evidence that the computation is not following the coefficient-weighted local difficulty. The reading is specific to this benchmark: on a second interface problem the same estimator correctly produces a strongly material-biased mesh, with a computed element-count ratio of $3.934$ against the predicted $4$. A byproduct gives the benchmark constants in closed form, so the problem data can be generated from $\gamma$ alone at any precision.
Read the full abstract

Robotics

InstructMove: A Text-Indispensable Benchmark for Instruction-Following Manipulation

Mengao Zhao, Ziang Li, Chaodong Huang et al. (+15 more)

Vision-language-action (VLA) models have made general-purpose robot manipulation increasingly plausible by conditioning robot actions on natural-language instructions. A key test of such generality is whether policies actually follow language instructions. Yet many manipulation benchmarks leave this ability underdetermined: the intended object or destination is often visually salient or uniquely feasible, allowing policies to succeed without grounding the instruction. We argue that instruction-following evaluation should be text-indispensable: multiple actions should be visually and physically plausible, while only one should be consistent with the language instruction. We introduce InstructMove, a text-indispensable benchmark for instruction-following manipulation. InstructMove instantiates this principle in pick-and-place scenes with semantic distractors, decomposing instruction following into category identification, attribute discrimination, spatial reasoning, and compositional pick-and-place. InstructMove supports a train-eval protocol with InstructMove training data and held-out evaluation tasks, with additional diagnostics for language dependence. Experiments with representative VLA policies show that InstructMove provides a controlled testbed for diagnosing visual shortcuts and that InstructMove simulation data can improve real-world instruction-following manipulation performance. Code: https://github.com/HorizonRobotics/RoboOrchardSim
Read the full abstract

All authors Mengao Zhao, Ziang Li, Chaodong Huang, Mengchen Ma, Haoyi Jiang, Yiwei Jin, Xinjie Wang, Yun Du, Xuewu Lin, Taojun Ding, Hongyu Xie, Jackson Jiang, Chunlei Yu, Kaihua Zhang, Lichao Huang, Liu Liu, Tianwei Lin, Zhizhong Su

Cryptography and Security

The Anonymity Gap: Understanding Real Privacy in Shielded UTXO-based Protocols for DeFi

Hanze Guo, Stefanos Chaliasos, Yebo Feng et al. (+1 more)

Shielded UTXO-based protocols are becoming a core form of privacy infrastructure for DeFi. Unlike mixers that organize privacy mainly around deposits and withdrawals, these protocols allow assets, once inside the shielded pool, to continue moving and being re-spent within the hidden state, and to become public only when users withdraw or interact with public DeFi protocols. Their anonymity is therefore no longer a flat pool-size problem, but a provenance problem that propagates across the note/UTXO, proof, and transaction layers. Yet, a unified analysis framework for this setting is still missing. We propose a layered system model and an analysis pipeline that uses prior history as the temporal baseline, applies cumulative pruning and cross-proof propagation to each proof's Commitment Set, and recursively traces the survivors through historical hidden-state transitions to derive the final transaction-level Anonymity Set Size. We evaluate our methodology on the complete on-chain histories of all four Railgun production deployments and five independent Hinkal pools across six EVM chains, analyzing 186,356 unshielding spend transactions. Using only public protocol traces and constraints, our non-heuristic analysis yields mean Anonymity Set Size reductions of 40.1%-59.0% relative to each deployment's temporal baseline; 3,679 transactions retain at most 10 addresses, including 1,228 singletons. Public token constraints are the strongest and most stable source of pruning in both protocols, while the effects of tree number, proof roots, and value constraints vary with protocol design and historical state. Together with representative cases, these results reveal interpretable anonymity-loss patterns and implications for user behavior and future protocol design.
Read the full abstract

All authors Hanze Guo, Stefanos Chaliasos, Yebo Feng, Jiahua Xu

Computation and Language

What Does Activation Steering Control? Attribution Across Answer Encodings and Output-Sensitive Subspaces

Zhiwei Gao, Shaowen Peng, Shoko Wakamiya et al. (+1 more)

Activation steering is often evaluated under the answer encoding used to construct the direction. A reported gain may reflect the intended judgment or compatibility with answer identifiers seen during construction. We introduce Cross-Encoding Steering Evaluation, which freezes an intervention while re-encoding answers to the same held-out items. On NormBank, after A/B/C identifiers are reassigned, contrastive activation addition (CAA) induces larger target-versus-source score changes for the extraction indices than for the semantic labels under the new mapping. We call this extraction-index following. Varying identifier vocabulary (A/B/C, X/Y/Z, or 1/2/3) and row order shows that the effect tracks extraction index rather than row position. After matching direction norms across layers, extraction-index following emerges mainly at later depths. A low-rank output-sensitive component containing 15.4% of the direction's squared norm retains 96.3% of this effect. An Inference-Time Intervention (ITI)-style method also favors extraction-index over semantic-label following on NormBank in three models. In aggregate, MNLI favors extraction-index following, whereas Social Chemistry 101 (SC101) favors semantic-label following. Multiple-choice and open-ended evaluations can yield different behavioral conclusions. Thus, a steering gain under one answer encoding does not by itself identify what the intervention controls.
Read the full abstract

All authors Zhiwei Gao, Shaowen Peng, Shoko Wakamiya, Eiji Aramaki

Robotics

CSymPlan: Certified Symbolic Planning and Control for High-DOF Manipulators

Aditya Narendra, Ashok Kumar Saini, Mahathi Anand et al. (+3 more)

Robot manipulators are commonly engineered around a decoupled motion-generation stack: a planner computes a collision-free path and a lower-level controller tracks the resulting reference. This separation is computationally convenient, but it can produce references that are difficult to execute under actuator limits, tracking error, model mismatch, and small obstacle clearances. We present CSymPlan, a certified symbolic planning and control framework for high-DOF manipulators with two complementary implementations: an offline implementation that precomputes certified reach-avoid feedback policies for known workspaces; and an online implementation that synthesizes or updates symbolic policies at runtime from changing task and perception information using parallelization. The offline implementation reduces the manipulator dynamics to a sampled perturbed double-integrator model in operational space through feedback linearization, treats torque-realization errors, modeling inaccuracies, and measurement uncertainty as bounded disturbances, and refines the synthesized symbolic policy to the Franka FR3 through a quantization–lookup–torque realization pipeline. The online implementation uses the same abstraction and refinement interface, but replaces the precomputed policy table with a runtime pFaces request–synthesis–execution loop. In randomized simulated benchmarks and perception-driven Franka FR3 experiments, both implementations complete reach-avoid tasks with zero safety violations; whenever no certified action exists, the robot holds, replans, or stops safely instead of executing an uncertified command.
Read the full abstract

All authors Aditya Narendra, Ashok Kumar Saini, Mahathi Anand, Mahmoud Khaled, Fares J. Abu-Dakka, Abdalla Swikir

Machine Learning

Hierarchy-Aware Semantic Losses for Knowledge Graph Link Prediction

Filip Kronström and Ross D. King

Knowledge graphs are often accompanied by ontological class hierarchies that encode valuable semantic information, yet many link prediction methods either ignore such hierarchies or incorporate them indirectly through additional graph edges. Recent work introduced hierarchy-aware graph neural networks (GNNs), which use semantic losses derived from box embeddings to encourage satisfaction of subclass relationships during GNN-based representation learning. While this approach has shown promise for biological regression tasks, its effectiveness for knowledge graph link prediction has not been investigated. In this paper we evaluate hierarchy-aware semantic losses on link prediction across three benchmark datasets: AIFB, CoDEx, and BioKG. We combine graph neural network encoders with box-embedding-based semantic losses that encourage learned representations to better satisfy ontology-derived class hierarchies, and compare this approach to both standard link prediction models and models incorporating subclass relations as graph edges. Across all datasets, hierarchy-aware semantic losses significantly improve mean reciprocal rank (MRR) and consistently outperform models that incorporate hierarchy information through additional subclass edges. Relative to the baseline GNN models, MRR improved by 7.6%, 2.4%, and 15.5% on AIFB, CoDEx, and BioKG, respectively. Furthermore, semantic losses consistently outperform the alternative of augmenting the graph with subclass edges. These results are consistent with ontology-derived class hierarchies providing complementary information to graph structure, and suggest that encouraging hierarchical consistency through semantic losses is an effective and comparatively parameter-efficient mechanism for improving knowledge graph link prediction.
Read the full abstract

Information Retrieval

Hypergraph Embedding Indexing for Efficient Dense Vector Retrieval

Kishore Konda

Dense vector retrieval has become the foundation of modern semantic search, yet existing approximate nearest neighbor (ANN) indexes treat an embedding as an indivisible point in a high-dimensional space. In this work, we propose the Hypergraph Embedding Index (HEI), a framework that instead organizes documents according to combinations of highly activated latent embedding dimensions. This formulation enables inverted-index style candidate generation while preserving the semantic ranking capabilities of dense embeddings. We further demonstrate that constructing multiple complementary hypergraphs substantially improves retrieval coverage without the combinatorial growth associated with increasing the dimensionality of a single hypergraph. Finally, we establish that the statistical properties of embedding activations strongly influence coordinate-inverted indexing efficiency, introducing activation diversity as a diagnostic metric governing embedding indexability in coordinate-inverted frameworks.
Read the full abstract

Artificial Intelligence

SA-RSQ: A Versatile Sparse Representation Framework for Multi-modal Recommender Systems

Xiang Wang, Shigang Quan, Tingzhen Chang et al. (+5 more)

Deploying high-dimensional multimodal features in industrial recommender systems incurs substantial storage and latency overhead. Hard quantization is compact but introduces boundary distortion, whereas dense soft quantization couples representation quality to the limited storage budget. We propose Sparse Activation-based Residual Soft Quantization (SA-RSQ), which uses Top-K sparse routing and softmax weights to store compact (Index, Probability) tuples. The stored tuples decouple per-item storage from codebook dimensionality; for a fixed selected support, gradients propagate through the routing weights and weighted reconstruction without relying on a straight-through estimator. Experiments on a proprietary food-delivery advertising dataset show favorable reconstruction-performance and CTR trade-offs across storage budgets of 8-48 bytes per item. A preliminary Next-Distribution Prediction study and a one-week online A/B test further demonstrate the practical potential of SA-RSQ, with relative lifts of +2.51% in CTR and +3.66% in CPM.
Read the full abstract

All authors Xiang Wang, Shigang Quan, Tingzhen Chang, Kang Yang, Sitong Chen, Yabo Fan, Xingxing Wang, Zhaodian He

Software Engineering

Fairness Hazard Analysis for Socio-Technical Processes: A Multiple-Case Study in Bias-sensitive Organisational Settings

Giovanna Broccia, Lucio Lelii, Roberto Cirillo et al. (+5 more)

Fairness is increasingly recognised as a first-class requirement in socio-technical processes, where interactions among human actors, software systems, and AI technologies may lead to unfair outcomes in decision-making workflows. If left unaddressed, fairness hazards may accumulate and reinforce systemic bias, highlighting the need to engineer fairness proactively. Despite growing interest in fairness-aware systems, systematic methods for identifying fairness hazards in socio-technical processes and deriving requirements-level mitigations remain limited. To support fairness-by-design during requirements engineering (RE), Fairness Hazard Analysis (FHA) is introduced as a methodology for systematically identifying, analysing, and mitigating fairness hazards. FHA is first assessed through a proof-of-concept validation conducted via two focus groups. Then, a qualitative multiple-case study involving two organisations examines its applicability in real-world settings. The proof-of-concept validation highlighted the benefits derived from the structured nature of the method, and suggested the need to include iterative, dialogic reflection with domain experts. In the multiple case-study where FHA was applied, the practitioners involved were positively impressed by the results and confirmed the relevance of the identified fairness hazards (spanning up to 27% of the process elements), as well as the appropriateness of most of the proposed mitigations, while noting that contextual factors might hinder their implementation. The evaluation also highlighted mitigation patterns, such as independent review and collective decision-making, which can be transferred to different organisations. This paper contributes a structured and empirically validated methodology for integrating fairness considerations in RE and preventing systemic bias in socio-technical processes.
Read the full abstract

All authors Giovanna Broccia, Lucio Lelii, Roberto Cirillo, Dario Di Nucci, Samuel Fricker, Fabio Palomba, Giorgio O. Spagnolo, Alessio Ferrari

Robotics

Privileged Critic Training Enables Sensor-Free Thruster Fault Adaptation in End-to-End RL

Ricard Marsal I Castan and Miguel A. Olivares-Méndez

Fault-tolerant navigation for thruster-actuated robots requires online adaptation to failures that are neither binary nor fully observable: thrusters may degrade continuously, fail dead, or jam stuck-open. Classical fault detection pipelines require dedicated sensors unavailable at deployment; oracle controllers that observe the true failure state are equally impractical. We show that privileged critic training is sufficient for sensor-free fault adaptation: giving the PPO value function access to the true degradation state dgt during training, while the actor receives only standard task observations, shapes a policy that compensates for failures at deployment without any dedicated fault sensing. We propose RAFT (Recurrent Asymmetric Fault Tolerant), a policy with recurrent memory trained with a privileged asymmetric critic. Evaluated on a floating-platform robot (8 thrusters, 1 reaction wheel) under up to four simultaneous thruster failures, RAFT achieves 70.2% success at four concurrent failures, closing 84% of the gap from a failure-naive baseline (4.8%) to an oracle policy that sees the full degradation state at deployment (82.4%). All code, checkpoints, and data are open-source.
Read the full abstract

Artificial Intelligence

Budget-Constrained Embodied Perception: Four Resource Walls and a Pre-Registered Evaluation of Access-Structured Perception on Open Models at less than 31B

Defu Lin, Wenhui Chen, Ziyao Lin et al. (+3 more)

Embodied multimodal agents must answer from growing observation streams under a fixed per-decision token budget. We formalize this constraint through four resource walls: a perceptual Shannon wall for bounded state, a horizon wall for query-independent frame selection, a round wall for non-adaptive retrieval, and a conditional composition wall for fixed-depth inference. We introduce ASP, a training-free wrapper for frozen multimodal models that combines a capped structured state, a verbatim episodic index, and query-conditioned budget allocation with iterative access. Following a pre-registered protocol, we evaluate seven open-weight models from 3B to 31B on SEW-Bench, a license-free synthetic long-horizon walkthrough benchmark constructed to instantiate these walls. The registered natural-video benchmarks were not run because their frames require dataset agreements; our evidence therefore concerns access mechanisms, not natural-scene perception. Under a 4,096-token decision budget, ASP reaches 75 to 94% episodic retrieval accuracy, compared with 3 to 19% for equal-budget query-independent sampling, and budget reallocation outperforms quadrupling the sampling budget on every backbone. However, the full three-component architecture does not validate channel duality: removing the compressive state raises the flagship mean from 35.4 to 58.0, ASP does not outperform the verbatim-only baseline on any backbone, and two of four pre-registered falsification criteria fire. These results show that query-conditioned access, rather than parameter count or context growth alone, is decisive under a fixed budget, while prompted online compression does not earn its cost in this setting.
Read the full abstract

All authors Defu Lin, Wenhui Chen, Ziyao Lin, Jianlin Chen, Peiji Long, Chi Man Vong

Artificial Intelligence

Toward Effective and Reliable LLM Agents via Dynamic Ontology

Xiaohui Zhang, Zequn Sun, Chengyuan Yang et al. (+3 more)

Large language model (LLM) agents rely heavily on knowledge encoded in model parameters or presented as unstructured context. In domain-specific tasks, this leaves important semantic connections implicit. This often results in incomplete evidence use and brittle multi-step decisions. Ontologies offer a way to externalize domain concepts and relations as machine-interpretable structures, but constructing task-usable ontologies traditionally requires substantial effort from domain experts and is difficult to scale. Automatic construction is also challenging: an ontology that appears semantically plausible may not contain the relational structures needed for actual decision making. We present OaK, an ontology-as-a-kernel framework that dynamically constructs and refines task-oriented ontologies for LLM agents. Given task requirements and training data, OaK constructs an ontology and its knowledge graph, generates task-adaptation functions for graph reasoning, and uses judge feedback to iteratively refine both. By making relevant concepts and relations explicit, the ontology grounds knowledge retrieval and multi-step decision making. We evaluate OaK on TravelPlanner, CRMArenaPro, and ToolQA. Results show that OaK improves standard LLM agents, strengthens evidence grounding, and boosts the reliability of multi-step reasoning.
Read the full abstract

All authors Xiaohui Zhang, Zequn Sun, Chengyuan Yang, Yuanning Cui, Lingbing Guo, Wei Hu

Information Retrieval

Cascading Relevance-driven Recommendation Network for CTR Prediction in Trigger-Introduced Recommendation

Kaixuan Chen, Wenwen Wang, Xing Fang et al. (+2 more)

E-commerce has emerged as crucial platforms for people's daily consumption and shopping interests. There is a new recommendation scenario, Trigger-Introduced Recommendation (TIR), where users click interested product, which is defined as the trigger item, containing their instant interest, and in the undertaking page following the relevant target items. Distinguished from traditional search and recommendation scenarios, trigger contains relatively strong instant interest, which is more vague and implicit compared to search terms. Relying on large amounts of labeled data, existing methods lack the exploration of trigger relevance, which affects users' immersive experience. To alleviate this problem, we propose the Cascading Relevance-driven Recommendation Network (CRRN) to emphasize the interaction and relevance between trigger and target, comprising three essential components: 1) the Trigger-Target Interaction layer extracts interaction features of trigger and target based on personalized gating. 2) Cascading Interest Fusion module explicitly estimates users' trigger intention and fuses instant and personalized interests adaptively with cascading attention blocks. 3) Category-assisted Pairwise Loss enhances trigger relevance with the guidance of category association between trigger and target. Extensive experiment results show that CRRN outperforms recent state-of-the-art methods on both industrial and public datasets. Online A/B tests further validate the effectiveness of our method. Our code is available at https://github.com/a-little-cabbage/CRRN.
Read the full abstract

All authors Kaixuan Chen, Wenwen Wang, Xing Fang, Yang Huang, Jing Wang

Computer Vision

Optimize Surgical Triplet Recognition: A Knowledge-Driven Mixture-of-Experts Solution

Yiyi Zhang, Yuchen Yuan, Ying Zheng et al. (+4 more)

Surgical action triplet recognition constitutes a critical task in context-aware robot-assisted surgery, facilitating automatic surgical action perception by identifying instrument, verb, target, and their association. However, existing works struggle to analyze such complex surgical scenes due to three main issues: (1) component-level optimization conflicts caused by entangled feature spaces, (2) category-level optimization conflicts arising from severe data imbalance, and (3) lack of domain knowledge guidance that limits model interpretability and robustness. To address these challenges, we propose a Mixture-of-Experts-guided Co-Optimization (MoeCo) framework powered by knowledge-driven learning. Within the co-optimization pipeline, to first mitigate component-level conflicts, we introduce a component-tailored adapter that disentangles task-specific features across spatial-temporal regimes, facilitating effective component specialization. Next, we develop a coordinated gradient learning strategy to handle category-level conflicts, which adaptively rebalances positive-negative gradients to enhance the perception of rare categories. Notably, inspired by surgical domain expertise, we introduce a knowledge-driven mixture-of-experts mechanism that dynamically integrates multimodal large language model-guided knowledge via activated experts, thereby enriching the co-optimization pipeline with more expressive and robust representations. Extensive experiments on the public CholecT45 and CholecT50 datasets confirm the effectiveness of the proposed co-optimization pipeline and the superiority of dynamic priors integration via the knowledge-driven mixture-of-experts mechanism.
Read the full abstract

All authors Yiyi Zhang, Yuchen Yuan, Ying Zheng, Jialun Pei, Jinpeng Li, Zheng Li, Pheng-Ann Heng

Artificial Intelligence

ParallelWorld: Test-Time Scaling for Agentic Embodied Reasoning

Min Chen, Shengjun Zhang, Yuxin Li et al. (+4 more)

Embodied AI has emerged as a key paradigm for autonomous systems operating in complex physical environments. While end-to-end models have established strong local capabilities for perception and control, scaling these capabilities to extended, multi-stage tasks remains difficult. Agentic embodied systems address this challenge by introducing high-level planners that organize perception, reasoning, and executable skills over longer interaction horizons. However, existing agentic embodied frameworks typically generate actions for direct execution without explicitly simulating how alternative action sequences shape future observations and task progress, leading agents to commit to suboptimal interactions before considering their long-term consequences. To address this limitation, we propose ParallelWorld, an adaptive-horizon test-time scaling framework that grounds agentic embodied reasoning in the prospective simulation of action outcomes. Specifically, we design an agent system to simulate and evaluate alternative trajectories in parallel before committing to an action. A verifier assesses intermediate state transitions with respect to the task objective, dynamically pruning unpromising branches and guiding subsequent expansion. Based on the evaluated long-horizon outcomes, the agent selects a trajectory, executes only its first action, and replans as new observations become available. Experiments on ESI-Bench and LIBERO-Pro demonstrate improvements in active spatial reasoning and language-conditioned manipulation, respectively, highlighting the effectiveness of prospective planning for both understanding and manipulation tasks.
Read the full abstract

All authors Min Chen, Shengjun Zhang, Yuxin Li, Zhang Zhang, Xin Fei, Chong Xia, Yueqi Duan