Information Retrieval
An Event is Worth One Token: Event Tokenization for Industrial-scale LLM Recommendation
Fan Xia, Zhaoheng Zheng, Iman Setayesh et al. (+12 more)
LLM-based recommendation has scaled along model capacity and sequence length, yet each position encodes only text, semantic IDs, or a few categorical features, discarding rich user, item, context, and outcome signals available at each event. Under autoregressive modeling, this yields weak queries at each position and, since each position becomes context for the next, the degradation compounds across the sequence. We propose an event-centric paradigm that represents each interaction by its full temporal snapshot, and identify a new scaling dimension we term snapshot resolution: the amount of information encoded per event. To efficiently scale snapshot resolution, we introduce AMBER (Autoregressive Modeling via Bottlenecked Event Representation), which compresses each temporal snapshot into a compact Event
Token, a new LLM input modality. The representation is learned end-to-end, while Event
Tokens are pre-computed and cached for serving, decoupling snapshot resolution from real-time serving compute. On industrial-scale ranking and
retrieval benchmarks, AMBER advances the compute-quality Pareto frontier relative to alternative recommendation paradigms. At sufficient capacity, a single unified tokenizer even outperforms dedicated per-entity tokenizers, demonstrating positive transfer across structurally different entity types. AMBER's Event
Tokens also transfer across model architectures: when integrated into a heavily optimized non-LLM ranker as serving-time historical features, they yield statistically significant improvements. Further scaling Event Tokenizer capacity provides additional improvements.
Read the full abstract ▾
All authors Fan Xia, Zhaoheng Zheng, Iman Setayesh, Ruogu Lin, Yiqin Pan, Samarth Mittal, Wentao Bao, Vinti Pandey, Sachin Patil, Jianpeng Cheng, Jun Xiao, Zhuang Wang, Xiangjun Fan, Sri Reddy, Minghai Chen
Information Theory · Cross-listed from quant-ph
Certified decoding of quantum LDPC codes
Ragavi Krishnamoorthy, Florian Gerhardt, Johannes Knaute et al. (+8 more)
Quantum low-density parity-check (qLDPC) codes reduce the
qubit overhead of fault-tolerant
quantum computation by an order of magnitude, but their decoding is harder than its classical counterpart: because many physical errors are equivalent up to stabilizers, the degenerate maximum-likelihood (ML) decoder must compare the probabilities of entire equivalence classes of errors, that is, partition functions, rather than single errors. The workhorse decoder BP+OSD sidesteps degeneracy heuristically and offers no guarantees. We treat degenerate decoding as probabilistic inference in an undirected graphical model: the probability of each logical class is the partition function of an unconstrained, strictly positive Markov random field over the code's check variables, a construction that generalizes the random-bond Ising mapping of the surface code to arbitrary CSS codes and to spacetime decoding with measurement errors and
circuit-level noise. On this model we build two decoders. The first estimates all class partition functions by annealed importance sampling with common random numbers and attaches to every decision a certificate of optimality: a paired bootstrap test, or, composed with constant-factor
estimators such as WISH, an exact optimality proof. The second is region-based: the Bethe free energy, whose bias cancels between classes, reproduces exact ML decoding on every tested surface-code instance at millisecond cost, and enlarging the regions to elimination clusters makes exact degenerate ML decoding of the [[72,12,6]] bivariate bicycle code feasible. Across surface codes and the bivariate bicycle codes [[72,12,6]] and [[144,12,12]], under code-capacity, phenomenological, and
circuit-level noise, the sampling decoder matches or exceeds BP+OSD while certifying the bulk of its decisions, and the certificate flags exactly the syndromes on which any fast decoder should be distrusted.
Read the full abstract ▾
All authors Ragavi Krishnamoorthy, Florian Gerhardt, Johannes Knaute, Thomas Klir, Stefan Raimund Maschek, Erik Schulze, Tomislav Maras, Alexander Dotterweich, Loong Kuan Lee, Christian Bauckhage, Nico Piatkowski
Systems and Control
Goodput Maximization for Large Language Model Edge Inference: A Two-Phase Maskable PPO Approach
Xiaojing Chen, Qi Zhang, Wei Ni et al. (+2 more)
This paper presents a novel two-phase maskable proximal policy optimization (TP-MPPO)
algorithm, which maximizes the system goodput counting request throughput with strict service level objective (SLO) compliance for large
language model (LLM) inference services in wireless edge networks. In the first phase of TP-MPPO, we optimize the task offloading decisions by MPPO with action masking mechanism, effectively avoiding exploring invalid actions and reducing the action space. In the second phase, closed-form solutions are derived for uplink bandwidth allocation; a greedy
algorithm is designed for downlink bandwidth allocation to provide immediate rewards for the MPPO in the next round. The two stages alternate till convergence. Simulation results demonstrate that TP-MPPO can improve the system reward by 33.3%–87.5% compared to its
benchmarks and achieve the highest goodput.
Read the full abstract ▾
All authors Xiaojing Chen, Qi Zhang, Wei Ni, Shunqing Zhang, Yanzan Sun
Machine Learning
Reflection Steering: Disentangling Reflection from Reasoning in Activation Space for Token-Efficient Inference
Jiarui Hu, Zhiyuan Wen, Xiaoyun Liu et al. (+2 more)
Large
reasoning models often produce
reasoning traces with verification, revision, and backtracking. When reflection merely re-checks established results, it wastes
reasoning tokens and increases latency. Most existing reflection steering methods add a label-derived mean-difference direction across preset layers, but its
entanglement with
reasoning and length signals destabilizes the accuracy-efficiency trade-off. In this paper, we propose Reflection Steering, a training-free framework for controlling reflection-associated computation within LLMs by disentangling reflection-related activations from general
reasoning. Specifically, we contrast reflective and non-reflective hidden states at each LLM layer, denoise the resulting reflection directions with PCA, and orthogonalize them against general-
reasoning directions. To limit downstream amplification from early-layer interventions, we calibrate each layer across multiple intervention strengths on a small set, retain only stable layers, and apply bounded projection removal to their residual-stream activations. We conduct extensive experiments across two public
benchmarks and three open-weight LLMs against state-of-the-art activation-steering baselines. Results show that Reflection Steering reduces
reasoning tokens by 16.9% on average across six matched settings. Besides, our method further introduces a bounded reflection intervention-strength parameter $\alpha$, enabling deployment-time adjustment to balance
token savings, accuracy, and generation stability.
Read the full abstract ▾
All authors Jiarui Hu, Zhiyuan Wen, Xiaoyun Liu, Jiaxing Shen, Yu Yang
Computer Vision
CropCop: An Auditable 120-Class Plant-Health Model from Benchmark Reconstruction to a Quantised Runtime Artifact
Rana Muhammad Ahmed and Sabahat Abbas
A plant-health score can appear precise while resting on duplicated image families, a long-tailed label space, or a runtime file that was never evaluated. We present CropCop, a closed-set recognition system spanning 120 operational plant-health classes and an evidence chain from corpus reconstruction to direct execution of the final quantised artifact. Starting from 117,546 audited images, we rejected the inherited partition after confirming 3,233 duplicate relationships across split boundaries and froze a 109,107-image
benchmark with zero crossings among the audited trusted leakage groups and a 151.7 largest-to-smallest class ratio. A fully fine-tuned DINOv3 ConvNeXt-Tiny reference achieved 98.51% accuracy and 96.87% macro-F1 on the locked internal test. A compact MobileNetV4 Conv-Medium derivative achieved 98.46% accuracy and 96.27% macro-F1 without being presented as evidence for a new
distillation method. Validation-only post-training quantisation selected dynamic activations with per-channel weights, and the final 22.60 MiB ExecuTorch/XNNPACK PTE achieved 98.46% accuracy and 96.23% macro-F1 when executed directly. Only six of 16,363 top-1 decisions changed between the converted INT8 graph and the PTE, while paired analysis showed a modest class-balanced loss; an exploratory post hoc fruit-label slice localized a larger recall decline than aggregate accuracy revealed. CropCop establishes strong leakage-controlled internal recognition and software-runtime fidelity; it does not establish performance on unseen farms, camera pipelines, or physical Android hardware.
Read the full abstract ▾
Numerical Analysis
Preconditioning for Diffuse Interface Tumor Growth Models
Jessica Bosch, Peli̇n Çi̇loğlu, Chen Greif et al. (+1 more)
Computational models of tumor growth form a contemporary area of study. Diffuse interface models have been proposed as an important tool for cancer modeling. In this work, we consider preconditioners for numerical simulations of two tumor growth models based on diffuse interface models. For numerical efficiency, we propose block preconditioners that rely on using effective Schur-complement approximations. We show that these methods combined with state-of-the-art adaptive finite element discretizations lead to robust simulations in two and three dimensions. In extensive numerical experiments, we show that the proposed methods show robust convergence behavior.
Read the full abstract ▾
All authors Jessica Bosch, Peli̇n Çi̇loğlu, Chen Greif, Martin Stoll
Hardware Architecture
Syn2Logic: End-to-End Neuromorphic Design Automation
Artur Podobas
In this work, we propose a view on electronic Neuromorphic Design Automation (eNDA), which we see as a design automation flow that bridges computational neuroscience modeling with traditional Electronic Design Automation (EDA) flow. We introduce the term, give examples of how it can be implemented, and design a prototype implementation: Syn2Logic. Syn2Logic is an entire eNDA framework, that allows neuroscientists to model neural behavior using a custom DSL and a compiler that takes the same model description down to synthesizable RTL hardware. We end the paper by applying the eNDA-flow through Syn2Logic to show how to – without writing a single line of hardware description
language (HDL) code– (i) generate what we believe is the fastest C. elegans accelerator that runs significantly faster than state-of-the-art simulators, (ii) create (to the best of our knowledge) the fastest, most generic neuromorphic sudoku solver that outperforms CP-SAT and SCIP on TOP1465 puzzles, (iii) create a 5.6 million FPS/Watt accelerator on a tiny FPGA that outperforms existing neuromorphic architectures in terms of speed and energy-efficiency on the MNIST
dataset, and (iv) create a generic accelerator for unsupervised learning that outperforms most existing unsupervised methods on the OPS-SAT
benchmark.
Read the full abstract ▾
Machine Learning
Resilient Decentralized Wireless Federated Learning via Gradient Tracking with AdamW
Nguyen Van Thieu, Ti Ti Nguyen, Ons Aouedi et al. (+2 more)
Wireless Internet-of-Things (IoT) edge networks require decentralized learning (DecL) methods that can operate reliably under both heterogeneous local data and communication-constrained wireless links. However, existing decentralized optimization schemes often incur substantial communication overhead and degraded performance when transmissions are constrained by strict airtime budgets, fading channels, and packet losses. This paper proposes QEF-GT-AdamW, a communication-efficient and outage-resilient
algorithm for DecL over wireless communication (WCom) networks. The proposed method combines gradient tracking to mitigate the effect of non-IID data, AdamW-based adaptive optimization to improve training stability, and dual-stream biased quantization with error feedback to reduce communication payloads for both model and tracking exchanges. To address unreliable broadcast communication, the proposed framework further employs a local fallback strategy when scheduled packets are not successfully received. We explicitly model the effect of bandwidth, transmit power, airtime constraints, and fading channels on DecL performance, and establish convergence guarantees for the proposed
algorithm under compressed and unreliable wireless communication. Experimental results on heterogeneous MNIST and CIFAR-10 settings show that QEF-GT-AdamW consistently improves robustness and convergence performance over representative DecL baselines while achieving favorable accuracy-communication trade-offs under limited wireless resources.
Read the full abstract ▾
All authors Nguyen Van Thieu, Ti Ti Nguyen, Ons Aouedi, Vu Nguyen Ha, Symeon Chatzinotas
Information Theory
Constrained Maximum Entropy Contiguous Aggregations
Roberto Bruno and Ugo Vaccaro
Given a probability distribution $p = (p_1, \dots, p_n)$ and an integer $1\leq m \leq n$, a contiguous aggregation of $p$ is a probability distribution $q = (q_1, \dots, q_m)$ such that each $q_i$ is a sum of consecutive elements of $p$. Given $p$ and a positive number $R$, we consider the problem of computing a maximum
entropy contiguous aggregation $q$ of $p$, under the constraint that its Shannon
entropy $H(q)$ is at most $R$. We devise a dynamic programming
algorithm that solves the problem exactly, and two time-efficient greedy
algorithms that provide close-to-optimal solutions. We discuss a few scenarios where our problem arises.
Read the full abstract ▾
Computation and Language
ClueWeaver: Reward-Guided Dual-Agent Evidence Reasoning for Compact LLMs on Literary Long Narratives
Jihao Zhu, Zhiwei Yang, Wenxiao Zhang et al. (+7 more)
Humanities and social science research requires close reading of long narrative materials such as novels, scripts, archives, and case reports, yet many users have limited access to costly proprietary long-context models. Compact, locally deployable
language models are a practical alternative, but directly feeding them an entire long context remains costly, hard to inspect, and prone to missing sparse evidence. We present ClueWeaver, an evidence-aware dual-
agent framework for long-narrative question answering with compact local models. A Finder identifies passages containing answer-critical clues through
retrieval-guided
segmentation, while an Interpreter derives the answer from the selected evidence, produces rationales with paragraph-ID citations, and applies an internal self-calibration pass for high-risk questions. Both
agents are optimized with reward-guided reinforcement learning: Finder rewards emphasize evidence retention and faithful paragraph-ID references, and Interpreter rewards emphasize correctness, grounding, and concise explanations. This decomposition makes evidence selection and
reasoning more inspectable than end-to-end prompting. Experiments across multiple long-context narrative question answering and claim verification settings show that ClueWeaver substantially improves local end-to-end
language models while providing evidence coverage and paragraph-referenced
reasoning traces. Code is available at https://github.com/Ameame1/ClueWeaver.
Read the full abstract ▾
All authors Jihao Zhu, Zhiwei Yang, Wenxiao Zhang, Junqian Zhao, Qi You, Fangqi Wang, Zheyuan Deng, Hanzhe Yang, Yu Liu, Jin B. Hong
Data Structures and Algorithms
Not All Degree Constraints Are Created Equal when Computing Spanning Trees
Narek Bojikian, Alexander Firbas, Robert Ganian et al. (+2 more)
We study the computation of minimum spanning trees subject to local degree constraints. Recent work (ICALP 2026) established that three natural formalizations of this problem share the exact same parameterized complexity under standard structural graph parameters, including treewidth, pathwidth and clique-width. This applies to the cases where every vertex has a single target degree (Specified Degree MST), or a degree upper bound (Bounded Degree MST), or is equipped with a set of admissible degrees (Set of Degrees MST). In this paper, we investigate these problems under more restrictive parameterizations and reveal that their complexity landscapes fundamentally diverge on bounded-treedepth graphs. Specifically, we prove that the former two problems are fixed-parameter tractable when parameterized by the treedepth of the input graph. In sharp contrast, we show that Set of Degrees MST remains W[1]-hard parameterized by treedepth, even when combined with the feedback vertex number (i.e., deletion distance to treewidth $1$). Finally, we show that this divergence seems to be specific to treedepth: we exclude an analogous W[1]-hardness result for Set of Degrees MST w.r.t. the vertex cover number and also rule out fixed-parameter
algorithms for the former two problems w.r.t. deletion distance to constant pathwidth.
Read the full abstract ▾
All authors Narek Bojikian, Alexander Firbas, Robert Ganian, Hung P. Hoang, Krisztina Szilagyi
Computer Vision
Video-IFBench: Evaluating Instruction Following of Multimodal LLMs in Video Understanding Scenarios
Hongbo Liu, Peixian Chen, Sihan Liu et al. (+12 more)
Multimodal Large
Language Models (MLLMs) have shown strong performance in
video understanding. However, their ability to follow instructions in this domain remains under-explored. Real-world
video understanding requires models not only to interpret
video content correctly, but also to satisfy diverse user-specified constraints. Existing
benchmarks focus primarily on task accuracy rather than instruction adherence, leaving this capability insufficiently evaluated. To address this gap, we introduce
Video-IFBench, a comprehensive
benchmark for evaluating instruction following in
video understanding, where models must satisfy diverse user-specified constraints, including those grounded in visual and audio content. We develop an instruction taxonomy with four templates, including single-task, multi-task, selection, and nested instructions, covering 32 task types and 39 manually designed constraint categories spanning both semantic and format requirements. To reduce annotation cost, we build a semi-automatic data construction pipeline that combines MLLMs, programmatic processing, and human verification, resulting in 1.5K samples. We conduct a large-scale evaluation of more than 20 recent MLLMs and show that
video instruction following remains challenging for current models, especially for instructions with many constraints, semantic constraints, or complex conditional structures that require selecting the correct branch or path based on
video content. We hope our work will facilitate future research on instruction following in
video understanding scenarios.
Read the full abstract ▾
All authors Hongbo Liu, Peixian Chen, Sihan Liu, Peiyuan Zhang, Kai Zou, Dian Zheng, Xiaoxing Hu, Yuhao Dong, Mengdan Zhang, Yunhang Shen, Haoyu Cao, Wei Liu, Weibo Gu, Xing Sun, Shengjie Zhao
Information Retrieval
TransRetrieval: Scaling Up Transformer-Based Retrieval for Industrial Recommendation
Zhifei Zheng, Yunfei Liu, Bin Liu et al. (+7 more)
Applying scaling laws to recommendation
retrieval is hindered by feature heterogeneity: naively stacking
Transformer layers yields diminishing returns because heterogeneous fields produce severe
token-norm divergence. We present TransRetrieval, a
Transformer-based
retrieval framework that scales with both computational budget and cross-domain data. The key enabler is (1) weighted average aggregation, which restores the homogeneous-
token assumption
Transformers rely on. Building on this, we introduce (2) target
token compression that cuts per-candidate FLOPs by 85% while preserving cross-
attention expressiveness, and (3) position-style domain
embeddings that unify multiple domains at negligible additional cost, turning cross-domain data into a scaling asset. On a 40-billion-interaction industrial
dataset and the public KuaiRand
benchmark, scaling compute from 0.1 to 2 MFLOPs per target yields +19.3/+22.2 pt Recall@2000, confirming robust log-linear scaling. In online A/B tests, TransRetrieval lifts platform revenue by 2.53% under the same end-to-end latency constraint as the production baseline.
Read the full abstract ▾
All authors Zhifei Zheng, Yunfei Liu, Bin Liu, Qiren Zhu, Hanbing Liu, Ziru Xu, Han Zhu, Jian Xu, Qi Qi, Bo Zheng
Human-Computer Interaction
The Well-Being Palette: An Action-Word Selection Tool Designed for Low-Burden Reflection on Workplace Well-Being
Nobuhiko Muramoto, Takayuki Nagaya, Tomoko Tanaka et al. (+2 more)
Background: Workplace well-being interventions need formats that can be used repeatedly with minimal disruption to daily work. We developed the Well-Being Palette, a web-based action-word selection tool designed for brief, low-burden reflection on workplace well-being. Methods: In a three-month exploratory field study at a private-sector corporate research institute in Japan, 88 analyzed participants selected up to three well-being-related action words after reflecting on positive actions or experiences from each workday. We examined application usage, PERMA Profiler scores, selected-word patterns across departments, selected-word diversity using Shannon
entropy, and exploratory associations with sharing workshops. Results: During the formal intervention period, the application captured 3,480 input records and 10,104 selected words, and all 72 available action words were selected. Overall PERMA scores increased from baseline to post-intervention, and no clear decline was observed at the one-month follow-up among available cases. Application logs revealed departmental differences in selected-word categories. Cumulative selected-word diversity increased over time, and sharing workshops showed exploratory associations with more sustained PERMA patterns and broader cumulative selected-word diversity. Conclusion: The Well-Being Palette was feasible for repeated use in a real workplace and provided complementary log-based information on how workers recognized and labeled well-being-related experiences. The findings should be interpreted as exploratory and hypothesis-generating, because the study did not include a randomized control condition and did not directly measure perceived burden or completion time.
Read the full abstract ▾
All authors Nobuhiko Muramoto, Takayuki Nagaya, Tomoko Tanaka, Koichiro Iwai, Katsunori Kohda
Numerical Analysis
Adaptive Hybrid Subspace Levenberg Marquardt Algorithm with Adequacy Monitor for Large Scale Least Squares Problems
M. Duc Hoang and Timothy J. Lewis
The Levenberg-Marquardt (LM)
algorithm is the most widely used method for solving nonlinear least-squares problems, as it combines the robustness of steepest descent with the fast local convergence of the Gauss-Newton method. However, its computational cost can become prohibitive for large-scale problems because each iteration requires solving a large damped linear system, and conventional step acceptance strategies may require repeated solves as the damping parameter is adjusted. Despite this computational challenge, many large-scale least-squares problems exhibit effective low-dimensional structure, with only a small number of parameter-space directions strongly informed by the data. We propose an adaptive hybrid subspace Levenberg-Marquardt (HSLM)
algorithm that constructs a low-dimensional subspace from complementary sources of gradient,
memory, Krylov-subspace, and randomized
curvature information and computes a spectrally damped LM step within this subspace. A distinguishing feature of the method is a deterministic adequacy monitor that quantifies how much descent information is captured by the reduced space and adaptively enriches the subspace when necessary. Step acceptance is decoupled from damping adjustment: Armijo backtracking determines the accepted step length, while the ratio of actual to predicted reduction is used solely to update the damping parameter, thereby avoiding repeated damped-system solves during step acceptance. For the HSLM
algorithm, we establish global convergence to stationarity and prove local linear and superlinear convergence. Numerical experiments on neural-network training problems show that HSLM achieves convergence behavior comparable to classical and Krylov subspace LM (KSLM) while substantially reducing per-iteration computational cost, with increasing advantages observed as the parameter dimension grows.
Read the full abstract ▾
Computation and Language
TOPAS: Workflow-Aware Prefix-State Scheduling for Multi-Agent LLM Serving
Hongqiu Ni, Han Tian, Chi Zhang et al. (+2 more)
Prefix caching introduces a fundamental tradeoff in multi-
agent large
language model (LLM) serving: retaining a long system-
prompt key-value (KV) cache for an
agent accelerates future calls, yet it reduces the GPU
memory available for batching concurrent requests. In multi-stage workflows, existing schedulers tend to prioritize either immediate prefix locality or overall workflow progress. However, under a shared KV cache budget, optimizing either objective in isolation can prolong tasklevel job completion time (JCT) through downstream delays or frequent prefix replacement. To strike a balance, we here propose TOPAS, a Task-Oriented Prefix-Aware Scheduler that jointly decides which
agent prefixes to keep in the cache and which requests to schedule for execution. TOPAS scores candidate post-decision states by trading off the expected reduction in each task's longest remaining service path against the near-term benefit of downstream prefix reuse, accounting for the costs of prefix movement and preemption. A task-level aging mechanism is also incorporated to prevent starvation. We implement TOPAS within the SGLang framework and assess its performance on three synthetic DAGs and two MetaGPT software-development workflows. Compared with the best performing baseline for each workload and metric, TOPAS reduces the mean/p99 JCT by up to 39.8%/49.4% on the synthetic workloads, while lowering mean JCT by 9.8% on MetaGPT-SOP and mean/p99 JCT by 22.0%/26.6% on MetaGPT-TL.
Read the full abstract ▾
All authors Hongqiu Ni, Han Tian, Chi Zhang, Guopeng Li, Haisheng Tan
Information Retrieval
Query Expansion Is More Than Generation: Improving Dense Retrieval through Better Integration
Siyuan Sun and Mihai Surdeanu
Large
language models (LLMs) can generate query expansions without task-specific training, yet the same expansions often make a frozen dense retriever worse. We identify an underexplored factor: prior work has often focused on what text is generated, while how generated text is incorporated into dense retrievers has received less systematic
attention. By holding generated expansions fixed, we show that performance degradation can often be attributed to the integration method itself. We introduce AnchorQE, a training-free method that separately encodes the original query and its expansion before interpolating them. The interpolation factor is estimated using an unsupervised online strategy that operates over a small part of the unlabeled test stream. Intuitively, our strategy assigns high expansion trust only when expansions are both
retrieval-strong and consistent with the original query's retrieved evidence. We show that AnchorQE improves
retrieval effectiveness by up to 12.89% when compared to widely-used expansion-only or text-level concatenation baselines across TREC-DL, LoTTE, and BEIR. Further, we show that our online strategy to estimate the interpolation factor outperforms a fixed weight tuned on a development partition by up to 3.81%.
Read the full abstract ▾
Computer Vision
Asymmetric Cross-Modal Fine-Grained Visual Categorization: ACF-Net and the BirdPro Benchmark
Bohan Deng, Shuo Ye and Zitong Yu
Audio-visual cross-modal Fine-Grained Visual Categorization (FGVC) aims to identify fine-grained categories by jointly leveraging visual and auditory information. However, FGVC under asymmetric cross-modal scenarios has received limited
attention, where paired
video and audio are not strictly synchronized and may not even correspond to the same individual or moment. Such weak and ambiguous cross-modal correspondence poses substantial challenges to effective representation learning and modality
alignment. To address these issues, we propose ACF-Net, a novel optical flow-guided framework for asymmetric audio-visual fine-grained learning. ACF-Net consists of two key modules: Optical Flow-Guided Motion (OFGM) and Asymmetric CrossModal Adaptive Fusion (ACAF). OFGM captures motion-sensitive visual cues and suppresses irrelevant background interference, thereby enhancing discriminative dynamic representations in
videos. ACAF estimates modality reliability under weakly matched audio-
video pairs and performs uncertainty-aware adaptive fusion to improve category-level recognition robustness. To support research on asymmetric cross-modal FGVC, we further construct BirdPro, a new bird-oriented audio-visual
benchmark, since existing
datasets often lack large-scale category-level audio-
video associations under non-strict temporal and instance correspondence. BirdPro contains 1,919 audio recordings and 11,965
videos covering 194 bird species. Extensive experiments show that ACF-Net achieves the best results compared with representative baseline methods, outperforming the strongest baselines by 2.97% and 1.92% in the fused and mismatched settings, respectively.
Read the full abstract ▾
Artificial Intelligence
Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models
Pengfei Zhou, Hexin Wang, Zhengfeiyang Zhang et al. (+5 more)
A common strategy for scaling world models is to train on more crawled
video with more compute. We argue that this strategy is inefficient: scaling world models also requires a recursive data engine that offers grounded reward signals. The success of code
agents illustrates why this matters. As code is executable, compilers and runtimes can provide high-quality rewards for Reinforcement Learning (RL) post-training of LLMs. By contrast, spatial generation still relies largely on fuzzy proxies such as CLIP scores. These signals are fuzzy and biased, making them hard to support RL post-training. Compared with these, game development provides a missing reward environment for spatial world models. A scene encoded by a game engine is an executable world specification: the engine can efficiently check collision, physics, navigability and bounded playability, while the developer provides the global verification signal by judging whether the scene should be accepted. Game development also provides real-world long-horizon trajectory data for RL post-training. We therefore propose Reinforcement Learning with Human-Engine Verification (RLHEV), a post-training paradigm that combines dense engine signals with implicit human acceptance feedback from the development process.
Read the full abstract ▾
All authors Pengfei Zhou, Hexin Wang, Zhengfeiyang Zhang, Yixing Ma, Zhenglin Wan, Kaipeng Zhang, Wangbo Zhao, Yang You
Computer Vision
OpenVeinNet: Robust Open-Set Finger Vein Verification with Dynamic Snake Convolution and Graph Learning
Sushrut Patwardhan and Raghavendra Ramachandra
Finger vein verification is a promising biometric modality for secure authentication because vascular patterns are internal, difficult to observe externally, and relatively resistant to presentation attacks. However, reliable verification remains challenging in open-set settings, where test identities are unseen during training and non-enrolled probes must be rejected at inference. This paper presents OpenVeinNet, a finger vein verification framework designed for cross-
dataset and open-set evaluation. The proposed model combines Dynamic Snake Convolution with graph-based feature modelling. Dynamic Snake Convolution extracts local curvilinear and tubular vein structures using adaptive sampling, while the graph convolutional backbone models long-range topological relationships between vein regions. To improve the discriminative quality of the
embedding space, we introduce a Centroid Angular Hybrid Loss, which jointly encourages intra-class compactness and inter-class angular separation for cosinesimilaritybased verification. Experiments are conducted on five public finger vein
datasets: FV-300, MMCBNU, FV-USM, PolyU, and VERA. The method is evaluated using leaveonedatasetout training under both enrolmentbased unknownrejection and fullsubject verification protocols, and is compared with handcrafted and recent deep learning-based baselines. The results show that OpenVeinNet achieves strong cross-
dataset generalisation, consistently low equal error rates, and competitive true accept rates at fixed false accept rate operating points. Ablation studies further confirm the individual and combined contributions of adaptive tubular feature extraction, graph-based relational modelling, and the proposed loss function. These findings indicate that explicitly modelling local vein geometry, global vascular relationships, and angularly compact
embeddings is effective for openset finger vein verification.
Read the full abstract ▾
Information Theory
Joint Beamforming Design and Port Selection in Fluid Antenna-Assisted Multi-Cell Networks: A Personalized Federated Learning Approach
Liwen Gao, Li Zheng, Xing Hao et al. (+2 more)
This paper investigates joint beamforming and port selection in multi-
cell fluid
antenna-assisted (FAS) networks. In such networks, active beamforming and discrete FA port selection are coupled through intra-
cell and inter-
cell interference and are jointly optimized to maximize the weighted sum-rate (WSR). We develop a
federated representation learning (FedRep) framework with a position-aware dual-branch deep neural network (PA-DNN). The PA-DNN uses channel state information and port positional encoding as inputs, and jointly outputs beamforming vectors and port selections through two task-specific branches. To support decentralized training across heterogeneous
cells, the FedRep framework shares global beamforming-related parameters among base stations while keeping port-selection parameters local for
cell-specific adaptation. Simulation results show that the proposed scheme achieves a higher weighted sum-rate than conventional FL and port-selection
benchmark schemes.
Read the full abstract ▾
All authors Liwen Gao, Li Zheng, Xing Hao, Ziru Chen, Lin X. Cai
Machine Learning · Cross-listed from stat.ML
Adaptive Regularization for Random Features: A Neighboring Early-Stopping Rule with Oracle-Rate Guarantees
Caixing Wang, Zhibo Chen and Yue Wang
Random feature methods provide a scalable approximation to kernel ridge regression (KRR), but the regularization parameter that yields the oracle learning rate depends on unknown smoothness and capacity parameters. In this work, we propose a neighboring early-stopping rule for adaptive regularization in KRR with random features (KRR-RF). The method uses a grid that is uniform in inverse regularization and compares only adjacent
estimators, reducing the number of discrepancy comparisons relative to standard all-pairs Lepskii-type procedures. Both the neighboring discrepancy and its empirical complexity term can be computed directly in the random feature space, without constructing the exact kernel Gram
matrix. We establish a high-probability comparison bound for neighboring KRR-RF
estimators and show that, under standard source and capacity conditions together with suitable grid and random feature budget conditions, the selected
estimator attains the oracle
polynomial learning rate up to logarithmic factors. The result allows the regularization parameter to be selected without prior knowledge of the source and capacity exponents and covers both well-specified and partially misspecified regimes. Our analysis is based on an empirical random feature effective dimension that connects the observable stopping threshold with the population complexity of the random feature model. Simulation and real-data experiments illustrate the prediction performance and computational behavior of the proposed method in comparison with standard tuning procedures.
Read the full abstract ▾
Programming Languages
A Programming Paradigm for Spatiotemporal Composability
Yifan Shi, Wei Zhang and Tianyi Cui
Modern software – from plugin systems to self-evolving
agent harnesses – increasingly requires dynamic composition, yet its formal foundations remain underdeveloped. We identify two orthogonal dimensions of the problem: temporal composability, the ability to completely revert a component's side effects upon removal, and spatial composability, the ability to declare and reactively manage inter-component dependencies. We address the two dimensions by lifting classical effect and coeffect concepts to runtime mechanisms. In particular, we formalize revertible effects, in which every context transformation carries an inverse that the runtime holds, establishing temporal composability local to one component. We formalize reactive coeffects, in which every context change is classified against a component's coeffect specification to drive its activation and deactivation, establishing spatial composability local to one component. We then unify the effect context and the coeffect context into a single context type and mediate every effect and coeffect through it, yielding a discipline we call the context paradigm; the mediation induces an observational equivalence up to which the effects of distinct components interleave without disturbing one another. Combining these mechanisms into the notion of a component, we give a calculus of dynamic composition whose metatheory carries spatiotemporal composability from a single component to a whole system of interleaved components. We implement these ideas in Cordis, a meta-framework of spatiotemporal composability that provides a core library with effect tracking and coeffect resolution, as well as a declarative component loader with configuration reconciliation and hot module replacement.
Read the full abstract ▾
Robotics
Dynamic Modeling of a Welding Torch Umbilical and Its Impact on Robot Dynamics
Nicolas Gautier, Yves Guillermit, Mathieu Porez et al. (+2 more)
Robotic welding is widely used in industrial manufacturing, where the welding torch is often connected to the generator through an external umbilical. With the increasing deployment of lightweight and collaborative
robots, the dynamic influence of this umbilical can significantly affect the
robot motion and the actuation forces. This paper proposes a constrained multibody dynamic model of a welding umbilical, represented as a serial chain of rigid bodies interconnected by passive joints with elastic and dissipative effects. Prescribed motions at the distal anchor point are introduced through holonomic kinematic constraints. The equations of motion are reduced by projecting the dynamics onto the subspace of admissible velocities, yielding an efficient formulation free of Lagrange multipliers. The reaction wrench exerted by the umbilical on the
robot is explicitly recovered. A planar case study illustrates the approach.
Read the full abstract ▾
All authors Nicolas Gautier, Yves Guillermit, Mathieu Porez, Fabien Rousset, Damien Chablat
Information Theory
Serial Depth of Adaptive Parallel Sampling: Lower Bounds and Schedules for Masked Diffusion Models
Chuling Wen, Weijie Liang, Jian Lu et al. (+1 more)
Masked
diffusion models generate sequences in rounds, predicting several masked positions at once. Fewer rounds can accelerate decoding, but sampling positions independently can lose their dependence and bias the output. How few rounds suffice for a prescribed error budget? Beyond error bounds for individual decoding rules, we study sharp lower bounds on the number of rounds required for a given target distribution. We introduce serial depth: the minimum number of rounds, averaged over target sequences, needed to meet a forward Kullback-Leibler error budget. With exact conditional probabilities, we prove these bounds for all deterministic rules that may adapt to generated values and construct matching schedules for several distribution families, with depths ranging from $\log\log n$ to linear in sequence length $n$. To narrow the gap to trained models, we show that these lower bounds remain valid for learned predictors and give sufficient accuracy conditions on visited contexts for schedules to retain their error guarantees. On two pretrained models across five text domains, a schedule suggested by the theory achieves higher average log-likelihood on held-out text in five rounds than random selection in eight. A preregistered confirmation study certifies a relative improvement on independent dialogue data.
Read the full abstract ▾
All authors Chuling Wen, Weijie Liang, Jian Lu, Zhouchen Lin
Artificial Intelligence
CaSKG: Counterfactual-Causal Skill Graphs for Scalable Agent Skill Retrieval
Zhiyuan Li, Linyuan Gao, Xuechun Ding et al. (+3 more)
Reusable skill libraries allow large
language model (LLM)
agents to reuse procedural knowledge across tasks, but they also turn
memory access into a challenging
retrieval problem. Full-library prompting preserves coverage at high context cost, vector
retrieval returns compact neighborhoods but treats skills as independent text, and graph-based
retrieval can recover workflow context only when the edges that carry relevance are reliable. We propose CaSKG, a counterfactual-causal skill graph framework that calibrates procedural relations before
retrieval. CaSKG first builds a high-recall directed candidate graph from semantic, lexical, input/output, and structural evidence, with repair evidence and an optional LLM judge further refining candidate scores. It then applies direction-conditioned textual counterfactual probes that remove, substitute, and reorder skill pairs, aggregates the evidence with
Bayesian smoothing, and publishes a state-filtered weighted graph for task-conditioned expansion. The graph is constructed offline and used without changing the downstream
agent policy or task interface. Across six LLM backbones on ALFWorld ID-140 and ScienceWorld U211, CaSKG achieves the highest task score in all twelve combinations of model and
benchmark. Relative to Graph-of-Skills (GoS), it improves the six-model macro-average ScienceWorld score from 72.62 to 80.50 and ALFWorld success from 80.01% to 86.79%, while reducing mean environment steps on both
benchmarks. Qualitative and ablation analyses further show that calibrated edges help
retrieval preserve prerequisites, state-changing actions, verification routines, and final completion steps. These results position edge-confidence calibration as an effective route to compact and executable skill
retrieval at scale\footnote{Code is available at: https://github.com/ZhiyuanLi218/Caskg }.
Read the full abstract ▾
All authors Zhiyuan Li, Linyuan Gao, Xuechun Ding, Hongwei Chen, Yuan Wu, Yi Chang
Machine Learning · Cross-listed from math.OC
A Multi-View Coupled Tensor Decomposition for Lightweight Online Adaptive Traffic Prediction
Quan Yu, Jie Ni, Yu-Hong Dai et al. (+1 more)
Accurate online traffic prediction is essential for intelligent transportation systems, where
forecasting must be performed continuously under imperfect sensing conditions. Missing observations and anomalous disturbances make this task challenging, particularly when prediction relies on a single traffic view. This paper proposes a Multi-View Coupled Tensor Decomposition (MVCTD) model for online traffic prediction from imperfect multi-view observations, such as speed, flow, and occupancy. The proposed model uses coupled tensor decomposition to build a structured latent
forecasting space, in which shared spatial structures across traffic views and view-specific temporal dynamics are jointly modeled. A group sparse regularization is further introduced to capture correlated abnormal responses induced by real traffic anomalies and thus reduce their influence on forecasts. For streaming deployment, MVCTD performs iterative refinement only on the current latent tensor, while the remaining model variables are updated by lightweight closed-form steps based on summarized historical information, thereby avoiding repeated optimization over the full historical sequence. Experiments on real-world traffic
datasets demonstrate that MVCTD achieves accurate forecasts with favorable runtime under severe missingness, confirming its suitability for online traffic prediction.
Read the full abstract ▾
All authors Quan Yu, Jie Ni, Yu-Hong Dai, Xiongjun Zhang
Machine Learning
FedQoS: Federated QoS-Risk Learning for Heterogeneous Indoor-Outdoor Access Selection
Nguyen Van Thieu, Ti Ti Nguyen, Ons Aouedi et al. (+3 more)
Reliable access selection in dynamic and heterogeneous indoor-outdoor environments is challenging because instantaneous
radio measurements alone cannot capture future QoS degradation caused by mobility, blockage, traffic load, and resource competition. This paper proposes FedQoS, a
federated QoS-risk learning framework for predicting the future reliability of candidate access links and supporting access-node selection without centralizing user-level network data. In FedQoS, each access node locally learns from its observed network logs, including
radio, traffic, load, and service-context features, while a global QoS-risk predictor is trained through
federated aggregation. The learned model estimates the probability of QoS failure for each candidate link, and the controller uses these risk scores to select reliable access nodes under dynamic network conditions. To evaluate the framework, we construct physics-based synthetic indoor-outdoor wireless
datasets using the Sionna framework, covering normal traffic, mobility, event-driven congestion, and non-IID client observations. Simulation results show that learning-based access selection substantially reduces the QoS-failure rate compared with signal-based and historical-QoS heuristic methods. FedQoS achieves near-centralized predictive performance and provides clear reliability gains under mild non-IID data while remaining competitive under the more challenging severe non-IID condition. These results demonstrate the potential of
federated QoS-risk learning for reliable, data-local access selection in dynamic wireless environments.
Read the full abstract ▾
All authors Nguyen Van Thieu, Ti Ti Nguyen, Ons Aouedi, Zerihun Huruy, Vu Nguyen Ha, Symeon Chatzinotas
Computer Vision
Pose-Anchored Optical Flow for Low-Latency Human Action Anticipation in Human-Robot Teaming
Lewis de Zoete Grundy, Chris McCarthy and Christopher Fluke
Human-
robot interaction (HRI) requires
robots to interpret human actions early in their execution in order to respond safely, efficiently, and naturally. However, many existing approaches to human action recognition rely either on sparse skeletal representations, which lack fine-grained motion cues, or dense optical flow, which can be computationally expensive for low-latency perception pipelines. In this paper, we propose PoseOFF, a pose-anchored optical flow representation that captures local motion information around human joints to support earlier human intent understanding. By conditioning motion feature extraction on human pose, PoseOFF encodes localised motion dynamics at semantically meaningful body locations, forming a structured motion representation that is explicitly aligned with human kinematics. We evaluate PoseOFF across multiple
benchmark datasets and backbone architectures for action anticipation, demonstrating consistent improvements in recognition accuracy, particularly at early observation ratios. Our results show that PoseOFF enables models to achieve comparable or improved performance while observing less of the action sequence, highlighting its effectiveness for early prediction. Importantly, these gains are achieved without requiring full-frame motion processing, making the approach practical for real-time and resource-constrained settings. These findings suggest that pose-centred motion representations such as PoseOFF can enhance the ability of interactive
robot systems to infer human actions earlier, supporting more responsive and anticipatory behaviour in human-
robot interaction scenarios.
Read the full abstract ▾
Human-Computer Interaction
ScentEcho: Exploring Adsorbent Materials for Accurate Odor Collection and Playback
Chih-Hung Lee, Yuchi Sun, Rui Zhang et al. (+2 more)
Delivering odors that feel realistic and recognizable remains a core challenge for olfactory interaction systems, particularly in applications that demand precise scent delivery. A key limitation lies in the difficulty of capturing, preserving, and playing back real-world scent sources in a reliable and scalable manner. This study explores the potential of adsorbent materials for supporting realistic scent playback. We present ScentEcho, a portable system that enables modular scent collection and release. Through user evaluations, we identify which adsorbent materials tend to perform better for specific odors, and observe that perceived intensity strongly influences similarity ratings. In addition, odor recognition follows a graded pattern, with users moving from broad category identification to more specific source recognition as similarity increases. These findings offer practical insights for designing olfactory interfaces that are both expressive and perceptually aligned with user expectations.
Read the full abstract ▾
All authors Chih-Hung Lee, Yuchi Sun, Rui Zhang, Suhang Wei, Qi Lu