Mobile Crowdsensing and Crowdsourcing

Latest papers

• RAIM: Robust Aggregation of Inexpensive Models for Hallucination Detection

  Elia Onofri, Roberto Di Pietro · 1 October 2026

  Automatic evaluation of faithfulness increasingly relies on a large language model acting as a judge, yet the most reliable judges are proprietary frontier models, costly and ill-suited to high-throughput monitoring. We investigate whether a panel of cheap open-weight judges (4--9B) can be aggregate…

• Optimal Design for Active Preference Learning with Biased LLM Judges

  Zhongman Du, Huiming Zhang, Haodong Zhu, Baochang Zhang · 1 October 2026

  Learning from human preferences is central to large language model (LLM) alignment, but human preference annotation is costly. Active preference learning reduces this cost by selecting informative comparisons, and LLM judges can provide additional scalable feedback. However, the preferences of the j…

• More Choices, Fewer Decisions: Ordinal-Scale Bias in JEV-like Direct-Decision Models

  Tianxiang Gao, Jinzhe Li, Zhiyuan Li, Yi Chang, Yuan Wu · 1 October 2026

  Direct-decision models turn text into low-latency structured labels and scores, making them attractive for classification and automatic evaluation. Yet reliability requires more than accuracy: a model must also use the ordinal decision scale supplied by the user faithfully. We analyze JEV~1.13 and t…

• Budget Boundary Effects in Test-Time Mathematical Reasoning

  Guilin Zhang, Ziqi Tan, Wulan Guo, Kai Zhao, Hongyun Yang, Mei Luo, Qi Ning, Feng Yang · 1 October 2026

  A cumulative token cap can fall inside a mathematical derivation, forcing a test-time controller to choose between stopping at the cap (strict) and allowing the current attempt to finish (advisory). We measure this boundary choice with paired offline replays of 19,200 public traces: 120 AIME, BrUMO …

• Do System One Decisions Add Up? A Study of Probabilistic Coherence

  Saman Sarker Joy · 30 September 2026

  A decision model can give probabilities that sum to one for every question yet disagree with itself when the same decision is broken into smaller steps. We study this form of probabilistic coherence in Jev and the English Laya checkpoint, using 2,500 matched examples per system across TREC, CLINC150…

• Breaking the Uniformity Trap: Scaling Video Diffusion Model via SplitMoE

  Yu Xu, Yuxin Zhang, Xiao Yang, Haotian Yang, Yizhi Wang, Xinwei Huang, Minxuan Lin, Angtian Wang, Chongyang Ma, Fan Tang · 30 September 2026

  Mixture-of-Experts (MoE), popularized by large language models, is a promising paradigm for scaling visual generative models. However, conventional token-wise MoE routes tokens independently within a homogeneous expert pool and regularizes expert usage toward uniformity, making it poorly matched to …

• VStress: Correlation-Aware Auditing and Adaptive Budget Allocation for Repeated Verifiers

  Miaobo Hu, Shuhao Hu, Xiaobo Guo, Xin Wang, Bokun Wang, Peng Zhang, Daren Zha, Jun Xiao · 30 September 2026

  Repeated verifier calls are useful only when they contribute conditional information. We introduce VStress, an auditable replay contract, and VStress-CA, a correlation-aware allocation policy that estimates the conditional marginal information of an unqueried verifier on a sealed calibration split, …

• MoRE: Scaling mixture of experts with hardware-aware low-rank routing

  Honam Wong, Surbhi Goel, Enric Boix-Adser\`a · 30 September 2026

  Mixture-of-Experts (MoE) layers are central to frontier language models, and recent architectures push toward more and smaller experts. In this regime, the standard linear router becomes a bottleneck: with $M$ experts and hidden dimension $h$, its per-token cost $\Theta(Mh)$ dominates the MoE layer …

• Improving scalable oversight with co-trained monitors

  Joseph H. Rudoler, Kevin Tan, Benedict Tessler, Timothy Kong, Enric Boix Adser\`a · 30 September 2026

  Worker-monitor setups are a promising approach to AI oversight, but training workers against fixed monitors can incentivize monitor evasion. We study whether this failure mode can be avoided by co-training the monitor alongside the worker, and explore both supervised and self-supervised approaches. …

• Cross-Entropy Guided Routing in Mixture-of-Experts Large Language Models

  Yury Nahshan, Nati Daniel, Jacob Goldberger, Yoli Shavit · 30 September 2026

  Sparse mixture-of-experts (MoE) large language models scale model capacity by routing each token to a small subset of experts. Their routers are regularized with load balancing terms and learn affinity scores through the language-model objective. However, these objectives do not provide direct align…

• Emergent Specialization in Populations of Self-Supervised Collaborative Vision Experts Without a Shared Gate or Cross-Agent Gradients

  Aram Davtyan, Pablo Acuaviva, Sebastian Stapf, Paolo Favaro · 30 September 2026

  Can a population of neural networks develop a useful division of labor without a shared gate or gradients between agents? We study a setting where each network has its own weights, trains independently on the same heterogeneous data, and can ask another agent for help through a forward pass. Unlike …

• SlimWise: Decoupling Expert Pruning Across Prefill and Decode for Efficient MoE Serving

  Gunho Park, Kyoungho Jeun, Juntaek Oh, Byeongjun Shin, Baeseong Park, Minsoo Rhu · 29 September 2026

  Mixture-of-experts (MoE) models activate few experts per token, yet batched decoding can access nearly the entire expert pool, making expert-weight traffic a major bottleneck. Expert pruning reduces this traffic, but conventional approaches also prune compute-bound prefill, sacrificing model quality…

• MaskCoFT: Masked Co-Adaptive Fine-Tuning for Memory-Efficient MoE Inference

  Junfeng Wu, Zehao Fan, Hadjer Benmeziane, Kaoutar El Maghraoui, Liu Liu, Yinan Wang · 29 September 2026

  Mixture-of-experts (MoE) language models often exceed the memory of a single GPU. Expert offloading keeps most experts in host memory and loads them on demand, so decoding speed depends on how many experts each token must fetch. Caching and prefetching reduce this cost only as far as the routing all…

• Rethinking Training-Inference Mismatch in LLM Reinforcement Learning: Where It Arises and How to Correct It

  Tianrun Yu, Kaixiang Zhao, Shangzhe Li, Yuxiao Yang, Porter Jenkins, Weitong Zhang, Taylor W. Killian · 29 September 2026

  We study training-inference mismatch in reinforcement learning with verifiable rewards (RLVR) for large language models, where rollouts are sampled by an inference engine while gradients are computed by a training engine, and the two engines assign different probabilities to the same tokens. To acco…

• A Persistent State for Auditable Mixture-of-Experts Routing

  Abdurrahman Javat, Allan Kazakov · 29 September 2026

  Mixture-of-Experts (MoE) models repeatedly route tokens to sparse subsets of experts, but conventional routers expose no routing-specific record of how cross-layer influences accumulate. We introduce Scratchpad-Augmented Mixture-of-Experts (SA-MoE), which gives each router access to a low-dimensiona…

• Test-Time Scaling via Budgeted Multi-Attribute Verification

  Bo Xue, Ji Cheng, Shen-Huan Lyu, Yuanyu Wan, Shuang Qiu · 29 September 2026

  Verifying LLM-generated answers under a shared computational budget requires jointly deciding which candidates to inspect and which verification attributes to evaluate. We formulate this problem as multi-attribute good-arm identification under a global budget: each candidate is an arm evaluated alon…

• Curating Merchant-Matching Training Data with Two Confidence-Gated Local LLM Judges

  Donghao Huang, Jinling Pei, Zhaoxia Wang · 29 September 2026

  Merchant matching resolves a noisy payment descriptor to a retrieved merchant entity or returns no match. A key challenge in curating training labels is distinguishing teacher abstention from evidence that no acceptable entity exists: false no-match labels contaminate pseudo-labeled data, while cons…

• EAT: Expert Account Tracker for Efficient MoE Inference

  Yuexian Li, Yifei Yang, Zouying Cao, Hai Zhao · 29 September 2026

  Mixture-of-Experts (MoE) models have emerged as a revolutionary method to scale Transformer models. However, traditional MoE architecture still suffers from inefficiency since a large number of experts are unnecessarily activated. Existing approaches for reducing the number of activated experts ofte…

• Routing Drift Alone Does Not Diagnose Failure in Merged MoE LLMs

  Yuanyi Wang, Yanggan Gu, Su Lu, Guanghao Zhu, Pengkai Wang, Yifan Yang, Congkai Xie, Zhaoyi Yan, Jianmin Wu, Hongxia Yang · 29 September 2026

  Model merging efficiently combines specialized large language models (LLMs) without joint retraining, but can substantially alter expert routing in Mixture-of-Experts (MoE) models. Such \emph{routing drift} is often interpreted as routing failure, raising a fundamental question that remains unclear:…

• Function Over Form: Distributional Orthogonalization in Mixture-of-Experts with Replica Expert Mechanism

  Jinfan He, Yunzhuo Liu, Kai Zhang, Weidong Han, Key, Rayying · 29 September 2026

  The scaling of LLMs increasingly relies on MoE architectures to decouple active computation from total parameter count. However, the efficacy of MoE is often constrained by expert collapse and representation redundancy, both leading to underutilization of model capacity. To address these challenges,…

• Reasoning Concentrates Errors, and Self-Consistency Never Notices

  Asaad Althoubi · 29 September 2026

  Self-consistency assumes that independent samples disagree when a model is unsure, so agreement is evidence of correctness. Holding weights fixed and toggling only a reasoning mode, over five benchmarks and 74,944 samples, we show that reasoning concentrates a model's errors: the probability that tw…

• Adaptive Resource Allocation for Effective and Efficient LLM Social Survey Simulation

  Yuanzi Li, Xueyang Feng, Junhao Wang, Lei Wang, Xu Chen · 29 September 2026

  Large Language Models (LLMs) enable scalable social survey simulation, yet existing pipelines typically use the same strong general-purpose model and a fixed, often large, respondent history for every respondent-question request. This uniform approach overlooks three factors. First, stronger models …

• Metacognitive Selective Ensemble for Mobile Systems

  Sungmin Lee, Kichang Lee, Joonhee Lee, JaeYeon Park, Songkuk Kim, JeongGil Ko · 28 September 2026

  Deep ensembles improve robustness in mobile sensing, but repeatedly executing many models over continuous sensor streams is costly. Selecting only a few members reduces this cost, yet adaptive selection often requires additional model execution to obtain reliable evidence about inactive candidates. …

• Reinforcement Learning of Communication in a Mesh of Small Language Models

  Mehmet Kerem Turkcan · 28 September 2026

  Language models gain accuracy from more compute at test time, but majority voting over independent samples saturates: as samples grow, the vote converges to the model's most frequent answer. Communication can add what sampling cannot: an agent that solves a problem can pass the key step to the other…

• RAZOR: Pruning Replaceable Experts in LLMs

  Mingyang Song, Mao Zheng · 28 September 2026

  Mixture-of-experts (MoE) models activate few experts per token but store the full expert pool. Expert pruning reduces this storage burden; at a fixed pruning budget, the goal is to preserve the original model's output distribution as closely as possible. Yet an expert's usage or contribution magnitu…