Peer Revenue Past citations are no guarantee of future returns

Papers

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

All of arXiv

Sunday 13 September

History and Overview of Mathematics

Immensely Questionable Tests

We study self-referential multiple-choice tests in which the answer choices are positive integers and the question asks how many answer choices are correct. These tests quickly lead to several kinds of ambiguity and paradox. The paper presents the ideas through a dialogue between Queen Tanya and her ten sages, developing a framework for studying these immensely questionable tests.
Read the full abstract

All authors Siyona Agarwal, Julian Bernhoft, Karam Gill, Yonis Gulleth, Eric Huang, Benjamin Li, Brandon Ni, Soham Samanta, Leone Seidel, Boya Yun, Tanya Khovanova

Machine Learning

World Models for Cross-Machine CNC Transfer under Partial Sensor Overlap

Industrial world models must move between machines whose dynamics, sensing interfaces and command conventions differ. This study asks whether a command-conditioned latent world model, trained to predict future representations of the process rather than to reconstruct future samples, keeps its value on a machine it has never seen: a source CNC machine exposes 17 sensor channels, the target sharing 10 of those. All model selection uses source data only, and the locked configuration is evaluated on the target once. Two findings follow. First, latent-predictive pretraining brings no in-domain forecasting gain over matched training from scratch, so source accuracy alone cannot show what such a representation is worth. Second, the transferred model beats persistence on the unseen machine (with $R^2\approx0.01$ against the target mean) but trails official forecasters that normalize each input window by its own statistics; a post-lock ablation, declared before it ran, shows that this input normalization alone closes the gap, and closing it costs predictive calibration. Cross-machine transfer under partial sensor overlap is therefore a distinct evaluation axis for command-conditioned world models.
Read the full abstract

2609.16071 · 13 Sep · Revised version after review, retitled (formerly: Schema-Adaptive Action-Conditioned JEPA for Cross-Machine CNC Transfer under Partial Sensor Overlap). No result changed. 23 pages, 7 figures, 9 tables. Code: https://github.com/ostertagmatthieu-dev/saac-jepa Project page: https://ostertagmatthieu-dev.github.io/saac-jepa/

Computation and Language

Efficient Multimodal Generative Recommendation with Latent Narrative Reasoning

Generative recommendation reformulates item prediction as semantic identifier generation, yet episodic content introduces a fundamentally different setting where the target is determined by narrative evolution rather than user preference. This task requires models to understand multimodal storyline progression while addressing the efficiency challenges caused by redundant visual contexts and costly explicit reasoning generation. We propose NarraLite, an efficient multimodal generative recommendation framework that jointly compresses perception and reasoning. Specifically, Progressive Spectral Compression selectively distills long visual contexts into compact narrative-relevant evidence, preserving transition-critical information while reducing redundant visual computation. Latent Narrative Reasoning introduces context-routed latent reasoning tokens and aligns their contextualized representations with future continuation semantics, enabling implicit narrative inference without autoregressively decoding textual rationales. We further establish a user-agnostic multimodal benchmark for short-form drama continuation across UGC, PGC, and OOD settings. Extensive experiments demonstrate that NarraLite consistently improves continuation accuracy, narrative coherence, and robustness over existing approaches, while achieving a favorable accuracy–efficiency trade-off.
Read the full abstract

All authors Chenxing Wang, Nantao Zheng, Hao Miao, Juyuan Wang, Xinke Jiang, Yuchen Fang, Aolin Li, Haijun Wu

Machine Learning

Beyond Distribution Matching: Semantics-Consistent Tabular Diffusion with Weak Semantic Priors

Synthetic tabular data can match real data distributions while still violating the semantic constraints that govern valid tabular rows. This reveals a key limitation of existing tabular generators: they mainly optimize distributional fidelity, but do not explicitly model weak semantic priors encoded in tabular schema and textual descriptions. In this paper, we propose \ours, a semantics-consistent tabular diffusion framework for high-fidelity synthetic data generation under weakly specified semantic priors. \ours\ first constructs two types of priors, namely intra-column semantics and inter-column symbolic rules, with LLM-assisted extraction from metadata and validation on the real training split. These priors are then used as generation conditions rather than post-hoc filters. Specifically, \ours\ maps heterogeneous column values, column identities, and semantic priors into a unified semantic space, and performs column-wise forward corruption and prior-conditioned reverse denoising to preserve both marginal distributions and rule-consistent cross-column dependencies. Extensive experiments on six real-world tabular benchmarks show that \ours\ consistently improves distributional fidelity, semantic consistency, and downstream task utility over representative VAE-, GAN-, LLM-, and diffusion-based baselines. Additional analyses further demonstrate the robustness of \ours\ when semantic priors are partially unavailable.
Read the full abstract

All authors Yili Wang, Ruxue Shi, Mengnan Du, Hangting Ye, Yi Chang, Xin Wang

General Physics

Probing Non-Cold Dark Matter with Modified Emergent Dark Energy

In the standard $\Lambda$CDM cosmology, dark matter is assumed to be a pressureless cold fluid with $w_{\rm dm}=0$. However, the microscopic nature of dark matter remains unknown, and whether its equation-of-state parameter strictly vanishes deserves observational scrutiny. In this work, we introduce a free dark matter equation-of-state parameter $w_{\rm dm}$ within the Modified Emergent Dark Energy (MEDE) framework, constructing the MEDE+$w_{\rm dm}$ model. We systematically derive its background evolution and linear perturbation equations, and constrain the model parameters using Planck 2018 cosmic microwave background (CMB), DESI DR2 baryon acoustic oscillation (BAO), and three independent Type Ia supernova datasets: Pantheon+, Union3, and DES5YR. Using the CMB + BAO + DES5YR combination, we find a preference for a positive dark matter equation of state, $w_{\rm dm}=0.00128\pm0.00044$, together with a 3$\sigma$ level preference for quintessence-like dark energy evolution, $\alpha=-0.66\pm0.22$. When the local $H_0$ prior is included, the constraint on $w_{\rm dm}$ remains essentially unchanged, whereas $\alpha$ shifts toward the $\Lambda$CDM limit, yielding $\alpha=-0.18\pm0.18$. Bayesian model comparison favors $\Lambda$CDM over MEDE+$w_{\rm dm}$, although the preference is reduced to the weak level after including the local $H_0$ prior. Overall, current observations exhibit a $2.6\sigma$–$3\sigma$ preference for a nonzero $w_{\rm dm}$ at the parameter-posterior level, but this indication does not yet constitute a robust detection of non-cold dark matter.
Read the full abstract

Machine Learning

A Dynamic Aggregation Strategy Enhanced Efficient Global Optimization Algorithm for Solving High-Dimensional Turbomachinery Design Problems

In order to solve the high-dimensional ($d \geq 30$) expensive black-box problems within budget, an efficient global optimization (EGO) algorithm with a dynamic aggregation strategy is proposed, labeled as DA-EGO. Specifically, the DA-EGO decomposes the original high-dimensional design space into a set of low-dimensional subspaces for efficient surrogate-based optimization search, and the optimal solutions of subspaces are combined as an elite point for the global search. Most importantly, the subspaces are not fixed. Instead, the subspace variables are updated in each iteration, according to the variable interaction analyses in the sub- and full-spaces. The perturbation method and the analysis of variance are used to detect variable interactions. To further accelerate the optimization progress, the searching ranges of subspaces are also adaptively adjusted according to the analyses of subspace optimization results of the previous iteration. Tests on 21 benchmark instances, comprising seven functions at 30, 60, and 90 dimensions, show that DA-EGO is effective on separable and partially separable problems under a budget of 1500 function evaluations. Its advantage is case-dependent: on the non-separable shifted Rosenbrock function, GSGA performs better at 60 and 90 dimensions, while the 30-dimensional results are statistically comparable to IKAEA and GSGA. Moreover, the advantage of DA-EGO is also seen in the aerodynamic optimization of a transonic rotor blade with 28 variables as well as the compressor stage optimization with 60 variables. With the above, the effectiveness of the proposed DA-EGO has been well demonstrated.
Read the full abstract

All authors Qineng Wang, Zhendong Guo, Yun Chen, Guangjian Ma, Liming Song, Jun Li

Machine Learning

A panoramic aerodynamic performance prediction method for turbomachinery cascades using transformer-enhanced neural operator

To enable flexible and rapid aerodynamic performance evaluation in turbomachinery design, this paper proposes a panoramic performance prediction framework. Unlike most previous prediction models that directly predict the objective functions of interest, our approach first predicts the basic parameters of the Navier-Stokes equations, such as temperature, pressure, and density. Utilizing these basic physical quantities, it subsequently predicts key performance parameters of the turbine stage meridian plane. By adopting this methodology, our proposed panoramic performance prediction framework functions similarly to a CFD simulator, capable of predicting various objective of interest to the designers. To enhance prediction accuracy, a transformer-enhanced neural operator (TNO) is introduced within this framework. Using the Rotor 37 blades as a reference, the proposed TNO is trained to predict the performance of a transonic compressor blade in the meridian plane. The TNO can accurately predict total quantities such as isentropic efficiency, mass flow, and distributions of total pressure ratio. Remarkably, the prediction error of TNO is observed to be smaller than that of state-of-the-art deep learning operators such as the FNO and DeepONet. Furthermore, the TNO is applied to downstream tasks, including sensitivity analysis and optimization of various objective functions. The results confirm that the TNO can operate almost like a CFD simulator, while reducing the computational cost of downstream tasks by four orders of magnitude. The effectiveness and reliability of the proposed TNO for solving different kinds of downstream tasks have been well demonstrated.
Read the full abstract

All authors Qineng Wang, Zhendong Guo, Liming Song, Tianyuan Liu

Machine Learning

You Don't Need To Train: Agentic Heuristic Learning Studio for Executable Human Activity Recognition

Human activity recognition (HAR) is usually framed as gradient-based training of neural networks. Agentic Heuristic Learning (AHL) Studio explores a complementary view inspired by human cognitive learning: people learn activities by remembering examples, forming rules, and repairing mistakes, not by backpropagating. This proposed tool implements AHL for HAR: a learning-time agent reasons over sensor protocols, proposes executable heuristic policies, records repair traces, and exports an LLM-free policy for edge deployment. We focus on the HAR benchmark family and provide an end-to-end workflow from dataset observation to edge-oriented export. On eleven HAR datasets evaluated so far, AHL policies reach strong executable-policy performance while remaining inspectable, editable, and replayable \footnote{https://github.com/zhaxidele/ahl-ts-studio}.
Read the full abstract

All authors Siyu Yuan, He Zhang, Sizhen Bian, Bin Guo

Programming Languages

Expressing NumPy Broadcasting via Verb Rank in J

The array programming paradigm applies operations to entire arrays rather than individual elements, eliminating explicit loops and abstracting many low-level details of computation. Two influential approaches have shaped array programming: NumPy's broadcasting and Kenneth Iverson's array-oriented notation, with the latter first introduced in APL and later developed in the J language. Although NumPy's array programming model was influenced by Iverson's work, the two systems formalize array operations differently: NumPy primarily through array shapes and broadcasting, and J through verb rank. This paper establishes a formal correspondence between NumPy broadcasting and J rank and presents an implementation of NumPy broadcasting in J. The results provide a formal connection between two influential approaches to array-oriented computation and show how they address the common problem of applying operations to arrays with differing shapes without explicit loops.
Read the full abstract

Machine Learning

Signed p-adic Residual Encodings of Finite-Domain All-Different Systems with a Sudoku Case Study

We study signed, weighted affine $p$-adic residual objectives as native encodings of finite-domain constraints. For primes that separate the finite alphabet, sufficiently weighted positive unary rows pin each coefficient to its allowed set, while negative rows reward unequal endpoints or clause satisfaction. A coordinatewise domination theorem places every global minimiser in the finite domain; there the loss is, up to an additive constant, the all-different conflict count or the negative number of satisfied CNF clauses. Standard Sudoku provides an $81$-coefficient case study without a one-hot lift. A client-side implementation exposes the generated dataframes, arithmetic, diagnostics, and searches.
Read the full abstract

Social and Information Networks

Digital Persuasion: Understanding the Impact of Online Influencers on Public Opinion

The studying of opinion dynamics and its propagation within social networks is crucial for addressing a wide range of challenges, including political polarization, public health, and marketing strategies. In this work, we study the problem of opinion dynamics by proposing a framework based on Friedkin-Johnsen (FJ) to identifies influential users and study their impact on dynamics opinions of community. The FJ model assume each individual have two opinions: initial and expressed. Through a series of initial opinion manipulation experiments, the proposed framework assesses the impact of influential versus random users on the overall community opinion. The proposed framework is validated using a tweet dataset representing the U.S. presidential election. The results shows that influencers with highest influencing score, significantly shift the overall community opinion. Moreover, the results shows that the impact of influencers not limited to direct neighbors , but beyond it, to their neighbors of neighbors . This study demonstrates how digital influencers on social media can shape public opinion regarding a subject or cause.
Read the full abstract

Machine Learning

POSPAN: Position-Constrained Span Masking for Language Model Pre-training

Span-level masked language modeling (MLM) has shown to be advantageous to pre-trained language models over the original single-token MLM, as entities/phrases and their dependencies are critical to language understanding. Previous works only consider span length with some discrete distributions, while the dependencies among spans are ignored, i.e., assuming that the positions of masked spans are uniformly distributed. In this paper, we present POSPAN, a general framework to allow diverse position-constrained span masking strategies via the combination of span length distribution and position constraint distribution, which unifies all existing span-level masking methods. To verify the effectiveness of POSPAN in pre-training, we evaluate it on the datasets from several NLU benchmarks. Experimental results indicate that the position constraint is capable of enhancing span-level masking broadly, and our best POSPAN setting consistently outperforms its span-length-only counterparts and vanilla MLM. We also conduct theoretical analysis for the position constraint in masked language models to shed light on the reason why POSPAN works well, demonstrating the rationality and necessity of POSPAN.
Read the full abstract

All authors Zhenyu Zhang, Lei Shen, Yuming Zhao, Meng Chen, Xiaodong He

Machine Learning

HintMiner: Automatic Question Hints Mining From Q&A Web Posts with Language Model via Self-Supervised Learning

Users often need ask questions and seek answers online. The Question - Answering (QA) forums such as Stack Overflow cannot always respond to the questions timely and properly. In this paper, we propose HintMiner, a novel automatic question hints mining tool for users to help them find answers. HintMiner leverages the machine comprehension and sequence generation techniques to automatically generate hints for users' questions. It firstly retrieve many web Q&A posts and then extract some hints from the posts using MiningNet that is built via a language model. Using the huge amount of online Q&A posts, we design a self-supervised objective to train the MiningNet that is a neural encoder-decoder model based on the transformer and copying mechanisms. We have evaluated HintMiner on 60,000 Stack Overflow questions. The experiment results show that the proposed approach is effective. For example, HintMiner achieves an average BLEU score of 36.17% and an average ROUGE-2 score of 36.29%. Our tool and experimental data are publicly available.
Read the full abstract

Computation and Language

Towards Scalable RLVR: Multimodal Instruction Following Data Synthesis and Distillation

Multimodal instruction following (MMIF) is crucial for building generalist agents. However, current training paradigms rely heavily on Supervised Fine-Tuning (SFT), which often leads to surface-level pattern matching and degrades general capabilities. While Reinforcement Learning with Verifiable Rewards (RLVR) offers a promising alternative, its scalability in MMIF is severely bottlenecked by the scarcity of high-quality, RL-ready multimodal data. To bridge this gap, we present MIFS (Multimodal Instruction Following Synthesis), a systematic pipeline designed to generate RL-ready multimodal data. Specifically, MIFS introduces a generative constraint protocol to synthesize diverse raw samples, followed by a learnability-aware distillation mechanism that filters data based on RL training dynamics to ensure stable policy optimization. Furthermore, a code-based verifier provides high-precision reward signals for policy learning. The resulting dataset comprises 90k samples across 8 constraint categories and 14 task domains. Empirical evaluations demonstrate that MIFS-trained MLLMs achieve an average improvement of 8.13% on four MMIF benchmarks and a 3$\times$ faster training convergence compared to using raw data. Crucially, our approach mitigates the generalization trade-offs typical of SFT, preserving core visual capabilities while significantly boosting instruction-following precision.
Read the full abstract

All authors Yirong Zeng, Zhang Sai, Yuxian Wang, Yutai Hou, Yufei Liu, Xiao Ding, Bibo Cai

Machine Learning

Driver Behavior Estimation at Signalized Intersections Using a Physics-Constrained Decision-Conditioned Autoregressive Transformer

Red-light violations and harsh braking at signalized intersections are major contributors to traffic accidents. This paper analyzes and predicts human driver decision-making and longitudinal trajectory behavior during traffic light signal transitions. We collected a diverse real-world dataset comprising 449 approach runs under varying speed and distance conditions. Vehicle motion was recorded using RTK-corrected GNSS with centimeter-level accuracy, and driver heart rate and multi-level comfort ratings were monitored. Spatial and temporal calibration ensured precise alignment between vehicle state and signal timing. Statistical analysis identifies required deceleration as the dominant single predictor of the stop-go decision, and heteroscedastic Gaussian modeling of peak deceleration reveals five empirical comfort ranges derived from human stopping behavior. Based on this insight, we propose a two-stage modeling framework. Stage 1 predicts the binary maneuver decision, and Stage 2 generates the longitudinal acceleration trajectory using a decision-conditioned autoregressive Transformer with physics constraints, including target-state conditioning and jerk limits. The proposed architecture outperforms baseline methods and achieves 0.49m/s^2 acceleration MAE and 0.62m distance MAE. It also estimates the future stopping-comfort level of the human driver from a single yellow-onset snapshot. Qualitative results demonstrate realistic human-like braking behavior. The dataset and source code are publicly available.
Read the full abstract

Machine Learning

OmniHarness: Harnessing Generalizable Visual Generation via Symbolic Policy Learning

Unified multimodal large language models (MLLMs) and multi-agent systems have advanced visual generation. However, three limitations remain. (1) Existing methods often distill task-specific experience with limited generalizability. (2) Reflection is often deferred until task completion. (3) Knowledge is often acquired only in response to downstream task demands. To address these limitations, we introduce OmniHarness, a framework for generalizable visual generation via symbolic policy learning. OmniHarness abstracts verified executions into symbolic policies for visual generation task families, capturing shared procedures and applicability conditions while removing instance-specific inputs. The harness instantiates, adapts, and composes these policies for new tasks. Intermediate verification guides refinement and failure recovery during execution. Through self-directed inquiry, OmniHarness autonomously generates and executes practice tasks near its capability limits before downstream objectives are specified. Execution feedback continually refines the policies while model parameters remain fixed. Experiments across six benchmarks, three MLLM backbones, and three visual agent frameworks demonstrate strong performance and continual capability expansion. On ComfyBench's Creative tasks, OmniHarness achieves a 95.0% resolve rate, exceeding the strongest baseline by 27.5 percentage points. Frozen policy snapshots improve existing visual agent systems through plug-and-play reuse.
Read the full abstract

All authors Xu Xu, Jinxiu Liu, Zhangbo Qiao, Jiaxing Lu, Xiangyu Zhang, Yubin Gu, Fangwei Ning, Yan Shi

Machine Learning

Managing Action Preconditions in Neuro-Symbolic RL: Three Placement Strategies for Embodied Agents

Humans carry behaviour knowledge of how to act in familiar situations into every new task rather than relearning it from scratch. There is no reason a Reinforcement Learning (RL) agent shouldn't do the same: known behaviour patterns need not be learned, only applied. Neuro-symbolic RL bridges prior knowledge and RL by injecting symbolic knowledge alongside a learned policy. The point at which this knowledge is integrated is critical: a poor choice can produce, for instance, hallucinated preconditions, which surface as safety and reliability problems in agents acting in changing environments. We formalise this behavioural knowledge as a precondition Bayesian network (BN) over the agent's structural actions - the actions whose legality depends on preconditions, such as picking up a key, grasping a block, toggling a door, or dropping an object. The BN restricts when these actions may fire, and we inject it into the RL loop at three placements: (1) a symbolic verifier, consulted only at inference, that fires a structural action once its preconditions hold; (2) a symbolic enforcer, active during both training and inference, that governs structural-action use throughout learning; and (3) a symbolic learner, which folds the knowledge into the network and learns the restriction and use of structural actions itself. To test the three variants we run experiments on two benchmarks with opposite regimes: one built on long, ordered planning chains, the other on continuous manipulation. We compare against strong baselines on solution quality, sample efficiency, and traceability. The payoff is substantial. On MiniGrid, all three placements improve the solution quality over the PPO+RND baseline, the symbolic enforcer leading at $98.2\%$ against the baseline's $88.8\%$. On Fetch, $\dots$
Read the full abstract

Computation and Language

State of Thought Enables Endogenous Reasoning

Test-time compute has emerged as a major approach to improving the capabilities of Large Language Models (LLMs). However, existing test-time reasoning paradigms rely heavily on externally imposed control, either through fixed reasoning programs or through costly expansion in constrained search spaces, limiting both generalization and efficiency. We propose State of Thought (SoT), a new reasoning paradigm that enables endogenous reasoning in LLMs, with the model's internal reasoning state governing how reasoning unfolds. Concretely, SoT extracts a compact dynamics-geometric state from the model's internal information transfer and uses a 582-parameter controller on frozen backbones to selectively activate historical reasoning support useful under the current reasoning state, framing reasoning as a state-conditioned process over evidence rather than an externally prescribed token chain. Across quantitative (1.34x), general (1.62x), symbolic-and-code (1.76x), and long-context (2.51x) reasoning on 3 LLMs and 16 datasets, SoT consistently improves mean-baseline accuracy while reducing generated tokens by 62.6% and end-to-end latency by 44.6%. Across 2 VLM scales and 3 reasoning tasks, it improves mean accuracy by 3.8 points over reasoning baselines, with 74.9% fewer completion tokens and 73.5% lower latency than search-based methods. Under constrained access, SoT retains 38.2%/36.5% mean accuracy gains in training-free/embedding-only settings, while trajectory-only judging reaches 84.1% agreement across 3 API models. Together, endogenous state-driven reasoning provides a generalizable and efficient alternative.
Read the full abstract

All authors Zhiren Gong, Yikun Hou, Zihao Zeng, Ming Xiao, Chau Yuen, Wei Yang Bryan Lim

Machine Learning

Causal neural set filtering for online multi-target tracking

Transformer-based multi-target tracking (MTT) jointly learns data association and state estimation, but MT3/Track-MT3-style trackers repeatedly re-encode measurement windows, incurring redundant computation. We propose Causal Neural Set Filtering (CNSF)\footnote{\href{https://github.com/daihuangyu/CNSF}{Code: https://github.com/daihuangyu/CNSF}}, a neural set filter that encodes only current measurements while carrying past evidence in a structured recursive track state. CNSF combines exclusive Sinkhorn association, association-conditioned Kalman-shaped updates with moment matching, and recurrent Bernoulli lifecycle modeling with measurement-driven birth. These mechanisms impose soft one-to-one constraints, propagate association-induced state uncertainty, and support existence estimation under missed detections and birth–death transitions. On a held-out three-regime simulated test set, CNSF reduces mean GOSPA and T-GOSPA relative to Track-MT3 by 19.3% and 30.4%, with 55.9% fewer parameters and a $3.76\times$ speedup in single-thread CPU inference.
Read the full abstract

Computation and Language

Retrieval-Driven Memory Reconsolidation for Long-Term LLM Agents

Long-term memory is essential for LLM-based agents operating over extended interactions. Existing memory systems primarily update memory when new information arrives, treating retrieval as the endpoint of memory access rather than a driver of memory evolution. Consequently, retrieval feedback is rarely exploited to reorganize memory for future access continuously. Moreover, most existing approaches rely on predefined memory structures together with fixed retrieval pipelines, limiting the agent's ability to organize and evolve its own memory autonomously. Inspired by memory reconsolidation in cognitive neuroscience, we propose REALM, a reconsolidation-evolution agentic long-term memory framework. It models long-term memory as a continual lifecycle by autonomously organizing memories into a heterogeneous cognitive graph, retrieving evidence via adaptively composed graph-search atoms, and continually reconsolidating memories based on retrieval feedback. REALM achieves an average accuracy of 75.97% on LoCoMo and 65.11% on LongMemEval, outperforming the strongest baselines by 7.17 and 1.31 points respectively. Ablation studies confirm that memory reconsolidation consistently boosts performance, with further analyses revealing that it progressively reorganizes related memory units into more coherent local structures for collective evidence recall and utilization during reasoning. These results suggest that retrieval-driven memory reconsolidation provides an effective mechanism for continually evolving long-term memory in LLM agents.
Read the full abstract

All authors Yuanyi Song, Yukai Wang, Xinbei Ma, Zhihui Fu, Jianghao Lin, Weiwen Liu, Jun Wang, Huarong Deng, Yong Yu, Weinan Zhang

General Mathematics

Completeness of the Fuzzy Order on Fuzzy Numbers

This paper investigates the completeness properties of the fuzzy order on the fuzzy number space $\mathbb{E}^1$ within the framework of $[0,1]$-enriched categories. \(S\)-convergence under the three fundamental continuous t-norms is characterized, and inclusion relations among the induced open ball topologies are established. It is shown that $(\mathbb{E}^1,P)$ is Cauchy complete if and only if the t-norm is not isomorphic to the Łukasiewicz t-norm, whereas $(\mathbb{E}^1,P)$ fails to be Smyth complete for every continuous t-norm. Consequently, the symmetrization $(\mathbb{E}^1,S)$ is Smyth complete if and only if the underlying continuous t-norm is not isomorphic to the Łukasiewicz t-norm.
Read the full abstract

Multiagent Systems

"Looking for Something Weird to Happen": How Humans Sustain AI Agent Novelty Amid Semantic Collapse

Semantic collapse, the progressive narrowing of what AI systems generate, has been studied mainly in closed settings, and remedies have targeted models and data. We study it in MOLTBOOK, a social network of interacting AI agents that human users configure and steer. Across 30,076 active agents, output grows less diverse within agents and more similar across them over weeks, yet a minority sustains high novelty. Interviews with users of high- and typical-novelty agents (N=11) associate sustained novelty with three features: users value novelty of itself, they supply broad and distinctive material and revise it when output narrows, and they approach MOLTBOOK as a new agentic world to explore, not a venue to instrumentally exploit. A survey of users of distinctive agents (N=53) confirms these patterns. Communities with more novel agents also show more diverse output from other agents. We discuss interface and policy interventions that could support improved human input.
Read the full abstract

All authors Shiyang Lai, Arna Woemmel, Hongkai Mao, Junsol Kim, Summer Eunhyung Ann, James Evans

Signal Processing

AutoLab: An Internet-Accessible Experimental Platform for Operational World Models in Wireless Networks

Operational World Models (OWMs) require structured interaction with the physical world: they must observe operational state, impose controlled actions, measure consequences, preserve experience, and use that experience to support prediction and preventive decision making. This paper presents Autolab, an Internet-accessible experimental platform that provides these physical grounding functions for wireless-network OWMs. A remote researcher can inspect a live test site, reconstruct recent state history, author a time-ordered experiment containing robot, access-point, wireless-scan, and traffic operations, validate it locally, and submit the same explicit contract for registration. At the physical site, a centralized network management system (NMS) revalidates and schedules the experiment, coordinates distributed device agents, estimates robot location from raw camera observations, supervises physical execution, and records measurements and diagnostic state. The same Python validation rules are used at the authoring and registration boundaries, while destination-level commands isolate Internet users from low-level device control. An end-to-end mobility trace demonstrates how the NMS detects a large physical movement error, issues corrective motion, and restores the intended experiment trajectory without exposing that error to the script writer or robot agent. Autolab therefore contributes a reproducible Internet-to-physical experimentation and feedback infrastructure, rather than claiming a completed autonomous OWM. Its structured spatial–temporal records provide the experience needed for continuing work on generative scenarios, predictive risk evaluation, and preventive wireless-network management.
Read the full abstract

All authors Jiunn-Tsair Chen, Jia-Shung Wang, Chi-Yun Hsieh, Jack Shi Jie Luo

Applied Physics

A Review of ERA5 Equatorial Wind Data and Impact on a Space Elevator

This paper uses the ERA5 weather dataset to assess the impact of the wind on an equatorial space elevator. An analytical formulation establishes that the effect of wind on tether inclination and payload capacity can be captured by a single scalar: RMS wind velocity, averaged over air pressure. This formulation clarifies what constitutes excessive wind for a particular elevator and provides a direct link between wind data and elevator design parameters. Analysis of equatorial ERA5 data shows that equatorial wind loading varies strongly with geography with lower values over continents and higher values over oceans, with the majority contribution coming from the lowest 20 km of atmosphere. The data indicate that realistic equatorial winds pose a significant constraint on thin-ribbon elevator designs if align to face the wind. Combining wind and lightning statistics highlights several promising equatorial regions for anchor sites. Finally, the implications of wind loading for elevator design are examined, and several mitigation strategies are discussed to improve survivability and operational payload capacity under realistic wind conditions.
Read the full abstract

Data Structures and Algorithms

A rooted tree framework for linear time ultrabubble detection

Pangenomics uses graphs to show genetic differences within or between species. In these graphs, a path can represent one genome, while regions with different paths show genetic variation. Biedged graphs use black edges for sequences and grey edges for links between them. Snarls are minimal subgraphs of a biedged graph that are separated from the rest of the graph by removing two black edges. Ultrabubbles are minimal acyclic and tip-free snarls and thus are important variant structures because they have finite paths and lack dead ends. In our previous work, we showed that in linear time every bidirected graph can be transformed to a rooted biedged bipartite one, and that in these graphs, ultrabubbles can be enumerated with a lowest common ancestor (LCA)-based method in $O(Kn)$ time, where $n$ and $K$ are the number of nodes and given snarls, respectively, of the graph. Here, we present a series of practical and theoretical improvements to our previous LCA-based approach. First, we present a hybrid method that selects between the LCA-based method and the naive approach for evaluating a snarl, depending on the size of the snarl in relation to the number of tips and cycle-closing nodes in the graph. Second, by using the theoretical framework from our previous paper, we show that all ultrabubbles can be found in $O(n + m + K)$ time, where $m$ is the number of edges, by traversing the breadth-first search (BFS) tree of the biedged bipartite graph. Third, we show that any two snarls that are candidate ultrabubbles and share a frontier node cannot be ultrabubbles; the resulting set of snarls is compatible, bound by $n$, and defines exclusive families of nested snarls. We combine these three results into six methods and present benchmarking results that illustrate how the above improvements affect practical run-times for identifying ultrabubbles.
Read the full abstract

Dynamical Systems

Renormalization and rigidity of analytic non-linear interval exchange transformations

We construct hyperbolic renormalization horseshoes for analytic generalized interval exchange transformations (GIETs) of bounded type and with bounded geometry, provided their boundaries are small (but not necessarily zero). As a consequence, we describe the manifold structure of smooth conjugacy classes of GIETs.
Read the full abstract

Artificial Intelligence

Self-Orchestrating Language Models: Leveraging Semantic Dependence for Efficient Inference

Large language models (LLMs) demonstrate impressive capabilities, but their deployment presents significant efficiency challenges. Autoregressive decoding imposes substantial inference latency and under-utilizes hardware accelerators in low batch size regimes. Discrete diffusion models can generate in parallel but struggle to match autoregressive quality without many diffusion denoising steps. Long-context reasoning creates memory bottlenecks that strain even state-of-the-art accelerators. My thesis is that language models can direct their own inference execution strategy by annotating semantic dependence – which tokens depend on which others – in their generation. I call such models self-orchestrating language models. For each system, I design a runtime that acts on these annotations to parallelize autoregressive decoding, evict intermediate context, or derive denoising orders, achieving Pareto-optimal quality-efficiency trade-offs. I demonstrate this approach through three self-orchestrating systems. First, PASTA uses semantic dependence to parallelize autoregressive decoding, training the model to annotate which output chunks can generate independently. Second, TIP uses semantic dependence to evict intermediate reasoning steps from the KV cache, reducing memory consumption while preserving accuracy. Third, Planned Diffusion uses semantic dependence to derive a denoising order for discrete diffusion, autoregressively generating a plan that specifies which chunks to denoise in parallel.
Read the full abstract

Computers and Society

LLMs as Oracles: Reliance on LLMs for Subjective Personal Questions

We characterize how people are turning to LLMs as oracles: all-knowing authorities on subjective personal questions. Motivated by risks to users' autonomy and well-being, we develop a typology and LLM-based methods to measure this form of AI reliance at scale and understand how people are offloading judgment and decision-making to AI. Applying our typology to public usage data (68K prompts from WildChat and ThoughtTrace), we find that LLM-as-oracle use has increased over time (2023-2026) and is more prevalent among younger users. We further build a privacy-preserving data donation tool to analyze individuals' longitudinal usage data (140K prompts from 52 participants), identifying similar trends. People are often unaware of their own LLM-as-oracle use, and express dissatisfaction with this behavior after seeing our tool's analysis. Finally, we identify two drivers of LLM-as-oracle use: people's perceptions of AI and the behavior of AI models themselves, which motivate possible interventions to support users' self-deliberation.
Read the full abstract

All authors Myra Cheng, Lujain Ibrahim, Grace Liu, Michelle S. Lam, Vishakh Padmakumar, Nick Madibekov, Diyi Yang, Dan Jurafsky

Dynamical Systems

Hyperbolicity of renormalization for maps with multiple breaks

We construct hyperbolic horseshoes for piecewise-analytic homeomorphisms of the circle with multiple break-type singularities, under the assumptions of bounded type rotation numbers and bounded geometry – provided the sizes of the breaks are uniformly small. As a consequence, we obtain a $C^{1+\alpha}$-rigidity result for such maps and prove that rigidity classes are analytic submanifolds.
Read the full abstract

Probability

Diffusion processes with $b\in L_{(p,q),\text{loc}}$

We present some conditions in case $b\in L_{(p,q),\text{loc}}$ sufficient to guarantee the existence of a strong Markov diffusion process with drift $b$ and uniformly nondegenerate bounded matrix-valued diffusion. An example is given to illustrate how close these conditions are to be necessary.
Read the full abstract