arXiv subjects

Jin Zhu

Publications and source records attributed to Jin Zhu.

At least 19 recordsLinked to original sources

arXiv2026

Hydrated porous substrates modulate the spatiotemporal dynamics of bacterial turbulence

Boundary conditions strongly influence bacterial turbulence, motivating the question of how hydrated porous substrates affect near-interface collective motion. We characterize the spatiotemporal dynamics of dilute and dense Escherichia coli suspensions above agar substrates of varying concentrations, with glass serving as a nonporous reference. In dense suspensions shortly after loading, collective in-plane kinetic energy varies nonmonotonically with agar concentration, while individual swimming energy and characteristic spatial scales show comparatively little variation. Over five minutes above agar, the collective flow attenuates strongly, accompanied by shorter spatial correlations, longer temporal correlations, and a greater relative spectral weight at higher wavenumbers. To explore how the porous boundary may contribute to these changes, we extend mean-field kinetic theory (MFKT) to incorporate normal seepage and tangential slip at the interface. Linear stability analysis distinguishes near-interface collective modes from those in the bulk and identifies how fluid-layer thickness and permeability-dependent slip length modify the instability cutoff. The predicted reduction in the associated length scale provides a qualitative interpretation of the smaller flow structures observed over time and at higher agar concentrations. These findings reveal distinct substrate-dependent changes in the intensity, persistence, and spatial organization of near-interface bacterial turbulence.

cond-mat.soft↗

arXiv2026

Amortized Nonlinear Variable Selection with Prior-Data Fitted Networks

Variable selection is an important task for interpreting potentially complex systems in fields such as biology, business, and sociology. The importance of variable selection has attracted considerable attention in statistics and machine learning. In this paper, we are mainly interested in model-agnostic variable selection for identifying variables that have general nonlinear dependence on the response. We propose MambaPFN, short for Model-Agnostic Markov BlAnket selection with Prior-data Fitted Networks, which is built upon the Transformer, a building block of many popular large language models. Specifically, we consider a functional-mapping perspective on variable-selection learning, in which the Transformer is treated as a learnable mapping from a dataset to its relevant variables. To learn this mapping, MambaPFN introduces three new components: (i) a faithful, rich, and scalable scheme for generating pretraining data, (ii) an objective that targets each variable's posterior inclusion probability, and (iii) a modified Transformer architecture tailored to variable selection. Once pretrained, MambaPFN is applied to new datasets without parameter updates. Empirically, MambaPFN achieves desirable variable-selection performance in simulation studies and exhibits a scaling law---more pretraining datasets and larger models can continuously improve its performance. Applied to a Facebook comments dataset, MambaPFN selects the fewest variables and achieves the highest computational efficiency and predictive performance, improving upon the best baselines by about 20%.

cs.AI↗

arXiv2026

Equivariant Experience Replay for Continual Learning in Imaging Inverse Problems

In this work, we propose Equivariant Experience Replay, a new paradigm for achieving continual learning of deep networks for solving ill-posed imaging inverse problems. Inspired by recent advances on unsupervised learning methods such as equivariant imaging/splitting, we find the exploitation of group-symmetry structure is particularly relevant and effective in continual learning setting for ill-posed inversion tasks. We therefore propose this new experience replay scheme, which is tailored for such inverse problems. Our numerical study demonstrates the superiority of our method compared to existing continual learning methods for inverse problems in medical imaging and image processing.

eess.IV↗

arXiv2026

EviDial: When Correct Depression Predictions Lack Evidence

Depression dialogue benchmarks commonly assess models by comparing predicted symptom labels with clinical scale scores. However, a prediction may agree with a benchmark label even when the dialogue lacks enough evidence to justify it. We introduce EviDial, a benchmark that distinguishes label agreement from evidence-grounded assessment. EviDial comprises 382 depression dialogues from three sources and 2,744 participant-symptom cells, each classified as having absent, partial, conflicting, or sufficient evidence. Because evidence sufficiency lacks a directly observable gold standard, we derive calibrated evidence references from multiple judgments using generalizability theory, many-facet Rasch measurement, and random-effects latent class analysis. Our audit reveals that 82.8% of participant-symptom cells lack sufficient textual evidence for the corresponding symptom assessment, with substantial variation across sources. Across model families and prompting strategies, 69.2%-96.9% of predictions judged correct by benchmark labels are nonetheless unsupported by sufficient dialogue evidence. Further analyses show that strong agreement among LLM evaluators need not reflect independent evidence judgments, underscoring the need to calibrate automated reference panels. These findings demonstrate that label-based evaluation can overestimate evidence-grounded performance by conflating agreement with clinical labels and support in the observed dialogue. EviDial provides a measurement layer for separating these constructs and auditing LLM-based depression assessment more faithfully.

cs.CL↗

arXiv2026

Active turbulence in shear-thinning fluid

The study of active matter system has critical importance in revealing the physical essence of biological collective behavior. Dense bacterial suspension-a typical biological active matter, exhibits a wide range of phenomenona, among which bacterial turbulence has received extensive interest in recent years. This seemingly chaotic motion is widely studied in Newtonian fluid. However, studies based on complex fluids have predominantly focused on viscoelastic effects, leaving the role of shear-thinning viscosity largely unexplored despite its prevalence in natural bacterial environments like mucus and gastric fluids. Here, we experimentally employed Ficoll and Methocel polymers to study the impacts of various viscosities by Newtonian fluid and shear-thinning effects by non-Newtonian fluids on bacterial turbulence. We analyzed various physical properties, including energy, enstrophy, etc., and observed that the shear-thinning effect is significantly suppressed in high-concentration bacterial suspensions. While the ordered arrangement of polymer chains under shear flow leads to the microscopic anisotropic viscosity, the suppression is largely attributed to the disruption of polymer chains caused by strong interbacterial interactions in dense suspensions. To validate this hypothesis, we conducted experiments at a lower bacterial concentration and verified the findings using theoretical calculations based on the modified resistive force theory.

cond-mat.soft↗

arXiv2026

Inclined surfaces bias bacterial swarming expansion and edge organization

Bacterial swarming is the collective expansion of dense populations of motile cells across hydrated soft surfaces, yet gravity is usually treated as a fixed background condition in standard horizontal assays. We used surface inclination to examine how agar-surface orientation relative to gravity affects the expansion of Enterobacter sp. SM3 swarms. Colony expansion depended non-monotonically on inclination, with the strongest spreading at intermediate inclinations and weaker expansion under shallow or near-inverted conditions. Paired up-facing acute and down-facing obtuse configurations with the same tilt magnitude showed different expansion responses, suggesting that swarm expansion depended on both tilt magnitude and which side of the agar surface faced upward relative to gravity. Inclination also produced downhill-biased colony morphologies. PIV analysis showed generally lower mean activity under inclination than in the flat references, with a non-monotonic angular response and inward increases in speed and spatial velocity-correlation length. The downhill tip showed slower motion, shorter spatial correlations and smaller vortex cores than the upper region. To interpret the macroscopic trends, we extended a two-phase thin-film model by introducing an effective gravity coupling projected normal and tangential to the agar surface. Simulations suggest that the surface-tangential component mainly drives lateral redistribution, whereas the surface-normal component modifies film pressure and thereby pressure-dependent water replenishment, helping distinguish up-facing from down-facing configurations.

cond-mat.soft↗

arXiv2026

FinFIRST: Benchmarking Search Agents for Financial Information Retrieval, Sourcing and Traceability

Financial search is a highly demanding task for LLM agents, requiring not only a correct final answer but also temporally valid information retrieval, authoritative source selection, entity and period alignment, unit and definition consistency, and verifiable evidence for all conclusions. Existing benchmarks predominantly evaluate only the final answer, making it difficult to localize errors or assess whether an answer is well-founded. To address this gap, we introduce FinFIRST (Financial Information Retrieval, Sourcing and Traceability), the first financial benchmark to jointly evaluate answers and supporting evidence through atomic rubrics. FinFIRST comprises 123 expert-authored tasks spanning a graduated difficulty spectrum, constructed from aggregate patterns of real-world financial scenarios through an 18-field taxonomy, a six-axis coverage blueprint, a registry of 138 financial sources, contributions from over 50 finance experts, and a six-stage quality-control pipeline. Each task is accompanied by an evidence-grounded reference package decomposed into atomic criteria across three dimensions: raw-information acquisition, source verification, and computation and answer formation. We evaluate 15 model configurations under a unified tool setting. Claude-Opus-5 achieves the highest atomic score of 87.59%, while GPT-5.6-Sol attains the highest strict pass rate of 71.54%. Computation and answer formation consistently lag behind raw-information acquisition across systems. FinFIRST retains final-answer correctness as the primary objective while making the supporting research process measurable, verifiable, and diagnosable.

cs.CL↗

arXiv2026

The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence

We introduce the MiniMax-M2 series, a family of Mixture-of-Experts language models built around the principle that mini activations can unleash maximum real-world intelligence. The flagship M2 contains 229.9B total parameters with only 9.8B activated per token. Designed end-to-end for agentic deployment, the M2 series rests on three components: (i) agent-driven data pipelines producing large-scale, verifiable trajectories across agentic coding and agentic cowork, each grounded in an executable workspace and an artifact-aligned reward; (ii) Forge, a scalable agent-native RL system that adapts to long-horizon agent trajectories, paired with windowed-FIFO scheduling, prefix-tree merging, inference optimization, and a clean training-inference-agent decoupling that supports both white-box and black-box agents; (iii) the latest M2.7 checkpoint takes an early step toward self-evolution -- autonomously debugging training runs and modifying its own scaffold. Across M2 through M2.7, this combination translates a mini-activation footprint into frontier-tier performance on agentic coding, deep search, office-task, and reasoning benchmarks.

cs.AI↗

arXiv2026

Detecting LLM-Generated Tokens in Human--LLM Coauthored Text

The rise of human-AI collaborative writing has created a growing need for fine-grained detection methods that support localizing likely LLM-generated content in mixed-authorship documents. Existing methods for detecting LLM-generated text mainly focus on document-level classification and cannot identify which parts of the text are generated by LLMs. This paper introduces a new method to address this urgent need. Our method operates at the token level, the natural unit of modern language models, and builds on existing token-level detection scores. The key idea is to smooth adjacent token scores to reduce their variability, while using an adaptive Lepski-type rule to select the bandwidth according to the local authorship structure. Our method is simple to implement and does not require token-level labeled data for training. Theoretically, we characterize this trade-off and show that the proposed method achieves favorable mean square error performance in estimating the underlying signal. Empirically, we demonstrate strong performance of our method against a wide range of baselines in both synthetic datasets and a realistic dataset. We deploy a publicly accessible website that implements the methods as well.

cs.AI↗

arXiv2026

Perturbation is All You Need for Extrapolating Language Models

This paper develops a statistical theory of extrapolation for large language models, by reinterpreting them through pre-post-additive noise models. In contrast to the standard autoregressive next-token prediction based on an exact prefix, we introduce a perturbation-based procedure that first transforms the prefix into a semantic neighbour and then conditions on this perturbed variant for next-token prediction. This yields a hierarchical model with a pre-post-additive noise structure. Within this framework, we develop a rigorous theory of extrapolability, namely, the capacity of a model class to make reliable predictions for token sequences that lie outside the empirical support of the training corpus, by establishing five properties of the proposed procedure: adaptivity, contractivity, robustness, extrapolability, and double robustness. We evaluate the finite sample performance of the proposed procedure using both synthetic and real world language data. Results show that the proposed method consistently improves out-of-support prediction while maintaining competitive in-support performance, demonstrating that perturbation offers a practical route to language modelling.

stat.ML↗

arXiv2026

Segmenting Human-LLM Co-authored Text via Change Point Detection

The rise of large language models (LLMs) has created an urgent need to distinguish between human-written and LLM-generated text to ensure authenticity and societal trust. Existing detectors typically provide a binary classification for an entire passage; however, this is insufficient for human--LLM co-authored text, where the objective is to localize specific segments authored by humans or LLMs. To bridge this gap, we propose algorithms to segment text into human- and LLM-authored pieces. Our key observation is that such a segmentation task is conceptually similar to classical change point detection in time-series analysis. Leveraging this analogy, we adapt change point detection to LLM-generated text detection, develop a weighted algorithm and a generalized algorithm to accommodate heterogeneous detection score variability, and establish the minimax optimality of our procedure. Empirically, we demonstrate the strong performance of our approach against a wide range of existing baselines. The python implementation of our proposal is available at https://github.com/Mamba413/DetectLLMSegmentation.

cs.CL↗

arXiv2026

MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling

We present MaxProof, a population-level test-time scaling framework for competition-level mathematical proof in the MiniMax-M3 series. M3 first trains three proof-oriented capabilities -- proof generation, proof verification, and critique-conditioned proof repair -- using a defense-in-depth generative verifier engineered for low false-positive rate. These capabilities are merged into a single released M3 model. At test time, MaxProof treats the model as a generator, verifier, refiner, and ranker, searches over a population of candidate proofs, and returns one final proof through tournament selection. With MaxProof test-time scaling, the M3 model reaches 35/42 on IMO 2025 and 36/42 on USAMO 2026, exceeding the human gold-medal threshold on both.

cs.LG↗

arXiv2026

Identification of Genetic Factors Associated with Corpus Callosum Morphology: Conditional Strong Independence Screening for Non-Euclidean Responses

The corpus callosum, the largest white matter structure in the brain, plays a critical role in interhemispheric communication. Variations in its morphology are associated with various neurological and psychological conditions, making it a key focus in neurogenetics. Age is known to influence the structure and morphology of the corpus callosum significantly, complicating the identification of specific genetic factors that contribute to its shape and size. We propose a conditional strong independence screening method to address these challenges for ultrahigh-dimensional predictors and non-Euclidean responses. Our approach incorporates prior knowledge, such as age. It introduces a novel concept of conditional metric dependence, quantifying non-linear conditional dependencies among random objects in metric spaces without relying on predefined models. We apply this framework to identify genetic factors associated with the morphology of the corpus callosum. Simulation results demonstrate the efficacy of this method across various non-Euclidean data types, highlighting its potential to drive genetic discovery in neuroscience.

stat.AP↗

arXiv2026

Population-Scale Advancing Interface Modeling Reveals How Bacterial Swarms Encode Future Spatial Architecture

Motile bacteria shape microbial function by occupying space, yet how collective motion becomes population-scale architecture remains poorly resolved. Bacterial swarming is not merely surface motion, but a process by which motile populations commit to future macroscopic form. Here, in Enterobacter sp. SM3, a gut-associated swarmer linked to mucosal repair, we treat the advancing colony--environment interface as a morphodynamic state through which local motility becomes spatial order. We built SwarmEvo across thermal, hydration, and substrate-mechanical conditions and developed Morpher to resolve and propagate interface states. Counterintuitively, within the permissive assay range, condition labels only weakly separated future trajectories, whereas colony-specific interface geometry constrained later expansion, indicating that swarm fate is written into the interface rather than prescribed by condition identity. Boundary fidelity was decisive: a 0.67 percentage-point segmentation gap expanded into a 2.4--3.1 IoU-point forecasting loss. Preserving front displacement, protrusion continuity, and branch memory, Morpher predicted late-stage expansion with 95.42% mIoU, 10.61 px HD$_{95}$, and 3.93 px ASSD. These results identify the advancing interface as a state-bearing layer through which motility and environmental constraint are converted into future spatial form, enabling disease-relevant microbial organization to be read before endpoint architecture emerges.

cond-mat.soft↗

arXiv2026

READER: Reasoning-Enhanced AI-Generated Text Detection

Recent advances in large language models (LLMs) have made it increasingly difficult to distinguish human-written text from AI-generated content. Many existing detectors train supervised neural classifiers that achieve strong in-distribution performance but are often opaque and can degrade substantially under distribution shift. We present READER, a reasoning-enhanced AI text detector that outputs both a human/AI label and a structured rationale describing the evidence for its decision. A key component of our approach is READ, a curated supervision set of rationales and verdicts. We fine-tune an LLM on READ to build READER, which reasons before detecting at inference time. Despite having only 1.5B parameters, READER consistently outperforms existing detectors as well as prompted, high-capacity LLM baselines (GPT-5.2, Gemini-3-Pro, and DeepSeek-V3.2), which are 100 to 1000 times larger in scale.

cs.CL↗

arXiv2026

Kernelized Advantage Estimation: From Nonparametric Statistics to LLM Reasoning

Recent advances in large language models (LLMs) have increasingly relied on reinforcement learning (RL) to improve their reasoning capabilities. Three types of approaches have been widely adopted: The first relies on a deep neural network to estimate the value function of the learning policy in order to reduce the variance of the policy gradient. However, estimating and maintaining such a value network incurs substantial computational and memory overhead. The second avoids training a value network by approximating the value function using sample averages. However, it samples a large number of reasoning traces per prompt for accurate value function approximation, making it computationally expensive. The third samples only a single reasoning trajectory per prompt, which reduces computational cost but suffers from poor sample efficiency. This paper focuses on a practical, resource-constrained setting in which only a small number of reasoning traces can be sampled per prompt, while low-variance gradient estimation remains essential for high-quality policy learning. To address this challenge, we bring classical nonparametric statistical methods, which are both computationally and statistically efficient, to LLM reasoning. We employ kernel smoothing as a concrete example for value function estimation and the subsequent policy optimization. Numerical and theoretical results demonstrate that our proposal achieves accurate value and gradient estimation, leading to improved policy optimization.

cs.LG↗

arXiv2026

Learning Perturbations to Extrapolate Your LLM

Recent advancements in large language models demonstrate that injecting perturbations can substantially enhance extrapolation performance. However, current approaches often rely on discrete perturbations with fixed designs, which limits their flexibility. In this work, we propose a framework where token prefixes are perturbed by a learnable transformation of a continuous latent vector within an embedding space. To overcome the challenge of an intractable marginal likelihood, we derive unbiased estimating equations for model parameters and optimize them via stochastic gradient descent. We establish the statistical properties of the resulting estimator in over-parameterized regimes. Empirical evaluations on both synthetic and real-world datasets demonstrate that our proposal yields significant gains in out-of-domain settings over a range of state-of-the-art baseline methods.

stat.ML↗

arXiv2026

Sparsity-Constraint Optimization via Splicing Iteration

Sparsity-constrained optimization underlies many problems in signal processing, statistics, and machine learning. State-of-the-art hard-thresholding (HT) algorithms rely on an appropriately selected continuous step-size parameter to ensure convergence. In this paper, we propose a naturally convergent iterative algorithm, SCOPE (Sparsity-Constrained Optimization via sPlicing itEration). The algorithm is capable of optimizing nonlinear differentiable objective functions that are strongly convex and smooth on low-dimensional subspaces. SCOPE replaces the gradient step with a splicing operation guided directly by the objective value, thereby eliminating the need to tune any continuous hyperparameter. Theoretically, it achieves a linear convergence rate and recovers the true support set when the sparsity level is correctly specified. We also establish parallel theoretical results without relying on restricted-isometry-property-type conditions. We apply SCOPE's versatility and power to solve sparse quadratic optimization, learn sparse classifiers, and recover sparse Markov networks for binary variables. With our C++ implementation of SCOPE, numerical experiments on these tasks show that it achieves superior support recovery performance, confirming both its algorithmic efficiency and theoretical guarantees.

stat.ML↗