arXiv subjects

Tengfei Ma

Publications and source records attributed to Tengfei Ma.

At least 19 recordsLinked to original sources

arXiv2026

PRIME W0: Physical Priors from World Models for Embodied Manipulation

Vision-Language-Action (VLA) models excel at instruction following, yet most remain feed-forward: they condition actions only on the current observation and discard both long-horizon temporal context and the hierarchical structure of VLM representations. We present PRIME W0, a hierarchical conditional flow-matching framework that closes this gap through three synergistic designs: (1)per-layer KV injection from a pretrained VLM into an Adaptive MoE action expert; (2)dynamics-aware conditioning via asynchronous world-model subgoal-image prediction and a DINOv2 historical-frame semantic bridge; and (3)Action Dynamic Manifold (ADM) flow matching with covariance-structured noise that respects robot kinematic coupling. PRIME W0 is trained in four stages---VLM pre-training, DAT/NTP visuomotor pre-training, DiT flow-matching decoder assembly with WM injection, and end-to-end SFT---and achieves state-of-the-art results on LIBERO and real-robot benchmarks, with systematic ablations validating each architectural component.

cs.RO↗

arXiv2026

PrimeSim: A Generalist World Model Simulator from Large-Scale Cross-Embodiment Demonstrations

A robot world model that serves as a simulator must do more than generate plausible videos: it must faithfully follow commanded actions, maintain consistency across camera views, and sustain coherent long-horizon rollouts. We present PrimeSim, an action-conditioned, multiview world model simulator that addresses these challenges through progressive midtraining and posttraining. Starting from a pretrained video generator, we midtrain on 30,110 hours of robot demonstrations spanning 22 platforms. To improve action following, we introduce a unified cross-embodiment action representation and frame-aligned dual-path conditioning to strengthen action-frame correspondence. To maintain multiview consistency, we develop view-aware interleaved attention with explicit camera identities, enabling cross-view information exchange while preserving view-specific representations. We further introduce a fast-video, slow-memory posttraining framework that transforms the bidirectional video generator into an efficient autoregressive simulator. By combining fast causal generation, self-rollout training, and hierarchical temporal memory, PrimeSim mitigates error accumulation from self-generated histories and supports coherent long-horizon simulation. PrimeSim runs at 10.1 FPS, remains stable over long-horizon rollouts on rigid and deformable manipulation tasks, and transfers to held-out platforms within 100 to 200 gradient steps where the pretrained backbone does not. Against five open-source action-conditioned world models it leads four of the five WorldSimProbe suites and posts the best overall EWMBench score, while fine-grained local calibration still trails the field; its rollouts are faithful enough to support GRPO-based policy optimization. We release the model weights, inference code, and training code.

cs.RO↗

arXiv2026

ElectroChemLLM: A Multimodal LLM Pipeline for High-Fidelity Electrochemical Informatics

Electrochemistry is central to solving many modern-day challenges, including energy storage systems for a sustainable future, and its advancement relies heavily on the data from past findings. Existing automated pipelines are limited by text-only architectures, context fragmentation, and numerical hallucinations - collectively preventing accurate, large-scale curation of property databases. We introduce ElectrochemLLM, a multimodal information extraction pipeline that jointly identifies structured electrochemical records encompassing electrolyte compositions, electrode materials, cell configurations, and their measured physicochemical properties from unstructured scientific PDFs at scale. By combining hybrid document parsing with vision-capable LLM orchestration, the pipeline extracts verifiable, structured data across text, tables, and figures. Evaluated on the battery-electrolyte subset of our manually annotated benchmark of 232 papers, ElectrochemLLM achieves an F-1 score of 0.97, and has been applied to curate ElectroChemDB, a structured database spanning 15,000 electrochemical research articles. We demonstrate the utility of this resource by training machine learning models for electrolyte property prediction, illustrating a complete pathway from unstructured literature to predictive materials discovery.

cs.CL↗

arXiv2026

Unbounded Helson Forms with a Moment Representation

We study the positive Helson form $h_0[a,b]=\sum_{m,n\ge1}α(mn)a_n\overline{b_m}$ on the finitely supported sequences $c_{00}\subset\ell^2(\mathbb{N})$, where $α(n)=\int_{\mathbb{R}}n^{-s}dμ(s)<\infty$ for a finite positive Borel measure $μ$. Under the Carleman condition $\sum_{k\ge1}α(4^k)^{-1/(2k)}=\infty$, closability of $h_0$ is equivalent to $\sqrt{n}α(n)\to0$, and hence to $μ((-\infty,1/2])=0$. For measures concentrated on $(1/2,\infty)$, we identify the closure of the operator $N_0a=\sum_{n\ge1}a_nn^{-s}$, defined on $c_{00}$, with its maximal realization from $\ell^2(\mathbb{N})$ to $L^2(μ)$. We further prove that the sequences $a\in c_{00}$ satisfying $\sum_{n\ge1}a_n/\sqrt{n}=0$ form an operator core for the positive self-adjoint operator associated with the closure of $h_0$.

math.FA↗

arXiv2026

E$^2$-OPSD: Taming Entropy Overshoot in On-Policy Self-Distillation

On-policy self-distillation (OPSD) provides dense token-level supervision without a second model: one network acts as teacher with the reference solution and as student with only the problem. We identify a specific failure mode of this recipe. During training, student token entropy rises past the teacher's and remains elevated, a pattern we call entropy overshoot. We trace it to both sides of distillation. The reference-conditioned teacher is confident along its answer-directed reasoning path, but this confidence transfers poorly to student-generated prefixes, making its supervision overly tied to answer-specific cues rather than reusable reasoning patterns; meanwhile, the forward KL used by OPSD continually diffuses the student's predictive distribution without pulling it back. We introduce E$^2$-OPSD to address both causes. Exemplar-guided teaching replaces the current answer with a retrieved solved neighboring problem, providing transferable reasoning guidance without revealing the destination and better matching student-reachable states. Entropy-aware distillation uses the student-teacher entropy gap to determine the direction and strength of each token's correction. E$^2$-OPSD improves math reasoning by up to 4.3 points in mean@16 over OPSD, while out-of-domain evaluations show gains over the corresponding base models of up to 4.9 points in mean@16 and 5.5 points in pass@8. Despite these gains, E$^2$-OPSD remains simple, requiring no additional forward passes or networks. Code repo: https://github.com/orionfei/E2-OPSD.

cs.LG↗

arXiv2026

On the Spectra of Multiplicative Hilbert Operator on Bergman Spaces of Dirichlet Series

For $α>1$, we study the weighted multiplicative Hilbert operator \[ (T_αf)(s) = \int_{1/2}^{\infty} f(t)\bigl(ζ(s+t)^α-1\bigr) \left(t-\frac12\right)^{α-1}\,dt \] on the Hilbertian Bergman space $A_{α,0}^2$ of Dirichlet series with zero constant term. In the natural orthonormal basis, $T_α$ is represented by the weighted multiplicative Hilbert matrix \[ \left( \frac{Γ(α)\sqrt{d_α(m)d_α(n)}} {\sqrt{mn}\,(\log(mn))^α} \right)_{m,n\ge2}, \] where $d_α$ is the generalized divisor function defined by $ζ(s)^α=\sum_{n\ge1}d_α(n)n^{-s}$ for $\Re s>1$. Set $Λ_α=Γ(α/2)^2/Γ(α)$. We prove that the essential spectrum of $T_α$ is $[0,Λ_α]$ and that the spectrum in this interval is purely absolutely continuous with multiplicity one. Above $Λ_α$, there are at most finitely many eigenvalues, all of which are simple. Moreover, there is a unique $α_*\in(1,2)$ such that $T_α$ has eigenvalues if and only if $α>α_*$. Consequently, the associated sharp embedding inequality admits a non-zero extremizer precisely when $α>α_*$, and this extremizer is unique up to scalar multiplication. We also establish the asymptotic formula $\|T_α\|\simΓ(α+1)/(2(2\log 2)^α)$ as $α\to\infty$. A key step in the proof combines Mellin-transform asymptotics, strict total positivity, and eigenvalue counting to exclude embedded eigenvalues. The proof includes a general result on the essential and singular continuous spectra of weighted integral Hankel operators.

math.FA↗

arXiv2026

Do LLMs Understand Sequential Structure? A Controlled Study of Inference and Generation

Large language models (LLMs) are increasingly used as interactive agents and simulators, yet it remains unclear whether they can recover latent sequential structure beyond surface action frequencies. This distinction is critical for behavioral simulation, where actions are often shaped by prior context rather than marginal frequencies alone. We study this question using controlled two-player Rock--Paper--Scissors interactions and a one-player stochastic n-gram continuation task. Across these experiments, we test whether LLMs can identify latent strategies, follow simple Markov rules, and sustain higher-order conditional dependencies. Our framework separates distribution matching from conditional rule following. Results show that longer context does not improve identification, correct recognition does not ensure faithful simulation, and higher-order dependencies substantially degrade rule recovery. Apparent behavioral fidelity can therefore mask incorrect generative mechanisms.

cs.AI↗

arXiv2026

HyperGuide: Hyperbolic Guidance for Efficient Multi-Step Reasoning in Large Language Models

Searching over alternative continuations lets large language models (LLMs) compare the downstream consequences of a reasoning step before committing to it, but expanding and evaluating many branches makes inference expensive. Training value models to score intermediate steps does not avoid this cost, as they still rank candidates at inference time. We introduce HyperGuide, a framework that treats reasoning as movement through a tree of states embedded in hyperbolic space. HyperGuide first trains a state encoder on the Poincar'e ball, then trains a guidance head to predict the direction of a minimum-cost transition from the current state. The predicted direction is inserted into the decoder as a virtual token after each reasoning step, so inference follows a single autoregressive trajectory without expanding or reranking candidates. Because the supervision is ordinal rather than binary, it favors continuations that are both reliable and short, which steers generation toward successful, concise solutions. Experiments on competition mathematics and code generation show that HyperGuide matches or exceeds the accuracy of search- and verifier-based baselines while generating substantially fewer tokens than these baselines and about as many as few-shot prompting.

cs.AI↗

arXiv2026

Hesitation Has a Geometry: Entropy-Trained Hyperbolic Probes for Sparse Activation Steering

When a large language model solves a mathematical problem, its reasoning is largely hierarchical, and the solution often branches at a few tokens where the next-token entropy is high. Such tree-like structure embeds in hyperbolic space with far lower distortion than in Euclidean space. Activation steering, however, usually edits the hidden states of a pretrained model by adding one fixed Euclidean vector at every token, even though most tokens of a solution are already determined by the context. We propose Hyperbolic Entropy Steering (HEST), which embeds the hidden states in the Poincaré ball with a lightweight probe whose only label is the model's own next-token entropy. Where this entropy exceeds a threshold, HEST moves the embedded state along the geodesic of steepest descent of a readout of the probe and maps the change back to the hidden state. For the Busemann readout of a learned ideal point, we prove that a step of fixed length lowers it by the same amount at every state. On three instruction-tuned models from the Qwen2.5-Math and Llama-3.1 families, HEST with the Busemann readout improves greedy accuracy on MATH-500 and GSM8K in five of six settings, by up to 1.8 points, whereas a contrastive steering vector added at every token lowers accuracy. With a Euclidean probe trained in the same way, this gain disappears on Qwen2.5-Math-1.5B-Instruct. The gains are largest on problems where the model hesitates often, and accuracy on the remaining problems is almost unchanged.

cs.LG↗

arXiv2026

Bridging the Gap in Ophthalmic AI: MM-Retinal-Reason Dataset and OphthaReason Model toward Dynamic Multimodal Reasoning

Multimodal large language models (MLLMs) have recently demonstrated remarkable reasoning abilities under reinforcement learning (RL) paradigm. However, most existing multimodal medical reasoning models focus on basic reasoning, which refers to shallow inference based on visual feature matching. In contrast, real-world clinical diagnosis extends beyond basic reasoning, demanding complex reasoning that integrates heterogeneous clinical information (such as chief complaints and medical history) with multimodal medical imaging data. To bridge this gap, we introduce MM-Retinal-Reason, an ophthalmic multimodal dataset covering the full spectrum of perception and reasoning. Specifically, it is the first dataset in ophthalmology to encompass both basic and complex reasoning tasks with Chain-of-Thought (CoT) trajectories, aiming to enhance visual-centric reasoning and emulate realistic clinical decision-making. Building upon MM-Retinal-Reason, we propose OphthaReason, the first RL-enhanced ophthalmic multimodal reasoning model with step-by-step reasoning traces. To enable flexible adaptation to both basic and complex reasoning tasks, we further introduce Uncertainty-Aware Dynamic Thinking (UADT), which estimates sample-level uncertainty via entropy and dynamically modulates exploration depth through a shaped advantage mechanism. Comprehensive experiments demonstrate the effectiveness of our model on both basic and complex reasoning tasks, outperforming general-purpose MLLMs, medical MLLMs, RL-based medical MLLMs, and ophthalmic MLLMs by at least 15.47\%. Project Page: \href{https://github.com/lxirich/OphthaReason}{link}.

cs.AI↗

arXiv2026

A Comparative Study of Feature Selection Methods for EHR Diagnosis Codes in Opioid Use Disorder Prediction

Feature selection is a critical step in electronic health record (EHR)-based predictive modeling, where input variables are often high-dimensional, sparse, noisy, and redundant. Large feature sets not only increase computational burden and overfitting risk, but also make model interpretation difficult, leading to limited usefulness in clinical settings. In this study, we focus on diagnosis-related features and compare five feature selection paradigms for opioid use disorder (OUD) prediction: recurrence enrichment, NTK-motivated early gradient sensitivity, LightGBM-SHAP, Elastic Net, and large language model (LLM)-guided semantic selection. We use a unified preprocessing and evaluation framework and assess each method by downstream predictive performance, resampling stability, and representation of infrequent diagnosis codes. Our results demonstrate that performance improves with larger feature budgets with diminishing returns beyond a moderate size. NTK sensitivity provides the best overall balance of accuracy and stability, and LLM-guided selection contributes complementary clinically meaningful signals despite lower standalone performance.

cs.LG↗

arXiv2026

Learning Molecular Representations from Cellular Phenotypes with Structure Preservation

Phenotypic drug discovery enables the discovery of functional relationships between molecular structures and cellular responses. However, existing multimodal representation learning methods often optimize cross-modal alignment without considering the intrinsic organization of chemical space, resulting in distorted molecular representations and loss of structural information. We propose \textbf{PhenMol}, a structure-preserving framework for phenotype-aware molecular representation learning. PhenMol disentangles molecular and cellular representations into shared and private components, enabling phenotype-guided alignment while preserving chemical structures through a dedicated molecular branch. This design integrates cellular phenotype information without disrupting molecular neighborhood organization. Experiments on approximately $3.04 \times 10^{4}$ molecule--cell morphology pairs demonstrate that PhenMol improves molecular property prediction across 270 bioactivity tasks, molecule--phenotype retrieval, and clinical trial outcome prediction. Moreover, ECFP4-based structural analysis shows that PhenMol better preserves molecular neighborhoods and reduces embedding distortion compared with existing multimodal alignment methods. These results highlight the importance of structure-aware constraints in multimodal molecular representation learning and provide an effective approach for integrating cellular phenotypes with chemical knowledge for drug discovery.

cs.LG↗

arXiv2026

HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering

Electronic health record (EHR) question answering is often handled by LLM-based pipelines that are costly to deploy and do not explicitly leverage the hierarchical structure of clinical data. Motivated by evidence that medical ontologies and patient trajectories exhibit hyperbolic geometry, we propose HypEHR, a compact Lorentzian model that embeds codes, visits, and questions in hyperbolic space and answers queries via geometry-consistent cross-attention with type-specific pointer heads. HypEHR is pretrained with next-visit diagnosis prediction and hierarchy-aware regularization to align representations with the ICD ontology. On two MIMIC-IV-based EHR-QA benchmarks, HypEHR approaches LLM-based methods while using far fewer parameters. Our code is publicly available at https://github.com/yuyuliu11037/HypEHR.

cs.AI↗

arXiv2026

Oracle-Budgeted Molecular Optimization with Short-Term Graph Memory

Molecular optimization is commonly performed under a limited oracle budget, which makes deciding what to evaluate as important as deciding what to generate. We introduce short-term graph memory, a plug-in module that preserves the generator architecture and native update rule while learning from previously evaluated molecules to prioritize subsequent oracle queries. The module maintains an online graph neural surrogate that pre-screens each round's candidate pool, so the fixed oracle budget is spent on molecules with higher predicted utility. Applied to a fragment-based generator on a standard molecular optimization benchmark, it improves the mean top-10 score at no extra oracle cost and never falls behind the base on any oracle; the gain extends to all four generators we tested at a tight budget of one thousand calls. We then analyze how surrogate-guided selection interacts with the exploration and exploitation behavior of different generators. Its benefit at larger budgets is consistent with two properties of the backbone: how broadly it searches, and how effectively its native search already exploits oracle feedback. We provide a simple way to spend a fixed oracle budget more selectively, and evidence on which generators benefit from it.

cs.LG↗

arXiv2026

SC-JEPA: Stabilizing Latent Predictive Learning for Time-Series Anomaly Prediction

Time-series anomaly prediction aims to forecast future system failures before they fully emerge, making latent predictive models such as JEPA a promising framework for capturing precursor dynamics. However, directly applying continuous self-distillation to time-series data is often unstable and can lead to representation collapse, while also struggling to model precursors evolving at different temporal scales. To address this, we propose \textbf{SC-JEPA}, a new JEPA-based framework to model time-series anomaly prediction in a discretized predictive state space. It introduces a soft codebook bottleneck to stabilize latent predictive learning and encourage regime-level structure in the learned representations. Building on this stabilized latent space, we further design a multi-resolution predictive objective to capture precursor patterns at different temporal scales. Experiments on five real-world benchmarks show that SC-JEPA achieves strong and consistent early-warning performance.

cs.LG↗

arXiv2026

CAAD: Causality-Aware Multivariate Time Series Anomaly Detection via Multi-Scale Alignment and Structural Causal Consistency

The operational integrity of complex industrial systems relies on precise anomaly detection and diagnosis. The vast majority of existing methods narrowly focus on capturing temporal similarities of representations, often overlooking the disruption of internal causal relationships, which characterizes system failures and latent anomalies. In this paper, we propose a novel framework (CAAD) that reframes anomaly detection as the continuous verification of Granger causality consistency through exogenous variables. Specifically, the CAAD framework models exogenous time-series variables as residuals, identifying anomalies as significant deviations caused by external interventions. The proposed framework leverages multi-scale alignment to internalize system dynamics and utilizes a gradient-based matrix to monitor internal causal relationship breakdowns. By quantifying causal deviations of both dynamic evolution and relational topology, the CAAD is able to capture subtle causal shifts to achieve precise anomaly detection. Extensive experiments on real-world industrial datasets demonstrate that the CAAD achieves high-precision anomaly detection, outperforming most state-of-the-art baselines.

cs.LG↗

arXiv2026

Nuclear Toeplitz operators between Fock spaces

We characterize the nuclearity of Toeplitz operators $T_μ: F_α^p \to F_α^q$ with Borel measure symbols for $1\leq p,q\leq \infty$. For positive measures $μ$ and $q\leq p$, we provide necessary and sufficient conditions in terms of the Berezin transform and establish a rigidity property for nuclearity across this range. In the case $p<q$, we obtain separate necessary and sufficient conditions, indicating that the Berezin transform alone is insufficient for a complete characterization. Our results extend to Fock spaces on $\mathbb{C}^n$.

math.FA↗

arXiv2026

Propagating Structural Guidance: Synthesizing Fluorescein Angiography from Fundus Images and Sparse OCT Scans

Fundus fluorescein angiography (FFA) is critical for assessing retinal vascular abnormalities, but its acquisition is invasive and not always feasible. In contrast, color fundus photography (CFP) is non-invasive and widely accessible, which has motivated studies on CFP-to-FFA synthesis. However, prior works rely solely on CFP surface texture, fundamentally limiting the ability to reconstruct functional vascular information and subtle pathological changes. To address this, we propose a novel framework that synthesizes FFA from CFP with structural guidance provided by optical coherence tomography (OCT). We construct a multi-modal retinal imaging dataset with paired CFP, FFA, and OCT from 3,676 patient eyes--the first tri-modally aligned dataset in retinal imaging. To bridge the spatial gap between OCT and fundus modalities, we propose a Spatially Aligned Cross-Modal Fusion (SACMF) module that projects depth-resolved OCT features onto the fundus plane and injects them into the CFP encoder via adaptive layer normalization. Beyond feature fusion, we further introduce Token-wise Cross-Modality Alignment (TCMA), a token-level contrastive learning strategy that explicitly aligns CFP and FFA representations at corresponding spatial positions. Our method achieves superior synthesis performance compared to state-of-the-art methods. Moreover, extensive experiments demonstrate that the FFA images synthesized by our approach bring greater improvements in downstream disease diagnosis performance than existing methods, highlighting the clinical potential of our approach as a non-invasive decision-support tool in routine workflows. The code is available at https://github.com/while-plus/OCT-guide-FFA-Syn.

cs.CV↗