arXiv subjects

Tianqi Zhao

Publications and source records attributed to Tianqi Zhao.

At least 19 recordsLinked to original sources

arXiv2026

A Hybrid SMT-NRA Solver: Integrating 2D Cell-Jump-Based Local Search, MCSAT and OpenCAD

In this paper, we propose a hybrid framework for Satisfiability Modulo the Theory of Nonlinear Real Arithmetic (SMT-NRA for short). First, we introduce a two-dimensional cell-jump move, called \emph{2D-cell-jump}, generalizing the key operation, cell-jump, of the local search method for SMT-NRA. In contrast to the existing cell-jump, which updates assignments exclusively along a given line, the 2D-cell-jump enables search over an arbitrarily selected plane. Then, we propose an extended local search framework, named \emph{2D-LS} (following the existing local search framework, LS, for SMT-NRA). Finally, we present a hybrid framework for SMT-NRA integrating 2D-LS, MCSAT and OpenCAD, to improve search efficiency through information exchange. The experimental results demonstrate improvements in local search performance, highlighting the effectiveness of the proposed methods.

cs.AI↗

arXiv2026

TabClustPFN: A Prior-data Fitted Network for Tabular Data Clustering

Prior-data Fitted Networks (PFNs) have reframed supervised tabular learning as single-pass in-context inference without per-dataset optimization. Extending this paradigm to clustering is appealing yet fundamentally more challenging, due to absent supervision, unknown cluster cardinality, and label switching inherent to partition outputs. Existing PFN-based clustering methods address these challenges only partially, either requiring known cardinality as input or relying on unstable label-ordering conventions and overly restrictive synthetic priors. We introduce TabClustPFN, a clustering PFN that resolves all challenges jointly through co-designed prior, objective, and architecture. Our hybrid pretraining prior captures heterogeneous real-tabular geometry; our decoupled partition inference network--cardinality inference network architecture jointly infers cluster assignments and cardinality in a single pass; and our SoftARI training objective is permutation-invariant by construction, eliminating the need for any label-ordering convention. On a 44 curated real-world tabular benchmark, TabClustPFN achieves state-of-the-art clustering performance against classical, deep, and amortized baselines, with runtime comparable to efficient baselines. Code is available at https://github.com/Tianqi-Zhao/TabClustPFN.

cs.LG↗

arXiv2026

A New Bayesian Framework with Mass-Radius-Space Priors to Constrain the Neutron Star Equation of State

We propose a new Bayesian framework to infer the neutron star equation of state (EOS) from mass and radius observations and neutron matter theory by defining priors that directly parameterize mass-radius space instead of pressure-energy density space. We use direct and accurate inversion approximations to map mass-radius relations to the underlying EOS. We systematically compare its EOS inferences with those inferred from traditional EOS parameterizations, taking care to quantify the systematic prior uncertainties of both. Our results show that prior uncertainties should be included in all Bayesian approaches. The alternative framework provides broader and more uniform coverage of the physically allowed mass-radius space, especially small radius configurations, with enhanced computational efficiency. Substantially reduced dependence on prior choices seems to result from having both prior and posterior distributions in the same observational mass-radius space. Results indicate that direct parameterization in observed space offers a robust and efficient alternative to traditional methods.

astro-ph.HE↗

arXiv2026

PaceReasoner: Label-Free Learning to Answer Briefly from Long Reasoning

Extended chain-of-thought reasoning improves problem-solving performance but increases inference cost and latency, motivating more accurate answers with shorter reasoning. We introduce PaceReasoner, a label-free test-time reinforcement learning framework that uses a model's LONG responses to improve its SHORT-mode accuracy. Both modes share a trainable policy, creating a need for reliable supervision, sufficient SHORT training samples, and continued LONG responses to guide learning. PaceReasoner combines all-response and LONG-only answer consensus through progressive, confidence-weighted supervision. A behavior reward gradually shifts from encouraging SHORT exploration to rewarding agreement with LONG answers, while a ratio controller regulates the balance between modes. Across three model backbones and four benchmarks, PaceReasoner improves average SHORT accuracy over the baselines by 7.4--13.5 percentage points, with fewer than 25 reasoning tokens per response on average. Ablations support the key components, and cross-dataset results demonstrate transfer beyond the adaptation set.

cs.AI↗

arXiv2026

TabReliBench: Evaluating Tabular Foundation Models Beyond Predictive Accuracy

Tabular foundation models (TFMs) are increasingly popular for their strong predictive performance. Many also provide posterior predictive distributions (PPDs), whose reliability remains less studied. We assess reliability through point prediction, distributional quality, marginal and subgroup calibration, and interval efficiency. We then introduce TabReliBench, a large classification and regression benchmark for these comparisons and dataset-level analyses. We find that TFMs' rankings change between TabArena and our benchmark and across reliability metrics. Regression TFMs usually achieve near-nominal marginal coverage and retain narrow intervals, but this favorable marginal behavior does not imply valid conditional coverage. Dataset-level analyses show that classification difficulty often accompanies poor calibration, whereas regression predictive performance is not a reliable indicator of calibration. Ensembling improves predictive performance but does not consistently improve calibration of PPDs; TFMs also benefit little from conformal post-processing, which does not reliably resolve subgroup gaps. Reliable TFM selection therefore requires multidimensional evaluation beyond aggregate rankings. Code is available at https://github.com/Tianqi-Zhao/TabReliBench.

cs.LG↗

arXiv2026

Architecture Alignment With Sparse Priors in Tabular Foundation Models

Tabular foundation models (TFMs) are increasingly popular because they deliver strong predictions on new datasets through in-context learning, without task-specific training or extensive tuning. Yet released TFMs differ simultaneously in their pretraining priors, architectures, and objectives, obscuring their respective inductive biases. We therefore examine one concrete capability: irrelevant-feature suppression. Across synthetic tasks and real-world datasets, adding null features causes substantially greater predictive degradation in the row-token model TabDPT, whereas the cell-token alternating-axis model TabPFN v2 and other TFMs remain comparatively stable. This gap motivates us to ask whether architecture contributes to irrelevant-feature suppression. Because released TFMs remain confounded by other design choices, we train streamlined row-token and alternating-axis transformers under identical sparse-to-dense linear priors. Exact Bayes analysis shows that sparse prediction requires context-dependent feature gating, whereas the dense endpoint requires only uniform feature weighting. Consistent with this distinction, the alternating-axis model is substantially closer to the Bayesian optimal predictor on sparse tasks, while the architecture gap becomes negligible on dense tasks; almost all of the sparse gap arises from linear coefficient-estimation error. Finally, in both the controlled model and frozen TabPFN v2, we examine the effect of interventions on the feature-attention outputs on the linear coefficients, finding evidence of task-dependent selective routing of computation through feature-indexed pathways. Together, these results support architecture-prior alignment: preserving an addressable feature axis provides an inductive bias for task-adaptive relevance inference. Code is available at https://github.com/Tianqi-Zhao/ArchitecturePriorTFMs.

cs.LG↗

arXiv2026

A Very Big Video Reasoning Suite

Rapid progress in video models has largely focused on visual quality, leaving their reasoning capabilities underexplored. Video reasoning grounds intelligence in spatiotemporally consistent visual environments that go beyond what text can naturally capture, enabling intuitive reasoning over spatiotemporal structure such as continuity, interaction, and causality. However, systematically studying video reasoning and its scaling behavior is hindered by the lack of large-scale training data. To address this gap, we introduce the Very Big Video Reasoning (VBVR) Dataset, an unprecedentedly large-scale resource spanning 200 curated reasoning tasks following a principled taxonomy and over one million video clips, approximately three orders of magnitude larger than existing datasets. We further present VBVR-Bench, a verifiable evaluation framework that moves beyond model-based judging by incorporating rule-based, human-aligned scorers, enabling reproducible and interpretable diagnosis of video reasoning capabilities. Leveraging the VBVR suite, we conduct one of the first large-scale scaling studies of video reasoning and observe early signs of emergent generalization to unseen reasoning tasks. Together, VBVR lays a foundation for the next stage of research in generalizable video reasoning. The data, benchmark toolkit, and models are publicly available at https://video-reason.com/?v=vbvr .

cs.CV↗

arXiv2026

A Partially Supervised Latent-Space Variational Autoencoder for Generating Neutron Star Equations of State

We develop a partially supervised latent-space variational autoencoder (PSL-VAE) framework to reconstruct and generate neutron star (NS) equations of state (EOS). The PSL-VAE consists of an encoder network that maps high-dimensional EOS data into a lower-dimensional latent space and a decoder network that reconstructs the full EOS from the latent representation. The latent space includes supervised NS observables derived from the training EOS data, as well as variational latent variables that capture additional EOS features learned automatically. Using a PSL-VAE trained on a Skyrme EOS dataset, we find that a latent space consisting of two supervised observables, the maximum mass $M_{\max}$ and the canonical radius $R_{1.4}$, together with a single variational latent variable associated mainly with the EOS near the crust-core transition, is sufficient to reconstruct Skyrme EOSs with high fidelity. The decoder reconstructed EOSs reproduce $M_{\max}$ and $R_{1.4}$ with mean absolute percentage errors within $0.08\%$. Sampling the latent space generates new EOSs that are causal, thermodynamically stable, and consistent with imposed constraints on the supervised observables. The framework therefore provides a compact and physically interpretable parameterization of the NS EOS that is well suited for Bayesian inference with multimessenger observations, including pulsar mass-radius measurements and gravitational wave data.

astro-ph.IM↗

arXiv2026

Observable Signatures of a Quarkyonic Phase in Neutron Stars

Quarkyonic matter in $β$-equilibrium is a potential description of cold dense matter in neutron stars (NSs), that introduces non-interacting quarks alongside nucleons and leptons in NS cores. In this paper, we impose observational and theoretical constraints on the model to perform Bayesian inference on it, and find that it is possible to have quarkyonic matter equations of state that satisfy all current astrophysical observations, thereby reinforcing the argument for its use alongside traditional ones. To differentiate between NSs where a quarkyonic phase does and does not appear in the core, we identify some novel signatures based on the mass-radius relation. Focusing on canonical ($1.4\ \mathrm{M_\odot}$) NSs, we find the populations of NSs with and without quarkyonic cores show separability on the basis of the slope and curvatures of the mass-radius curve, the central sound speed of the star, and the radius difference between two NSs of $2\ \mathrm{M_\odot}$ and $1.4\ \mathrm{M_\odot}$. Our results indicate that observing a neutron star with these signatures matching the values for quarkyonic core NSs would provide a strong evidence for the existence of a quarkyonic phase or a similar crossover transition in its core.

nucl-th↗

arXiv2026

Detecting Nonproperness of Likelihood Equations

Given an algebraic statistical model, a challenging problem is classifying the data according to the number of positive critical points of the likelihood function. The positive critical points are the positive solutions to an algebraic system, say likelihood equations. So, identifying the number of positive critical points is a real root classification problem for the likelihood equations. A discriminant variety of a likelihood-equation system geometrically describes the data for which the number of real solutions becomes unusual. As an essential component of the discriminant variety, the nonproperness set collects the data such that the likelihood-equation system has a solution at infinity. So, the number of real solutions varies when the data passes the nonproperness set, and identifying the nonproperness set plays a crucial role in the real root classification. In this work, we develop a novel method for computing nonproperness sets of likelihood-equation systems. We prove the correctness of this method. We show experimentally that it is far more efficient than the known methods in the literature.

stat.ML↗

arXiv2026

VeriSkill: A Self-Evolution Framework for Program Verification Skills

Automating program verification with LLM agents requires generating specifications, annotations, auxiliary lemmas, and tool invocations, all of which depend on reusable skills. A natural remedy is skill self-evolution: distilling skills from trajectories and refining them through feedback. However, existing evolution methods struggle with program verification tasks because they cannot reliably identify skill-specific failures or extract actionable signals from opaque verifier feedback. In this paper, we propose VeriSkill, a self-evolution framework built for program verification. It attributes verification failures to skill deficiencies, distills diagnostic signatures into reusable lessons, and iteratively refines candidate skills, admitting only revisions that improve verification performance while preserving program semantics. Experiments show that VeriSkill consistently outperforms all baselines across multiple verification tools, agent frameworks, and LLM backends.

cs.AI↗

arXiv2026

Differentiable OPLS Force Field Parameterization for Ionic Electrolytes and High-Throughput Application to Lithium-ion Batteries

The rational design of ionic electrolytes for lithium-ion batteries (LIBs) is severely constrained by the vast solvent-salt combinatorial space and low efficiency of empirical trial-and-error. While molecular dynamics (MD) bridges microscopic solvation structures and macroscopic physicochemical properties, classical force fields often lack sufficient accuracy for multicomponent systems. To address these challenges, we develop an automated differentiable OPLS-AA force field parameterization workflow tailored for general ionic electrolytes. It employs topology-guided atom typification to reduce parameter redundancy and optimizes Lennard-Jones parameters via the DMFF framework, with experimental density as the fitting target and ionic conductivity as an independent validation metric. Rigorous convergence tests yield a standardized simulation protocol with $\sim$100,000-atom systems and 35-40 ns NVT runs to ensure reliable transport property quantification. High-throughput MD simulations of over 10,000 formulations spanning 67 solvents and 15 lithium salts are conducted on the Tianqiong platform, generating a comprehensive dataset covering five core properties: density, dielectric constant, viscosity, diffusion coefficient, and ionic conductivity. t-SNE visualization reveals partial clustering of distinct salt chemistries, continuous property gradients with concentration and temperature, and internal physical self-consistency, with solvent composition identified as another key performance regulator. Together, the accurate transferable force field and large-scale dataset provide a solid foundation for data-driven rational design of ionic electrolytes.

physics.chem-ph↗

arXiv2026

Skills Are Not Islands: Measuring Dependency and Risk in Agent Skill Supply Chains

Agent skills package reusable operational knowledge for Large Language Model (LLM) agents, yet as they grow in scope, they become dependency-bearing artifacts whose identities, versions, and provenance remain implicit. This opacity already causes duplicated dependencies and inconsistent installations, exposing a gap that dependency management has yet to close. We introduce Agent Skill Supply Chains (ASSCs) to characterize mixed skill-package-service dependency graphs and help close this gap. Borrowing from Software Bill of Materials (SBOMs), we design SkillDepAnalyzer to capture natural-language dependency evidence and model skills as dependency-bearing artifacts. On the SKILL-DEP benchmark, SkillDepAnalyzer recovers skill metadata and dependency graphs accurately and comprehensively, substantially outperforming an LLM-based baseline and package-centric SBOM tools. Applying SkillDepAnalyzer to over 1.43 million skills, we obtain ASSCs and explore their structural diversity and security signals. We find four structural patterns: skill metadata is activation-ready but governance-poor; dependency graphs span skill, package, and service dependencies with concentrated reuse; recursive skill reuse expands dependency graphs and creates hidden package inventory; and skill dependency clusters form around related workflows. We also find that inspecting a skill alone misses security-relevant signals hiding in its dependencies. By analyzing ASSCs, we identify and report known malicious skills persisting in ASSCs to their developers. Based on these findings, we recommend typed dependency manifests, first-class dependency-cluster management, risk-warning audit commands for skill infrastructure maintainers, and lockfile-like records for skill developers.

cs.SE↗

arXiv2026

TFZ-Tree: An Ultra-Lightweight Waveform Classification Framework for Resource-Constrained Devices

Under the trend of multi-waveform coexistence in 6G IoT, intelligent receivers must first identify physical-layer waveform types before performing correct demodulation and resource scheduling. However, existing signal identification research largely focuses on symbol-level modulation classification. Research directly targeting physical-layer waveform types (e.g., OFDM, OTFS, LoRa) is not only extremely scarce but also heavily reliant on deep neural networks and complex time-frequency transforms, making deployment on resource-constrained terminals difficult. Symbol modulation classification methods themselves cannot circumvent the prerequisite of ``waveform identification first.'' To address this dual gap, we propose an ultra-lightweight waveform classification framework based on time-frequency multidimensional features with a cooperative Z-test tree (ZTree). The framework employs low-complexity time-domain feature extraction, and the classification backend adopts a ZTree optimized by Z-statistical testing, which uses hypothesis testing confidence to automatically control decision tree splitting and size, ensuring efficient execution on resource-limited processors. Tested on ten 6G candidate waveforms including OFDM, OTFS, DSSS, LoRa, and NB-IoT, the method achieves 99.5\% average accuracy under AWGN and 87.4\% under TDL-C multipath channels, with main confusion between OTFS and LoRa. Implemented in C on an x86 platform, single inference latency is under 4~ms. To the best of our knowledge, this is the first work achieving real-time recognition of ten IoT waveform types. Future work will target deployment acceleration on embedded MCUs. Code and dataset are open-sourced at: https://github.com/Einstein-sworder/IoT-wave.

eess.SP↗

arXiv2026

Multi-Swing Transient Stability of Synchronous Generators and IBR Combined Generation Systems

In traditional views, the build-up of accelerating energy during faults can cause the well-known first-swing angle instability in synchronous generators (SGs). Interestingly, this letter presents a new insight that the accumulation of decelerating energy due to the low voltage ride-through (LVRT) and recovery control of grid-following inverter-based resources (GFL-IBRs), might also result in transient angle instability in SGs. The transient energy accumulated during angle-decreasing swing transforms into the acceleration energy of the subsequent swing, hence such phenomena often manifest as multi-swing instability. Both theoretical analysis and simulation support these findings.

eess.SY↗

arXiv2026

Code Clone Detection via an AlphaFold-Inspired Framework

Code clone detection plays a critical role in software maintenance and vulnerability analysis. Substantial methods have been proposed to detect code clones. However, they struggle to extract high-level program semantics directly from a single linear token sequence, leading to unsatisfactory detection performance. A similar single-sequence challenge has been successfully addressed in protein structure prediction by AlphaFold. Motivated by the successful resolution of the shared single-sequence challenge by AlphaFold, as well as the sequential similarities between proteins and code, we leverage AlphaFold for code clone detection. In particular, we propose AlphaCC, which represents code fragments as token sequences and adapts AlphaFold's sequence-to-structure modeling capability to infer code semantics. The pipeline of AlphaCC goes through three steps. First, AlphaCC transforms each input code fragment into a token sequence and, motivated by AlphaFold's use of multiple sequence alignment (MSA), novelly uses a retrieval-augmentation strategy to construct an MSA from lexically similar token sequences. Second, AlphaCC adopts a modified attention-based encoder based on AlphaFold to model dependencies within and across token sequences. Finally, unlike AlphaFold's protein structure prediction task, AlphaCC computes similarity scores between token sequences through a late interaction strategy and performs binary classification to determine code clone pairs. Comprehensive evaluations on three datasets, particularly two semantic clone detection datasets, show that AlphaCC consistently outperforms all baselines, demonstrating strong semantic understanding. AlphaCC further achieves strong performance on instances where tool-dependent methods fail, highlighting its tool-independence. Moreover, AlphaCC maintains competitive efficiency, enabling practical usage in large-scale clone detection tasks.

cs.SE↗

arXiv2026

Data-Driven Generation of Neutron Star Equations of State Using Variational Autoencoders

We develop a machine learning model based on a structured variational autoencoder (VAE) framework to reconstruct and generate neutron star (NS) equations of state (EOS). The VAE consists of an encoder network that maps high-dimensional EOS data into a lower-dimensional latent space and a decoder network that reconstructs the full EOS from the latent representation. The latent space includes supervised NS observables derived from the training EOS data, as well as latent random variables corresponding to additional unspecified EOS features learned automatically. Sampling the latent space enables the generation of new, causal, and stable EOS models that satisfy astronomical constraints on the supervised NS observables, while allowing Bayesian inference of the EOS incorporating additional multimessenger data, including gravitational waves from LIGO/Virgo and mass and radius measurements of pulsars. Based on a VAE trained on a Skyrme EOS dataset, we find that a latent space with two supervised NS observables, the maximum mass $(M_{\max})$ and the canonical radius $(R_{1.4})$, together with one latent random variable controlling the EOS near the crust--core transition, can already reconstruct Skyrme EOSs with high fidelity, achieving mean absolute percentage errors of approximately $(0.15\%)$ for $(M_{\max})$ and $(R_{1.4})$ derived from the decoder-reconstructed EOS.

astro-ph.HE↗

arXiv2025

Framework for phase transitions between the Maxwell and Gibbs constructions at finite temperature

The characteristics of the hadron-to-quark first-order phase transition differ depending on whether charge neutrality is locally or globally fulfilled. In $β$-equilibrated matter, these two possibilities correspond to the Maxwell and Gibbs constructions. Recently, we presented a new framework in which a continuously-varying parameter allows one to describe a first-order phase transition in intermediate scenarios to the two extremes of fully local and fully global charge neutrality. In this work, we extend the previous framework to finite temperatures and out-of-$β$ equilibrium conditions, making it available for simulations of core-collapse supernovae and binary neutron star mergers. We investigate its impact on key thermodynamic quantities across a range of baryon densities, temperatures, and electron fractions. We find that when matter is not in $β$-equilibrium, the pressure in the mixed phase is not constant even for the case of fully-local charge neutrality. Moreover, we compute the thermal index using three different approaches, demonstrating that the finite-temperature extension of an equation of state using a constant thermal index can be ill-defined when applied to the mixed phase.

nucl-th↗