arXiv subjects

Jiahao Liu

Publications and source records attributed to Jiahao Liu.

At least 37 records · Page 2Linked to original sources

arXiv2026

Mechanistic Interpretability of Structure-Aware Numerical Reasoning in LLaMA 3.1 8B

Recent work has shown that large language models (LLMs) exhibit strong numerical sequence modeling capabilities and show promise in time-series prediction. While LLMs display in-context learning capabilities, the mechanisms with which they accomplish time-series prediction remain unclear. Specifically, whether they truly understand the underlying structure, which at a minimum requires reasoning over first differences in the sequence of numbers. To study this, we investigate Llama 3.1-8B from a mechanistic interpretability point of view. Mechanistic interpretability is an emerging field concerned with the reverse engineering of the algorithms learned by neural networks such as LLMs. To assess Llamas' numerical sequence modeling capabilities and to facilitate our mechanistic interpretability analysis, we create a sequence modeling task that cannot be solved without picking up structural cues. Specifically, we sample n random numbers and repeat them with an offset. We find that Llama displays strong performance on our tasks suggesting that it can pick up on the underlying structure. To understand the mechanisms that allow it to do so, we perform probing experiments and activation patching based counterfactual analysis. Probing reveals that the model computes and stores first differences in its internal representations without explicit supervision, indicating that it tracks structural information about the sequence. Activation patching reveals that Llama retrieves the relevant first-difference with a mechanism similar to an induction circuit and subsequently adds it to the current value. Notably, our work represents one of the first studies to identify this form of concept induction in LLMs.

cs.LG↗

arXiv2026

Integrating Factual and Normative Industrial Knowledge via Constraint-Aware Graph Attention for Process Plan Recommendation

Integrating heterogeneous industrial knowledge, including factual relations and decision constraints, remains a core challenge in industrial information systems. Machining process planning exemplifies this problem because engineers must select operations by combining material properties, feature characteristics, and quality requirements. Existing methods rely mainly on similarity retrieval or classification, without a unified ranking objective or standardized evaluation. We propose PCA-GAT, which formulates machining process plan recommendation as a knowledge graph enhanced collaborative filtering problem. Bayesian Personalized Ranking provides the learning objective, while Recall@K and NDCG@K define evaluation. The knowledge graph supplies semantic structure when collaborative signals are sparse. Four domain constraints, material compatibility, precision requirements, feature applicability, and operation sequencing, are introduced as attention biases during graph propagation. Type-specific weights learn their importance, and an adaptive gate adjusts their influence using local context. On a real aerospace dataset with 115 parts and 507 plans, PCA-GAT achieves Recall@1 = 0.9087 and strong cold-start robustness, with about half the degradation of the strongest baseline under severe sparsity. Ablation studies show that knowledge graph enrichment is essential, constraints add value, and ungated constraint injection can hurt performance. The learned weights identify material-operation compatibility as the dominant factor, consistent with domain expertise. Results on three public benchmarks show no degradation when constraints are absent, supporting generalization beyond manufacturing. This study establishes a standardized recommendation protocol for engineering process planning and benchmarks seven methods across three categories, showing that knowledge representation is the main bottleneck.

cs.AI↗

arXiv2026

Heimdallr: Characterizing and Detecting LLM-Induced Security Risks in GitHub CI Workflows

GitHub Continuous Integration (CI) workflows increasingly integrate Large Language Models (LLMs) to automate review, triage, content generation, and repository maintenance. This creates a new attack surface: externally controllable workflow inputs can shape LLM prompts and outputs, which may in turn affect security decisions, repository state, or privileged execution. Although LLM security and CI security have each been studied extensively, their intersection remains underexplored. In this paper, we present the first study of LLM-induced security risks in GitHub CI workflows. We characterize the problem along the full execution chain and develop a taxonomy of high-level risk classes and concrete threat vectors. To detect such risks in practice, we design Heimdallr, a hybrid analysis framework that normalizes workflows into an LLM-Workflow Property Graph (L-WPG) and combines triggerability analysis, LLM-assisted dataflow summarization, and deterministic propagation to synthesize concrete threat-vector findings. Evaluated on 300 manually annotated unique workflows, Heimdallr achieves high accuracy on LLM-node identification (F1~=~0.994), triggerability classification (99.8%), and threat-vector detection (micro-average F1~=~0.917). As part of an ongoing detection and disclosure effort, we have so far responsibly disclosed 802 vulnerable workflow instances across 759 repositories and received 71 acknowledgments.

cs.CR↗

arXiv2026

SNR-Adaptive Unified Diffusion for Multi-Task Medical Image Segmentation

Clinical cardiac imaging pipelines currently deploy separate models for each dataset and modality, incurring redundant training costs and precluding knowledge sharing across anatomically related tasks. Consolidating semi-supervised learning, unsupervised domain adaptation, and domain generalisation into one model is therefore a practical necessity, yet naive joint training exposes a fundamental barrier: conflicting label semantics between datasets collapse LA Dice from 90.31\% to 83.38\%, while gradient imbalance across tasks of unequal complexity suppresses the weaker tasks throughout training. We present UniT-Diff, a unified diffusion segmentation framework that resolves these conflicts through three targeted mechanisms. An 11-channel task-specific output space physically partitions label categories, eliminating cross-task gradient sign reversal by construction. SNR-Adaptive Task Conditioning (SATC) scales the task token by the log signal-to-noise ratio of the current diffusion timestep, suppressing domain-specific bias during coarse denoising and restoring full task guidance as the signal clears. Task-Type-Aware Conditional Dropout (TTACD) permanently removes the task token for domain-generalisation inputs, routing them through a shared neutral pathway that draws on cross-dataset cardiac anatomy rather than source-vendor statistics. Under a single parameter set, UniT-Diff surpasses independently trained task-specific baselines on all three benchmarks simultaneously: +0.87\% on LA, +1.77\% on MMWHS, and +0.88\% on MNMS.

cs.CV↗

arXiv2026

W4A4 Quantization for Inference on Wan2.2-I2V-A14B

We summarize our submission to Sub-Challenge 1: W4A4 Quantization for Inference (HiF4 / MXFP4) of the ICME 2026 Low-Bit-width Large-Model Quantization Challenge. The sub-challenge targets 4-bit weight and 4-bit activation inference on Wan-AI/Wan2.2-I2V-A14B under HiF4 or MXFP4 numerical formats. We adapt two complementary ideas from LLM quantization, MixQ-style mixed precision for sparse activation outliers and SmoothQuant-style per-channel smoothing, together with block-wise HiF4 packing for Wan2.2 feed-forward linear layers. Calibration on representative OpenS2V-5M batches identifies heavy-tailed activation channels; smoothing rebalances dynamic range before W4A4 rounding; and a dual-branch GEMM preserves outlier columns in higher precision while the bulk of channels use strict W4A4. On official VBench I2V metrics, our pipeline stays within 2-3.5 percent of FP16 on most quality axes and improves motion smoothness, outperforming a native HiFloat4 baseline that degrades roughly 5 percent relative to FP16 across all reported scores.

cs.CV↗

arXiv2026

Bootstrapping the Four-Point NMHV Stress-Tensor Form Factor

We bootstrap the four-point next-to-maximally helicity-violating (NMHV) form factor of the chiral stress-tensor supermultiplet in planar maximally supersymmetric Yang-Mills theory through three loops at the symbol level. At two loops, an ansatz built from NMHV leading singularities and the relevant five-point one-mass integral function space is fixed uniquely by physical constraints; the resulting ratio function symbol contains 78 letters, all drawn from the 88-letter alphabet previously identified in the four-point MHV sector. At three loops, using this 88-letter alphabet as input and imposing extended Steinmann relations satisfied by the minimally-subtracted hard function, together with other physical constraints, we determine the three-loop symbol uniquely. Both results pass soft, double-soft and directional dual conformal invariance (DDCI) checks, provide the first multi-loop non-MHV form-factor data, and support the universality of the 88-letter alphabet for four-point form factors beyond the MHV sector.

hep-th↗

arXiv2026

Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models

Long-form chain-of-thought reasoning can improve LLM performance on complex tasks, but models often continue generating unnecessary reasoning after a correct answer has emerged. We refer to this behavior as overthinking. We study this phenomenon from the perspective of GRPO-style reinforcement learning (RL) post-training, framing it as a training-time credit-assignment problem rather than merely a decoding-time stopping problem. In rollouts sampled at the onset of GRPO training, we observe that successful trajectories can exhibit a slightly higher degree of overthinking than unsuccessful trajectories for the same prompts. This early imbalance provides a starting point for an undesirable feedback loop: because GRPO assigns sequence-level credit, it cannot distinguish the solution-reaching prefix from the unnecessary continuation that lengthens a successful trajectory. Both receive positive update signal, allowing the initial imbalance to grow into more severe overthinking during training. To address this issue, we introduce Dynamic Rollout Editing (DRE), a training-time intervention for successful trajectories that continue thinking after answer emergence. DRE preserves the accepted verified prefix, edits the remaining thinking, and prefers the edited trajectory within the same RL group, weakening the preference signal for unnecessary thinking without penalizing the reasoning needed to reach the answer. Experiments across diverse tasks show the effectiveness of DRE.

cs.CL↗

arXiv2026

Star Formation Drives Production of Low Energy Cosmic Rays

For over a century, the origin of low-energy cosmic rays (LECRs), the dominant heaters and ionizers of dense interstellar gas, remains elusive owing to solar modulation and uncertain transport processes. In this study, we introduce a new astrophysical approach based on HI Narrow Self-Absorption (HINSA) to obtain spatially resolved measurements of LECR ionization rates using high-fidelity HI observations toward the Orion region from the FAST telescope. The LECR ionization rate is found to scale with local star formation rate (SFR) as $log_{10}ζ= (1.4\pm 0.70)log_{10}\mathrm{SFR} + (-10.5\pm 2.9)$. Moreover, it increases with visual extinction, and is found to exceed, toward active star-forming regions, the value predicted for diffuse regions based on \textit{Voyager} measurements and an external propagation model. These findings demonstrate that LECRs are generated in situ by star-forming activities rather than penetrating from the broader Galactic cosmic-ray population. This is further supported by \textit{Fermi}-LAT gamma-ray observations toward the Orion region. Together, these results resolve a key uncertainty in cosmic-ray origin and establish a new avenue for quantifying the energetic feedback that regulates the interstellar medium.

astro-ph.GA↗

arXiv2026

Teacher-Guided Policy Optimization for On-Policy Reasoning Distillation under Large Policy Divergence

On-policy distillation (OPD) has become a promising paradigm for reasoning-oriented post-training of large language models (LLMs), especially when combined with reinforcement learning from verifiable rewards (RLVR). Existing OPD methods rely on reverse KL (RKL)-based teacher supervision over trajectories sampled from the student policy. However, we identify a critical limitation: under large teacher--student policy divergence, RL-driven exploration often produces trajectories outside the teacher distribution, resulting in uninformative negative feedback. To address this, we propose Teacher-Guided Policy Optimization (TGPO), an on-policy reasoning distillation method that remains effective under large policy divergence settings. Rather than relying solely on evaluative supervision, TGPO uses teacher to directly guide token level generation conditioning on student-generated contexts; together with RLVR-style trajectory level rewards, TGPO steers exploration toward improved continuations. Experiments on reasoning benchmarks show that TGPO consistently outperforms existing RKL-based OPD methods and remains robust across different teacher models.

cs.LG↗

arXiv2026

Inverting the Shield: Systematically Generating Safety Tests from Policy Specifications

The widespread integration of Large Language Models (LLMs) necessitates rigorous and systematic safety evaluation. Existing paradigms either rely on constructed benchmarks to assess safety from predefined perspectives, or employ dynamic red-teaming to probe potential vulnerabilities. While effective, these approaches face challenges, as they depend heavily on expert domain knowledge, offer limited systematic guarantees, and are vulnerable to rapid obsolescence. To address these limitations, we introduce a novel framework POLARIS that brings the rigor of specification-based software testing to AI safety. POLARIS first compiles unstructured natural-language policies into First-Order Logic (FOL) representations, establishing a traceable link between high-level rules and concrete test cases. This formalization enables the construction of a Semantic Policy Graph, where complex policy violation scenarios are encoded as traversable paths. By systematically exploring this graph, POLARIS uncovers compositional violation patterns, which are then instantiated into executable natural-language test queries, enabling coverage-driven and reproducible safety testing. Experiments demonstrate that POLARIS achieves higher policy coverage and attack success counts compared to established baselines. Crucially, by bridging formal methods and AI safety, POLARIS provides a principled, automated approach to ensuring LLMs adhere to safety-critical policies with verifiable traceability. We release our code at https://github.com/huac-lxy/POLARIS.

cs.AI↗

arXiv2026

From Hidden Profiles to Governable Personalization: Recommender Systems in the Age of LLM Agents

Personalization has traditionally depended on platform-specific user models that are optimized for prediction but remain largely inaccessible to the people they describe. As LLM-based assistants increasingly mediate search, shopping, travel, and content access, this arrangement may be giving way to a new personalization stack in which user representation is no longer confined to isolated platforms. In this paper, we argue that the key issue is not simply that large language models can enhance recommendation quality, but that they reconfigure where and how user representations are produced, exposed, and acted upon. We propose a shift from hidden platform profiling toward governable personalization, where user representations may become more inspectable, revisable, portable, and consequential across services. Building on this view, we identify five research fronts for recommender systems: transparent yet privacy-preserving user modeling, intent translation and alignment, cross-domain representation and memory design, trustworthy commercialization in assistant-mediated environments, and operational mechanisms for ownership, access, and accountability. We position these not as isolated technical challenges, but as interconnected design problems created by the emergence of LLM agents as intermediaries between users and digital platforms. We argue that the future of recommender systems will depend not only on better inference, but on building personalization systems that users can meaningfully understand, shape, and govern.

cs.IR↗

arXiv2026

Transparent and Controllable Recommendation Filtering via Multimodal Multi-Agent Collaboration

While personalized recommender systems excel at content discovery, they frequently expose users to undesirable or discomforting information, highlighting the critical need for user-centric filtering tools. Current methods leveraging Large Language Models (LLMs) struggle with two major bottlenecks: they lack multimodal awareness to identify visually inappropriate content, and they are highly prone to "over-association" -- incorrectly generalizing a user's specific dislike (e.g., anxiety-inducing marketing) to block benign, educational materials. These unconstrained hallucinations lead to a high volume of false positives, ultimately undermining user agency. To overcome these challenges, we introduce a novel framework that integrates end-to-cloud collaboration, multimodal perception, and multi-agent orchestration. Our system employs a fact-grounded adjudication pipeline to eliminate inferential hallucinations. Furthermore, it constructs a dynamic, two-tier preference graph that allows for explicit, human-in-the-loop modifications (via Delta-adjustments), explicitly preventing the algorithm from catastrophically forgetting fine-grained user intents. Evaluated on an adversarial dataset comprising 473 highly confusing samples, the proposed architecture effectively curbed over-association, decreasing the false positive rate by 74.3% and achieving nearly twice the F1-Score of traditional text-only baselines. Additionally, a 7-day longitudinal field study with 19 participants demonstrated robust intent alignment and enhanced governance efficiency. User feedback confirmed that the framework drastically improves algorithmic transparency, rebuilds user control, and alleviates the fear of missing out (FOMO), paving the way for transparent human-AI co-governance in personalized feeds.

cs.IR↗

arXiv2026

Unraveling the Key of Machine Learning-based Android Malware Detection

With the rapid advancement of machine learning (ML), ML-based Android malware detection has gained significant popularity due to its ability to automatically learn malicious patterns from Android apps. However, the lack of an in-depth and systematic analysis of existing research makes it difficult to obtain a holistic understanding of the state of the art in this field. In this work, we present the most comprehensive investigation to date of ML-based Android malware detection systems, combining both empirical and quantitative analyses. We first organize prior work into a unified taxonomy based on Android app representations and the ML modeling pipeline. Building on this taxonomy, we design a general-purpose framework for ML-based Android malware detection and re-implement 12 representative approaches from three research communities -- software engineering, security, and machine learning. Using this framework, we conduct a large-scale evaluation across three key dimensions: detection effectiveness, robustness to real-world challenges, and efficiency. Despite extensive research efforts and encouraging results, our findings reveal that existing learning-based Android malware detectors still face significant challenges, including vulnerability to malware evolution and susceptibility to adversarial attacks. We attribute these limitations to the detectors' ability to capture and leverage malware semantics, defined as semantic information that characterizes malicious behaviors derived from APK features. Finally, we summarize our key insights and provide actionable recommendations to guide future research in this domain.

cs.CR↗

arXiv2026

Unveiling axion signals in galactic supernovae with future MeV telescopes

Axion-like particles (ALPs) produced via the Primakoff process in the cores of Galactic core-collapse supernovae (SNe) could convert into MeV-energy gamma-rays through interactions with the Milky Way's magnetic field. To evaluate the detection prospects for such signals, we perform sensitivity projections for next-generation MeV telescopes by combining hypothetical instrument responses with realistic background estimates. Our analysis incorporates detailed simulations of the expected ALP flux from nearby SNe, the energy-dependent conversion probability in Galactic magnetic fields, and the telescope's angular/energy resolution based on advanced detector designs. Background components are modeled using data from current MeV missions and extrapolated to future sensitivity regimes. Our simulations demonstrate that next-generation telescopes with improved effective areas and energy resolution could achieve sensitivity to photon-ALP couplings as low as gagamma approx 1.61 x 10^-13 GeV^-1 for ALP masses ma < 10^-9 eV in Galactic Center. These results indicate that future MeV missions will probe unexplored regions of ALP parameter space, with conservative estimates suggesting they could constrain gagamma values two orders of magnitude below current astrophysical limits. Such observations would provide the most stringent tests to date for axion-like particles as a dark matter candidate in the ultra-light mass regime.

astro-ph.HE↗

arXiv2026

Drift-Aware Continual Tokenization for Generative Recommendation

Generative recommendation commonly adopts a two-stage pipeline in which a learnable tokenizer maps items to discrete token sequences (i.e. identifiers) and an autoregressive generative recommender model (GRM) performs prediction based on these identifiers. Recent tokenizers further incorporate collaborative signals so that items with similar user-behavior patterns receive similar codes, substantially improving recommendation quality. However, real-world environments evolve continuously: new items cause identifier collision and shifts, while new interactions induce collaborative drift in existing items (e.g., changing co-occurrence patterns and popularity). Fully retraining both tokenizer and GRM is often prohibitively expensive, yet naively fine-tuning the tokenizer can alter token sequences for the majority of existing items, undermining the GRM's learned token-embedding alignment. To balance plasticity and stability for collaborative tokenizers, we propose DACT, a Drift-Aware Continual Tokenization framework with two stages: (i) tokenizer fine-tuning, augmented with a jointly trained Collaborative Drift Identification Module (CDIM) that outputs item-level drift confidence and enables differentiated optimization for drifting and stationary items; and (ii) hierarchical code reassignment using a relaxed-to-strict strategy to update token sequences while limiting unnecessary changes. Experiments on three real-world datasets with two representative GRMs show that DACT consistently achieves better performance than baselines, demonstrating effective adaptation to collaborative evolution with reduced disruption to prior knowledge. Our implementation is publicly available at https://github.com/HomesAmaranta/DACT for reproducibility.

cs.IR↗

arXiv2026

Notes on Diagrammatic Coaction for Cosmological Wavefunction Coefficients: A Two-Site Prelude

We study the coaction of cosmological wavefunction coefficients of conformally coupled scalars in FRW background of a two-site example, which turns out to have an elegant diagrammatic interpretation. We show how the coaction acts on the twisted integrals for wavefunction coefficients, decomposing them into contributions associated with subtopologies and cuts, with the subtopologies admitting an interpretation as time-ordered integrals. This provides a clear interpretation of their analytic structure and suggests a broader applicability to more general cosmological diagrams.

hep-th↗

arXiv2026

Hyena Operator for Fast Sequential Recommendation

Sequential recommendation models, particularly those based on attention, achieve strong accuracy but incur quadratic complexity, making long user histories prohibitively expensive. Sub-quadratic operators such as Hyena provide efficient alternatives in language modeling, but their potential in recommendation remains underexplored. We argue that Hyena faces challenges in recommendation due to limited representation capacity on sparse, long user sequences. To address these challenges, we propose HyenaRec, a novel sequential recommender that integrates polynomial-based kernel parameterization with gated convolutions. Specifically, we design convolutional kernels using Legendre orthogonal polynomials, which provides a smooth and compact basis for modeling long-term temporal dependencies. A complementary gating mechanism captures fine-grained short-term behavioral bursts, yielding a hybrid architecture that balances global temporal evolution with localized user interests under sparse feedback. This construction enhances expressiveness while scaling linearly with sequence length. Extensive experiments on multiple real-world datasets demonstrate that HyenaRec consistently outperforms Attention-, Recurrent-, and other baselines in ranking accuracy. Moreover, it trains significantly faster (up to 6x speedup), with particularly pronounced advantages on long-sequence scenarios where efficiency is maintained without sacrificing accuracy. These results highlight polynomial-based kernel parameterization as a principled and scalable alternative to attention for sequential recommendation.

cs.IR↗

arXiv2026

Evidence of Ultrashort Orbital Transport in Heavy Metals Revealed by Terahertz Emission Spectroscopy

The orbital angular momentum of electrons offers a promising, yet largely unexplored, degree of freedom for ultrafast, energy-efficient information processing. As the foundation of orbitronics, understanding how orbital currents propagate and convert into charge currents is essential - but remains elusive due to the challenge in disentangling orbital and spin dynamics in ultrathin films. Although orbital currents have been predicted to propagate over long distances in materials, recent theoretical studies argue that lattice symmetry may constrain their mean free paths (MFPs) to the scale of a single atomic layer. In this work, we provide the first direct experimental evidence for ultrashort orbital MFPs in heavy metals (HMs) - W, Ta, Pt - revealed by femtosecond terahertz emission spectroscopy. This is enabled by sub-nanometer-precision control of thin-film thickness using wedge-shaped HM|Ni heterostructures. By employing a multi-component terahertz-emission model, we quantitatively extract the orbital MFPs, consistently finding them shorter than their spin counterparts. Furthermore, control experiments rule out interfacial orbital-to-charge conversion as the dominant mechanism, confirming that the process is governed by the bulk inverse orbital Hall effect. Our findings resolve a central controversy in orbitronics and provide key insights into orbital transport and conversion mechanisms.

cond-mat.mtrl-sci↗