Searcharxiv⌕ Search

arXiv subjects

Yi Li

Publications and source records attributed to Yi Li.

At least 37 records · Page 2Linked to original sources
arXiv2026

TasmScan: Continuation-Aware Taint Analysis for TVM Bytecode with Savelist Abstraction

The Open Network (TON), with a peak market capitalization exceeding $20 billion and over 175 million activated on-chain addresses, relies on the TVM (TON Virtual Machine) to execute smart contracts. TVM uses first-class continuations with savelists to manage control flow and register state across continuation invocations. Since savelist-captured registers allow data to flow across continuation boundaries without passing through the operand stack, bytecode-level analyses cannot construct complete data flow tracking without explicitly modeling savelist semantics. We present TasmScan, the first bytecode-level static analysis framework for TVM that enables cross-continuation data flow reasoning without requiring source code. TasmScan models savelist semantics via forward register analysis with a formal over-approximation guarantee for exact-resolved save sites and locally tracked register definitions, then lifts bytecode into TASIR, a typed intermediate representation, and performs path-sensitive taint analysis with context-aware sources to detect defects. We evaluate TasmScan on 2,921 contracts from the TON verifier registry and a labeled benchmark of 208 contracts with human-confirmed ground truth. On the full corpus, TasmScan resolves 294,546 dynamic continuation targets with 100% precision; ablation confirms that savelist propagation is essential for resolving indirect register calls that depend on cross-continuation register passing. On the benchmark, TasmScan detects 95.3% of defects across five classes with 96.8% precision. A 366-pair stratified sample from the full corpus estimates 85.8% overall precision. TasmScan offers a 17x median speedup over the state-of-the-art symbolic-execution baseline, and in the path-analysis comparison completes 100% of analyses with zero crashes or timeouts.

cs.SE↗
arXiv2026

Verification of Compiler-to-Accelerator Mappings for Machine Learning Accelerators

To meet the performance needs of modern machine learning (ML) applications, ML compiler frameworks support compiler-to-accelerator mappings that offload parts of application code to operations in specialized hardware accelerators. However, most of these frameworks do not verify these mappings down to the hardware level, potentially resulting in functional mismatches. In this paper we propose BOLT, the first framework for formally verifying the correctness of compiler-to-accelerator mappings for coarse-grained intrinsics in ML accelerators, with respect to a formal hardware semantics. BOLT does not require additional information from the compiler, and verifies the functional equivalence of the application code and the code for the mapped hardware accelerator intrinsic, including handling of complex loop nests and tensor data layouts in hardware. It effectively utilizes a pattern of *aligning* software loops with the hardware, followed by *relating* corresponding data layouts, to enable verification using well-aligned product programs. To support these steps, we propose two custom templates --- the sync-skeleton and the layout-sketch --- to guide users in aligning loops and specifying data layout relationships, respectively. We have developed a proof-of-concept prototype for BOLT and use it to successfully verify the correctness of several complex mappings for two recent open-source ML accelerators.

cs.PL↗
arXiv2026

Context-dependent agent evaluation with orthogonal equilibrium learning

Many applications require to evaluate agents under contextual information (e.g., a prompt, task, or user group). We study how to perform such context-dependent agent evaluation from offline feedback. Existing score-based models for this purpose (e.g., Bradley-Terry) impose a transitive preference ordering, which fails to reflect collective preferences when human judgements are heterogeneous. Inspired by social choice theory, we frame evaluation as a contextual game between two players, each selecting a distribution over agents as the strategy to receive greater collective preference than the other. Then, the support of the Nash equilibrium defines a context-specific set of winners. However, learning context-specific equilibria from offline logs is difficult because each context reveals human feedback on only a subset of agents, and, hence, a naive plug-in estimator can therefore be biased. To address these challenges, we propose NashEval, a general framework for robust contextual equilibrium learning. NashEval first constructs debiased estimates of the contextual payoff matrix that characterizes the game. NashEval then learns the context-to-equilibrium mapping with a tailored orthogonal loss, which avoids the need to solve a separate game for each context. We show theoretically that errors in estimating the nuisance functions underlying the payoff matrix affect the risk of the learned equilibrium (i.e., exploitability) only through higher-order terms. Across various experiments, NashEval improves robustness of equilibrium learning and consistently identifies the set of top-performing agents across contexts.

cs.AI↗
arXiv2026

Jev-Mem: System-One-Controlled Agentic Memory for Efficient AI Agents

Agentic memory is becoming essential for long-horizon AI agents, yet many existing systems rely on autoregressive LLMs to control how memories are organized, retrieved, and used, placing expensive generation on the critical path of memory operations. We introduce \textbf{\method}, a new agentic memory architecture inspired by System-One/System-Two cognition. System One captures fast, lightweight decision-making, whereas System Two performs slower, deliberative reasoning. Jev-Mem brings this division of labor to agentic memory through a dedicated System-One control plane, a structured multi-relational memory plane, and a System-Two reasoning plane. The System-One controller governs memory typing and relational organization during construction, and dynamically performs query routing, retrieval-budget allocation, graph traversal, candidate scoring, and adaptive stopping during retrieval. System Two is invoked only for complex reasoning and answer synthesis. This design improves both memory effectiveness and system efficiency: on LoCoMo Jev-Mem achieves an overall LLM-as-a-Judge score of 0.777, an 11.0\% relative improvement over the strongest baseline, while reducing memory construction time to 158\,s, a 6.6$\times$ speedup over the fastest competing memory system, and lowering average query latency to 0.93\,s, a 36.7\% reduction.

cs.AI↗
arXiv2026

Mind or Message? Auditing Theory of Mind in Multi-Agent Social Simulation

Language model agents are increasingly used to simulate social interaction, and the resulting transcripts read as though the agents understand one another. We ask whether that appearance rests on a model of the partner's mind or on the surface record of what the partner said. We build a social simulation in which both questions have exact answers: 40 multi-issue negotiations whose hidden preference weights and whose full Pareto frontier are known by construction. Two model families negotiate across 160 dyads, every transcript is frozen before any measurement, and 2880 counterfactual probes then hold the evidence byte identical while moving one factor at a time: the reader's own stake, the partner's tone, an identity label, and the order of recursion. The agents are socially fluent and economically poor. They reach agreement in 96.2% of dyads with 0 protocol failures, yet only 0.7% of deals land on the Pareto frontier, they leave 20.5% of the available joint value unclaimed, and they miss the one issue on which their interests are perfectly aligned in 76.6% of deals; on the frontier and on that aligned issue, a package drawn at random from the set both sides would accept does as well. The probes locate the failure. Swapping only the reader's own payoff sheet, while the partner's words and offers stay identical, moves the inferred top priority by 15.0 percentage points, which is egocentric projection rather than inference, while a tone rewrite moves it by 5.3 percentage points and an identity label by 0.0. Most tellingly, an agent predicts what its partner believes about it 72.5% of the time while that partner's belief is itself correct only 51.2% of the time: the agents track the conversation far better than they track the mind behind it.

cs.LG↗
arXiv2026

Sample-Conditioned Representation Selection for Audio Few-Shot Learning

Few-shot audio classifiers may rely on foreground-background co-occurrences and fail when those correlations shift. On SpurAudio, the resulting representation shift is concentrated and class dependent: for ResNet12, the top 10 percent of channels explain 82.80 percent of the null-corrected shift contribution. We propose SAMPLESELECT, which predicts a fixed-budget feature mask independently for each input while keeping the encoder and source classifier frozen. Training uses differentiable Gumbel Top-k selection with foreground classification and cross-background contrastive losses; inference uses deterministic Top-k masks and support-only linear adaptation. Across ResNet12 and Conv64 in 5-way 1-shot and 5-shot evaluation, SAMPLESELECT gives the best OOD accuracy among the compared methods and improves the matched full-representation control by 4.90-8.38 percentage points. Ablations and representation analyses further support the learned selection mechanism. Code is available at https://github.com/Cross-Innovation-Lab/SAMPLESELECT/

cs.AI↗
arXiv2026

Disorder-driven transport in ZrN thin films grown by ion-beam-assisted sputtering

We investigate the structural and electronic transport properties of zirconium nitride (ZrN) thin films grown by dc ion-beam assisted sputtering (IBAS) as a function of nitrogen partial pressure, sputtering power and deposition temperature. Variation of growth conditions enables controlled tuning from disordered metallic and superconducting behavior to insulating transport. Increasing nitrogen flow drives an increase in sheet resistance, suppression of superconducting transition temperature, and non-metallic conduction. XRD shows no measurable change in long range crystallinity or order. In the insulating regime, low-temperature transport is well described by 3D Mott variable-range hopping (VRH), with the characteristic temperature $T_0$ increasing monotonically with sheet resistance over four orders of magnitude. Despite this strong correlation between $T_0$ and disorder, $T_c$ exhibits no systematic dependence on $T_0$, indicating a decoupling between localization physics and the superconducting energy scale. Magnetotransport measurements are not well described by the standard BCS model nor the dirty type-II Werthamer-Helfand-Hohenberg model. The phase boundary is instead captured by a free-exponent power law, $μ_0 H_{c2}(T) = μ_0 H_{c2}(0)[1 - (T/T_c)^{n}]$ with $n \approx 3.47$, and extrapolates to $μ_0 H_{c2}(0) \approx 6.4$ T. The films have an extracted coherence length of 7 nm. These results establish IBAS-grown ZrN as a broadly tunable platform for investigating disorder-driven transport and the crossover between metallic conduction, electronic localization, and superconductivity.

cond-mat.supr-con↗
arXiv2026

PrivEscalate: Measuring and Augmenting the Threat of LLM-Automated Linux Privilege Escalation

As Large Language Model (LLM) agents increasingly automate offensive operations across the cyber kill chain, their efficacy in complex local post-exploitation tasks remains inadequately quantified. Among these, Linux privilege escalation is a key step between initial access and full system compromise. However, existing evaluations for this task are limited by small sample sizes (fewer than 15 scenarios), lacking the scale to compare model capabilities under executable verification. To address this, we present PrivEscalate, a large-scale benchmark for Linux privilege escalation, comprising 531 Dockerized scenarios spanning 14 sub-categories. We additionally derive 329 parameterized variants to measure sensitivity to environmental distractors. Evaluating six LLMs across three agent architectures reveals: (i) model capability is heterogeneous across vulnerability classes, with no single model dominating across the high-prevalence classes, motivating multi-dimensional risk assessments; (ii) LLM successes are sensitive to environmental perturbation, so configuration rotation can disrupt some exploit attempts but does not eliminate the measured risk; and (iii) agent architectures can materially change success rates and reorder model rankings, though the magnitude is model-dependent. Leveraging these insights, we develop PrivEscAgent, a domain-specialized wrapper that augments a generic ReAct agent with deterministic enumeration, category matching, and step planning. PrivEscAgent improves over prior Linux privilege-escalation agent baselines without underlying LLM modifications. We release PrivEscalate as an open-source, Dockerized measurement instrument supporting LLM agent evaluation, defensive tool validation, and red-team training.

cs.CR↗
arXiv2026

EventSpec: Defining and Detecting Event-Semantic Issues in Blockchain Ecosystems

In recent years, smart contracts have become the backbone of decentralized applications (DApps), and off-chain systems such as bridges, wallets, and indexers rely heavily on event logs to track contract execution and state changes. However, the Ethereum Virtual Machine (EVM) does not validate or enforce event semantics, so logs can diverge from on-chain state, misleading off-chain systems into accepting incorrect state transitions. Existing smart contract vulnerability detection tools focus on logic bugs, with limited support for detecting event-semantic defects. To address this gap, we collect audit reports and incident cases and apply open card sorting to define five classes of event-semantic defects: event collision, state-event mismatch, unauthorized event emission, event emission mismatch, and event parameter mismatch. We propose EventSpec, which infers event specifications from a contract corpus via behavior inference and semantic-constraint extraction and applies differential checking to identify event-semantic defects in target contracts. We run EventSpec on 6,617 real-world contracts and evaluate detection effectiveness based on manually labeled results; EventSpec achieves an overall comprehensive precision of 90.17%. We further provide an off-chain evaluation harness that reproduces two off-chain attack vectors on any EVM-compatible chain: event origin confusion caused by unintended emitters and event-state desynchronization where events lack matching state updates. Using this harness, we demonstrate the feasibility of these attacks on bridge relayers, blockchain explorers, and NFT marketplaces, and report six wallet issues, four of which were confirmed (including a $600 bounty), with two remaining pending.

cs.CR↗
arXiv2026

Resolving a conjecture on permutation polynomials over $\mathbb{F}_{2^n}$

Let $δ\in\mathbb{F}_{2^n}$ satisfy $\operatorname{Tr}_{\mathbb{F}_{2^n}/\mathbb{F}_2}(δ)=1$. We study the permutation behavior of $$ f(x) = \left(\frac{1}{x^2+x+δ}\right)^{2^k}+x $$ over $\mathbb{F}_{2^n}$. Helleseth and Zinoviev proved that $f(x)$ is a permutation for $k=0,1$, and remarked that numerical evidence suggests that no other cases occur. In this paper, we confirm their assertion by proving that, for $0\leq k<n$, $f(x)$ is a permutation of $\mathbb{F}_{2^n}$ if and only if $k=0$ or $k=1$.

math.NT↗
arXiv2026

Photonic magnetism and altermagnetism without magnetic materials

Magnetism, a fundamental property of solids arising from the collective alignment of electronic spins of magnetic atoms, has recently been expanded by the discovery of altermagnetism, a symmetry-driven phase distinct from both ferromagnetism and antiferromagnetism. Initial efforts to emulate altermagnetism in photonic systems are also being pursued, primarily through the magneto-optic response of materials; however, their intrinsic frequency limitations pose challenges for extending photonic altermagnetism into the optical regime, thereby restricting their material choices and optical applications. Here, we establish a microscopic framework of photonic magnetism through group theory symmetry analysis, defining photonic counterparts of electron spin and magnetic atoms. This approach enables the realization of photonic ferromagnetic, antiferromagnetic, and altermagnetic phases within structured optical lattices constructed by purely dielectric, nonmagnetic materials, which not only broadens the photonic magnetism concept, but also lifts the material and frequency limitations. Analytical models, numerical simulations, and experimental measurements reveal spin-momentum locking directly corresponding to their electronic analogs, showing d-, g-, and i-wave circular dichroism (CD) splitting bands at telecom wavelengths (around 1550 nm). These results demonstrate that altermagnetic order, and magnetism more broadly, can be reconstructed in photonic systems through symmetry and mode coupling alone, opening a new route towards spin-dependent light control and bosonic analogs of quantum magnetic phenomena in dielectric photonic crystals.

physics.optics↗
arXiv2026

A Universal Context-Reuse Layer for Cross-Model KV Sharing

Modern large language model (LLM) serving systems increasingly operate over repeated or shared context, yet each model typically performs its own prefill computation even when another model has already processed the same input. Existing KV-cache reuse mechanisms substantially reduce redundant computation within a single model, but generally assume that the producer and consumer of a cache are identical. We study \emph{cross-model KV sharing}, which translates the KV state produced by a source model into a representation that can be consumed by a different target model, including models that differ in scale, architecture, attention configuration, tokenizer, and model family. We evaluate the approach in both within-family and cross-family settings. For Qwen2.5-7B $\rightarrow$ Qwen2.5-1.5B, translated KV states improve LongBench2 accuracy from 27.59\% to 34.48\%, a gain of 6.89 percentage points over the native 1.5B baseline, while reducing handoff cost relative to native target prefill. For the cross-family Qwen2.5-1.5B $\rightarrow$ Gemma-2-2B setting, KV handoff reduces target-side prefill cost by up to 67.05\% at 4K context length while maintaining decoding perplexity close to native-model baselines. In a more heterogeneous Llama3.1-70B $\rightarrow$ Qwen2.5-7B setting, cross-family handoff achieves 44.0\% accuracy compared with 45.7\% for native Qwen2.5-7B inference, while reducing measured latency from 899ms to 138ms. These results provide initial evidence that KV states can serve as transferable computational representations rather than strictly model-local caches, and motivate \emph{context mobility} as a systems abstraction for reducing redundant prefill across heterogeneous LLM and multi-agent inference workflows.

cs.LG↗
arXiv2026

Learning to Allocate Incentives for Incentivized Advertising via Offline Model-Based Reinforcement Learning

Complete your ad view and grab a 5-cent bonus! In incentivized advertising, a platform promises users a bonus before observing downstream ad revenue, encouraging them to click and complete ads. It must balance the incentive promised in advance against the revenue realized afterward: insufficient incentives forfeit monetization opportunities, whereas excessive incentives reduce net profit. Because current incentives may also shape user expectations and future engagement, incentive allocation is a sequential decision problem with delayed revenue, cost sensitivity, and carryover effects. Existing work has not studied decision-making algorithms for this setting. Auto-bidding assumes available ad opportunities, while targeted promotion optimizes incentives outside the ad monetization pipeline. We formulate the problem as an MDP and develop an offline model-based RL framework for cost-controllable sequential incentive allocation. It learns a world model of user feedback and ad revenue, then performs conservative policy optimization. An independent counterfactual scorer evaluates each learned policy on held-out logs, enabling pre-launch selection without costly online exposure. Experiments on large-scale industrial data and online A/B tests show that the scorer provides a stable offline signal. The deployment path from causal inference to offline RL and then Offline-MBRL further validates the framework: MB-IQL improves per-user net profit by 7.96\% over TD3+BC, whereas reverting to plain IQL reduces it by 6.56\% (both \(p<0.0001\)).

cs.AI↗
arXiv2026

Four-loop Anomalous Dimensions of Scalar-QED Theory from Operator Product Expansion

We apply the Operator Product Expansion (OPE) algorithm to the renormalization of scalar-QED theory, with a specific focus on the fixed-charge operator $ϕ^Q$. Within the OPE framework, the anomalous dimension of the $ϕ^Q$ operator is perturbatively computed to four-loop order in the modified minimal subtraction scheme, extending beyond the previously available three-loop result. The beta functions, as well as the mass and field anomalous dimensions, are also computed at this order. An alternative loop-integrand construction method is proposed, based on graph decomposition and skeleton expansion techniques, for deriving the integrands of one-Particle-Irreducible correlation functions. This work represents the first non-trivial validation of the OPE algorithm for higher-loop renormalization beyond pure scalar theories. The present successful computations further confirm the efficiency and versatility of the OPE algorithm in renormalization analysis.

hep-th↗
arXiv2026

D3ER: Supporting Multi-Modal Recommendation via Disentangle and Distillation-based Dynamic Ensemble

Incorporating items' information shared among multiple modalities into a fused representation, multi-modal recommendation (MR) has demonstrated documented success than canonical unimodal recommendation. Although several attempts have been made to extract the discriminative information unique in each modality, existing methods suffer from a core limitation: the joint learning of modal-homogeneity discriminative information (HOI) and modal-heterogeneity discriminative information (HEI) tends to weaken their individual effectiveness. To remedy this deficiency, we propose a novel method, dubbed Disentangle and Distillation-based Dynamic Ensemble for multi-modal Recommendation (D3ER). We introduce gradient boosting into MR for the first time to formalize the optimization objective for alternately learning HOI and HEI. This design enables models dedicated to each type of information to focus on their proficient samples, thereby promoting specialized optimization. Furthermore, to mitigate the inherent high storage cost and risk of local optima in gradient boosting, we enhance our framework with knowledge distillation and a global correction regularization. Experiments on prevalent real-world datasets confirm the superiority of our proposed method on MR.

cs.IR↗
arXiv2026

Ab initio anatomy of quadrupole correlations in $^{16}$O and $^{20}$Ne

Azimuthal hadronic flow measured in ultra-relativistic ion--ion collisions provides a new means of imaging multipole correlations in the ground state of atomic nuclei. Early interpretations largely relied on a classical-rotor picture, in which the measured mean-square elliptic flow is directly related to an intrinsic quadrupole deformation. Atomic nuclei, however, contain additional many-body correlations generated by the Pauli exclusion principle, collective shape fluctuations and non-collective dynamical processes, whose impact on this correspondence has not yet been elucidated. Here, we resolve this issue through an ab initio analysis of $^{16}$O and $^{20}$Ne based on chiral nuclear interactions, combining the in-medium similarity renormalization group with the quantum-number-projected generator coordinate method. By successively isolating antisymmetrization, collective rotational and vibrational, and non-collective dynamical correlations, we determine, for the first time, how each component contributes to the mean-square quadrupole eccentricity. We uncover an unexpected compensation among these distinct correlation mechanisms: despite sizable individual contributions, the squared effective quadrupole deformation inferred from the elliptic flow remains close to the square intrinsic deformation of the nucleus. This result provides a microscopic explanation for the surprising success of the classical-rotor approximation and establishes a quantitative foundation for interpreting $^{16}$O+$^{16}$O and $^{20}$Ne+$^{20}$Ne collision data recently collected at the Large Hadron Collider.

nucl-th↗
arXiv2026

Fujiki Class $\mathcal C$ Varieties and a Kähler Criterion

In this article, we show that flips and divisorial contractions preserve the Kähler condition (for strongly $\mathbb{Q}$-factorial compact Kähler generalized klt pairs with $B+β_X$ big), and we give a criterion for varieties in Fujiki's class $\mathcal C$ to be Kähler. We also prove the existence of small $\mathbb Q$-factorializations for generalized klt pairs and of dlt modifications for generalized pairs.

math.AG↗