Search arXiv⌕ Search

arXiv subjects

Arpit Jain

Publications and source records attributed to Arpit Jain.

At least 19 recordsLinked to original sources

From LoRA to Language: Recovering Skill Documents from Adapters

Agent skills are short documents that teach a language model how to handle a class of tasks. To save context, these documents are increasingly compiled into low-rank adapters (LoRA), which keep the behaviour but lose the text: an adapter is hard to read, edit, audit or move to another model. We ask whether the skill document can be written back from the adapter and its frozen base model, and we score each recovered document by the share of the original's key instructions it states and by the tasks it solves. Reading the weights alone recovered little with the methods we tried; a learned map from weights to text passed on about one bit of the document. Running the adapter worked much better. The Executing Writer, a small writer trained on top of the adapted model, recovers 39-44% of the key instructions of held-out skills, against 1.3-1.5% with another skill's adapter, and on adapters fitted to 41 external skills its documents restore 85-91% of the original's task gain. These strongest results are on adapters whose training stored the document; adapters trained on behaviour alone are much harder for trained writers (1-2% of instructions). For these adapters we test an agent that runs the base and adapted models and writes a skill from where they differ. On ALFWorld its skills recover 58-71% of a LoRA's gain and carry over to models that cannot load the LoRA, lifting Llama-3.1-8B from 5% to 55%. Whether such a skill comes from the adapter depends on what the adapter learned: when its behaviour cannot be guessed, the adapter is the source; when it can, a reward loop without the adapter does as well.

cs.LG↗

EnvOS: Auditing Computer-Use Agents When the World Moves On : Phenomenon-Based Task Construction, Certification, and Evidence-Based Evaluation

Computer-use agents built on large language models (LLMs) work in software that can change while they act: an appointment moves, a policy is revised, a record is updated. Testing agents under such changes is harder than it looks. When an agent fails, the cause may be the agent, but it may also be a change that did not fire as intended, an update the agent never received, or a grader that scored the episode wrongly. We introduce EnvOS, a framework for building and certifying environments that change mid-task. Before any agent runs, EnvOS checks that each change fires correctly, that the task remains solvable, and that the grader separates correct from incorrect behavior; after each run, separate code re-checks the verdict from archived evidence. We apply it to stale information, where a value the agent has already seen changes before the agent acts on it. In clinic booking, Claude Opus 5 succeeds on 0/16 tasks when nothing extra is shown, 2/16 when reminded to re-check the source, and 15/16 when the updated value is shown; the gain over the reminder holds after correcting for all tests (p = 0.00293). In insurance-claim approval, Opus 5 re-checks on its own and succeeds on 10/10, whereas Claude Sonnet 5 rises from 1/10 to 9/10 when the current policy is shown again, a gain significant in its pre-registered test but not after correcting for all tests. Whether an agent caught a change thus varied with the model and the interface. We also stress-test the grading itself: on corrupted episodes designed blind from the rules, the EnvOS pipeline accepted none of 26 as clean, and on an externally generated set it caught 25 of 39, against 4 for simple log checks. Because every EnvOS environment is generated from a seed and graded by an audited automatic verifier, the same environments are natural candidates for training agents with reinforcement learning from verifiable rewards.

cs.AI↗

Same Entity, Different Script: Diagnosing Cross-Script Entity Matching Failures in Language Models

Multilingual language models can give different identity judgments when the same people's names are written in different scripts. We study this effect using 601 audited identity pairs with attested Devanagari and Latin forms, holding the question and relation fixed. Qwen2.5-7B's same-person accuracy falls from 35.1% in Latin to 8.5% in Devanagari under Marathi prompts, while different-person accuracy remains above 98%. Evaluation across five models reveals distinct response biases, and reduced tokenization fragmentation does not reliably close the gap. Replicating the design on 374 audited Malayalam pairs built from the same entities reproduces the effect in a second script and language family: same-person accuracy falls to 5.3%, about half the matched Devanagari rate, while the margin still ranks matching above non-matching names at 0.925 AUROC. Latin-trained probes recover label information from Devanagari states, exceeding a string-feature baseline under similarity-matched negatives. Scalar calibration recovers 87% of the raw model-probe balanced-accuracy gap, identifying decision criterion placement as a major contributor. Activation patching localises causal sensitivity to the second entity in Qwen's middle layers; one shared sensitivity direction transfers about half the full-state margin correction. A fact-independent intervention at this site raises held-out Marathi same-person accuracy from 6.5% to 33.5%, with 98.5% different-person accuracy. Together, these results distinguish script-dependent discrimination from criterion placement and identify a causal site for improving identity judgments.

cs.CL↗

Beyond the Performance Illusion: Structure-Aware Stratified Partitioning and Curriculum Distributionally Robust Optimization for Spatially Correlated Domains

Performance evaluation in AI systems commonly assumes that random dataset splits produce independent and identically distributed (i.i.d.) subsets. We show that this assumption often breaks down in spatiotemporally correlated domains such as aerial surveillance, precision agriculture, and medical imaging, leading to two systematic failures: data leakage, where correlated samples span training and validation splits and inflate performance estimates, and hidden stratification, where errors on minority subpopulations are obscured by aggregate metrics. To address these issues, we propose a unified evaluation and training framework for spatially correlated data. We introduce Structure-Aware Stratified Partitioning (SASP), which constructs validation splits that reduce spatiotemporal leakage while preserving meaningful class balance, and Curriculum Distributionally Robust Optimization (CDRO), a curriculum-based relaxation of distributionally robust training that stabilizes optimization under these stricter splits. Across multiple benchmarks, this combination yields consistently improved generalization, more reliable confidence calibration, and exposes failure modes that remain hidden under conventional random-split evaluation.

cs.LG↗

ReTreVal: Reasoning Tree with Validation and Cross-Problem Memory for Large Language Models

Every existing inference-time reasoning framework discards all failure context at problem boundaries, leaving a model solving problem 500 no wiser than it was on problem 1. We present ReTreVal (Reasoning Tree with Validation), a training-free framework that closes this gap through adaptive tree exploration with tool-augmented node refinement, typed-failure backtracking that injects categorized error context into the recovered branch, and a self-rewriting memory that accumulates and revises strategy entries across problems, enabling inference-time cross-problem learning on any fixed, unmodified LLM without fine-tuning. ReTreVal achieves 85.8% pass@1 on MATH-500 (+8.6 pp over Zero-Shot CoT, +8.6 pp over the strongest baseline Self-Refine) and 54.4% on MMLU-Pro (+15.3 pp over Self-Refine), with a 3.4:1 win-to-regression ratio confirming genuine error recovery rather than noise. These capabilities, previously requiring gradient updates, allow a 32B model to compete with much larger single-pass systems.

cs.AI↗

Phase-dependent electronic structure of two-dimensional Ag layers at the graphene/SiC interface

Intercalation at the graphene/SiC interface provides a controlled route to stabilize atomically thin layers with properties distinct from their bulk counterparts. In this platform, the structure and stability of the intercalated phase depend sensitively on the defect landscape of the starting substrate. For intercalated two-dimensional silver at the graphene/SiC interface, two phases have been observed: a phase epitaxial to the SiC lattice, Ag$_{(1)}$, readily obtained following the conventional intercalation method under ultra-high-vacuum conditions and extensively characterized, and a more densely packed phase, called Ag$_{(2)}$, which has remained largely unexplored. Here we report an in situ ultra-high-vacuum preparation method of the second phase intercalated at the graphene/SiC interface; this phase previously was prepared via high-pressure confinement heteroepitaxy. Low-energy electron diffraction shows that Ag$_{(2)}$ is rotated by 30 degree relative to the SiC lattice and forms supercells, in contrast to the $(1\times 1)$ epitaxial relation of Ag$_{(1)}$ with SiC. High-resolution angle-resolved photoemission spectroscopy reveals a more rich Ag$_{(2)}$ band dispersion compared to the Ag$_{(1)}$. In density functional theory calculations, by defining the unfolding entropy which, in a quantified way, finds that the band structure of Ag$_{(2)}$ is more suitable to be unfolded to the SiC primitive cell, and the resulting unfolded band dispersion is in great agreement with the experimental data. We further show that the different intercalated Ag phases tune the electronic properties of the overlying quasi-free-standing graphene layer differently: compared with Ag$_{(1)}$, Ag$_{(2)}$ yields an $\sim$1.75 times higher charge carrier density and modifies the charge-plasmon interaction of the graphene layer, indicating a change in effective screening at the interface.

cond-mat.mtrl-sci↗

Ultra-Confinement of Polaritons in Single Atomic Layer Ag Photonic Quantum Dots

Light scattering by two-dimensional (2D) van der Waals heterostructures (vdWHs) is immense, especially given their infinitesimal volume, thus enabling strong light-matter interactions. Surface 2D polariton waves manifest through large concentration of electromagnetic field in vertical direction, normal to their propagation. By confining vdWH materials into 2D photonic shapes, one can manipulate and compress light in lateral directions. Scattering-type scanning near-field optical microscopy is a perfect tool for direct imaging of the propagating polaritons and studying the properties of confined polaritons in nanostructures. Though, thus far the quantitative analysis, such the wavelength extraction, has been challenged for confined polaritons by incapability of mapping of the wave period on sub-wavelength scale and difficulty of identifying an adequate substrate's "background" to subtract. Here, an analytical approach is developed to reveal the local propagation constant of confined polaritons under abovementioned constraints and map it with the sub-wavelength resolution. Applied to analysis of the SiC/2D-Ag/EG (epitaxial graphene) photonic nanostructures, the technique uncovered that the polaritons are highly confined in both vertical ($\simλ$/50) and lateral directions ($\simλ$/40) by 2D metal.

cond-mat.mtrl-sci↗

Ultrafast Band-Gap Renormalization in Bilayer Graphene

We demonstrate, by femtosecond time- and angle-resolved photoemission spectroscopy, that photoinduced interlayer charge transfer in a heterostructure consisting of Bernal-stacked bilayer graphene and a single atomic layer of silver on 6H-SiC(0001) transiently modulates the intrinsic potential landscape across the silver-graphene interface. This acts as an ultrafast optoelectronic gate that drives momentum-dependent band renormalizations, resulting in a transient band-gap opening on femtosecond timescales. Simultaneously, the photogenerated hot-carrier population enhances electronic screening, leading to subsequent closing of the band-gap beyond the thermal equilibrium value. These findings reveal two different mechanisms for photoinduced, reversible control of the electronic band structure in bilayer graphene -- interlayer charge transfer and hot-carrier-enhanced screening -- providing a general framework for the ultrafast control of electronic properties in graphene-based heterostructures. This opens up novel pathways for the realization of ultrafast optoelectronic devices and the exploration of correlated quantum phases in bilayer graphene under non-equilibrium conditions.

cond-mat.mes-hall↗

Point defects and their dynamic behaviors in silver monolayer intercalated between graphene and SiC

Point defects give rise to sharp modifications in the structures and electronic properties of two-dimensional metals, offering an atomic-level platform for fundamental studies and potential applications. In this work, we investigate atomic-scale defects in a two-dimensional silver monolayer intercalated between epitaxial graphene and SiC using scanning tunneling microscopy. Dark and bright defects are identified as vacancies or substitutional impurities within the silver monolayer, each hosting a localized electronic state. Remarkably, under tunneling electron excitation at negative bias, the bright defects exhibit dynamic behaviors characterized by inelastic switching between two states. The switching can be reversibly controlled by the microscope tip, enabling the defects to function as atomic-scale two-level conductance switches. Analysis of defect switching reveals possible defect origins and the relationship between dark and bright defect species. Our findings establish a pathway to precise manipulation of defects in two-dimensional metals and uncover previously unexplored dynamics with potential use in nanoelectronics.

cond-mat.mes-hall↗

Defect-Mediated Phase Engineering of 2D Ag at the Graphene/SiC Interface

Atomically thin silver (Ag) films offer unique opportunities in plasmonic, quantum optics, and energy harvesting, yet conventional growth methods struggle to achieve structural control at the monolayer limit. Here, we demonstrate phase-selective synthesis of large-area, crystalline 2D Ag films via defect-engineered confinement heteroepitaxy (CHet) at the epitaxial graphene/silicon carbide (EG/SiC) interface. By tuning graphene growth and post-growth defect introduction, two distinct Ag phases are achieved with disparate properties: a nearly commensurate Ag(1) lattice stabilized by vacancy and line defects in epitaxial graphene, and a denser Ag(2) phase preferentially grown with sp3-rich zero-layer graphene. Structural and spectroscopic characterization confirm lattice registry with the SiC substrate, while theoretical calculations reveal a thermodynamic preference for Ag(2) but an easier nucleation for Ag(1). Both phases are found to be semiconducting, with the Ag(2) phase exhibiting slightly enhanced n-doping of graphene. Notably, nonlinear optical measurements reveal a three-order magnitude difference in second-order susceptibility between the two phases, demonstrating promise for phase-tunable 2D metals in reconfigurable optoelectronic and metamaterial platforms.

cond-mat.mtrl-sci↗

Understanding and Controlling V-Doping and S-Vacancy Behavior in Two-Dimensional Semiconductors- Toward Predictive Design

Doping in transition metal dichalcogenide (TMD) monolayers provides a powerful method to precisely tailor their electronic, optical, and catalytic properties for advanced technological applications, including optoelectronics, catalysis, and quantum technologies. However, doping efficiency and outcomes in these materials are strongly influenced by the complex interactions between introduced dopants and intrinsic defects, particularly sulfur vacancies. This coupling between dopants and defects can lead to distinctly different behaviors depending on doping concentration, presenting significant challenges in the predictable and controlled design of TMD properties. For example, in this work we systematically varied the p-type vanadium (V) doping density in tungsten disulfide (WS2) monolayers and observed a transition in doping behavior. At low concentrations, V-dopants enhance the native optical properties of WS2, as evidenced by increased photoluminescence, without introducing new electronic states. However, at higher concentrations, V-dopants promote the formation of vanadium-sulfur vacancy complexes that generate mid-gap states, with energies that can be precisely tuned by controlling the vanadium concentration. Using a combination of excitation- and temperature-dependent photoluminescence microscopy, atomic-resolution scanning transmission electron microscopy, and first-principles calculations, we identify attractive interactions between p-type V-dopants and n-type monosulfur vacancies. Our results provide mechanistic understanding of how enthalpic dopant-defect interactions versus entropic effects govern the balance between property enhancement versus perturbation of transition metal dichalcogenides and suggest a pathway toward the rational design of doping strategies for next-generation optoelectronic, catalytic, and quantum devices.

cond-mat.mtrl-sci↗

Giant and Tunable Bosonic Quantum Interference Induced by Two-Dimensional Metals

Harnessing quantum interference among bosons provides significant opportunities as bosons often carry longer coherence time than fermions. As an example of quantum interference, Fano resonance involving phonons or photons describes the coupling between discrete and continuous states, signified by an asymmetric spectral lineshape. Utilizing photon-based Fano resonance, molecule sensing with ultra-high sensitivity and ultrafast optical switching has been realized. However, phonon-based Fano resonance, which would expand the application space to a vaster regime, has been less exploited because of the weak coupling between discrete phonons with continuous states such as electronic continuum. In this work, we report the discovery of giant phonon-based Fano resonance in a graphene/2D Ag/SiC heterostructure. The Fano asymmetry, being proportional to the coupling strength, exceeds prior reports by two orders of magnitude. This Fano asymmetry arises from simultaneous frequency and lifetime matching between discrete and continuous phonons of SiC. The introduction of 2D Ag layers restructures SiC at the interface and facilitates resonant scattering to further enhance the Fano asymmetry, which is not achievable with conventional Ag thin films. With these unique properties, we demonstrated that the phonon-based Fano resonance can be used for ultrasensitive molecule detection at the single-molecule level. Our work highlights strong Fano resonance in the phononic system, opening avenues for engineering quantum interference based on bosons. Further, our findings provide opportunities for advancing phonon-related applications, including biochemical sensing, quantum transduction, and superconductor-based quantum computing.

cond-mat.mtrl-sci↗

iPAL: A Machine Learning Based Smart Healthcare Framework For Automatic Diagnosis Of Attention Deficit/Hyperactivity Disorder (ADHD)

ADHD is a prevalent disorder among the younger population. Standard evaluation techniques currently use evaluation forms, interviews with the patient, and more. However, its symptoms are similar to those of many other disorders like depression, conduct disorder, and oppositional defiant disorder, and these current diagnosis techniques are not very effective. Thus, a sophisticated computing model holds the potential to provide a promising diagnosis solution to this problem. This work attempts to explore methods to diagnose ADHD using combinations of multiple established machine learning techniques like neural networks and SVM models on the ADHD200 dataset and explore the field of neuroscience. In this work, multiclass classification is performed on phenotypic data using an SVM model. The better results have been analyzed on the phenotypic data compared to other supervised learning techniques like Logistic regression, KNN, AdaBoost, etc. In addition, neural networks have been implemented on functional connectivity from the MRI data of a sample of 40 subjects provided to achieve high accuracy without prior knowledge of neuroscience. It is combined with the phenotypic classifier using the ensemble technique to get a binary classifier. It is further trained and tested on 400 out of 824 subjects from the ADHD200 data set and achieved an accuracy of 92.5% for binary classification The training and testing accuracy has been achieved upto 99% using ensemble classifier.

cs.AI↗

Dropout Inference with Non-Uniform Weight Scaling

Dropout as regularization has been used extensively to prevent overfitting for training neural networks. During training, units and their connections are randomly dropped, which could be considered as sampling many different submodels from the original model. At test time, weight scaling and Monte Carlo approximation are two widely applied approaches to approximate the outputs. Both approaches work well practically when all submodels are low-bias complex learners. However, in this work, we demonstrate scenarios where some submodels behave closer to high-bias models and a non-uniform weight scaling is a better approximation for inference.

cs.LG↗

Design Rule Checking with a CNN Based Feature Extractor

Design rule checking (DRC) is getting increasingly complex in advanced nodes technologies. It would be highly desirable to have a fast interactive DRC engine that could be used during layout. In this work, we establish the proof of feasibility for such an engine. The proposed model consists of a convolutional neural network (CNN) trained to detect DRC violations. The model was trained with artificial data that was derived from a set of $50$ SRAM designs. The focus in this demonstration was metal 1 rules. Using this solution, we can detect multiple DRC violations 32x faster than Boolean checkers with an accuracy of up to 92. The proposed solution can be easily expanded to a complete rule set.

cs.LG↗

ORL: Reinforcement Learning Benchmarks for Online Stochastic Optimization Problems

Reinforcement Learning (RL) has achieved state-of-the-art results in domains such as robotics and games. We build on this previous work by applying RL algorithms to a selection of canonical online stochastic optimization problems with a range of practical applications: Bin Packing, Newsvendor, and Vehicle Routing. While there is a nascent literature that applies RL to these problems, there are no commonly accepted benchmarks which can be used to compare proposed approaches rigorously in terms of performance, scale, or generalizability. This paper aims to fill that gap. For each problem we apply both standard approaches as well as newer RL algorithms and analyze results. In each case, the performance of the trained RL policy is competitive with or superior to the corresponding baselines, while not requiring much in the way of domain knowledge. This highlights the potential of RL in real-world dynamic resource allocation problems.

cs.LG↗

Regularizing deep networks using efficient layerwise adversarial training

Adversarial training has been shown to regularize deep neural networks in addition to increasing their robustness to adversarial examples. However, its impact on very deep state of the art networks has not been fully investigated. In this paper, we present an efficient approach to perform adversarial training by perturbing intermediate layer activations and study the use of such perturbations as a regularizer during training. We use these perturbations to train very deep models such as ResNets and show improvement in performance both on adversarial and original test data. Our experiments highlight the benefits of perturbing intermediate layer activations compared to perturbing only the inputs. The results on CIFAR-10 and CIFAR-100 datasets show the merits of the proposed adversarial training approach. Additional results on WideResNets show that our approach provides significant improvement in classification accuracy for a given base model, outperforming dropout and other base models of larger size.

cs.CV↗

Learning from Synthetic Data: Addressing Domain Shift for Semantic Segmentation

Visual Domain Adaptation is a problem of immense importance in computer vision. Previous approaches showcase the inability of even deep neural networks to learn informative representations across domain shift. This problem is more severe for tasks where acquiring hand labeled data is extremely hard and tedious. In this work, we focus on adapting the representations learned by segmentation networks across synthetic and real domains. Contrary to previous approaches that use a simple adversarial objective or superpixel information to aid the process, we propose an approach based on Generative Adversarial Networks (GANs) that brings the embeddings closer in the learned feature space. To showcase the generality and scalability of our approach, we show that we can achieve state of the art results on two challenging scenarios of synthetic to real domain adaptation. Additional exploratory experiments show that our approach: (1) generalizes to unseen domains and (2) results in improved alignment of source and target distributions.

cs.CV↗