Showing 1–50 of 194 results for author: Tiwari, A

A Leakage-Free Stacked Ensemble Method for Multiclass Classification

Authors: S. P. Sharmila, Aruna Tiwari

Abstract: Multiclass classification is a fundamental problem across a wide range of domains. It is still challenging due to possession of high inter-class similarity, class imbalance datasets, and variability in data distributions. Rule-based classifiers such as XGBoost often achieve stronger performance on structured features, but they are limited in capturing smooth functional relationships among variable… ▽ More Multiclass classification is a fundamental problem across a wide range of domains. It is still challenging due to possession of high inter-class similarity, class imbalance datasets, and variability in data distributions. Rule-based classifiers such as XGBoost often achieve stronger performance on structured features, but they are limited in capturing smooth functional relationships among variables. Similarly, neural network models can represent complex nonlinear interactions but frequently suffer from overfitting and generalization issues. To address these limitations, we propose LFS-FRAME, a Leakage-Free Stacked ensemble framework that integrates functional learning using Kolmogorov-Arnold Networks (KAN) and rule-based learning via XGBoost for robust multiclass classification. The proposed framework constructs unbiased meta-features by employing a strict out-of-fold stacking strategy to ensure complete isolation between training and validation data hence preventing performance leakage. By learning over probabilistic outputs from heterogeneous base learners, the meta-classifier effectively exploits both global functional patterns and sharp decision boundaries present in the complex data. Experimental evaluations on multi-class datasets demonstrate that LFS-FRAME improves performance metrics, and overall accuracy is 89.85% in identifying major families and 81.74% in identifying sub-families relative to strong single-model baselines. These results highlight the effectiveness of leakage-free functional and rule-based stacking for reliable and generalizable multiclass classification. △ Less

Submitted 24 July, 2026; originally announced July 2026.

Comments: 7 pages, 3 figures, This paper is presented at IEEE World Congress on Computational Intelligence (WCCI 2026) June 2026, Maastricht, The Netherlands

A Measurement Study on the Adoption of Pledges and Unveils in the OpenBSD Operating System

Authors: Jukka Ruohonen, Krzysztof Sierszecki, Abhishek Tiwari

Abstract: The paper presents a longitudinal measurement study on the adoption of the pledge and unveil system calls in OpenBSD. These system calls are used to sandbox programs and libraries. Given a dataset covering 19 releases, many programs and libraries were modified to use the system calls already before their introductions in official releases. The adoption rates have also steadily grown; a linear tren… ▽ More The paper presents a longitudinal measurement study on the adoption of the pledge and unveil system calls in OpenBSD. These system calls are used to sandbox programs and libraries. Given a dataset covering 19 releases, many programs and libraries were modified to use the system calls already before their introductions in official releases. The adoption rates have also steadily grown; a linear trend provides a coarse but sensible heuristic. Although particularly programs residing in /usr/bin and /usr/sbin have been modified to use the system calls, the sizes of programs and libraries do not correlate well with the amounts of pledge and unveil system calls invoked. Regarding the pledges made, standard input and output operations have frequently been requested, although the full fine-grained arsenal offered by pledge has generally been utilized in OpenBSD. The same observation is seen in that particularly read operations to given paths have frequently been unveiled. All in all, the measurement results indicate that the adoption of system call minimization and sandboxing techniques is not necessarily as troublesome as has often been discussed in the literature. △ Less

Submitted 3 July, 2026; originally announced July 2026.

Comments: Proceedings of the IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER 2026), Limassol, IEEE, pp. 1-6

$M^3 QuestionIng$: Multi-modal Multi-span Medical Question Answering

Authors: Anisha Saha, Vaibhav Rathore, Abhisek Tiwari, Akash Ghosh, Sai Ruthvik Edara, Sriparna Saha

Abstract: The growing adoption of AI in healthcare, particularly in preventive care, highlights the critical need for accessibility and precision in Medical Question Answering (MedQA). In recent years, significant efforts have been made to develop multi-span medical question-answering systems, where the answer to a query may span multiple sections or paragraphs of a source document. However, existing system… ▽ More The growing adoption of AI in healthcare, particularly in preventive care, highlights the critical need for accessibility and precision in Medical Question Answering (MedQA). In recent years, significant efforts have been made to develop multi-span medical question-answering systems, where the answer to a query may span multiple sections or paragraphs of a source document. However, existing systems fall short of aligning with real-world scenarios, where source documents often include both textual and visual content, requiring answers to incorporate images for better comprehension. To address this gap, we propose $M^3QAFrame$, a multi-modal, multi-span medical question-answering framework that leverages visual cues to enhance the generation of comprehensive answers drawn from diverse textual and visual spans. The model takes the context, query, and images as input and outputs an answer containing both textual answers and relevant images. The text and image embeddings are processed using a transformer-based architecture to determine the sentence and image relevance. We curate a multi-modal, multi-span medical question-answering ($M^3 QuestionIng$) dataset containing queries, medical contexts, associated medical images, and extractive answers. Additionally, each query-answer pair is labeled with user intent and query type to enhance query and context comprehension. Extensive experiments show that our approach consistently outperforms existing methods across various evaluation metrics. △ Less

Submitted 19 May, 2026; originally announced June 2026.

SCOPE: A Syndrome-Driven Control Plane for QEC-Enabled Quantum Networks

Authors: Xiaojie Fan, Zian Wang, Ashutosh Tiwari, Himanshu Gupta

Abstract: As quantum networks evolve from experimental testbeds to fault-tolerant systems, the primary performance metric shifts from physical link fidelity to end-to-end logical error rate. However, current control planes remain ill-equipped for this transition: routing decisions are typically decoupled from Quantum Error Correction (QEC) strategies, relying on topology or scalar fidelity metrics that fail… ▽ More As quantum networks evolve from experimental testbeds to fault-tolerant systems, the primary performance metric shifts from physical link fidelity to end-to-end logical error rate. However, current control planes remain ill-equipped for this transition: routing decisions are typically decoupled from Quantum Error Correction (QEC) strategies, relying on topology or scalar fidelity metrics that fail to predict how specific physical noise structures interact with logical codes. Optimizing this coupled route-and-code performance requires precise, real-time visibility into network error biases, yet traditional active tomography is operationally prohibitive due to throughput collapse and service interruption. We present SCOPE (Syndrome-based COntrol PlanE), a network-layer architecture that enables joint routing and coding optimization using purely passive telemetry. Instead of injecting probes, SCOPE harvests error syndromes -- the parity-check outcomes naturally generated by QEC decoders during user service. By aggregating these signals, SCOPE's inference engine reconstructs the network's time-varying error map, capturing complex, context-dependent noise correlations. This visibility drives a decision engine that proactively pushes optimal route-and-code configurations to source nodes. NetSquid and IBM-calibrated simulations show that SCOPE reduces estimation error by more than 60% relative to a standard EM baseline. In large-scale networks, this precision reduces logical error rates by 30-35% (up to 65%) against topology-aware baselines. △ Less

Submitted 7 June, 2026; originally announced June 2026.

Lingo_Research_Group at SemEval-2026 Task 9: Evaluating Prompt Variants for Polarization Detection

Authors: Pritam Kadasi, Anuj Tiwari, Mayank Singh

Abstract: Our submission presented in this paper is for SemEval-2026 Task 9: Multilingual Text Classification Challenge - Polarization Detection and it covers all three subtasks: (1) binary polarization detection, (2) polarization type classification and (3) polarization manifestation identification. We adopt a systematic approach of research on short designed prompts by considering twelve designed prompts… ▽ More Our submission presented in this paper is for SemEval-2026 Task 9: Multilingual Text Classification Challenge - Polarization Detection and it covers all three subtasks: (1) binary polarization detection, (2) polarization type classification and (3) polarization manifestation identification. We adopt a systematic approach of research on short designed prompts by considering twelve designed prompts that are different in terminology clarity, detail of the definition, guidance of reasoning and in-context examples use. The experiments are conducted using aya-101 and Gemma3-27B, with the latter chosen for the submission at the end of the development through performance considerations. Our system has an average macro level F1-score of 0.762 on Subtask 1, 0.587 on Subtask 2 and 0.444 on Subtask 3 with the average accuracy of 0.819, 0.678 and 0.498, respectively, on the official test set averaged among 22 languages, respectively. With cross-task and cross-lingual analysis, we demonstrate that prompt-based approaches can be used effectively to detect coarse grained polarization but encounter more and more difficulties as far as fine-grained and multi-label sociolinguistic classification is concerned. △ Less

Submitted 2 June, 2026; originally announced June 2026.

Comments: Accepted at the SemEval Workshop, ACL 2026

From Script to Semantics: Prompting Strategies for African NLI

Authors: Anuj Tiwari, Terry Oko-odion, Hannah Nwokocha

Abstract: Large language models (LLMs) are increasingly evaluated in multilingual settings, yet their inference behavior in low-resource African languages remains underexplored especially under pure prompting without fine-tuning. We present a systematic study of prompting strategies for Natural Language Inference (NLI) in Swahili, Yoruba, and Hausa using the AfriXNLI benchmark. We evaluate five prompting st… ▽ More Large language models (LLMs) are increasingly evaluated in multilingual settings, yet their inference behavior in low-resource African languages remains underexplored especially under pure prompting without fine-tuning. We present a systematic study of prompting strategies for Natural Language Inference (NLI) in Swahili, Yoruba, and Hausa using the AfriXNLI benchmark. We evaluate five prompting strategies Baseline (zero-shot), Script-Aware, Language Specific, Contrastive, and Native-Label Self-Translation (NL-STP) across two mid-sized open weight models (Llama3.2-3B and Gemma3-4B). To isolate the effect of prompt design, the effect of few-shot examples and Chain-of-Thought reasoning is eliminated in our study. We find a significant difference in performance of class wise across strategies with highly neutral class collapse and high prediction skew in some configurations. Contrastive prompting proves to be the most reliable and steadily improving strategy over language and model and has better balance of class behavior and balance of overall accuracy gains. Notably, well-constructed prompts are sufficient to beat more powerful baselines that are provided with few-shot prompts and Chain-of-Thought prompts. We have found that prompt formulation is essential to multilingual NLI with low-resource languages and that language aware decision structuring can be used to meaningfully enhance robustness in resource challenged settings. △ Less

Submitted 2 June, 2026; originally announced June 2026.

Comments: Accepted at the RAIL Workshop, LREC 2026

Sample-Size Scaling of the African Languages NLI Evaluation

Authors: Anuj Tiwari, Oluwapelumi Ogunremu, Terry Oko-odion, Jesujuwon Egbewale, Hannah Nwokocha

Abstract: African languages have very little labelled data, and it is unclear if augmenting the quantity of annotation data reliably enhances downstream performance. The study is a systematic sample-size scaling study of natural language inference (NLI) on 16 African languages based on the AfriXNLI benchmark. Under controlled conditions, two multilingual transformer models with roughly 0.6B parameters XLM-R… ▽ More African languages have very little labelled data, and it is unclear if augmenting the quantity of annotation data reliably enhances downstream performance. The study is a systematic sample-size scaling study of natural language inference (NLI) on 16 African languages based on the AfriXNLI benchmark. Under controlled conditions, two multilingual transformer models with roughly 0.6B parameters XLM-R Large fine-tuned on XNLI and AfroXLM-R Large are tested on sample sizes of between 50 and 500 labeled examples and average their results across random subsampling runs. As opposed to the usual belief of monotonic increase with increased data, we find a strongly language sensitive and often non-monotonic scaling behavior. Some languages show early saturation or decrease in performance with sample size as well as high variance in low resource regimes. These results indicate that the volume of data is not enough to guarantee stable profits to African NLI, creating the necessity of language sensitive datasets creation and stronger multi-lingual modelling strategies. △ Less

Submitted 2 June, 2026; originally announced June 2026.

Comments: Accepted at the AfricaNLP Workshop, EACL 2026

Turning Back Without Forgetting: Selective Backward Refinement for Parameter-Efficient Continual Learning

Authors: Anushka Tiwari, Kaiyi Ji

Abstract: While prompt-based parameter-efficient continual learning mitigates catastrophic forgetting by isolating task-specific prompts, this isolation also limits later tasks from improving earlier ones, leaving backward knowledge transfer underexplored. We address this limitation by proposing Selective bAckward refinement for positive Backward knowledge transfER (SABER), a replay-free framework that enab… ▽ More While prompt-based parameter-efficient continual learning mitigates catastrophic forgetting by isolating task-specific prompts, this isolation also limits later tasks from improving earlier ones, leaving backward knowledge transfer underexplored. We address this limitation by proposing Selective bAckward refinement for positive Backward knowledge transfER (SABER), a replay-free framework that enables controlled backward transfer in prompt-based continual learning. SABER determines when backward refinement is beneficial using complementary task-correlation criteria based on prompt-gradient geometry and loss-distribution similarity, and how to perform refinement safely by restricting updates to non-interfering directions in the prompt parameter space. Extensive experiments across multiple continual learning benchmarks and diverse pretrained backbones, including T5-Large, LLaMA, and Qwen, demonstrate that SABER consistently achieves positive backward transfer while maintaining strong overall average performance. Code is available at https://github.com/OptMN-Lab/SABER-ICML-2026/. △ Less

Submitted 7 June, 2026; v1 submitted 31 May, 2026; originally announced June 2026.

Comments: Accepted at ICML 2026

Advancing Creative Physical Intelligence in Large Multimodal Models

Authors: Cheng Qian, Hyeonjeong Ha, Jiayu Liu, Jeonghwan Kim, Emre Can Acikgoz, Bingxuan Li, Kunlun Zhu, Jiateng Liu, Aditi Tiwari, Zhenhailong Wang, Xiusi Chen, Mahdi Namazifar, Heng Ji

Abstract: Large multimodal models (LMMs) have rapidly advanced in perception and reasoning; however, it remains unclear whether these capabilities generalize to discovering visually grounded solutions in open-ended environments, beyond pattern recognition. In such settings, intelligence requires more than answering well-posed questions: it involves identifying how elements in a scene can be repurposed in no… ▽ More Large multimodal models (LMMs) have rapidly advanced in perception and reasoning; however, it remains unclear whether these capabilities generalize to discovering visually grounded solutions in open-ended environments, beyond pattern recognition. In such settings, intelligence requires more than answering well-posed questions: it involves identifying how elements in a scene can be repurposed in non-obvious yet physically feasible ways. This form of creative problem-solving is central to human intelligence, but remains largely untested in current benchmarks. To evaluate this ability, we introduce MM-CreativityBench, a benchmark for affordance-grounded creative tool use in visually rich, physically constrained environments. Each instance presents a scenario image with structured views of candidate entities and their parts, enabling fine-grained, interactive evaluation of how models iteratively inspect the scene, identify relevant affordances, and compose visually and physically grounded solutions. Our experiments show that current LMMs often fall short, not due to lack of generative capability, but because they do not sustain grounded exploration. Models often overlook relevant entities, under-examine critical parts, or hallucinate attributes not grounded in the image. Motivated by this failure mode, we propose affordance-grounded alignment, which casts creative tool use as a preference learning problem. Using Direct Preference Optimization, we encourage models to prefer attribute-affordance reasoning grounded in visual evidence over hallucinated alternatives. In addition, we incorporate supervision derived from an affordance knowledge base to guide broader entity exploration and multi-turn planning. Our results show consistent gains in selecting the correct entities and parts, while substantially reducing hallucination and grounding-related errors. △ Less

Submitted 29 May, 2026; v1 submitted 25 May, 2026; originally announced May 2026.

Comments: 51 Pages, 9 Figures, 7 Tables, Previous Work CreativityBench: arXiv:2605.02910

A Reproducibility Analysis of PO4ISR: Diagnosing and Mitigating Semantic Drift in LLM-Based Session Recommendation

Authors: Aditya Tiwari, Konduri Naga Lakshmi Rekha, Rajesh Kumar Mundotiya

Abstract: Reasoning-based Large Language Models (LLMs) like PO4ISR have set new benchmarks in session-based recommendation. However, the reproducibility of their reasoning capabilities across diverse semantic domains remains unexplored. In this work, we conduct a rigorous reproducibility study of PO4ISR to assess its generalization limits. Our analysis reveals a critical failure mode: standard reasoning pro… ▽ More Reasoning-based Large Language Models (LLMs) like PO4ISR have set new benchmarks in session-based recommendation. However, the reproducibility of their reasoning capabilities across diverse semantic domains remains unexplored. In this work, we conduct a rigorous reproducibility study of PO4ISR to assess its generalization limits. Our analysis reveals a critical failure mode: standard reasoning prompts suffer from severe contextual drift in long sessions, leading to performance degradation on semantically complex datasets like Games and Bundle. To quantify and resolve this stability gap, we introduce PO4ISR++, a robustness-enhanced implementation that integrates reflexive prompting and consistent rank detection. Unlike the original static prompting strategy, our approach dynamically adapts to cross-domain cues. We benchmark both the original implementation and our robust variant on ML-1M, Games, and Bundle. Our results confirm that while the original model struggles in new domains, our reproducible extension restores performance, yielding a stabilized gain of up to 54% on Games and 96% on Bundle. We release open-source artifacts, including the reproduced baseline and our enhanced framework, to facilitate reliable future research in LLM-based recommendation. △ Less

Submitted 29 April, 2026; originally announced May 2026.

Push and Pull in Community College Cross-Enrollment: Remoteness, Articulation, and Student Mobility

Authors: Conrad Borchers, Robin Schmucker, Ashutosh Tiwari, Zachary A. Pardos

Abstract: Cross-enrollment across institutions can expand access to courses and support student progression. Still, little is known about how geographic constraints and institutional policies jointly shape cross-enrollment within community college (CC) systems. We adopt a push-pull framework: geographic remoteness constrains feasible cross-institution mobility, while credit mobility may attract enrollment e… ▽ More Cross-enrollment across institutions can expand access to courses and support student progression. Still, little is known about how geographic constraints and institutional policies jointly shape cross-enrollment within community college (CC) systems. We adopt a push-pull framework: geographic remoteness constrains feasible cross-institution mobility, while credit mobility may attract enrollment expressed as articulation (CC-to-university: credit toward a four-year partner) and course equivalencies (CC-to-CC: equivalencies across the system). Using de-identified administrative records from a 12-institution community college system (100,547 students; 1,290,311 course enrollments), we quantify outgoing and incoming cross-enrollment and relate these patterns to institutional remoteness and credit mobility. We find that less remote colleges exhibit higher outgoing and incoming cross-enrollment than more remote colleges. Further, cross-enrolled students are more likely to take articulated courses, and institutions with higher equivalency ratios receive higher incoming cross-enrollment (8.62% vs. 6.70%). This association was slightly stronger at more remote colleges. This study demonstrates how analysis of complex college systems can surface factors shaping student mobility and inform the design of cross-enrollment and articulation policies in CC systems. △ Less

Submitted 16 May, 2026; originally announced May 2026.

Comments: Accepted as work-in-progress paper to the 13th ACM Conference on Learning @ Scale (L@S '26)

Orth-Dion: Eliminating Geometric Mismatch in Distributed Low-Rank Spectral Optimization

Authors: Tatsuhiro Nakamori, Laura Gomezjurado Gonzalez, Ganesh Talluri, Ansh Tiwari, Hideyuki Kawashima, Ioannis Mitliagkas, Guillaume Rabusseau, Hiroki Naganuma

Abstract: Low-rank gradient compression reduces communication in distributed training by representing updates with rank-$r$ factors. Dion is a recent method that approximates Muon, a spectral optimizer that orthogonalizes momentum, using one step of power iteration followed by column normalization (rescaling each column of the right factor to unit length). This makes it compatible with fully sharded data pa… ▽ More Low-rank gradient compression reduces communication in distributed training by representing updates with rank-$r$ factors. Dion is a recent method that approximates Muon, a spectral optimizer that orthogonalizes momentum, using one step of power iteration followed by column normalization (rescaling each column of the right factor to unit length). This makes it compatible with fully sharded data parallel training, but it converges more slowly than full-rank spectral methods. We show that this gap is geometric: column normalization does not yield the rank-$r$ polar factor that Muon implicitly targets, so the resulting direction violates the dual-norm constraint of the low-rank spectral geometry, and the rate picks up an extra factor of $\sqrt{r}$ even though the low-rank approximation of the gradient itself is accurate. The same mismatch enters the smoothness term and the error-feedback recursion in the analysis, which has a knock-on effect on empirical performance. We propose Orth-Dion, which replaces column normalization with QR orthogonalization of the right factor. Under non-Euclidean smoothness, with $L_r$ the curvature constant along rank-$r$ directions, Orth-Dion attains rate $O(\sqrt{L_r/T})$, matching exact spectral methods at the same per-step communication cost as Dion. The proof removes the bounded-drift assumption common in prior error-feedback analyses via a self-consistent fixed-point argument, and uses a time-averaged contraction that only requires the error sequence to contract on average rather than at every step. Experiments on large-scale language model pre-training validate the predicted $\sqrt{r}$ scaling and show that Orth-Dion closes the convergence gap to Muon at Dion's communication cost. △ Less

Submitted 7 May, 2026; originally announced May 2026.

Comments: 24 pages, 3 figures, 11 tables

LIFT: Last-Mile Fine-Tuning for Table Explicitation

Authors: Divij Khaitan, Ashish Tiwari

Abstract: We propose last-mile fine-tuning, or Lift, a pipeline in which a pre-trained large language model extracts an initial table from unstructured clipboard text, and a fine-tuned small language model (1B-24B parameters SLM) repairs errors in the extracted table. On a benchmark of 2,596 tables from three datasets, Lift matches or exceeds end-to-end SLM fine-tuning on tree-edit-distance-based similarity… ▽ More We propose last-mile fine-tuning, or Lift, a pipeline in which a pre-trained large language model extracts an initial table from unstructured clipboard text, and a fine-tuned small language model (1B-24B parameters SLM) repairs errors in the extracted table. On a benchmark of 2,596 tables from three datasets, Lift matches or exceeds end-to-end SLM fine-tuning on tree-edit-distance-based similarity (TEDS) metric while requiring as little as 1,000 training examples - where it outperforms end-to-end fine-tuning by up to 0.144 TEDS points. We term this approach last-mile fine-tuning and show it also more robust to input format variability. Comparisons with self-debug and end-to-end fine-tuning approaches show that last-mile fine-tuning provides an attractive option when training data is limited or when robustness to input variation is sought without compromising on accuracy. △ Less

Submitted 13 May, 2026; originally announced May 2026.

Comments: 9 pages, 1 figure, 3 tables

Skew Polycyclic Codes over $\frac{\mathbb{F}_{p^m}[u]}{\langle u^t \rangle}$

Authors: Akanksha Tiwari, Ritumoni Sarma

Abstract: Let $R^t$ denote the finite chain ring $\frac{\mathbb{F}_{p^m}[u]}{\langle u^t \rangle},$ where $p$ is a prime and $t$ is a positive integer. In this article, for a prime $p$ and an automorphism $θ$ of $\mathbb{F}_{p^m}$, we give the structure of the left ideals of the ring $\frac{R^t[x,Θ]}{\langle f(x) \rangle},$ where $f(x)$ is in the center of the skew polynomial ring $R^t[x,Θ]$ and $Θ$ is an a… ▽ More Let $R^t$ denote the finite chain ring $\frac{\mathbb{F}_{p^m}[u]}{\langle u^t \rangle},$ where $p$ is a prime and $t$ is a positive integer. In this article, for a prime $p$ and an automorphism $θ$ of $\mathbb{F}_{p^m}$, we give the structure of the left ideals of the ring $\frac{R^t[x,Θ]}{\langle f(x) \rangle},$ where $f(x)$ is in the center of the skew polynomial ring $R^t[x,Θ]$ and $Θ$ is an automorphism of $R^t$ that extends $θ$ with $Θ(u)=u$. These left ideals are also referred to as skew polycyclic codes associated to $f(x).$ In particular, when the central element \( f(x)\) is \(x^{np^s}-λ\), where $λ=λ_0+uλ_1+\cdots +u^{t-1}λ_{t-1}$ with $λ_0\ne0,$ and \( n=1,2 \), we give a more refined form of the left ideals (which are also called skew constacyclic codes). Moreover, the case $λ_1 \neq 0$ is analyzed in detail, yielding a simpler form of generators that reveals a more refined structural characterization of the left ideals. As an application, for $n=1,t=3$ and $n=2,t=2$ we give a full description of the left ideals by including certain necessary conditions that were omitted in available literature, preventing the different classes of left ideals from being mutually disjoint and in certain cases, we also compute $i$-th torsion codes. △ Less

Submitted 13 May, 2026; originally announced May 2026.

MSC Class: 94B05; 94B15; 16S36; 16S90

Constacyclic codes of length $np^s$ over $\frac{\mathbb{F}_{p^m}[u]}{\langle u^t\rangle}$: Torsions and Cardinalities

Authors: Akanksha Tiwari, Pramod Kanwar, Ritumoni Sarma

Abstract: The purpose of this article is to study constacyclic codes of length $np^s$ over $R^t:=\frac{\mathbb{F}_{p^m}[u]}{\langle u^t \rangle },$ where $t$ is a natural number and $\gcd(n,p)=1$. We give generators of all the ideals of $R^{t,n}_δ:=\frac{R^t[x]}{\langle x^{np^s}-δ\rangle},$ where $δ= δ_0+uδ_1+\dots+u^{t-1}δ_{t-1}$ is a unit in $R^t$. For $n=1,\ 2, \ 3$ and $t=3$, we provide all types of ide… ▽ More The purpose of this article is to study constacyclic codes of length $np^s$ over $R^t:=\frac{\mathbb{F}_{p^m}[u]}{\langle u^t \rangle },$ where $t$ is a natural number and $\gcd(n,p)=1$. We give generators of all the ideals of $R^{t,n}_δ:=\frac{R^t[x]}{\langle x^{np^s}-δ\rangle},$ where $δ= δ_0+uδ_1+\dots+u^{t-1}δ_{t-1}$ is a unit in $R^t$. For $n=1,\ 2, \ 3$ and $t=3$, we provide all types of ideals (constacyclic codes) and also give the torsional degrees as well as cardinalities of these codes. △ Less

Submitted 12 May, 2026; originally announced May 2026.

MSC Class: 94B05; 94B15; 16P70; 13C12

CreativityBench: Evaluating Agent Creative Reasoning via Affordance-Based Tool Repurposing

Authors: Cheng Qian, Hyeonjeong Ha, Jiayu Liu, Jeonghwan Kim, Jiateng Liu, Bingxuan Li, Aditi Tiwari, Dwip Dalal, Zhenhailong Wang, Xiusi Chen, Mahdi Namazifar, Yunzhu Li, Heng Ji

Abstract: Recent advances in large language models have led to strong performance on reasoning and environment-interaction tasks, yet their ability for creative problem-solving remains underexplored. We study this capability through the lens of creative tool use, where a model repurposes available objects by reasoning about their affordances and attributes rather than relying on canonical usage. As a first… ▽ More Recent advances in large language models have led to strong performance on reasoning and environment-interaction tasks, yet their ability for creative problem-solving remains underexplored. We study this capability through the lens of creative tool use, where a model repurposes available objects by reasoning about their affordances and attributes rather than relying on canonical usage. As a first step, we introduce CreativityBench, a benchmark for evaluating affordance-based creativity in LLMs. To this end, we build a large-scale affordance knowledge base (KB) with 4K entities and 150K+ affordance annotations, explicitly linking objects, parts, attributes, and actionable uses. Building on this KB, we generate 14K grounded tasks that require identifying non-obvious yet physically plausible solutions under constraints. Evaluations across 10 state-of-the-art LLMs, including closed and open-source models, show that models can often select a plausible object, but fail to identify the correct parts, their affordances, and the underlying physical mechanism needed to solve the task, leading to a significant drop in performance. Furthermore, improvements from model scaling quickly saturate, strong general reasoning does not reliably translate to creative affordance discovery, and common inference-time strategies such as Chain-of-Thought yield limited gains. These results suggest that creative tool use remains a major challenge for current models, and that CreativityBench provides a useful testbed for studying this missing dimension of intelligence, with potential implications for planning and reasoning modules in future agents. △ Less

Submitted 6 May, 2026; v1 submitted 6 April, 2026; originally announced May 2026.

Comments: 57 Pages, 14 Tables, 27 Figures

Super Apriel: One Checkpoint, Many Speeds

Authors: SLAM Labs, :, Oleksiy Ostapenko, Raymond Li, Torsten Scholak, Alireza Mousavi-Hosseini, Aman Tiwari, Denis Kocetkov, Joel Lamy Poirier, Kelechi Ogueji, Nanda H Krishna, Rafael Pardinas, Sathwik Tejaswi Madhusudhan, Shruthan Radhakrishna, Srinivas Sunkara, Valerie Becaert

Abstract: We release Super Apriel, a 15B-parameter supernet in which every decoder layer provides four trained mixer choices -- Full Attention (FA), Sliding Window Attention (SWA), Kimi Delta Attention (KDA), and Gated DeltaNet (GDN). A placement selects one mixer per layer; placements can be switched between requests at serving time without reloading weights, enabling multiple speed presets from a single c… ▽ More We release Super Apriel, a 15B-parameter supernet in which every decoder layer provides four trained mixer choices -- Full Attention (FA), Sliding Window Attention (SWA), Kimi Delta Attention (KDA), and Gated DeltaNet (GDN). A placement selects one mixer per layer; placements can be switched between requests at serving time without reloading weights, enabling multiple speed presets from a single checkpoint. The shared checkpoint also enables speculative decoding without a separate draft model. The all-FA preset matches the Apriel 1.6 teacher on all reported benchmarks; recommended hybrid presets span $2.9\times$ to $10.7\times$ decode throughput at 96% to 77% quality retention, with throughput advantages that compound at longer context lengths. With four mixer types across 48 layers, the configuration space is vast. A surrogate that predicts placement quality from the per-layer mixer assignment makes the speed-quality landscape tractable and identifies the best tradeoffs at each speed level. We investigate whether the best configurations at each speed level can be identified early in training or only after convergence. Rankings stabilize quickly at 0.5B scale, but the most efficient configurations exhibit higher instability at 15B, cautioning against extrapolation from smaller models. Super Apriel is trained by stochastic distillation from a frozen Apriel 1.6 teacher, followed by supervised fine-tuning. We release the supernet weights, Fast-LLM training code, vLLM serving code, and a placement optimization toolkit. △ Less

Submitted 21 April, 2026; originally announced April 2026.

Comments: Models: https://huggingface.co/ServiceNow-AI/SuperApriel-15B-Base and https://huggingface.co/ServiceNow-AI/SuperApriel-15B-Instruct . Dev model: https://huggingface.co/ServiceNow-AI/SuperApriel-0.5B-Base . Training code: https://github.com/ServiceNow/Fast-LLM . Async RL: https://github.com/ServiceNow/pipeline-rl . Training logs: https://wandb.ai/servicenow-team/Super_Apriel

ACM Class: I.2.6; I.2.7

PCA-Driven Adaptive Sensor Triage for Edge AI Inference

Authors: Ankit Hemant Lade, Sai Krishna Jasti, Nikhil Sinha, Indar Kumar, Akanksha Tiwari

Abstract: Multi-channel sensor networks in industrial IoT often exceed available bandwidth. We propose PCA-Triage, a streaming algorithm that converts incremental PCA loadings into proportional per-channel sampling rates under a bandwidth budget. PCA-Triage runs in O(wdk) time with zero trainable parameters (0.67 ms per decision). We evaluate on 7 benchmarks (8--82 channels) against 9 baselines. PCA-Triag… ▽ More Multi-channel sensor networks in industrial IoT often exceed available bandwidth. We propose PCA-Triage, a streaming algorithm that converts incremental PCA loadings into proportional per-channel sampling rates under a bandwidth budget. PCA-Triage runs in O(wdk) time with zero trainable parameters (0.67 ms per decision). We evaluate on 7 benchmarks (8--82 channels) against 9 baselines. PCA-Triage is the best unsupervised method on 3 of 6 datasets at 50% bandwidth, winning 5 of 6 against every baseline with large effect sizes (r = 0.71--0.91). On TEP, it achieves F1 = 0.961 +/- 0.001 -- within 0.1% of full-data performance -- while maintaining F1 > 0.90 at 30% budget. Targeted extensions push F1 to 0.970. The algorithm is robust to packet loss and sensor noise (3.7--4.8% degradation under combined worst-case). △ Less

Submitted 6 April, 2026; originally announced April 2026.

Comments: 16 pages, 13 figures, 7 benchmarks

ACM Class: I.2.6; C.3

Structure of Polycyclic Codes over $\frac{\mathbb{F}_{p^m}[u]}{\langle u^t \rangle}$ and their Cardinalities

Authors: Akanksha Tiwari, Pramod Kanwar, Ritumoni Sarma

Abstract: The purpose of this article is to study polycyclic codes over the ring $\frac{\mathbb{F}_{p^m}[u]}{\langle u^t \rangle}, \,t \geq 1$, and their associated torsion codes. It is shown that if $φ$ is a surjective ring homomorphism from a commutative ring $A$ to a Noetherian ring $B$ with $ ker(φ)=\langle π\rangle$ then for every ideal $I$ of $A$, there exists $a_1,a_2,\dots,a_n$ in $I$ such that… ▽ More The purpose of this article is to study polycyclic codes over the ring $\frac{\mathbb{F}_{p^m}[u]}{\langle u^t \rangle}, \,t \geq 1$, and their associated torsion codes. It is shown that if $φ$ is a surjective ring homomorphism from a commutative ring $A$ to a Noetherian ring $B$ with $ ker(φ)=\langle π\rangle$ then for every ideal $I$ of $A$, there exists $a_1,a_2,\dots,a_n$ in $I$ such that $I=\langle a_1,a_2,\dots,a_n\rangle+π(I:π)$. Using this, we obtain generators of all ideals of the ring $\frac{\frac{\mathbb{F}_{p^m}[u]}{\langle u^t \rangle}[x]}{\langle ω(x)\rangle},$ where $ω(x)\in \frac{\mathbb{F}_{p^m}[u]}{\langle u^t \rangle}[x] $. For the case when $ω(x)=f(x)^{p^s}$ where $f(x)$ is an irreducible polynomial in $\mathbb{F}_{p^m}[x]$ and $s$ is a non-negative integer, we obtain several other results, including computation of torsion ideals and their torsional degrees when $t=4$. We use the torsional degree to compute the cardinality of polycyclic codes over the ring $\frac{\mathbb{F}_{p^m}[u]}{\langle u^4 \rangle}$ and illustrate the result with some examples that verify the computed cardinality. △ Less

Submitted 11 August, 2026; v1 submitted 5 April, 2026; originally announced April 2026.

MSC Class: 94B05; 94B15; 16P70; 13C12

Regime-Calibrated Fleet Repositioning with a Spatial Queue-Regret Decomposition

Authors: Indar Kumar, Akanksha Tiwari

Abstract: Ride-hailing and autonomous mobility-on-demand operators reposition idle supply before future demand is fully observed. We study a retrieval-calibrated predict-then-optimize approach for this problem: historical demand regimes are matched to the current query block, combined into a calibrated demand prior, and passed to a fleet-balancing controller. The paper makes three contributions. First, we t… ▽ More Ride-hailing and autonomous mobility-on-demand operators reposition idle supply before future demand is fully observed. We study a retrieval-calibrated predict-then-optimize approach for this problem: historical demand regimes are matched to the current query block, combined into a calibrated demand prior, and passed to a fleet-balancing controller. The paper makes three contributions. First, we train a leakage-safe similarity gate whose objective penalizes demand error, pickup spatial mismatch, and queue shortage risk rather than retrieval rank alone. Second, we develop a spatial queue-regret decomposition for a stable queueing surrogate, linking demand-field error to wait through queueing sensitivity, allocator sensitivity, and Wasserstein pickup mismatch. Third, we evaluate learned retrieval and external-style rebalancing baselines in a common simulator. In the calibrated-demand gate experiment, across eight New York City scenarios and ten seeds, the spatial gate reduces mean wait to 82.3s, compared with 85.3s for hand-tuned similarity and 85.8s for a distributional-only baseline. In a separate replay-demand controller comparison, a scenario chance-MPC analog and a share-target transportation LP improve on Wen-style rebalancing (92.2s/92.2s vs. 100.1s), a reduced GPR chance-MPC comparator is intermediate at 94.4s, and an oracle MPC diagnostic is 91.3s. △ Less

Submitted 10 May, 2026; v1 submitted 4 April, 2026; originally announced April 2026.

Comments: 13 pages, 4 figures, 8 tables. Code: https://github.com/IndarKarhana/regime-calibrated-dispatch

MSC Class: 90B06; 90B20; 90C05 ACM Class: I.2.8; G.1.6; J.7

RuleForge: Automated Generation and Validation for Web Vulnerability Detection at Scale

Authors: Ayush Garg, Sophia Hager, Jacob Montiel, Aditya Tiwari, Michael Gentile, Zach Reavis, David Magnotti, Wayne Fullen

Abstract: Security teams face a challenge: the volume of newly disclosed Common Vulnerabilities and Exposures (CVEs) far exceeds the capacity to manually develop detection mechanisms. In 2025, the National Vulnerability Database published over 48,000 new vulnerabilities, motivating the need for automation. We present RuleForge, an AWS internal system that automatically generates detection rules--JSON-based… ▽ More Security teams face a challenge: the volume of newly disclosed Common Vulnerabilities and Exposures (CVEs) far exceeds the capacity to manually develop detection mechanisms. In 2025, the National Vulnerability Database published over 48,000 new vulnerabilities, motivating the need for automation. We present RuleForge, an AWS internal system that automatically generates detection rules--JSON-based patterns that identify malicious HTTP requests exploiting specific vulnerabilities--from structured Nuclei templates describing CVE details. Nuclei templates provide standardized, YAML-based vulnerability descriptions that serve as the structured input for our rule generation process. This paper focuses on RuleForge's architecture and operational deployment for CVE-related threat detection, with particular emphasis on our novel LLM-as-a-judge (Large Language Model as judge) confidence validation system and systematic feedback integration mechanism. This validation approach evaluates candidate rules across two dimensions--sensitivity (avoiding false negatives) and specificity (avoiding false positives)--achieving AUROC of 0.75 and reducing false positives by 67% compared to synthetic-test-only validation in production. Our 5x5 generation strategy (five parallel candidates with up to five refinement attempts each) combined with continuous feedback loops enables systematic quality improvement. We also present extensions enabling rule generation from unstructured data sources and demonstrate a proof-of-concept agentic workflow for multi-event-type detection. Our lessons learned highlight critical considerations for applying LLMs to cybersecurity tasks, including overconfidence mitigation and the importance of domain expertise in both prompt design and quality review of generated rules through human-in-the-loop validation. △ Less

Submitted 2 April, 2026; originally announced April 2026.

Comments: 11 pages, 10 figures. To be submitted to CAMLIS 2026

RG-TTA: Regime-Guided Meta-Control for Test-Time Adaptation in Streaming Time Series

Authors: Indar Kumar, Akanksha Tiwari, Sai Krishna Jasti, Ankit Hemant Lade

Abstract: Test-time adaptation (TTA) enables neural forecasters to adapt to distribution shifts in streaming time series, but existing methods apply the same adaptation intensity regardless of the nature of the shift. We propose Regime-Guided Test-Time Adaptation (RG-TTA), a meta-controller that continuously modulates adaptation intensity based on distributional similarity to previously-seen regimes. Using… ▽ More Test-time adaptation (TTA) enables neural forecasters to adapt to distribution shifts in streaming time series, but existing methods apply the same adaptation intensity regardless of the nature of the shift. We propose Regime-Guided Test-Time Adaptation (RG-TTA), a meta-controller that continuously modulates adaptation intensity based on distributional similarity to previously-seen regimes. Using an ensemble of Kolmogorov-Smirnov, Wasserstein-1, feature-distance, and variance-ratio metrics, RG-TTA computes a similarity score for each incoming batch and uses it to (i) smoothly scale the learning rate -- more aggressive for novel distributions, conservative for familiar ones -- and (ii) control gradient effort via loss-driven early stopping rather than fixed budgets, allowing the system to allocate exactly the effort each batch requires. As a supplementary mechanism, RG-TTA gates checkpoint reuse from a regime memory, loading stored specialist models only when they demonstrably outperform the current model (loss improvement >= 30%). RG-TTA is model-agnostic and strategy-composable: it wraps any forecaster exposing train/predict/save/load interfaces and enhances any gradient-based TTA method. We demonstrate three compositions -- RG-TTA, RG-EWC, and RG-DynaTTA -- and evaluate 6 update policies (3 baselines + 3 regime-guided variants) across 4 compact architectures (GRU, iTransformer, PatchTST, DLinear), 14 datasets (6 real-world multivariate benchmarks + 8 synthetic regime scenarios), and 4 forecast horizons (96, 192, 336, 720) under a streaming evaluation protocol with 3 random seeds (672 experiments total). Regime-guided policies achieve the lowest MSE in 156 of 224 seed-averaged experiments (69.6%), with RG-EWC winning 30.4% and RG-TTA winning 29.0%. Overall, RG-TTA reduces MSE by 5.7% vs TTA while running 5.5% faster; RG-EWC reduces MSE by 14.1% vs standalone EWC. △ Less

Submitted 29 March, 2026; originally announced March 2026.

Comments: 18 pages, 8 figures

MSC Class: 68T07 ACM Class: I.2.6; I.5.4

OmniPatch: A Universal Adversarial Patch for ViT-CNN Cross-Architecture Transfer in Semantic Segmentation

Authors: Aarush Aggarwal, Akshat Tomar, Amritanshu Tiwari, Sargam Goyal

Abstract: Robust semantic segmentation is crucial for safe autonomous driving, yet deployed models remain vulnerable to black-box adversarial attacks when target weights are unknown. Most existing approaches either craft image-wide perturbations or optimize patches for a single architecture, which limits their practicality and transferability. We introduce OmniPatch, a training framework for learning a univ… ▽ More Robust semantic segmentation is crucial for safe autonomous driving, yet deployed models remain vulnerable to black-box adversarial attacks when target weights are unknown. Most existing approaches either craft image-wide perturbations or optimize patches for a single architecture, which limits their practicality and transferability. We introduce OmniPatch, a training framework for learning a universal adversarial patch that generalizes across images and both ViT and CNN architectures without requiring access to target model parameters. △ Less

Submitted 21 March, 2026; originally announced March 2026.

Comments: 10 pages, 4 figures, ICLR 2026: Principled Design for Trustworthy AI

EnterpriseOps-Gym: Environments and Evaluations for Stateful Agentic Planning and Tool Use in Enterprise Settings

Authors: Shiva Krishna Reddy Malay, Shravan Nayak, Jishnu Sethumadhavan Nair, Sagar Davasam, Aman Tiwari, Sathwik Tejaswi Madhusudhan, Sridhar Krishna Nemala, Srinivas Sunkara, Sai Rajeswar

Abstract: Large language models are shifting from passive information providers to active agents intended for complex workflows. However, their deployment as reliable AI workers in enterprise is stalled by benchmarks that fail to capture the intricacies of professional environments, specifically, the need for long-horizon planning amidst persistent state changes and strict access protocols. In this work, we… ▽ More Large language models are shifting from passive information providers to active agents intended for complex workflows. However, their deployment as reliable AI workers in enterprise is stalled by benchmarks that fail to capture the intricacies of professional environments, specifically, the need for long-horizon planning amidst persistent state changes and strict access protocols. In this work, we introduce EnterpriseOps-Gym, a benchmark designed to evaluate agentic planning in realistic enterprise settings. Specifically, EnterpriseOps-Gym features a containerized sandbox with 164 database tables and 512 functional tools to mimic real-world search friction. Within this environment, agents are evaluated on 1,150 expert-curated tasks across eight mission-critical verticals (including Customer Service, HR, and IT). Our evaluation of 14 frontier models reveals critical limitations in state-of-the-art models: the top-performing Claude Opus 4.5 achieves only 37.4% success. Further analysis shows that providing oracle human plans improves performance by 14-35 percentage points, pinpointing strategic reasoning as the primary bottleneck. Additionally, agents frequently fail to refuse infeasible tasks (best model achieves 53.9%), leading to unintended and potentially harmful side effects. Our findings underscore that current agents are not yet ready for autonomous enterprise deployment. More broadly, EnterpriseOps-Gym provides a concrete testbed to advance the robustness of agentic planning in professional workflows. △ Less

Submitted 13 March, 2026; originally announced March 2026.

OSExpert: Computer-Use Agents Learning Professional Skills via Exploration

Authors: Jiateng Liu, Zhenhailong Wang, Rushi Wang, Bingxuan Li, Jeonghwan Kim, Aditi Tiwari, Pengfei Yu, Denghui Zhang, Heng Ji

Abstract: General-purpose computer-use agents have shown impressive performance across diverse digital environments. However, our new benchmark, OSExpert-Eval, indicates they remain far less helpful than human experts. Although inference-time scaling enables adaptation, these agents complete complex tasks inefficiently with degraded performance, transfer poorly to unseen UIs, and struggle with fine-grained… ▽ More General-purpose computer-use agents have shown impressive performance across diverse digital environments. However, our new benchmark, OSExpert-Eval, indicates they remain far less helpful than human experts. Although inference-time scaling enables adaptation, these agents complete complex tasks inefficiently with degraded performance, transfer poorly to unseen UIs, and struggle with fine-grained action sequences. To solve the problem, we introduce a GUI-based depth-first search (GUI-DFS) exploration algorithm to comprehensively explore and verify an environment's unit functions. The agent then exploits compositionality between unit skills to self-construct a curriculum for composite tasks. To support fine-grained actions, we curate a database of action primitives for agents to discover during exploration; these are saved as a skill set once the exploration is complete. We use the learned skills to improve the agent's performance and efficiency by (1) enriching agents with ready-to-use procedural knowledge, allowing them to plan only once for long trajectories and generate accurate actions, and (2) enabling them to end inference-time scaling earlier by realizing their boundary of capabilities. Extensive experiments show that our environment-learned agent takes a meaningful step toward expert-level computer use, achieving a around 20 percent performance gain on OSExpert-Eval and closing the efficiency gap to humans by around 80 percent △ Less

Submitted 9 March, 2026; originally announced March 2026.

Comments: 26 pages

Stress Tests REVEAL Fragile Temporal and Visual Grounding in Video-Language Models

Authors: Sethuraman T V, Savya Khosla, Aditi Tiwari, Vidya Ganesh, Rakshana Jayaprakash, Aditya Jain, Vignesh Srinivasakumar, Onkar Kishor Susladkar, Srinidhi Sunkara, Aditya Shanmugham, Rakesh Vaideeswaran, Abbaas Alif Mohamed Nishar, Simon Jenni, Derek Hoiem

Abstract: This work investigates a fundamental question: Do Video-Language Models (VidLMs) robustly account for video content, temporal sequence, and motion? Our investigation shows that, surprisingly, they often do not. We introduce REVEAL{}, a diagnostic benchmark that probes fundamental weaknesses of contemporary VidLMs through five controlled stress tests; assessing temporal expectation bias, reliance o… ▽ More This work investigates a fundamental question: Do Video-Language Models (VidLMs) robustly account for video content, temporal sequence, and motion? Our investigation shows that, surprisingly, they often do not. We introduce REVEAL{}, a diagnostic benchmark that probes fundamental weaknesses of contemporary VidLMs through five controlled stress tests; assessing temporal expectation bias, reliance on language-only shortcuts, video sycophancy, camera motion sensitivity, and robustness to spatiotemporal occlusion. We test leading open- and closed-source VidLMs and find that these models confidently describe reversed scenes as forward, answer questions while neglecting video content, agree with false claims, struggle with basic camera motion, and fail to aggregate temporal information amidst simple spatiotemporal masking. Humans, on the other hand, succeed at these tasks with ease. Alongside our benchmark, we provide a data pipeline that automatically generates diagnostic examples for our stress tests, enabling broader and more scalable evaluation. We will release our benchmark and code to support future research. △ Less

Submitted 11 February, 2026; originally announced February 2026.

BioME: A Resource-Efficient Bioacoustic Foundational Model for IoT Applications

Authors: Heitor R. Guimarães, Abhishek Tiwari, Mahsa Abdollahi, Anderson R. Avila, Tiago H. Falk

Abstract: Passive acoustic monitoring has become a key strategy in biodiversity assessment, conservation, and behavioral ecology, especially as Internet-of-Things (IoT) devices enable continuous in situ audio collection at scale. While recent self-supervised learning (SSL)-based audio encoders, such as BEATs and AVES, have shown strong performance in bioacoustic tasks, their computational cost and limited r… ▽ More Passive acoustic monitoring has become a key strategy in biodiversity assessment, conservation, and behavioral ecology, especially as Internet-of-Things (IoT) devices enable continuous in situ audio collection at scale. While recent self-supervised learning (SSL)-based audio encoders, such as BEATs and AVES, have shown strong performance in bioacoustic tasks, their computational cost and limited robustness to unseen environments hinder deployment on resource-constrained platforms. In this work, we introduce BioME, a resource-efficient audio encoder designed for bioacoustic applications. BioME is trained via layer-to-layer distillation from a high-capacity teacher model, enabling strong representational transfer while reducing the parameter count by 75%. To further improve ecological generalization, the model is pretrained on multi-domain data spanning speech, environmental sounds, and animal vocalizations. A key contribution is the integration of modulation-aware acoustic features via FiLM conditioning, injecting a DSP-inspired inductive bias that enhances feature disentanglement in low-capacity regimes. Across multiple bioacoustic tasks, BioME matches or surpasses the performance of larger models, including its teacher, while being suitable for resource-constrained IoT deployments. For reproducibility, code and pretrained checkpoints are publicly available. △ Less

Submitted 10 February, 2026; originally announced February 2026.

Predicting Camera Pose from Perspective Descriptions for Spatial Reasoning

Authors: Xuejun Zhang, Aditi Tiwari, Zhenhailong Wang, Heng Ji

Abstract: Multi-image spatial reasoning remains challenging for current multimodal large language models (MLLMs). While single-view perception is inherently 2D, reasoning over multiple views requires building a coherent scene understanding across viewpoints. In particular, we study perspective taking, where a model must build a coherent 3D understanding from multi-view observations and use it to reason from… ▽ More Multi-image spatial reasoning remains challenging for current multimodal large language models (MLLMs). While single-view perception is inherently 2D, reasoning over multiple views requires building a coherent scene understanding across viewpoints. In particular, we study perspective taking, where a model must build a coherent 3D understanding from multi-view observations and use it to reason from a new, language-specified viewpoint. We introduce CAMCUE, a pose-aware multi-image framework that uses camera pose as an explicit geometric anchor for cross-view fusion and novel-view reasoning. CAMCUE injects per-view pose into visual tokens, grounds natural-language viewpoint descriptions to a target camera pose, and synthesizes a pose-conditioned imagined target view to support answering. To support this setting, we curate CAMCUE-DATA with 27,668 training and 508 test instances pairing multi-view images and poses with diverse target-viewpoint descriptions and perspective-shift questions. We also include human-annotated viewpoint descriptions in the test split to evaluate generalization to human language. CAMCUE improves overall accuracy by 9.06% and predicts target poses from natural-language viewpoint descriptions with over 90% rotation accuracy within 20° and translation accuracy within a 0.5 error threshold. This direct grounding avoids expensive test-time search-and-match, reducing inference time from 256.6s to 1.45s per example and enabling fast, interactive use in real-world scenarios. △ Less

Submitted 6 February, 2026; v1 submitted 5 February, 2026; originally announced February 2026.

Towards Analyzing N-language Polyglot Programs

Authors: Jyoti Prakash, Abhishek Tiwari, Mikkel Baun Kjærgaard

Abstract: Polyglot programming is gaining popularity as developers integrate multiple programming languages to harness their individual strengths. With the recent popularity of platforms like GraalVM and other multi-language runtimes, creating and managing these systems has become much more feasible. However, current research on analyzing multilingual programs mainly focuses on two languages, leaving out th… ▽ More Polyglot programming is gaining popularity as developers integrate multiple programming languages to harness their individual strengths. With the recent popularity of platforms like GraalVM and other multi-language runtimes, creating and managing these systems has become much more feasible. However, current research on analyzing multilingual programs mainly focuses on two languages, leaving out the increasing complexity of systems that use three or more. For example, modern web systems often link JavaScript, WebAssembly, and Rust within the same execution chain. This paper envisions the landscape of software systems with three-language polyglot communication. We identify fundamental challenges in analyzing them and propose a conceptual roadmap to advance static analysis techniques to address them. Our vision aims to stimulate discussion and inspire new research directions toward scalable, language-agnostic analysis frameworks for next-generation polyglot systems. △ Less

Submitted 30 January, 2026; originally announced February 2026.

Shielded RecRL: Explanation Generation for Recommender Systems without Ranking Degradation

Authors: Ansh Tiwari, Ayush Chauhan

Abstract: We introduce Shielded RecRL, a reinforcement learning approach to generate personalized explanations for recommender systems without sacrificing the system's original ranking performance. Unlike prior RLHF-based recommender methods that directly optimize item rankings, our two-tower architecture keeps the recommender's ranking model intact while a language model learns to produce helpful explanati… ▽ More We introduce Shielded RecRL, a reinforcement learning approach to generate personalized explanations for recommender systems without sacrificing the system's original ranking performance. Unlike prior RLHF-based recommender methods that directly optimize item rankings, our two-tower architecture keeps the recommender's ranking model intact while a language model learns to produce helpful explanations. We design a composite reward signal combining explanation length, content relevance, and coherence, and apply proximal policy optimization (PPO) with a KL-divergence constraint to fine-tune a large language model with only 0.4% of its parameters trainable via LoRA adapters. In experiments on an Amazon Books dataset (approximately 50K interactions in the fantasy and romance genres), Shielded RecRL improved the relative click-through rate (CTR) by 22.5% (1.225x over baseline) while keeping the recommender's item-ranking behavior virtually unchanged. An extensive ablation study confirms that our gradient shielding strategy and reward design effectively balance explanation quality and policy drift. Our results demonstrate that Shielded RecRL enhances user-facing aspects of recommendations through rich, personalized explanations without degrading core recommendation accuracy. △ Less

Submitted 14 October, 2025; originally announced January 2026.

SceneDiff: A Benchmark and Method for Multiview Object Change Detection

Authors: Yuqun Wu, Chih-hao Lin, Henry Che, Aditi Tiwari, Chuhang Zou, Shenlong Wang, Derek Hoiem

Abstract: We investigate the problem of identifying objects that have been added, removed, or moved between a pair of captures (images or videos) of the same scene at different times. Accurately identifying verifiable changes is extremely challenging -- some objects may appear to be missing because they are occluded or out of frame, while others may appear different due to large viewpoint changes. To study… ▽ More We investigate the problem of identifying objects that have been added, removed, or moved between a pair of captures (images or videos) of the same scene at different times. Accurately identifying verifiable changes is extremely challenging -- some objects may appear to be missing because they are occluded or out of frame, while others may appear different due to large viewpoint changes. To study this problem, we introduce the SceneDiff Benchmark, the first multiview change detection dataset for scenes captured along different camera trajectories, comprising 350 diverse video pairs with dense object instance-level annotations. We also introduce the SceneDiff algorithm, a training-free approach that solves for image poses, segments images into objects, and compares them using semantic and geometric features. By building on pretrained models, SceneDiff generalizes across domains without retraining and naturally improves as the underlying models advance. Experiments on multiview and two-view benchmarks demonstrate that our method outperforms existing approaches by large margins (53.0\% and 30.6\% relative AP improvements). Project page: https://yuqunw.github.io/SceneDiff △ Less

Submitted 31 March, 2026; v1 submitted 18 December, 2025; originally announced December 2025.

IndiMathBench: Autoformalizing Mathematical Reasoning Problems with a Human Touch

Authors: Param Biyani, Shashank Kirtania, Yasharth Bajpai, Sumit Gulwani, Ashish Tiwari

Abstract: Reliable autoformalization remains challenging even in the era of large language models (LLMs). The scarcity of high-quality training data is a major bottleneck. Expert annotation requires substantial time and deep expertise in both mathematics and theorem proving. We introduce IndiMathBench, a human-verified benchmark designed to evaluate mathematical theorem proving, curated using an AI-powered… ▽ More Reliable autoformalization remains challenging even in the era of large language models (LLMs). The scarcity of high-quality training data is a major bottleneck. Expert annotation requires substantial time and deep expertise in both mathematics and theorem proving. We introduce IndiMathBench, a human-verified benchmark designed to evaluate mathematical theorem proving, curated using an AI-powered human-assisted pipeline for formalizing natural language problems in Lean. IndiMathBench is composed of 312 formal Lean 4 theorems paired with their corresponding informal problem statements, sourced from Indian Mathematics Olympiads. Through category-based retrieval, iterative compiler feedback, and multi-model ensembles, our pipeline generates candidate formalizations that experts efficiently validate via an interactive dashboard with automated quality summaries. Evaluation across multiple frontier models demonstrates that autoformalization remains challenging, with substantial gaps between syntactic validity and semantic correctness, while theorem proving success rates remain low even with iterative refinement, demonstrating that \benchmark~presents a challenging testbed for mathematical reasoning. IndiMathBench is available at https://github.com/prmbiy/IndiMathBench. △ Less

Submitted 10 March, 2026; v1 submitted 30 November, 2025; originally announced December 2025.

Distributions In, Distributions Out: The Case for Soft-Label Training

Authors: Agamdeep Singh, Ashish Tiwari, Hosein Hasanbeig, Priyanshu Gupta

Abstract: Supervised classifiers output a distribution over classes but are typically trained against a single label obtained by collapsing multiple annotators into a majority vote. On tasks where annotator disagreement reflects genuine ambiguity -- natural language inference, politeness, visually ambiguous categorization -- this collapse discards information and forces models to express uniform confidence… ▽ More Supervised classifiers output a distribution over classes but are typically trained against a single label obtained by collapsing multiple annotators into a majority vote. On tasks where annotator disagreement reflects genuine ambiguity -- natural language inference, politeness, visually ambiguous categorization -- this collapse discards information and forces models to express uniform confidence on inputs where humans systematically disagree. We compare soft-label training, which uses the full annotation distribution as the target, against hard-label training across three datasets spanning vision and NLP (ChaosNLI, POPQUORN, CIFAR-10H). Soft-label training matches or exceeds hard-label accuracy on every dataset, reduces KL divergence to the annotator distribution by 32% on average (p < 10^-4), and produces predictions whose per-sample entropy correlates 61% more strongly with annotator entropy -- models trained on distributions are uncertain precisely where humans are. We argue these benefits follow from a basic observation: when annotators legitimately disagree, the annotation distribution is the correct learning target, not a noisy estimate of it. △ Less

Submitted 30 July, 2026; v1 submitted 17 November, 2025; originally announced November 2025.

A Deep Learning Model for Predicting Transformation Legality

Authors: Avani Tiwari, Yacine Hakimi, Riyadh Baghdadi

Abstract: Compilers must check the legality of code transformations to guarantee the correctness of applying a sequence of code transformations to a given code. While such a legality check needs to be precisely computed in general, we can use an approximate legality prediction model in certain cases, such as training a reinforcement learning (RL) agent for schedule prediction. In this paper, we propose an a… ▽ More Compilers must check the legality of code transformations to guarantee the correctness of applying a sequence of code transformations to a given code. While such a legality check needs to be precisely computed in general, we can use an approximate legality prediction model in certain cases, such as training a reinforcement learning (RL) agent for schedule prediction. In this paper, we propose an approximate method for legality checks. We propose a novel DL model for predicting the legality of transformations. The model takes the code representation and a list of transformations as input and predicts whether applying those transformations to the code is legal. We implement and evaluate the proposed model, demonstrating its effectiveness. Our evaluation shows an F1 score of 0.91 on a test set of randomly generated programs. To further evaluate the model in a practical scenario, we used the model to replace the legality check used during the training of an RL agent designed for automatic code optimization. We demonstrate that such a replacement enables the agent to train on twice as many steps, resulting in faster training and reducing resource usage by approximately 80\% for CPU and 35\% for RAM. The agent trained using this approach maintains comparable performance, with only a 4\% reduction on benchmarks from the Polybench suite compared to the traditional method. △ Less

Submitted 8 November, 2025; originally announced November 2025.

Empirical Derivations from an Evolving Test Suite

Authors: Jukka Ruohonen, Abhishek Tiwari

Abstract: The paper presents a longitudinal empirical analysis of the automated, continuous, and virtualization-based software test suite of the NetBSD operating system. The longitudinal period observed spans from the initial roll out of the test suite in the early 2010s to late 2025. According to the results, the test suite has grown continuously, currently covering over ten thousand individual test cases.… ▽ More The paper presents a longitudinal empirical analysis of the automated, continuous, and virtualization-based software test suite of the NetBSD operating system. The longitudinal period observed spans from the initial roll out of the test suite in the early 2010s to late 2025. According to the results, the test suite has grown continuously, currently covering over ten thousand individual test cases. Failed test cases exhibit overall stability, although there have been shorter periods marked with more frequent failures. A similar observation applies to build failures, failures of the test suite to complete, and installation failures, all of which are also captured by the NetBSD's testing framework. Finally, code churn and kernel modifications do not provide longitudinally consistent statistical explanations for the failures. Although some periods exhibit larger effects, including particularly with respect to the kernel modifications, the effects are small on average. Even though only in an exploratory manner, these empirical observations contribute to efforts to draw conclusions from large-scale and evolving software test suites. △ Less

Submitted 7 May, 2026; v1 submitted 2 November, 2025; originally announced November 2025.

Comments: Proceedings of the IEEE International Conference on Software Analysis, Evolution and Reengineering - Companion (SANER-C 2026), Limassol, IEEE, pp. 325-332

ConDABench: Interactive Evaluation of Language Models for Data Analysis

Authors: Avik Dutta, Priyanshu Gupta, Hosein Hasanbeig, Rahul Pratap Singh, Harshit Nigam, Sumit Gulwani, Arjun Radhakrishna, Gustavo Soares, Ashish Tiwari

Abstract: Real-world data analysis tasks often come with under-specified goals and unclean data. User interaction is necessary to understand and disambiguate a user's intent, and hence, essential to solving these complex tasks. Existing benchmarks for evaluating LLMs on data analysis tasks do not capture these complexities or provide first-class support for interactivity. We introduce ConDABench, a framewor… ▽ More Real-world data analysis tasks often come with under-specified goals and unclean data. User interaction is necessary to understand and disambiguate a user's intent, and hence, essential to solving these complex tasks. Existing benchmarks for evaluating LLMs on data analysis tasks do not capture these complexities or provide first-class support for interactivity. We introduce ConDABench, a framework for generating conversational data analysis (ConDA) benchmarks and evaluating external tools on the generated benchmarks. \bench consists of (a) a multi-agent workflow for generating realistic benchmarks from articles describing insights gained from public datasets, (b) 1,420 ConDA problems generated using this workflow, and (c) an evaluation harness that, for the first time, makes it possible to systematically evaluate conversational data analysis tools on the generated ConDA problems. Evaluation of state-of-the-art LLMs on the benchmarks reveals that while the new generation of models are better at solving more instances, they are not necessarily better at solving tasks that require sustained, long-form engagement. ConDABench is an avenue for model builders to measure progress towards truly collaborative models that can complete complex interactive tasks. △ Less

Submitted 10 October, 2025; originally announced October 2025.

Local Timescale Gates for Timescale-Robust Continual Spiking Neural Networks

Authors: Ansh Tiwari, Ayush Chauhan

Abstract: Spiking neural networks (SNNs) promise energy-efficient artificial intelligence on neuromorphic hardware but struggle with tasks requiring both fast adaptation and long-term memory, especially in continual learning. We propose Local Timescale Gating (LT-Gate), a neuron model that combines dual time-constant dynamics with an adaptive gating mechanism. Each spiking neuron tracks information on a fas… ▽ More Spiking neural networks (SNNs) promise energy-efficient artificial intelligence on neuromorphic hardware but struggle with tasks requiring both fast adaptation and long-term memory, especially in continual learning. We propose Local Timescale Gating (LT-Gate), a neuron model that combines dual time-constant dynamics with an adaptive gating mechanism. Each spiking neuron tracks information on a fast and a slow timescale in parallel, and a learned gate locally adjusts their influence. This design enables individual neurons to preserve slow contextual information while responding to fast signals, addressing the stability-plasticity dilemma. We further introduce a variance-tracking regularization that stabilizes firing activity, inspired by biological homeostasis. Empirically, LT-Gate yields significantly improved accuracy and retention in sequential learning tasks: on a challenging temporal classification benchmark it achieves about 51 percent final accuracy, compared to about 46 percent for a recent Hebbian continual-learning baseline and lower for prior SNN methods. Unlike approaches that require external replay or expensive orthogonalizations, LT-Gate operates with local updates and is fully compatible with neuromorphic hardware. In particular, it leverages features of Intel's Loihi chip (multiple synaptic traces with different decay rates) for on-chip learning. Our results demonstrate that multi-timescale gating can substantially enhance continual learning in SNNs, narrowing the gap between spiking and conventional deep networks on lifelong-learning tasks. △ Less

Submitted 13 October, 2025; originally announced October 2025.

Apriel-1.5-15b-Thinker

Authors: Shruthan Radhakrishna, Aman Tiwari, Aanjaneya Shukla, Masoud Hashemi, Rishabh Maheshwary, Shiva Krishna Reddy Malay, Jash Mehta, Pulkit Pattnaik, Saloni Mittal, Khalil Slimi, Kelechi Ogueji, Akintunde Oladipo, Soham Parikh, Oluwanifemi Bamgbose, Toby Liang, Ahmed Masry, Khyati Mahajan, Sai Rajeswar Mudumba, Vikas Yadav, Sathwik Tejaswi Madhusudhan, Torsten Scholak, Sagar Davasam, Srinivas Sunkara, Nicholas Chapados

Abstract: We present Apriel-1.5-15B-Thinker, a 15-billion parameter open-weights multimodal reasoning model that achieves frontier-level performance through training design rather than sheer scale. Starting from Pixtral-12B, we apply a progressive three-stage methodology: (1) depth upscaling to expand reasoning capacity without pretraining from scratch, (2) staged continual pre-training that first develops… ▽ More We present Apriel-1.5-15B-Thinker, a 15-billion parameter open-weights multimodal reasoning model that achieves frontier-level performance through training design rather than sheer scale. Starting from Pixtral-12B, we apply a progressive three-stage methodology: (1) depth upscaling to expand reasoning capacity without pretraining from scratch, (2) staged continual pre-training that first develops foundational text and vision understanding, then enhances visual reasoning through targeted synthetic data generation addressing spatial structure, compositional understanding, and fine-grained perception, and (3) high-quality text-only supervised fine-tuning on curated instruction-response pairs with explicit reasoning traces spanning mathematics, coding, science, and tool use. Notably, our model achieves competitive results without reinforcement learning or preference optimization, isolating the contribution of our data-centric continual pre-training approach. On the Artificial Analysis Intelligence Index, Apriel-1.5-15B-Thinker attains a score of 52, matching DeepSeek-R1-0528 despite requiring significantly fewer computational resources. Across ten image benchmarks, its performance is on average within five points of Gemini-2.5-Flash and Claude Sonnet-3.7, a key achievement for a model operating within single-GPU deployment constraints. Our results demonstrate that thoughtful mid-training 2 design can close substantial capability gaps without massive scale, making frontier-level multimodal reasoning accessible to organizations with limited infrastructure. We release the model checkpoint, all training recipes, and evaluation protocols under the MIT license to to advance open-source research. △ Less

Submitted 1 October, 2025; originally announced October 2025.

Model Context Protocol for Vision Systems: Audit, Security, and Protocol Extensions

Authors: Aditi Tiwari, Akshit Bhalla, Darshan Prasad

Abstract: The Model Context Protocol (MCP) defines a schema bound execution model for agent-tool interaction, enabling modular computer vision workflows without retraining. To our knowledge, this is the first protocol level, deployment scale audit of MCP in vision systems, identifying systemic weaknesses in schema semantics, interoperability, and runtime coordination. We analyze 91 publicly registered visio… ▽ More The Model Context Protocol (MCP) defines a schema bound execution model for agent-tool interaction, enabling modular computer vision workflows without retraining. To our knowledge, this is the first protocol level, deployment scale audit of MCP in vision systems, identifying systemic weaknesses in schema semantics, interoperability, and runtime coordination. We analyze 91 publicly registered vision centric MCP servers, annotated along nine dimensions of compositional fidelity, and develop an executable benchmark with validators to detect and categorize protocol violations. The audit reveals high prevalence of schema format divergence, missing runtime schema validation, undeclared coordinate conventions, and reliance on untracked bridging scripts. Validator based testing quantifies these failures, with schema format checks flagging misalignments in 78.0 percent of systems, coordinate convention checks detecting spatial reference errors in 24.6 percent, and memory scope checks issuing an average of 33.8 warnings per 100 executions. Security probes show that dynamic and multi agent workflows exhibit elevated risks of privilege escalation and untyped tool connections. The proposed benchmark and validator suite, implemented in a controlled testbed and to be released on GitHub, establishes a reproducible framework for measuring and improving the reliability and security of compositional vision workflows. △ Less

Submitted 26 September, 2025; originally announced September 2025.

Comments: Accepted to NeurIPS 2025 Workshop on Bridging Language, Agent, and World Models for Reasoning and Planning (LAW 2025)

Towards Systematic Specification and Verification of Fairness Requirements: A Position Paper

Authors: Qusai Ramadan, Jukka Ruohonen, Abhishek Tiwari, Adam Alami, Zeyd Boukhers

Abstract: Decisions suggested by improperly designed software systems might be prone to discriminate against people based on protected characteristics, such as gender and ethnicity. Previous studies attribute such undesired behavior to flaws in algorithmic design or biased data. However, these studies ignore that discrimination is often the result of a lack of well-specified fairness requirements and their… ▽ More Decisions suggested by improperly designed software systems might be prone to discriminate against people based on protected characteristics, such as gender and ethnicity. Previous studies attribute such undesired behavior to flaws in algorithmic design or biased data. However, these studies ignore that discrimination is often the result of a lack of well-specified fairness requirements and their verification. The fact that experts' knowledge about fairness is often implicit makes the task of specifying precise and verifiable fairness requirements difficult. In related domains, such as security engineering, knowledge graphs have been proven to be effective in formalizing knowledge to assist requirements specification and verification. To address the lack of formal mechanisms for specifying and verifying fairness requirements, we propose the development of a knowledge graph-based framework for fairness. In this paper, we discuss the challenges, research questions, and a road map towards addressing the research questions. △ Less

Submitted 22 September, 2025; originally announced September 2025.

Comments: Accepted at the 2025 IEEE 33rd International Requirements Engineering Conference Workshops

Vulnerability Patching Across Software Products and Software Components: A Case Study of Red Hat's Product Portfolio

Authors: Jukka Ruohonen, Sani Abdullahi, Abhishek Tiwari

Abstract: Motivated by software maintenance and the more recent concept of security debt, the paper presents a time series analysis of vulnerability patching of Red Hat's products and components between 1999 and 2024. According to the results based on segmented regression analysis, the amounts of vulnerable products and components have not been stable; a linear trend describes many of the series well. Nor d… ▽ More Motivated by software maintenance and the more recent concept of security debt, the paper presents a time series analysis of vulnerability patching of Red Hat's products and components between 1999 and 2024. According to the results based on segmented regression analysis, the amounts of vulnerable products and components have not been stable; a linear trend describes many of the series well. Nor do the amounts align well with trends characterizing vulnerabilities in general. There are also visible breakpoints indicating that the linear trend is not universally applicable and that the growing security debt may be stabilizing. △ Less

Submitted 16 September, 2025; originally announced September 2025.

Comments: Submitted to SecITC 2025

AU-Harness: An Open-Source Toolkit for Holistic Evaluation of Audio LLMs

Authors: Hoang Nguyen, Sidharth Surapaneni, Akshay Kalkunte, Jash Mehta, Aman Tiwari, Oluwanifemi Bamgbose, Khyati Mahajan, Jash Shah, Shruthan Radhakrishna, Sathwik Tejaswi Madhusudhan, Vikas Yadav, Sai Rajeswar

Abstract: Large Audio Language Models (LALMs) are rapidly advancing, but evaluating them remains challenging due to inefficient and non-standardized toolkits that limit fair comparison and systematic assessment. Existing evaluation frameworks exhibit three critical limitations: (1) slow and inefficient processing pipeline that bottlenecks large-scale studies, (2) inadequate multi-turn dialogue support, leav… ▽ More Large Audio Language Models (LALMs) are rapidly advancing, but evaluating them remains challenging due to inefficient and non-standardized toolkits that limit fair comparison and systematic assessment. Existing evaluation frameworks exhibit three critical limitations: (1) slow and inefficient processing pipeline that bottlenecks large-scale studies, (2) inadequate multi-turn dialogue support, leaving fundamental questions about cross-turn context integration and performance dynamics over extended conversations in LALMs unanswered; and (3) the absence of unified and scalable evaluation framework capable of keeping pace with the rapid growth of both LALMs and audio benchmarks. To address these issues, we introduce AU-Harness, an efficient and comprehensive evaluation framework for LALMs. Our system achieves a speedup of up to 151% over existing evaluation toolkits through optimized batch processing and parallel execution, enabling large-scale evaluations previously considered impractical. We provide standardized prompting protocols and flexible configurations for fair model comparison across diverse scenarios. AU-Harness unlocks a range of in-depth analyses difficult to conduct without a unified foundation, including multi-turn dialogue dynamics, enabling the study of true audio reasoning capabilities in existing LALMs. AU-Harness provides both practical evaluation tools and insights into model limitations, advancing systematic LALM development. △ Less

Submitted 11 May, 2026; v1 submitted 9 September, 2025; originally announced September 2025.

TensoIS: A Step Towards Feed-Forward Tensorial Inverse Subsurface Scattering for Perlin Distributed Heterogeneous Media

Authors: Ashish Tiwari, Satyam Bhardwaj, Yash Bachwana, Parag Sarvoday Sahu, T. M. Feroz Ali, Bhargava Chintalapati, Shanmuganathan Raman

Abstract: Estimating scattering parameters of heterogeneous media from images is a severely under-constrained and challenging problem. Most of the existing approaches model BSSRDF either through an analysis-by-synthesis approach, approximating complex path integrals, or using differentiable volume rendering techniques to account for heterogeneity. However, only a few studies have applied learning-based meth… ▽ More Estimating scattering parameters of heterogeneous media from images is a severely under-constrained and challenging problem. Most of the existing approaches model BSSRDF either through an analysis-by-synthesis approach, approximating complex path integrals, or using differentiable volume rendering techniques to account for heterogeneity. However, only a few studies have applied learning-based methods to estimate subsurface scattering parameters, but they assume homogeneous media. Interestingly, no specific distribution is known to us that can explicitly model the heterogeneous scattering parameters in the real world. Notably, procedural noise models such as Perlin and Fractal Perlin noise have been effective in representing intricate heterogeneities of natural, organic, and inorganic surfaces. Leveraging this, we first create HeteroSynth, a synthetic dataset comprising photorealistic images of heterogeneous media whose scattering parameters are modeled using Fractal Perlin noise. Furthermore, we propose Tensorial Inverse Scattering (TensoIS), a learning-based feed-forward framework to estimate these Perlin-distributed heterogeneous scattering parameters from sparse multi-view image observations. Instead of directly predicting the 3D scattering parameter volume, TensoIS uses learnable low-rank tensor components to represent the scattering volume. We evaluate TensoIS on unseen heterogeneous variations over shapes from the HeteroSynth test set, smoke and cloud geometries obtained from open-source realistic volumetric simulations, and some real-world samples to establish its effectiveness for inverse scattering. Overall, this study is an attempt to explore Perlin noise distribution, given the lack of any such well-defined distribution in literature, to potentially model real-world heterogeneous scattering in a feed-forward manner. △ Less

Submitted 4 September, 2025; originally announced September 2025.

Comments: To appear in Pacific Graphics 2025 (CGF Journal Track), Project page: https://yashbachwana.github.io/TensoIS/

Quantum Verifiable Rewards for Post-Training Qiskit Code Assistant

Authors: Nicolas Dupuis, Adarsh Tiwari, Youssef Mroueh, David Kremer, Ismael Faro, Juan Cruz-Benito

Abstract: Qiskit is an open-source quantum computing framework that allows users to design, simulate, and run quantum circuits on real quantum hardware. We explore post-training techniques for LLMs to assist in writing Qiskit code. We introduce quantum verification as an effective method for ensuring code quality and executability on quantum hardware. To support this, we developed a synthetic data pipeline… ▽ More Qiskit is an open-source quantum computing framework that allows users to design, simulate, and run quantum circuits on real quantum hardware. We explore post-training techniques for LLMs to assist in writing Qiskit code. We introduce quantum verification as an effective method for ensuring code quality and executability on quantum hardware. To support this, we developed a synthetic data pipeline that generates quantum problem-unit test pairs and used it to create preference data for aligning LLMs with DPO. Additionally, we trained models using GRPO, leveraging quantum-verifiable rewards provided by the quantum hardware. Our best-performing model, combining DPO and GRPO, surpasses the strongest open-source baselines on the challenging Qiskit-HumanEval-hard benchmark. △ Less

Submitted 28 August, 2025; originally announced August 2025.

FastAvatar: Instant 3D Gaussian Splatting for Faces from Single Unconstrained Poses

Authors: Hao Liang, Zhixuan Ge, Soumendu Majee, Ashish Tiwari, G. M. Dilshan Godaliyadda, Ashok Veeraraghavan, Guha Balakrishnan

Abstract: We present FastAvatar, a fast and robust algorithm for single-image 3D face reconstruction using 3D Gaussian Splatting (3DGS). Given a single input image from an arbitrary pose, FastAvatar recovers a high-quality, full-head 3DGS avatar in approximately 3 seconds on a single NVIDIA A100 GPU. We use a two-stage design: a feed-forward encoder-decoder predicts coarse face geometry by regressing Gaussi… ▽ More We present FastAvatar, a fast and robust algorithm for single-image 3D face reconstruction using 3D Gaussian Splatting (3DGS). Given a single input image from an arbitrary pose, FastAvatar recovers a high-quality, full-head 3DGS avatar in approximately 3 seconds on a single NVIDIA A100 GPU. We use a two-stage design: a feed-forward encoder-decoder predicts coarse face geometry by regressing Gaussian structure from a pose-invariant identity embedding, and a lightweight test-time refinement stage then optimizes the appearance parameters for photorealistic rendering. This hybrid strategy combines the speed and stability of direct prediction with the accuracy of optimization, enabling strong identity preservation even under extreme input poses. FastAvatar achieves state-of-the-art reconstruction quality (24.01 dB PSNR, 0.91 SSIM) while running over 600x faster than existing per-subject optimization methods (e.g., FlashAvatar, GaussianAvatars, GASP). Once reconstructed, our avatars support photorealistic novel-view synthesis and FLAME-guided expression animation, enabling controllable reenactment from a single image. By jointly offering high fidelity, robustness to pose, and rapid reconstruction, FastAvatar significantly broadens the applicability of 3DGS-based facial avatars. △ Less

Submitted 25 November, 2025; v1 submitted 25 August, 2025; originally announced August 2025.

Comments: 11 pages, 5 figures, website: https://hliang2.github.io/FastAvatar/

Apriel-Nemotron-15B-Thinker

Authors: Shruthan Radhakrishna, Soham Parikh, Gopal Sarda, Anil Turkkan, Quaizar Vohra, Raymond Li, Dhruv Jhamb, Kelechi Ogueji, Aanjaneya Shukla, Oluwanifemi Bamgbose, Toby Liang, Luke Kumar, Oleksiy Ostapenko, Shiva Krishna Reddy Malay, Aman Tiwari, Tara Bogavelli, Vikas Yadav, Jash Mehta, Saloni Mittal, Akshay Kalkunte, Pulkit Pattnaik, Khalil Slimi, Anirudh Sreeram, Jishnu Nair, Akintunde Oladipo , et al. (10 additional authors not shown)

Abstract: While large language models (LLMs) have achieved remarkable reasoning capabilities across domains like code, math and other enterprise tasks, their significant memory and computational costs often preclude their use in practical enterprise settings. To this end, we introduce Apriel-Nemotron-15B-Thinker, a 15-billion parameter model in the ServiceNow Apriel SLM series that achieves performance agai… ▽ More While large language models (LLMs) have achieved remarkable reasoning capabilities across domains like code, math and other enterprise tasks, their significant memory and computational costs often preclude their use in practical enterprise settings. To this end, we introduce Apriel-Nemotron-15B-Thinker, a 15-billion parameter model in the ServiceNow Apriel SLM series that achieves performance against medium sized state-of-the-art models such as o1-mini, QWQ32B, and EXAONE-Deep-32B while maintaining only half the memory footprint of those alternatives. Apriel-Nemotron-15B-Thinker model is trained in a four stage training pipeline including 1) Base Model upscaling, 2) Continual Pre-training 3) Supervised Fine-tuning (SFT) and 4) Reinforcement Learning using GRPO. Comprehensive evaluations across a diverse suite of benchmarks consistently demonstrate that our Apriel-Nemotron-15B-Thinker model matches or exceeds the performance of its 32-billion parameter counterparts, despite being less than half their size. △ Less

Submitted 13 August, 2025; originally announced August 2025.

TEN: Table Explicitization, Neurosymbolically

Authors: Nikita Mehrotra, Aayush Kumar, Sumit Gulwani, Arjun Radhakrishna, Ashish Tiwari

Abstract: We present a neurosymbolic approach, TEN, for extracting tabular data from semistructured input text. This task is particularly challenging for text input that does not use special delimiters consistently to separate columns and rows. Purely neural approaches perform poorly due to hallucinations and their inability to enforce hard constraints. TEN uses Structural Decomposition prompting - a specia… ▽ More We present a neurosymbolic approach, TEN, for extracting tabular data from semistructured input text. This task is particularly challenging for text input that does not use special delimiters consistently to separate columns and rows. Purely neural approaches perform poorly due to hallucinations and their inability to enforce hard constraints. TEN uses Structural Decomposition prompting - a specialized chain-of-thought prompting approach - on a large language model (LLM) to generate an initial table, and thereafter uses a symbolic checker to evaluate not only the well-formedness of that table, but also detect cases of hallucinations or forgetting. The output of the symbolic checker is processed by a critique-LLM to generate guidance for fixing the table, which is presented to the original LLM in a self-debug loop. Our extensive experiments demonstrate that TEN significantly outperforms purely neural baselines across multiple datasets and metrics, achieving significantly higher exact match accuracy and substantially reduced hallucination rates. A 21-participant user study further confirms that TEN's tables are rated significantly more accurate (mean score: 5.0 vs 4.3; p = 0.021), and are consistently preferred for ease of verification and correction, with participants favoring our method in over 60% of the cases. △ Less

Submitted 12 August, 2025; originally announced August 2025.

GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning

Authors: Anushka Tiwari, Sayantan Pal, Rohini K. Srihari, Kaiyi Ji

Abstract: Prompt-based continual learning (CL) offers a parameter-efficient way to adapt large language models (LLMs) across task sequences. However, existing methods often rely on task-aware inference and maintain an expanding set of task-specific prompts, leading to (1) severe performance degradation on earlier tasks when task identifiers are unavailable for prompt selection at inference time, and (2) lim… ▽ More Prompt-based continual learning (CL) offers a parameter-efficient way to adapt large language models (LLMs) across task sequences. However, existing methods often rely on task-aware inference and maintain an expanding set of task-specific prompts, leading to (1) severe performance degradation on earlier tasks when task identifiers are unavailable for prompt selection at inference time, and (2) limited scalability as task sequence grows. We propose GRID, a unified framework designed to address these challenges. GRID incorporates an output-space-aware decoding mechanism that enhances backward transfer by leveraging representative inputs and automatic label semantic normalization, alongside a gradient-guided prompt selection strategy that compresses less informative prompts into a single aggregated representation for scalable, memory-efficient continual learning. Extensive experiments on long-sequence and negative-transfer benchmarks show that GRID improves backward transfer, achieves competitive forward transfer, and substantially reduces prompt memory across encoder-decoder and decoder-only architectures, including T5, Qwen, and LLaMA. Source code is available at https://github.com/AnushkaTi/GRID. △ Less

Submitted 9 June, 2026; v1 submitted 19 July, 2025; originally announced July 2025.

Revisiting CroPA: A Reproducibility Study and Enhancements for Cross-Prompt Adversarial Transferability in Vision-Language Models

Authors: Atharv Mittal, Agam Pandey, Amritanshu Tiwari, Sukrit Jindal, Swadesh Swain

Abstract: Large Vision-Language Models (VLMs) have revolutionized computer vision, enabling tasks such as image classification, captioning, and visual question answering. However, they remain highly vulnerable to adversarial attacks, particularly in scenarios where both visual and textual modalities can be manipulated. In this study, we conduct a comprehensive reproducibility study of "An Image is Worth 100… ▽ More Large Vision-Language Models (VLMs) have revolutionized computer vision, enabling tasks such as image classification, captioning, and visual question answering. However, they remain highly vulnerable to adversarial attacks, particularly in scenarios where both visual and textual modalities can be manipulated. In this study, we conduct a comprehensive reproducibility study of "An Image is Worth 1000 Lies: Adversarial Transferability Across Prompts on Vision-Language Models" validating the Cross-Prompt Attack (CroPA) and confirming its superior cross-prompt transferability compared to existing baselines. Beyond replication we propose several key improvements: (1) A novel initialization strategy that significantly improves Attack Success Rate (ASR). (2) Investigate cross-image transferability by learning universal perturbations. (3) A novel loss function targeting vision encoder attention mechanisms to improve generalization. Our evaluation across prominent VLMs -- including Flamingo, BLIP-2, and InstructBLIP as well as extended experiments on LLaVA validates the original results and demonstrates that our improvements consistently boost adversarial effectiveness. Our work reinforces the importance of studying adversarial vulnerabilities in VLMs and provides a more robust framework for generating transferable adversarial examples, with significant implications for understanding the security of VLMs in real-world applications. △ Less

Submitted 28 June, 2025; originally announced June 2025.

Comments: Accepted to MLRC 2025

Journal ref: Transactions on Machine Learning Research (TMLR), 2025. Available at OpenReview: https://openreview.net/forum?id=5L90cl0xtf

TuneGenie: Reasoning-based LLM agents for preferential music generation

Authors: Amitesh Pandey, Jafarbek Arifdjanov, Ansh Tiwari

Abstract: Recently, Large language models (LLMs) have shown great promise across a diversity of tasks, ranging from generating images to reasoning spatially. Considering their remarkable (and growing) textual reasoning capabilities, we investigate LLMs' potency in conducting analyses of an individual's preferences in music (based on playlist metadata, personal write-ups, etc.) and producing effective prompt… ▽ More Recently, Large language models (LLMs) have shown great promise across a diversity of tasks, ranging from generating images to reasoning spatially. Considering their remarkable (and growing) textual reasoning capabilities, we investigate LLMs' potency in conducting analyses of an individual's preferences in music (based on playlist metadata, personal write-ups, etc.) and producing effective prompts (based on these analyses) to be passed to Suno AI (a generative AI tool for music production). Our proposition of a novel LLM-based textual representation to music model (which we call TuneGenie) and the various methods we develop to evaluate & benchmark similar models add to the increasing (and increasingly controversial) corpus of research on the use of AI in generating art. △ Less

Submitted 10 June, 2025; originally announced June 2025.

Comments: 15 pages

MSC Class: I.2.6