arXiv subjects

Janibul Bashir

Publications and source records attributed to Janibul Bashir.

12 recordsLinked to original sources

arXiv2026

From Propagation to Protection: Risk-Aware Diffusion for Harm Minimization in Signed Social Networks

Real-world social relationships are not uniformly supportive. Information through hostile connections can increase resistance, anxiety, or misinformation rather than adoption. Classical models such as Independent Cascade and Linear Threshold, together with Influence Maximization (IM), which maximizes spread from a limited seed set, treat activation as discrete and irreversible. Its counterpart, Influence Minimization (Inf-Min), limits undesirable spread but similarly relies on simplified activation assumptions. Signed extensions incorporate polarity but largely retain this irreversibility, leaving no room for beliefs to weaken, reverse, or recover under competing influence. Moreover, both objectives typically treat individuals uniformly, without accounting for differences in vulnerability or prioritizing protection of those most at risk. We introduce RASH, a signed, susceptibility-aware diffusion model in which node awareness is continuous, bounded, and non-monotonic, and prove that despite this added expressiveness it remains monotone and {\gamma}-weakly submodular where only positive or negative edges exist, preserving tractable greedy approximation guarantees where strict submodularity provably fails. Building on RASH, we formulate Harm Minimization (HM), which maximizes aggregate reach while minimizing the awareness shortfall (harm). We prove HM is NP-hard, yet its harm-reduction formulation inherits the same monotonicity and weak-submodularity structure, admitting a greedy algorithm with a bounded approximation ratio. Across six structurally diverse signed networks, RASH is the only diffusion model tested to our knowledge that ever allows awareness to reverse after activation, letting sustained discouraging influence drive awareness from positive toward negative, and HM achieves the highest harm reduction of any method evaluated, including its own boundary cases (IM and Inf-Min)

cs.SI↗

arXiv2026

QTrack: Query-Driven Reasoning for Multi-modal MOT

Multi-object tracking (MOT) has traditionally focused on estimating trajectories of all objects in a video, without selectively reasoning about user-specified targets under semantic instructions. In this work, we introduce a query-driven tracking paradigm that formulates tracking as a spatiotemporal reasoning problem conditioned on natural language queries. Given a reference frame, a video sequence, and a textual query, the goal is to localize and track only the target(s) specified in the query while maintaining temporal coherence and identity consistency. To support this setting, we construct RMOT26, a large-scale benchmark with grounded queries and sequence-level splits to prevent identity leakage and enable robust evaluation of generalization. We further present QTrack, an end-to-end vision-language model that integrates multimodal reasoning with tracking-oriented localization. Additionally, we introduce a Temporal Perception-Aware Policy Optimization strategy with structured rewards to encourage motion-aware reasoning. Extensive experiments demonstrate the effectiveness of our approach for reasoning-centric, language-guided tracking. Code and data are available at https://github.com/gaash-lab/QTrack

cs.CV↗

arXiv2026

Bolbosh: Script-Aware Flow Matching for Kashmiri Text-to-Speech

Kashmiri is spoken by around 7 million people but remains critically underserved in speech technology, despite its official status and rich linguistic heritage. The lack of robust Text-to-Speech (TTS) systems limits digital accessibility and inclusive human-computer interaction for native speakers. In this work, we present the first dedicated open-source neural TTS system designed for Kashmiri. We show that zero-shot multilingual baselines trained for Indic languages fail to produce intelligible speech, achieving a Mean Opinion Score (MOS) of only 1.86, largely due to inadequate modeling of Perso-Arabic diacritics and language-specific phonotactics. To address these limitations, we propose Bolbosh, a supervised cross-lingual adaptation strategy based on Optimal Transport Conditional Flow Matching (OT-CFM) within the Matcha-TTS framework. This enables stable alignment under limited paired data. We further introduce a three-stage acoustic enhancement pipeline consisting of dereverberation, silence trimming, and loudness normalization to unify heterogeneous speech sources and stabilize alignment learning. The model vocabulary is expanded to explicitly encode Kashmiri graphemes, preserving fine-grained vowel distinctions. Our system achieves a MOS of 3.63 and a Mel-Cepstral Distortion (MCD) of 3.73, substantially outperforming multilingual baselines and establishing a new benchmark for Kashmiri speech synthesis. Our results demonstrate that script-aware and supervised flow-based adaptation are critical for low-resource TTS in diacritic-sensitive languages. Code and data are available at: https://github.com/gaash-lab/Bolbosh.

cs.CL↗

arXiv2026

GroundedSurg: A Multi-Procedure Benchmark for Language-Conditioned Surgical Tool Segmentation

Clinically reliable perception of surgical scenes is essential for advancing intelligent, context-aware intraoperative assistance such as instrument handoff guidance, collision avoidance, and workflow-aware robotic support. Existing surgical tool benchmarks primarily evaluate category-level segmentation, requiring models to detect all instances of predefined instrument classes. However, real-world clinical decisions often require resolving references to a specific instrument instance based on its functional role, spatial relation, or anatomical interaction capabilities not captured by current evaluation paradigms. We introduce GroundedSurg, the first language-conditioned, instance-level surgical grounding benchmark. Each instance pairs a surgical image with a natural-language description targeting a single instrument, accompanied by structured spatial grounding annotations including bounding boxes and point-level anchors. The dataset spans ophthalmic, laparoscopic, robotic, and open procedures, encompassing diverse instrument types, imaging conditions, and operative complexities. By jointly evaluating linguistic reference resolution and pixel-level localization, GroundedSurg enables a systematic and realistic evaluation of vision-language models in clinically realistic multi-instrument scenes. Extensive experiments demonstrate substantial performance gaps across modern segmentation and VLMs, highlighting the urgent need for clinically grounded vision-language reasoning in surgical AI systems. Code and data are publicly available at https://github.com/gaash-lab/GroundedSurg

cs.CV↗

arXiv2025

Diffusion Models for Influence Maximization on Temporal Networks: A Guide to Make the Best Choice

The increasing prominence of temporal networks in online social platforms and dynamic communication systems has made influence maximization a critical research area. Various diffusion models have been proposed to capture the spread of information, yet selecting the most suitable model for a given scenario remains challenging. This article provides a structured guide to making the best choice among diffusion models for influence maximization on temporal networks. We categorize existing models based on their underlying mechanisms and assess their effectiveness in different network settings. We analyze seed selection strategies, highlighting how the inherent properties of influence spread enable the development of efficient algorithms that can find near-optimal sets of influential nodes. By comparing key advancements, challenges, and practical applications, we offer a comprehensive roadmap for researchers and practitioners to navigate the landscape of temporal influence maximization effectively.

cs.SI↗

arXiv2025

TITAN: Query-Token based Domain Adaptive Adversarial Learning

We focus on the source-free domain adaptive object detection (SF-DAOD) problem when source data is unavailable during adaptation and the model must adapt to an unlabeled target domain. The majority of approaches for the problem employ a self-supervised approach using a student-teacher (ST) framework where pseudo-labels are generated via a source-pretrained model for further fine-tuning. We observe that the performance of a student model often degrades drastically, due to the collapse of the teacher model, primarily caused by high noise in pseudo-labels, resulting from domain bias, discrepancies, and a significant domain shift across domains. To obtain reliable pseudo-labels, we propose a Target-based Iterative Query-Token Adversarial Network (TITAN), which separates the target images into two subsets: those similar to the source (easy) and those dissimilar (hard). We propose a strategy to estimate variance to partition the target domain. This approach leverages the insight that higher detection variances correspond to higher recall and greater similarity to the source domain. Also, we incorporate query-token-based adversarial modules into a student-teacher baseline framework to reduce the domain gaps between two feature representations. Experiments conducted on four natural imaging datasets and two challenging medical datasets have substantiated the superior performance of TITAN compared to existing state-of-the-art (SOTA) methodologies. We report an mAP improvement of +22.7, +22.2, +21.1, and +3.7 percent over the current SOTA on C2F, C2B, S2C, and K2C benchmarks, respectively.

cs.CV↗

arXiv2025

ATR-Bench: A Federated Learning Benchmark for Adaptation, Trust, and Reasoning

Federated Learning (FL) has emerged as a promising paradigm for collaborative model training while preserving data privacy across decentralized participants. As FL adoption grows, numerous techniques have been proposed to tackle its practical challenges. However, the lack of standardized evaluation across key dimensions hampers systematic progress and fair comparison of FL methods. In this work, we introduce ATR-Bench, a unified framework for analyzing federated learning through three foundational dimensions: Adaptation, Trust, and Reasoning. We provide an in-depth examination of the conceptual foundations, task formulations, and open research challenges associated with each theme. We have extensively benchmarked representative methods and datasets for adaptation to heterogeneous clients and trustworthiness in adversarial or unreliable environments. Due to the lack of reliable metrics and models for reasoning in FL, we only provide literature-driven insights for this dimension. ATR-Bench lays the groundwork for a systematic and holistic evaluation of federated learning with real-world relevance. We will make our complete codebase publicly accessible and a curated repository that continuously tracks new developments and research in the FL literature.

cs.LG↗

arXiv2025

Context Aware Grounded Teacher for Source Free Object Detection

Source-free object detection (SFOD) faces persistent challenges due to class imbalance-driven context bias and instability in teacher-student training under noisy pseudo-labels. Existing techniques tend to ignore context bias and class-imbalance shifts, especially in medical data. To tackle this, we propose Grounded Teacher (GT), a bias-aware source-free framework that grounds the teacher model through relational and semantic regularization. To explicitly model directional confusion between classes, GT introduces a Relational Context Module (RCM) that maintains an exponential moving average (EMA) estimate of cross-domain contextual bias. Building upon this, a Semantic Augmentation (SA) strategy selectively augments minority and confusable classes through adaptive MixUp in both source-similar and source-dissimilar target regions, improving minority recall without overfitting dominant categories. To stabilize learning under biased pseudo-labels, we design a Semantic-Aware Loss (SAL) that applies diagonally normalized weights, preventing gradient explosion while emphasizing minority-majority corrections. Additionally, a frozen Expert branch derived from large vision foundation models (LVFMs) serves as a supervisory reference during training, refining pseudo-label quality without adding inference overhead. GT's behavior-driven bias quantification makes it broadly applicable across domains without relying on dataset priors. Evaluations on Cityscapes-to-Foggy (50.8 mAP) and medical transfers (+5.9 AP50 on DDSM-to-INBreast) show consistent gains and improved minority-class detection, with less than 12\% additional training cost. Code and model are available at https://github.com/Tajamul21/Grounded-Teacher.

cs.CV↗

arXiv2024

FATE: Focal-modulated Attention Encoder for Multivariate Time-series Forecasting

Climate change stands as one of the most pressing global challenges of the twenty-first century, with far-reaching consequences such as rising sea levels, melting glaciers, and increasingly extreme weather patterns. Accurate forecasting is critical for monitoring these phenomena and supporting mitigation strategies. While recent data-driven models for time-series forecasting, including CNNs, RNNs, and attention-based transformers, have shown promise, they often struggle with sequential dependencies and limited parallelization, especially in long-horizon, multivariate meteorological datasets. In this work, we present Focal Modulated Attention Encoder (FATE), a novel transformer architecture designed for reliable multivariate time-series forecasting. Unlike conventional models, FATE introduces a tensorized focal modulation mechanism that explicitly captures spatiotemporal correlations in time-series data. We further propose two modulation scores that offer interpretability by highlighting critical environmental features influencing predictions. We benchmark FATE across seven diverse real-world datasets, including ETTh1, ETTm2, Traffic, Weather5k, USA-Canada, Europe, and LargeST datasets, and show that it consistently outperforms all state-of-the-art methods, including temperature datasets. Our ablation studies also demonstrate that FATE generalizes well to broader multivariate time-series forecasting tasks.

cs.LG↗

arXiv2023

An Analysis of Various Design Pathways Towards Multi-Terabit Photonic On-Interposer Interconnects

In the wake of dwindling Moore's Law, to address the rapidly increasing complexity and cost of fabricating large-scale, monolithic systems-on-chip (SoCs), the industry has adopted dis-aggregation as a solution, wherein a large monolithic SoC is partitioned into multiple smaller chiplets that are then assembled into a large system-in-package (SiP) using advanced packaging substrates such as silicon interposer. For such interposer-based SiPs, there is a push to realize on-interposer inter-chiplet communication bandwidth of multi-Tb/s and end-to-end communication latency of no more than 10ns. This push comes as the natural progression from some recent prior works on SiP design, and is driven by the proliferating bandwidth demand of modern data-intensive workloads. To meet this bandwidth and latency goal, prior works have focused on a potential solution of using the silicon photonic interposer (SiPhI) for integrating and interconnecting a large number of chiplets into an SiP. Despite the early promise, the existing designs of on-SiPhI interconnects still have to evolve by leaps and bounds to meet the goal of multi-Tb/s bandwidth. However, the possible design pathways, upon which such an evolution can be achieved, have not been explored in any prior works yet. In this paper, we have identified several design pathways that can help evolve on-SiPhI interconnects to achieve multi-Tb/s aggregate bandwidth. We perform an extensive link-level and system-level analysis in which we explore these design pathways in isolation and in different combinations of each other. From our link-level analysis, we have observed that the design pathways that simultaneously enhance the spectral range and optical power budget available for wavelength multiplexing can render aggregate bandwidth of up to 4Tb/s per on-SiPhI link.

cs.ET↗

arXiv2022

Mathematical Analysis of Path MTU Discovery With New Generation Networks

In this paper we have presented the effects of path mtu discovery in IPv4 & IPv6 in mathematical, logical and graphical representation. We try to give a mathematical model to the working of path mtu discovery and calculated its behaviour using a transmission of a packet. We analysed the time consumed to transmit a single packet from source to destination in IPv6 network in the presence of PMTUD and similarly in IPv4 network with DF bit 1. Based on our analysis, we concluded that the communication time increases with the varying MTU of the intermediate nodes. Moreover, we formulated the mathematical model to determine the communication delay in a network. Our model shows that the asymptotic lower bound for time taken is $Ω(n)$ and the asymptotic upper bound is $Θ(n^2)$, using PMTUD. We have find that the packet drop frequency follows the Bernoulli's trials and which helps to define the success probability of the packet drop frequency, which shows that the probability is higher for packet drop rate for beginning $2\%$ of the total nodes in the path. We further found that $^{n}C_{a}$ possible number of a-combinations without repetitions that can be formed for a particular number of packet drop frequency. The relation between summation (acts as a coefficient in the time wastage equation) of each combination and their frequency resulted in symmetric graph and also mathematical and statistical structures to measure time wastage and its behaviour. This also helps in measuring the possible relative maximum, minimum and average time wastage. We also measured the probability of relative maximum, min and average summation for a given value of packet drop frequency and number of nodes in a path.

cs.NI↗

arXiv2020

Dynamic MTU : Technique to reduce packet drops in IPv6 network resulted due to smaller path mtu size

With an increase in the number of internet users and the need to secure internet traffic, the unreliable IPv4 protocol has been replaced by a more secure protocol, called IPv6 for Internet system. The IPv6 protocol does not allow intermediate routers to fragment the on-going IPv6 packet. Moreover, due to IP tunneling, some extra headers are added to the IPv6 packet, exceeding the packet size higher than the maximum transmission unit (MTU), resulting in increase in packet drops. One probable solution is to find the MTU of every link in advance using the Internet Control Message Protocol (ICMP) packets and accordingly fragment the packets at the source itself. However, most of the intermediate routers and the network firewalls do not allow ICMP packets to traverse through their network, resulting in network black holes, where we cannot know the MTU of some links in advance. This method tries to handle the packet drops in IPv6 network by proposing a DMTU scheme where we dynamically adjust the MTU of each link depending upon the original size of the IPv6 packet, thereby reducing the number of packet drops by a significant amount. Using mathematical and graphical analysis, our scheme proves to be much more efficient than the state-of-the-art PMTUD scheme. In this paper the method, mathematical and graphical representations are focusing solely in IPv6 Internet communication.

cs.NI↗