arXiv subjects

Muhammad Ahmed

Publications and source records attributed to Muhammad Ahmed.

9 recordsLinked to original sources

arXiv2026

PersistentKV: Page-Aware Decode Scheduling for Long-Context LLM Serving on Commodity GPUs

Autoregressive large language model (LLM) serving is increasingly limited by key-value (KV) cache movement rather than dense matrix multiplication. Modern paged-attention systems reduce fragmentation, and mature kernels like FlashInfer provide highly optimized decode attention. However, the best single-kernel implementation is not always the best serving schedule: low-active long-context decode can under-utilize GPUs, while mixed sequence lengths introduce tension between many exact-length launches and coarse padded batches. We present PersistentKV, a native block-table decode attention engine and page-aware scheduling study for grouped-query attention (GQA). PersistentKV maps work by KV-head group, executes directly over native page tables, and adds a compact workqueue schedule executing only non-empty row-KV-head-sequence-split tasks. On an RTX 3060 (FP16, page size 16, Hq=32, Hkv=8, d=128), a calibrated roofline-style policy selects FlashInfer for small active batches, PersistentKV sequence splitting for batch size 1 (B1) long-context steps, and PersistentKV workqueue scheduling for supported B8 long-context GQA steps. With cost-model constants fixed on calibration traces, five held-out seeds improve mean wall decode-token throughput by 1.04x to 1.08x on B8 bimodal, uniform, and Zipf-like workloads, and by 1.40x on a B1 bucketed trace. For the B4 boundary case and uncalibrated GQA ratios, the policy avoids regressions by routing to FlashInfer. We also report an attention-plus-MLP timing proxy and workload counters showing workqueue scheduling reduces launch fan-out from 16.00 to 2.00 launches per step on held-out bimodal B8. These results show that work assignment is a decisive serving-system variable.

cs.LG↗

arXiv2026

Parallel Causal Associative Fields: Gated Sparse Memory for Long-Context Language Modeling

Transformers achieve strong language modeling performance by providing direct token-to-token communication paths, but causal self-attention scales quadratically with context length. Recurrent and state-space models reduce this cost, yet compress history into sequentially updated fixed-size states. This paper studies a third primitive: a parallel content-addressed memory over causal successor records. The proposed Parallel Causal Associative Field (PCAF) writes local records from a context window into hash buckets, retrieves a bounded candidate set for the current query, forms a sparse cache distribution over successor tokens, and mixes that cache with a parametric local language model through a learned gate. The resulting model maintains sparse long-context access while avoiding a single fixed recurrent state bottleneck. We evaluate PCAF under full autoregressive pretraining on WikiText-103 and PG-19 using a distributed Google Cloud TPU v4-32 pod. At 303M parameters and context length T = 2048, PCAF-semantic reaches 36.31 perplexity on WikiText-103 and 52.45 perplexity on PG-19, compared with 47.49 and 53.84 for a matched dense Transformer. PCAF-semantic simultaneously processes 0.61-0.62M tokens/s across the TPU pod, versus 0.43M tokens/s for dense and local attention baselines. Supporting 41M-parameter multi-seed sweeps and single-GPU component ablations show that the associative cache, retrieval capacity, and learned gate materially affect the speed-quality trade-off.

cs.LG↗

arXiv2026

From Knowledge to Action: Outcomes of the 2025 Large Language Model (LLM) Hackathon for Applications in Materials Science and Chemistry

Large language models (LLMs) are rapidly changing how researchers in materials science and chemistry discover, organize, and act on scientific knowledge. This paper analyzes a broad set of community-developed LLM applications in an effort to identify emerging patterns in how these systems can be used across the scientific research lifecycle. We organize the projects into two complementary categories: Knowledge Infrastructure, systems that structure, retrieve, synthesize, and validate scientific information; and Action Systems, systems that execute, coordinate, or automate scientific work across computational and experimental environments. The submissions reveal a shift from single-purpose LLM tools toward integrated, multi-agent workflows that combine retrieval, reasoning, tool use, and domain-specific validation. Prominent themes include retrieval-augmented generation as grounding infrastructure, persistent structured knowledge representations, multimodal and multilingual scientific inputs, and early progress toward laboratory-integrated closed-loop systems. Together, these results suggest that LLMs are evolving from general-purpose assistants into composable infrastructure for scientific reasoning and action. This work provides a community snapshot of that transition and a practical taxonomy for understanding emerging LLM-enabled workflows in materials science and chemistry.

cond-mat.mtrl-sci↗

arXiv2026

Large Language Models in Game Development: Implications for Gameplay, Playability, and Player Experience

This paper investigates how the integration of large language models influences gameplay, playability, and player experience in game development. We report a collaborative autoethnographic study of two game projects in which LLMs were embedded as architectural components. Reflective narratives and development artifacts were analyzed using gameplay, playability, and player experience as guiding constructs. The findings suggest that LLM integration increases variability and personalization while introducing challenges related to correctness, difficulty calibration, and structural coherence across these concepts. The study provides preliminary empirical insight into how generative AI integration reshapes established game constructs and introduces new architectural and quality considerations within game engineering practice.

cs.SE↗

arXiv2025

Modernizing CNN-based Weather Forecast Model towards Higher Computational Efficiency

Recently, AI-based weather forecast models have achieved impressive advances. These models have reached accuracy levels comparable to traditional NWP systems, marking a significant milestone in data-driven weather prediction. However, they mostly leverage Transformer-based architectures, which often leads to high training complexity and resource demands due to the massive parameter sizes. In this study, we introduce a modernized CNN-based model for global weather forecasting that delivers competitive accuracy while significantly reducing computational requirements. To present a systematic modernization roadmap, we highlight key architectural enhancements across multiple design scales from an earlier CNN-based approach. KAI-a incorporates a scale-invariant architecture and InceptionNeXt-based blocks within a geophysically-aware design, tailored to the structure of Earth system data. Trained on the ERA5 daily dataset with 67 atmospheric variables, the model contains about 7 million parameters and completes training in just 12 hours on a single NVIDIA L40s GPU. Our evaluation shows that KAI-a matches the performance of state-of-the-art models in medium-range weather forecasting, while offering a significantly lightweight design. Furthermore, case studies on the 2018 European heatwave and the East Asian summer monsoon demonstrate KAI-a's robust skill in capturing extreme events, reinforcing its practical utility.

cs.CV↗

arXiv2023

Permutation-Aware Action Segmentation via Unsupervised Frame-to-Segment Alignment

This paper presents an unsupervised transformer-based framework for temporal activity segmentation which leverages not only frame-level cues but also segment-level cues. This is in contrast with previous methods which often rely on frame-level information only. Our approach begins with a frame-level prediction module which estimates framewise action classes via a transformer encoder. The frame-level prediction module is trained in an unsupervised manner via temporal optimal transport. To exploit segment-level information, we utilize a segment-level prediction module and a frame-to-segment alignment module. The former includes a transformer decoder for estimating video transcripts, while the latter matches frame-level features with segment-level features, yielding permutation-aware segmentation results. Moreover, inspired by temporal optimal transport, we introduce simple-yet-effective pseudo labels for unsupervised training of the above modules. Our experiments on four public datasets, i.e., 50 Salads, YouTube Instructions, Breakfast, and Desktop Assembly show that our approach achieves comparable or better performance than previous methods in unsupervised activity segmentation. Our code and dataset are available on our research website: https://retrocausal.ai/research/.

cs.CV↗

arXiv2023

Learning by Aligning 2D Skeleton Sequences and Multi-Modality Fusion

This paper presents a self-supervised temporal video alignment framework which is useful for several fine-grained human activity understanding applications. In contrast with the state-of-the-art method of CASA, where sequences of 3D skeleton coordinates are taken directly as input, our key idea is to use sequences of 2D skeleton heatmaps as input. Unlike CASA which performs self-attention in the temporal domain only, we feed 2D skeleton heatmaps to a video transformer which performs self-attention both in the spatial and temporal domains for extracting effective spatiotemporal and contextual features. In addition, we introduce simple heatmap augmentation techniques based on 2D skeletons for self-supervised learning. Despite the lack of 3D information, our approach achieves not only higher accuracy but also better robustness against missing and noisy keypoints than CASA. Furthermore, extensive evaluations on three public datasets, i.e., Penn Action, IKEA ASM, and H2O, demonstrate that our approach outperforms previous methods in different fine-grained human activity understanding tasks. Finally, fusing 2D skeleton heatmaps with RGB videos yields the state-of-the-art on all metrics and datasets. To our best knowledge, our work is the first to utilize 2D skeleton heatmap inputs and the first to explore multi-modality fusion for temporal video alignment. Our code and dataset are available on our research website: https://retrocausal.ai/research/.

cs.CV↗

arXiv2023

Sequential Embedding-based Attentive (SEA) classifier for malware classification

The tremendous growth in smart devices has uplifted several security threats. One of the most prominent threats is malicious software also known as malware. Malware has the capability of corrupting a device and collapsing an entire network. Therefore, its early detection and mitigation are extremely important to avoid catastrophic effects. In this work, we came up with a solution for malware detection using state-of-the-art natural language processing (NLP) techniques. Our main focus is to provide a lightweight yet effective classifier for malware detection which can be used for heterogeneous devices, be it a resource constraint device or a resourceful machine. Our proposed model is tested on the benchmark data set with an accuracy and log loss score of 99.13 percent and 0.04 respectively.

cs.CR↗

arXiv2021

Formalization of Transform Methods in Higher-order Logic: A Survey

Most of the engineering and physical systems are generally characterized by differential and difference equations based on their continuous-time and discrete-time dynamics, respectively. Moreover, these dynamical models are analyzed using transform methods to prove various properties of these systems, such as, transfer function, frequency response and stability, and to find out solutions of the differential/difference equations. The conventional techniques for performing the transform methods based analysis have been unable to provide an accurate analysis of these systems. Therefore, higher-order-logic theorem proving, a formal method, has been used for accurately analyzing systems based on transform methods. In this paper, we survey developments for transform methods based analysis in various higher-order-logic theorem provers and overview the corresponding real world case studies from the avionics, medicine and transportation domains that have been analyzed based on these developments.

cs.LO↗