arXiv subjects

Saptarshi Majumder

Publications and source records attributed to Saptarshi Majumder.

5 recordsLinked to original sources

arXiv2026

AMDKernelVault: Large-Scale Datasets and Agentic Training for AMD GPU Kernel Optimization

We introduce AMDKernelVault, an open HIP and Triton kernel corpus and training framework for recent AMD CDNA GPUs. Existing LLM-based kernel agents are largely CUDA/NVIDIA-centric and often depend on repeated frontier-LLM calls for generation, reflection, and optimization. To address this gap, we develop HIPKernelGen and TritonKernelGen, agent-driven pipelines that transform PyTorch references into HIP or Triton kernels, compile and validate candidates under ROCm, and latency-profile them on AMD hardware. The corpus contains 62,153 execution-verified HIP kernel samples, 2,377 production-grounded ROCm Libraries QA entries, and 39,893 Triton kernels. We further train Qwen3-8B with supervised fine-tuning and execution-aware reinforcement learning as a demonstration of the corpus's utility. Under fixed evaluation budgets, it achieves the highest correctness among the compared models on PyTorch-to-HIP (34.0% Pass@1), TritonBench-G (33.2% Corr@3), and ROCmBench (41.94% Corr@3), but does not uniformly lead compilation or speed metrics. The corpus and documentation are available at https://huggingface.co/datasets/amd/AIG-Datasets, and the associated training and kernel-generation code is available at https://github.com/AMD-AGI/hip_kernel_llm_lab.

cs.CL↗

arXiv2026

Pause and Think: A Dataset and Benchmark for Video-Grounded Assistive Action Suggestion

Recent Vision-Language Models (VLMs) struggle with grounded reasoning, temporal consistency, and context aware planning in videos. We introduce pause-and-think-T, a reasoning-centric training dataset that encourages models to pause, reason over visual evidence, and produce concise, actionable responses. The dataset promotes structured reasoning prior to answer generation, guiding models toward human-like, scene-grounded assistance. We fine-tune a compact 4B-parameter model and evaluate it on our pause-and-think-B benchmark targeting contextual understanding and goal planning tasks. The model achieves 58.0% accuracy at 59x fewer parameters than Qwen3-VL-235B (58.9%), matching GPT-5.2 on scene understanding and surpassing GPT-4o. Beyond our benchmark, it also shows strong out-of-distribution performance on EgoThink and TempCompass, with substantial gains in affordance, assistance, attribution recognition, situated reasoning, and temporal order, without benchmark-specific training. Our results indicate that targeted reasoning supervision enables compact models to deliver actionable, visually grounded guidance while generalizing beyond training data, without requiring large-scale model expansion.

cs.CV↗

arXiv2025

Geak: Introducing Triton Kernel AI Agent & Evaluation Benchmarks

The demand for AI-generated GPU kernels is rapidly growing, influenced by the need for scalable, hardware-optimized solutions in both industry and academia. As deep learning workloads grow in complexity and diversity, it is imperative to automate low-level kernel development to meet performance and productivity demands. Major cloud providers, semiconductor companies, and research institutions are now investing heavily in AI-driven code generation for GPUs, aiming to reduce manual optimization efforts while achieving near-expert performance on hardware like AMD MI300X. The Triton language, a Python-based DSL for GPU programming, has emerged as a popular target for such AI-generated kernels due to its balance of performance and ease-of-coding. In this work, we present an evaluation suite for Triton-based GPU kernels and GEAK (Generating Efficient AI-centric GPU Kernels)-a framework that leverages cutting-edge LLMs to generate performant Triton code specifically for AMD GPUs, including the AMD MI300X and MI250. GEAK leverages inference-time compute scaling to produce Triton-based GPU kernels using a reasoning loop adapted from Reflexion-style feedback mechanisms. On two evaluation benchmarks, GEAK significantly outperformed the baselines of directly prompting frontier LLMs as well as Reflexion-based generation pipelines by achieving correctness up to $63$% and execution speed up of up to $2.59$X. These results highlight the promise of GEAK-like agentic code generation for accelerating the adoption of diverse hardware platforms and democratizing access to expert-level kernel performance.

cs.CL↗

arXiv2020

EMRs with Blockchain : A distributed democratised Electronic Medical Record sharing platform

Medical data sharing needs to be done with the utmost respect for privacy and security. It contains intimate data of the patient and any access to it must be highly regulated. With the emergence of vertical solutions in healthcare institutions, interoperability across organisations has been hindered. The authors of this paper propose a blockchain based medical-data sharing solution, utilising Hyperledger Fabric to regulate access to medical data, and using the InterPlanatory File System for its storage. We believe that the combination of these two distributed solutions can enable patients to access their medical records across healthcare institutions while ensuring non-repudiation, immutability and providing data-ownership. It would enable healthcare practitioners to access all previous medical records in a single location, empowering them with the data required for the effective diagnosis and treatment of patients. Making it safe and straightforward, it would also enable patients to share medical data with research institutions, leading to the creation of reliable data sets, laying the groundwork required for the creation of personalised medicine.

cs.CR↗

arXiv2020

Depression Status Estimation by Deep Learning based Hybrid Multi-Modal Fusion Model

Preliminary detection of mild depression could immensely help in effective treatment of the common mental health disorder. Due to the lack of proper awareness and the ample mix of stigmas and misconceptions present within the society, mental health status estimation has become a truly difficult task. Due to the immense variations in character level traits from person to person, traditional deep learning methods fail to generalize in a real world setting. In our study we aim to create a human allied AI workflow which could efficiently adapt to specific users and effectively perform in real world scenarios. We propose a Hybrid deep learning approach that combines the essence of one shot learning, classical supervised deep learning methods and human allied interactions for adaptation. In order to capture maximum information and make efficient diagnosis video, audio, and text modalities are utilized. Our Hybrid Fusion model achieved a high accuracy of 96.3% on the Dataset; and attained an AUC of 0.9682 which proves its robustness in discriminating classes in complex real-world scenarios making sure that no cases of mild depression are missed during diagnosis. The proposed method is deployed in a cloud-based smartphone application for robust testing. With user-specific adaptations and state of the art methodologies, we present a state-of-the-art model with user friendly experience.

cs.LG↗