Skip to content

Author

Suman Banerjee

We have 6 of 17 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Sep 2026

Koa-decision: Fast and Consistent Structured Decision Making with Generative LLMs

Industry applications often demand low-latency classification, yet current large language model (LLM) approaches remain poorly suited for latency-critical applications. Existing prompting and constrained decoding produce verbose, multi-token outputs that require expensive token-by-token generation, while encoder-based...

Sheng-Hong Dai, S. Pentyala, Ying-Chi Liu et al. · 1 citation
Preprint Oct 2026

Shared Context, Separate Engines: Stateful Streaming Inference for Multimodal LLMs on Edge SoCs

Edge SoCs combine CPUs, GPUs, and NPUs, yet runtimes for multimodal large language models (MLLMs) keep generation on one engine and leave others idle. Streaming workloads allow ingestion and answering to overlap, but backend-local KV state binds queries to the engine that built their history. Stage performance and co-r...

Yi-Long Li, Cheng-Po Yan, Yi-Jing Zeng et al. · 0 citations
#machine learning Preprint Sep 2026

Koa-action: Fast and Consistent Structured Decision Making with Generative LLMs

Koa-action is a framework for low-latency atomic actions -- fast, single-step decisions such as classification, semantic endpointing, Boolean checks, and scoring -- formulated as constrained generation with single-token outputs by introducing atomic label tokens and applying supervised fine-tuning.

Sheng-Hong Dai, S. Pentyala, Ying-Chi Liu et al. · 0 citations
#machine learning Preprint Sep 2026

Statistical Convergence of Transformer Encoder-Accelerated Robust Reinforcement Learning

Obtaining the optimal action-value function in Markov decision processes is computationally intensive in large state--action spaces. In this study, we present statistically rigorous convergence results for a robust reinforcement learning algorithm warm-started by a transformer-based action-value function prediction, wh...

Suman Banerjee, Hiroyasu Tsukamoto · 0 citations
Preprint Sep 2026

QEmbed: A Deep Learning Based Cardinality Estimator for Efficient Query Processing

This paper proposes a deep learning model formally called QEmbed, built upon the Masked Autoencoder for Distribution Estimation (MADE) auto-regressive framework to learn joint data distributions for selectivity estimation, and designs a hybrid encoding scheme that combines one-hot and embedding encodings.

Pooja Rajput, Suman Banerjee · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.