Sandeep Mishra

Software Engineer — Google · IIT Kharagpur

I work on multimodal AI, large language models, and distributed systems. Currently building large-scale data pipelines at Google; published first-author work at EACL 2026 on vision-language auto-completion.

Smart India Hackathon
Computer Vision Image Processing ISRO

Satellite Image Mosaicing Software

Grand Finale Winner  · Smart India Hackathon · ISRO

Won the Smart India Hackathon Grand Finale among 15,000 students, competing under the Indian Space Research Organization problem statement. Developed seamless satellite image mosaicing software, acknowledged by ISRO as a viable production solution — IP shared equally with the organisation.

Router-Suggest
Multimodal AI Vision-Language LLM Routing EACL 2026

Router-Suggest: Dynamic Routing for Multimodal Auto-Completion

First-author · EACL 2026 Industry Track · with D. Budagam, A. Mandal, B. Santra, P. Goyal, M. Gupta

Defined the Multimodal Auto-Completion (MAC) vision-language task from scratch — covering task definition, dataset curation, and evaluation protocol. Benchmarked state-of-the-art VLMs (Qwen2-VL, MiniCPM-V, PaliGemma) and proposed Router-Suggest, a dynamic routing framework achieving 2.3×–10× speedup over the best VLM baseline while maintaining near-parity accuracy.

Chat-Ghosting
NLP Dialog Systems Benchmarking EACL 2026

Chat-Ghosting: Auto-Completion in Dialog Systems

Co-author · EACL 2026 · with A. Mandal, B. Santra, T. Abhishek, P. Goyal, M. Gupta

Introduced the first comprehensive benchmark for chat-ghosting (predictive text completion in conversations) across 4 public dialog datasets. Proposed an entropy-based dynamic early stopping mechanism that significantly improves Partial-Precision and TES metrics, making auto-completion practical for real dialog applications.

Cross-Lingual QA
NLP Prefix Tuning mT5 IIT Kharagpur

Zero-Shot Cross-Lingual QA via Prefix Tuning on mT5

Research Project · Prof. Pawan Goyal, CSE IIT Kharagpur

Investigated parameter-efficient fine-tuning using prefix tuning on mT5 for zero-shot cross-lingual question answering. Demonstrated competitive transfer performance with less than 1% trainable parameters compared to full fine-tuning, validating PEFT as a practical approach for multilingual NLP.

Semantic Search Engine
NLP BERT Semantic Search TensorFlow

Efficient Product Embeddings & Semantic Search Engine

Research Project · Prof. B. Adhikari, Mathematics IIT Kharagpur

Showed BERT contextual embeddings outperform Word2Vec and GloVe by 10× on product retrieval across 14,000 Amazon products. Built a working semantic search engine with 3-D TensorFlow Embedding Projector visualisation for interpretability.

EACL 2026 — Industry Track

Router-Suggest: Dynamic Routing for Multimodal Auto-Completion in Visually-Grounded Dialogs

Sandeep Mishra, D. Budagam, A. Mandal, B. Santra, P. Goyal, M. Gupta

Defined the MAC vision-language task; benchmarked SOTA VLMs; proposed Router-Suggest achieving 2.3×–10× speedup with near-parity accuracy.

PDF →

EACL 2026

Chat-Ghosting: Methods for Auto-Completion in Dialog Systems

A. Mandal, Sandeep Mishra, B. Santra, T. Abhishek, P. Goyal, M. Gupta

First comprehensive benchmark for chat-ghosting across 4 public dialog datasets; entropy-based dynamic early stopping significantly improves Partial-Precision and TES.

PDF →
Loading repositories…