3 papers
cs.RO2026
LePlanner: An Iterative Amortized Controller For World Models
Saksham Bansal, Om Naphade, Chayan Aggarwal +1
World models trained with joint-embedding predictive architectures learn compact, structured latent representations from physical interaction, yet planning in these latent spaces t…
cs.AI2026
Think Deep, Speak Once: Relit, A Recursive Latent Implicit Transformer Framework
Abhishek Panwar, Maheep Singh, Saksham Bansal
Chain-of-Thought (CoT) prompting has become the dominant paradigm for eliciting reasoning in Large Language Models (LLMs), yet it creates substantial computational overhead by forc…
cs.LG2025
Small LLMs with Expert Blocks Are Good Enough for Hyperparamter Tuning
Om Naphade, Saksham Bansal, Parikshit Pareek
Hyper-parameter Tuning (HPT) is a necessary step in machine learning (ML) pipelines but becomes computationally expensive and opaque with larger models. Recently, Large Language Mo…