Skip to content
View rohitsalla's full-sized avatar
😴
I may be slow to respond.
😴
I may be slow to respond.
11 followers · 108 following

Achievements

Achievement: Quickdraw

Achievements

Achievement: Quickdraw

Block or report rohitsalla

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
rohitsalla/README.md

🔬 Research Interests

I work on multimodal AI and reliable retrieval & reasoning, with a focus on:

  • VLM/MLLM reliability & diagnostics
  • Multi-query LLM reasoning (contradictions, consistency)
  • Retrieval systems under semantic drift (RAG, continual indexing)
  • Training dynamics & phase transitions (data mixture effects)
  • Robotics perception (when it supports reliable decision-making)

🧪 What I'm Building Here

On this GitHub you’ll find reproducible experiments, clean ablations, and paper-aligned code.

  • paper repos: code + configs + scripts to reproduce results
  • experiments: ablations, sweeps, evaluation utilities
  • notes: reading notes + mini writeups (ideas → experiments)

📊 GitHub Stats

📌 Connect

Pinned Loading

  1. CRS CRS Public

    Python

  2. ivy ivy Public

    Forked from ivy-llc/ivy

    The Unified AI Framework

    Python

  3. katib katib Public

    Forked from kubeflow/katib

    Repository for hyperparameter tuning

    Go

  4. quaterion quaterion Public

    Forked from qdrant/quaterion

    Blazing fast framework for fine-tuning similarity learning models

    Python