Skip to content
View S1rlvk's full-sized avatar

Block or report S1rlvk

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.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

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

Report abuse
S1rlvk/README.md

Sarthak Sattigeri

I am a B.Tech Computer Science & Biosciences student at Manipal University Jaipur, working on ML evaluation, vision-language models, and robotic manipulation.

My current research focus is on testing where frontier and open-weight models fail when they are pushed from language-level reasoning into grounded physical tasks. I am especially interested in VLM affordance prediction, robotic grasping, egocentric video understanding, and multilingual LLM behavior.

Research Interests

  • Vision-language model evaluation for robotics and physical affordances
  • Robotic manipulation, grasping, and part grounding
  • Multilingual LLM evaluation, especially Hindi and Indian-language settings
  • Egocentric video, IMU signals, and activity boundary detection
  • Reliable benchmarks with simple baselines, reproducible code, and failure-mode analysis

Selected Work

  • SmolWAM on RoboCasa: Moving a 0.88B world-action model from LIBERO to RoboCasa kitchens. Zero-shot it failed 30 of 30 episodes; after behavior-cloning fine-tuning on 3,108 demos it succeeds in 9 of 20 episodes in held-out kitchens. Includes the adapter, training recipe, results and videos.
  • VLM Force Prediction: Zero-shot benchmark testing whether a VLM can infer robotic grasping force from images; includes physics-based ground truth, fragile-object safety analysis, and result scripts.
  • Phase-Conditioned Trajectory: Research code for phase-conditioned Kalman filtering of hand trajectories and next-phase prediction experiments.
  • WEAR IMU Segmentation: IMU vs. I3D vs. fusion experiments for subtask boundary detection using 18-subject LOSO cross-validation.
  • IODarkWatch: Open-source maritime domain awareness project for detecting suspicious vessel behavior and AIS gaps in the Indian Ocean region.

Publications & Preprints

  • GroundBench: A factorized, counterfactual benchmark for locating where VLMs fail at affordance prediction. Poster, NeurIPS 2026 RoboPAD Workshop. arXiv:2609.13308
  • Extending Beacon to Hindi: Cross-lingual sycophancy evaluation in English, Hindi literal translation, and Hindi culturally adapted settings. arXiv:2602.00046
  • Part Grounding, Not Action Knowledge: VLM affordance prediction experiments on articulated-object manipulation. Currently under arXiv review/hold.

Tools

Python, PyTorch, MuJoCo, robosuite, RoboCasa, scikit-learn, OpenCV, MediaPipe, MiDaS, FilterPy, NumPy, Pandas, Matplotlib, Hugging Face Transformers, LM Studio, Git, LaTeX.

Contact

Popular repositories Loading

  1. IODarkWatch IODarkWatch Public

    Open-Source Maritime Domain-Awareness for the Indian Ocean

    HTML 2

  2. ChatThero-Lite ChatThero-Lite Public

    Accessible therapeutic AI optimized for Apple Silicon (M1/M2/M4) with 90% crisis detection accuracy. Implementation of ChatThero paper with professional-grade evaluation, Docker support, and compre…

    Python 2

  3. S1rlvk S1rlvk Public

    Config files for my GitHub profile.

    1

  4. Development-of-an-Intelligent-Freight-Forecasting-Model Development-of-an-Intelligent-Freight-Forecasting-Model Public

    HTML 1

  5. up-for-grabs.net up-for-grabs.net Public

    Forked from up-for-grabs/up-for-grabs.net

    This is a list of projects which have curated tasks specifically for new contributors. These issues are a great way to get started with a project, or to help share the load of working on open sourc…

    JavaScript

  6. ZoomTutor ZoomTutor Public

    AI/LLM interface specifically designed around understanding large, complex topics, projects or papers.

    Python