kseelams/cs593-flowq

AI model by kseelams

Open original source ↗

From the publisher

Model card & documentation

Source preview

Read the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.

Research prototype extending Q2RL-style value estimation and action gating to frozen flow-matching imitation policies. Only the original Robomimic Lift, Can and Square tasks and PH demonstrations are used. The completed work is stage 1: train and evaluate Flow BC. Value estimation, likelihood/entropy and A/B/C runner code is implemented, but a trained-policy Q-gating pilot has not been run. No RL improvement is claimed. These are actual simulator results from one training seed (0), 10,000 BC updates per task, and evaluation reset seeds 30000–30019. Models were frozen throughout evaluation. Square is still weak, and these small evaluations are not evidence of a statistically significant improvement. See report, all-task metrics, and reference audit. This Git repository contains source, configurations, dependency pins and compact evaluation records. Datasets, pretrained weights, videos, raw trajectories, local environments and machine-specific setup history are not stored in Git. Checkpoint hashes in results/ identify the locally evaluated models. The commands…

kseelams/cs593-flowq on Hugging Face A short preview, not the full document.

Read the full model card ↗ · Preview checked 2026-11-21T08:26:42.228Z

Inside the original model card — Document outline
  1. FlowQ: frozen Flow-Matching BC for Robomimic
  2. Setup
  3. Original demonstration data
  4. Train and evaluate Flow BC
  5. Checks and Lift video rendering
  6. Implemented stage 2 (not yet run with the trained checkpoints)
  7. References and attribution

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Links from the model card

References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.

Documentation belongs to its respective authors. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

Model overview

kseelams/cs593-flowq is a task-unspecified model repository published by kseelams on Hugging Face. A library was not reported.

This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.

Model facts

Task
Not reported
Library
Not reported
Recent downloads (30 days)
0
Cumulative likes
0
Hugging Face trending score
0
Reported safetensors parameters
Not reported
Architecture
Not reported
License
Not reported — check the model card
Access
Not gated by Hugging Face
Created
2026-11-21T06:36:39.000Z
Last modified
2026-11-21T06:39:16.000Z

Compatibility and lineage

Language coverage was not reported.

Base-model lineage was not included.

Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.

Use and evaluate

Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.

No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.

Model card and usage instructions

Model files and configuration

Community discussion

Source and freshness

Source: Hugging Face Hub. Metadata observed 2026-11-21T07:02:33.996Z. Daily imports are snapshots, not real-time monitoring.

Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.

Open original source

Related models