Trim Isaac 0.5 model card sections

README.md

@@ -76,14 +76,6 @@ Each mixture-of-experts layer gives every token access to 256 learned experts an
 
 ![Isaac 0.5 architecture from source families through mHarmony, sequence packing, shared backbone, and perception and control interfaces.](isaac_model_card_assets/model-architecture.png)
 
-## Training system
-
-mHarmony, our typed input compiler, converts every data source into one stream of text, vision, time, state, and action events while preserving provenance. Isaac uses the same format in training and serving.
-
-Training examples are packed into 16,384-token sequences with 2% padding across the full mixture. Video is decoded outside the training process so corrupted files can restart without interrupting a run. Visual blocks are distributed across workers before encoding to prevent one long video from slowing an entire step. The released hyper-sparse configuration reaches 24% model FLOP utilization.
-
-![Isaac training data plane, including process tiers, node-coherent planning, and sequence packing.](isaac_model_card_assets/training-data-plane.png)
-
 ## Performance benchmarks
 
 We evaluate the same Isaac checkpoints across multimodal video understanding, spatial grounding, held-out action prediction, and closed-loop robot control.
@@ -92,18 +84,6 @@ We evaluate the same Isaac checkpoints across multimodal video understanding, sp
 
 *Up and to the left is better. Ringed Isaac 0.5 results sit on the frontier; hollow markers are dominated.*
 
-## Robot-control evaluation
-
-Our YAM-native simulation and data engine is built around MolmoSpaces. It spans five hardware revisions and four grippers, producing 20 arm-and-gripper configurations with one common observation and action interface. Reach, joint limits, contact geometry, force limits, calibration, and collision envelopes remain specific to each configuration.
-
-The current zero-shot suite contains 42 tasks across nine manipulation families, including object interaction, spatial rearrangement, articulation, insertion, tool use, and multistage tasks. Compound tasks run continuously across subgoals, and grasp outcomes require valid contact with a stable object.
-
-We vary placement, lighting, instruction wording, and distractors while keeping each task and scorer fixed. Alongside task success, we report completion time, path length, jerk, collisions, slips, controller saturation, and safety interventions. Timeouts, invalid actions, dropped observations, and controller faults count as failures.
-
-Simulation provides repeatable coverage. Physical trials measure deployment directly. Where possible, we pair both and hold out complete robot families to measure transfer before hardware-specific adaptation. LIBERO and SIMPLER provide additional standardized comparisons under matched observations, instructions, action horizons, controllers, and serving paths.
-
-![YAM simulation tasks spanning single-step interaction, spatial manipulation, articulation, tool use, and ordered multistage tasks.](isaac_model_card_assets/yam-simulation-tasks.png)
-
 ## Where Isaac sits among open models
 
 | Model | Robot training scope | Obs. steps | RTC-trained | Prev. actions | Mistake modeling | Non-robot video | Flow expert | Open source |
@@ -133,10 +113,6 @@ The release includes:
 - checkpoint, data, and model-I/O manifests;
 - the technical report, model card, and reproduction guide.
 
-### Usage
-
-> **[TODO: Add final installation command and checkpoint-specific inference example.]**
-
 ## Resources
 
 - **Weights:** [Hugging Face](https://huggingface.co/PerceptronAI/Isaac-0.5)