LWM-TF Lab

A wireless foundation model on 5G NR time-frequency resource grids. Paper · Model & code

Loading data…

How one training slot is made. Pick an example and follow it through the eight stages of the released generator (dataset/ in wi-lab/lwm-tf, Sionna 2.1). The 24 examples cover 4 channel classes × 3 modulations × static/mobile. Every number and array below was produced by that code and precomputed; nothing is simulated in your browser.

①

Link configuration

config.py · build_pusch_config → transmitter.py · build_resource_gridpaper §II-A

The resource grid geometry (PRBs, SCS and DMRS) is fixed per batch. DMRS uses mapping type A, configuration type 1, and the REs of the CDM group without data stay empty. The four additional positions trade pilot overhead against time tracking.

DMRS additional position
②

Axis sampling

corpus.py · plan_mix · channel.py · draw_target_snr_db · link_adaptation.py · draw_modulation_orderspaper §II, parameter-space table

The corpus plan is fixed before any channel is drawn. It holds exactly 250k slots per class, split evenly over the DMRS positions, with 25% static UEs in every cell. Target SNR and modulation are drawn per slot, independently of each other and of the channel.

③

Transmit chain

transmitter.py · transmit_per_mcsTS 38.212 / 38.211, paper §II-A
④

Channel

channel.py · build_channel, set_topology (TR 38.901) · deepmimo.py · LinkPool, synthesizepaper §II-B

TR 38.901 draws one single-sector topology per slot, with path loss and shadow fading. DeepMIMO uses ray-traced paths with centred subcarriers, first-arrival timing and per-path Doppler u·v/λ at the OFDM symbol starts.

⑤

Noise calibration

channel.py · noise_variance_for_snrpaper §II-B

At fixed transmit power the scenarios sit tens of dB apart. Noise is therefore set from the drawn target SNR, σ² = ḡγ g1−γ / 10ρ/10, with γ = 0 in this corpus. Then Y = H·X + W.

⑦

Receiver & labels

receiver.py · build_channel_estimator, decode_per_mcspaper §II-D

A 3GPP receiver runs on every slot to produce its labels: an LS estimate on the DMRS, LMMSE equalization, max-log demapping, then LDPC decoding and the transport-block CRC. The encoder never sees this chain; its input is Y itself.

⑧

Normalize & store

corpus.py · receive → _flushpaper §II-D

Each slot is divided by its RMS and stored as float16, with Re/Im interleaved per port. The scale and every label go to a separate file that only the downstream probes read.