Add higher-capacity last-four-layer fusion

README.md

@@ -79,6 +79,74 @@ The raw 8-second console output, machine-readable comparison, and detailed
 interpretation are archived in
 [`results/easycom_open_stream_8s_vs_20s_2026-08-23/`](results/easycom_open_stream_8s_vs_20s_2026-08-23/README.md).
 
+### Last-4 query-layer learned mixture
+
+A frozen Qwen2.5-Omni-3B experiment now reads the query states from the final
+four Thinker layers and learns four global softmax mixture weights before the
+same `10 x 3` anticipation head. With an 8-second open-stream context, 2 FPS
+video, 5 Hz outputs, and 25 head-training epochs, it reaches **73.45085** mAP
+at 0.2 seconds and **60.53423** mean mAP on official test Sessions 3, 2, and 1.
+Relative to the recorded single-final-layer 8-second run, this is **+1.45317**
+at 0.2 seconds and **+2.01486** mean mAP, with positive gains at every horizon.
+
+The final oldest-to-newest layer weights are
+`[0.246384, 0.248327, 0.241774, 0.263515]`. Because they remain almost uniform,
+the result currently demonstrates the value of multi-layer query readout, not
+yet the value of learning the mixture. A fixed uniform last-4 mean is the next
+required control. The complete table, machine-readable metrics, provenance,
+and naming caveat are archived in
+[`results/easycom_frozen_3b_8s_last4_learned_mix_2026-08-26/`](results/easycom_frozen_3b_8s_last4_learned_mix_2026-08-26/README.md).
+
+#### Higher-capacity last-4 concat-MLP ablation
+
+`train_turn_head.py` also supports a higher-capacity fusion control. It
+flattens each `[4, 2048]` last-layer stack to `8192` dimensions, applies
+`LayerNorm -> Linear(8192, 2048) -> GELU`, and then uses the unchanged
+anticipation MLP. This adds about 16.8 million fusion parameters, compared
+with four logits in the scalar-mixture experiment. Keep the seed and training
+recipe fixed for a clean capacity ablation:
+
+```bash
+CUDA_VISIBLE_DEVICES=0 \
+OMP_NUM_THREADS=4 \
+MKL_NUM_THREADS=4 \
+OPENBLAS_NUM_THREADS=4 \
+python train_turn_head.py \
+  --feature-root /data1/yfzx/wangx/Datasets/easycom/omni_features/open_stream_2fps_8s_last4_stack \
+  --target-root /data1/yfzx/wangx/Datasets/easycom/easycom_target_frame \
+  --output checkpoints/easycom_frozen_3b_8s_last4_concat_mlp_25ep.pth \
+  --sessions 4 5 6 7 8 9 10 11 12 \
+  --epochs 25 \
+  --batch-size 512 \
+  --learning-rate 7e-5 \
+  --weight-decay 5e-5 \
+  --warmup-epochs 10 \
+  --warmup-factor 0.3 \
+  --dropout 0.2 \
+  --loss lstr-mce \
+  --layer-fusion concat-mlp \
+  --expected-mode open-stream-replay \
+  --seed 0 \
+  --device cuda:0
+```
+
+Evaluate with the same dense stacked test features:
+
+```bash
+CUDA_VISIBLE_DEVICES=0 python infer_turn_head.py \
+  --feature-root /data1/yfzx/wangx/Datasets/easycom/omni_features/open_stream_2fps_8s_last4_stack \
+  --target-root /data1/yfzx/wangx/Datasets/easycom/easycom_target_frame \
+  --checkpoint checkpoints/easycom_frozen_3b_8s_last4_concat_mlp_25ep.pth \
+  --output-dir results/easycom_frozen_3b_8s_last4_concat_mlp_25ep \
+  --expected-mode open-stream-replay \
+  --batch-size 1024 \
+  --device cuda:0
+```
+
+Treat this as a capacity ablation. If it improves, compare it against a
+parameter-matched single-layer MLP and use stronger regularization or a clean
+development session before attributing the gain to cross-layer fusion.
+
 ## Current Ego4D context-length results
 
 The following single-seed snapshot was recorded on 2026-08-22. Both variants