Edit for tone; remove em dashes

README.md

@@ -15,22 +15,22 @@ tags:
   - emnlp2026
 ---
 
-# PRISM — EgoExo4D
+# PRISM
 
-**P**redictive **R**ecomposition v**I**a **S**emantic Latent Deco**M**position for
-View-invariant Video Representation Learning — **EMNLP 2026 (Main Conference)**.
+Predictive Recomposition via Semantic Latent Decomposition for View-invariant Video
+Representation Learning. EMNLP 2026, main conference.
 
 [Paper][paper] · [Project page][project] · [Code][code]
 
 PRISM decomposes each video clip into a view-invariant latent `z_vi` and a view-variant
-latent `z_vv`, then recomposes them under language supervision — `z_vi` of clip A with
-`z_vv` of clip B is trained to match the embedding of the correspondingly recombined
-caption. Because that composition never occurs in the training data, semantics that leaked
-between the two streams cannot survive it. The clip embedding this model returns is the
-view-invariant stream, so cosine similarity measures *what is happening*, not *where the
-camera is*.
-
-This checkpoint is trained on **EgoExo4D**, with ego and exo views and captions generated
+latent `z_vv`, then recomposes the two under language supervision: `z_vi` of clip A paired
+with `z_vv` of clip B is trained to match the embedding of the correspondingly recombined
+caption. That composition never occurs in the training data, so semantics that leaked
+between the streams cannot survive it. The clip embedding this model returns is the
+view-invariant stream, which makes cosine similarity a measure of what is happening rather
+than of where the camera is.
+
+This checkpoint is trained on EgoExo4D, using both ego and exo views and captions generated
 by Gemini 3.
 
 ## Usage
@@ -49,12 +49,12 @@ pixel_values = proc(images=frames, return_tensors="pt").pixel_values[None]
 pixel_values = pixel_values.to("cuda", torch.bfloat16)      # (1, T, 3, 384, 384)
 valid_mask = torch.ones(pixel_values.shape[:2], dtype=torch.bool, device="cuda")
 
-emb = model.encode(pixel_values, valid_mask)                # (1, 512) — L2-normalized
+emb = model.encode(pixel_values, valid_mask)                # (1, 512), L2-normalized
 ```
 
 | | |
 |:---|:---|
-| `model.encode(pixel_values, valid_mask)` | `(B, 512)` L2-normalized clip embedding — mean-pooled `z_vi` over valid frames |
+| `model.encode(pixel_values, valid_mask)` | `(B, 512)` L2-normalized clip embedding, mean-pooled `z_vi` over valid frames |
 | `model.encode_streams(pixel_values, valid_mask)` | `{"z_vi_seq", "z_vv_seq"}`, each `(B, T, 512)` per-frame |
 
 **Inputs.** `pixel_values` is `(B, T, 3, 384, 384)`, frames sampled at 4 fps, up to
@@ -66,10 +66,11 @@ For batched encoding of a clip manifest, see `scripts/encode.sh` in the [code re
 
 ## Results
 
-**Cross-view semantic alignment.** Gains over the best baseline, ViewpointRosetta:
-**+10.4** Retrieval and **+11.5** Association, plus +7.46 Recognition and +7.32
-Anticipation. On Skill Assessment PRISM is comparable (55.28 vs 55.82) — proficiency cues
-depend on execution style rather than action identity, and land in the view-variant stream.
+**Cross-view semantic alignment.** Gains over the best baseline, ViewpointRosetta: +10.4 on
+Retrieval, +11.5 on Association, +7.46 on Recognition, +7.32 on Anticipation. Skill
+Assessment is the exception, where PRISM (55.28) only matches ViewpointRosetta (55.82);
+proficiency cues depend on execution style rather than action identity, so they land in the
+view-variant stream.
 
 | Method | <sub>**EgoExo4D**</sub><br>Retr. ego→exo | <br>exo→ego | <br>avg | <br>Recog. top-1 | <br>Skill | <sub>**EgoExoLearn**</sub><br>Assoc. avg | <br>Antic. avg | <br>Skill |
 |:---|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|
@@ -91,8 +92,8 @@ tasks, and ahead of the best in-domain model on phase ordering and phase progres
 | ViewpointRosetta | ✘ | 54.17 | 0.047 | 46.93 | −0.150 |
 | **PRISM** | ✘ | **70.53** | **0.601** | **73.57** | **0.647** |
 
-**Robustness to background correlation (UNSCENE)** — videos whose action contradicts the
-background, averaged over three text encoders: PRISM reaches **14.9** R@10 / **0.181** RSA
+**Robustness to background correlation (UNSCENE).** On videos whose action contradicts the
+background, averaged over three text encoders, PRISM reaches 14.9 R@10 and 0.181 RSA,
 against 7.5 / 0.098 for ViewpointRosetta and 14.1 / 0.146 for DINOv2.
 
 Full tables, ablations, and the DEVIAS stream-probe analysis are in the [paper][paper] and
@@ -102,8 +103,8 @@ the [code repo][code].
 
 | Component | |
 |:---|:---|
-| Vision backbone | `google/siglip2-so400m-patch14-384` — **frozen**, not stored here |
-| Text backbone | `Qwen/Qwen3-Embedding-0.6B` — **frozen**, not stored here |
+| Vision backbone | `google/siglip2-so400m-patch14-384`, frozen and not stored here |
+| Text backbone | `Qwen/Qwen3-Embedding-0.6B`, frozen and not stored here |
 | Decompositional Encoder θ | 4-layer Q-Former (2 queries → `z_vi`, `z_vv`) + 12-layer causal temporal stack per stream |
 | Compositional Latent Predictor φ | 4-layer causal transformer over `concat(z_vv, z_vi)`, with `cls_head` / `vi_head` / `vv_head` |
 | Target encoder θ̄ | EMA of θ, decay 0.998 |
@@ -126,10 +127,10 @@ are generated online by a local vLLM server running `Qwen/Qwen3-1.7B`. Full reci
 
 ## Limitations
 
-Trained on EgoExo4D — skill-centric, mostly indoor, ego/exo camera pairs. Domains far from
-that distribution are untested. Clips longer than 32 s are truncated to the first 128
-sampled frames. The training pipeline depends on decoupled view-invariant / view-variant
-captions, which most datasets do not ship.
+Trained on EgoExo4D, which is skill-centric, mostly indoor, and recorded as ego/exo camera
+pairs. Domains far from that distribution are untested. Clips longer than 32 s are truncated
+to the first 128 sampled frames. The training pipeline needs decoupled view-invariant and
+view-variant captions, which most datasets do not ship.
 
 ## Citation