物理は活性化に宿るか?動画拡散モデルにおける物理量の局在化
Does Physics Live in the Activations? Localizing Physical Quantities in Video Diffusion Models
動画拡散Transformerの内部表現を調べ、運動や剛体力学の物理量がノイズ除去過程の早い段階で線形に読み出せ、物体トークンに局在することを示した研究。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Jonas Kneifl, Jakub Skalski, Bartłomiej Twardowski, Kamil Deja
分類: cs.CV, cs.LG
原文アブストラクト
Video generation models produce strikingly realistic sequences and are increasingly proposed as world models, yet recent benchmarks reveal pronounced deficits in their physical reasoning. This raises the question of whether these models internalize physical principles or merely reproduce familiar motion patterns. We address this by probing internal representations of video Diffusion Transformers (DiTs) for simulator-derived ground-truth physical quantities spanning kinematic motion and rigid-body dynamics under gravity and contact. We find that these quantities are linearly decodable with high accuracy early in the denoising process, substantially outperforming a baseline decoded directly from the model's own noised latents, indicating that the relevant physical information is actively constructed during denoising rather than already present in the input. Additionally, we show that activations at on-object tokens carry the relevant physical information and that quantities defined over multiple frames are readable from single latent frames. Hence, information is sharply localized within the token sequence and is computed globally but stored locally. The probes further show partial extrapolation, transferring to scene variations and object configurations outside their training regime, so what they read is not simply a correlate of the scenes they were fit on. When fitted directly in the full-resolution activation space, the probing directions can serve as steering vectors to change the model's output.
関連論文
- CLAP: クロスエンボディメント動画世界モデルはゼロショット物理シミュレータ動画生成/世界モデル