身体性を持つSLMにおける幾何条件付け:0.8Bハイブリッドモデルでの訓練制御とロバスト性診断
Geometry Conditioning in an Embodied SLM: Training Controls and Robustness Diagnostics in a 0.8B Hybrid Model
0.8Bのハイブリッド言語モデルを操作タスクに適応させ、幾何学的入力の条件付けが性能に与える影響を評価した。訓練時の幾何学的整合性による明確な優位性は見られず、座標不変性と物理的配置の汎化のギャップを示した。
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: Hao Li, Haofei Sun, Lin He
分類: cs.RO, cs.AI
原文アブストラクト
We study how physical-state inputs affect a 0.8B hybrid language model adapted for manipulation with 6.2M trainable parameters. Six conditions are trained on three LIBERO-Spatial tasks and evaluated over three seeds and 540 held-out rollouts. Conditioning recurrent decay gates on geometric increments yields 28.9% success, compared with 36.7% when those increments are shuffled during training and 24.4% without explicit object/goal geometry. Both geometry policies receive correct inputs at evaluation. A token adapter using the same increments scores 27.8%; differences vary across seeds and remain inconclusive. Token-clock conditioning scores 11.1%, including one seed that fails to converge. In separate robustness tests, a state-only relative-coordinate policy retains 7/10 success under frame relabeling, whereas all four tested visual policies fall to at most 3/20 after a 5 cm object displacement. These results show no reliable advantage from training-time geometric alignment under this recipe and illustrate the gap between coordinate invariance and physical-layout generalization. Episode records, seed-level analyses, and figure-generation code accompany the paper.