Research map / Vision-language and multimodal / Robot action and navigation
Tactile Modality Fusion for Vision-Language-Action Models
Charlotte Morissette, Amin Abyaneh, Wei-Di Chang, Anas Houssaini, David Meger, Hsiu-Chin Lin, Jonathan Tremblay, Gregory Dudek
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add FiLM tactile conditioning to OpenVLA-OFT | OpenVLA-OFT · In-distribution average | success rate (%): 58.10 -> 86.67 | Improved |
| add FiLM tactile conditioning to OpenVLA-OFT | OpenVLA-OFT · OOD average | success rate (%): 54.67 -> 86.67 | Improved |
| use FiLM fusion instead of token concatenation | TacFiLM · ID average | direct insertion (%): 10.48 -> 37.14 | Improved |
| use FiLM fusion instead of token concatenation | TacFiLM · ID average | avg max force (N): 10.27 -> 8.65 | Improved |
| use FiLM fusion instead of cross-attention | TacFiLM · ID average | success rate (%): 48.00 -> 86.67 | Improved |
| add tactile concatenation to vision-only VLA | OpenVLA-OFT · Open-Drawer (ID) | success rate (%): 33.33 -> 26.67 | Hurt |
| add tactile cross-attention to vision-only VLA | OpenVLA-OFT · ID average | success rate (%): 58.10 -> 48.00 | Hurt |
| apply FiLM to only early ViT blocks (ablation) | TacFiLM · Circle-Peg 3mm (ID) | success rate (%): 100.00 -> 93.33 | No clear effect |
| apply FiLM to only early ViT blocks (ablation) | TacFiLM · Circle-Peg 3mm (ID) | direct insertion (%): 36.67 -> 60.00 | Improved |
| apply FiLM to all vs middle/late blocks only (ablation) | TacFiLM · Pentagon-Peg 3mm (OOD) | success rate (%): 100.00 -> 100.00 | No clear effect |
| add tactile FiLM under dimmed camera | OpenVLA-OFT · Circle-Peg 3mm (80% dimmed) | success rate (%): 93.33 -> 100.00 | Improved |
| add tactile FiLM under 50% frame updates | OpenVLA-OFT · Circle-Peg 3mm (50% frames) | success rate (%): 73.33 -> 100.00 | Improved |
Closest papers by meaning
- Universal Visuo-Tactile Video Understanding for Embodied Interaction (NeurIPS 2025 · similarity 0.90)
- ForceVLA: Enhancing VLA Models with a Force-aware MoE for Contact-rich Manipulation (NeurIPS 2025 · similarity 0.89)
- EgoTac: In-the-wild Tactile Prediction from Egocentric Vision (NeurIPS 2026 · similarity 0.88)
- Touch in the Wild: Learning Fine-Grained Manipulation with a Portable Visuo-Tactile Gripper (NeurIPS 2025 · similarity 0.88)
- A Touch, Vision, and Language Dataset for Multimodal Alignment (ICML 2024 · similarity 0.88)
- AnyTouch: Learning Unified Static-Dynamic Representation across Multiple Visuo-tactile Sensors (ICLR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
