Google AgentHands: AI agents with synchronized speech gestures in XR
dl_weekly · x · 2026-09-01
Google XR introduced AgentHands, a research prototype published at CHI 2026. It uses an LLM to generate interactive hand gestures synchronized with speech for conversational agents, providing spatially grounded guidance. This approach significantly improves spatial grounding and warning salience compared to speech-only baselines, making conversations about physical surroundings more intuitive.
More from Multimodal
- Structuring ComfyUI for Batch Product Shots Without Drift — ayanbhadwa · 2026-09-01
- Any lora for characters? — NefariousnessFun4043 · 2026-09-01
- Kijai released FastH3 checkpoint, but standard ComfyUI workflows won't run it yet — bub000 · 2026-09-01
- OpenAI Sol is the first model that truly understands music, tester says — evilsocket · 2026-09-01
- Three months running Latentsync on 8GB locally: the real cost of "free" — cloudybrain07 · 2026-09-01
- Generating Cinematic Titles with "Reverse Calligraphy" Concept — umesh_ai · 2026-09-01