CMU's SeeQ: Generalist Robot Value Functions Nearly Double Success Rates

CMU's SeeQ trains generalist robot value functions on top of PaliGemma, nearly doubling real-task success rates; ablations highlight TD learning, VLM pretraining and verbalized subtask decoding as key factors.

2026-09-29 ~ 2026-09-29 · 3 related posts

• CMU's SeeQ: generalist robot value function on a VLM nearly doubles real-world task success — aviral_kumar2 · 2026-09-29
• SeeQ ablations: TD learning, VLM pretraining and language subtask decoding all matter — aviral_kumar2 · 2026-09-29
• SeeQ robot project retrospective: 'things just worked' when the ML was done right — aviral_kumar2 · 2026-09-29