Unverified50% confidenceBenchmarkExact time
On the LIBERO-Pro benchmark, after 15 rounds of generation and training, CoDA raised the success rate under position perturbation from 25% to 84%, and under instruction perturbation from 1% to 76%.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAfter RL post-training, the small model's accuracy improves from 4% to 45% (pass@1).73% similarUnverifiedIn tests on four manipulation task families, CoDA raised the out-of-distribution (OOD) success rate from 5.3% after supervised fine-tuning to 27.6%, exceeding the strongest closed-loop baseline by 9.5 percentage points under the same generation budget.72% similarUnverifiedChunkAct improves task success rate on the LIBERO-Pro benchmark by 5.0 percentage points over the current state-of-the-art method in the agentic robotics field67% similarVerifiedIn a reproduction experiment training for 40 epochs on CIFAR-10, plain-56 achieved a training accuracy of 84.0% and plain-20 achieved a training accuracy of 95.1%, even though plain-56's parameter count (853,018) is approximately three times that of plain-20 (269,722).67% similarUnverifiedDuring training, the held-out FID dropped from 33.7 to 27.0, FD-DINOv2 dropped from 570 to 218, and detector-based object accuracy improved from 65% to 90%.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1041798API
curl https://kongchang.com/api/v1/knowledge/claims/1041798MCP
get_claim(id=1041798)