Joint Consistency frames test-time aggregation as energy minimization using pairwise interactions and evaluation signals, outperforming existing voting methods across reasoning benchmarks.
Argus detects backdoor attacks in decentralized learning by having nodes share local trigger analyses with neighbors and filter updates via structural similarity, reducing attack success by up to 90 points without a central server.
Terminator learns optimal early-exit points for chain-of-thought reasoning to cut token lengths by 14%-55% and boost inference speed over 2x with minimal accuracy loss.