A Self-Evolving Embodied System (SEES) that learns from failures and improves the VLA policy without additional expert demonstrations, and can be integrated with different VLA backbones to progressively improve their long-horizon performance.
Settle extends the accuracy-token-count Pareto frontier of the evaluated stopping methods and predicts whether a correct answer will remain correct in completed traces.
Using controlled corruption, this work decouple these two roles and finds a reversal: making a noisy token easier to predict reduces its damage as a target but increases it as context.
Su-Qin Yuan, Runqi Lin, Ke-Yu Lin et al.· 0 citations
It is shown that preference alignment preserves the human response distribution only under a restrictive condition, and no consistent evidence that real human preferences satisfy it, and human-likeness is established as an explicit dimension of alignment rather than something assumed to follow from preference alignment...
Su-Qin Yuan, Runqi Lin, Mu-Yang Li et al.· 0 citations
GauntletBench, a web-based benchmark for evaluating agent generalisation in challenging scenarios, focusing on three underexplored capabilities (temporal perception, graphical understanding, and 3D reasoning), is introduced, revealing the substantial gap between current agent capabilities and those required for complex...
Mykola Vysotskyi, Runqi Lin, Grzegorz Biziel et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.