Existing sequential recommenders usually allocate a fixed computational budget to every item in a user's interaction history, regardless of the item's contribution to the final prediction. We challenge this de facto design with two diagnostic findings. (1) Non-uniform computational need: items within the same sequence...
Zhan-Shuo Cao, Jia-Kai Tang, Yu-Qi Zhou et al.· 0 citations
Diverse cloud-scale foundation/multimodal models and locally deployable models suitable for inference on consumer-grade GPUs are evaluated, achieving the highest accuracy of up to 90% on MCQs, similarity score of 0.72 on literature synthesis, and accuracy of 80% on a small sample of multimodal reasoning questions, with...
Shun Ye, V. C. Suja, Chen-Long Li et al.· arXiv.org· 0 citations
TurnSight is proposed, a turn-level hindsight self-distillation framework that derives supervision directly from execution-conditioned hindsight and selects reliable supervision through cross-horizon directional agreement.
Changle Qu, Sun-Hao Dai, Hengyi Cai 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.