Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Drafting Agents, Not Just Tokens: Speculative Recursive Self-Improvement for Agentic Systems
Xin Xu, Ke Cheng, Hao Wang +11
Improving an agent through successive revisions requires balancing exploration and evaluation under a limited budget. A narrow search can miss useful sequences of edits, while full…
cs.LG2026
LoopFM: Learning frOm HistOrical RePresentations of Foundation Model for Recommendation
Shali Jiang, Hua Zheng, Boyang Liu +46
Knowledge distillation (KD) transfers a single scalar prediction from a large foundation model (FM) to compact vertical models (VMs), suffering from diminishing transfer ratio -- t…
cs.LG2026
PRISM: Parallel Residual Iterative Sequence Model
Jie Jiang, Ke Cheng, Xin Xu +8
Generative sequence modeling faces a fundamental tension between the expressivity of Transformers and the efficiency of linear sequence models. Existing efficient architectures are…