AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
We have 8 of 16 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
ChronicleRec is a pre-train-and-transfer framework that compresses an ultra-long behavior sequence once into a chronologically ordered set of Chronicle Tokens, which can be cached per user, decoupling ultra-long sequence modeling from online candidate scoring.
DPGFlow is proposed, the first Flow Matching framework specifically designed for CDSR, which enables stable and efficient few-step inference and facilitates effective knowledge transfer under heterogeneous and noisy behaviors.
This paper empirically identifies two structural flaws rooted in geometric properties and dataset sparsity, and proposes a novel two-stage framework to close the long-short-view performance gap and introduces a modified softmax to counter prefix position bias.
Causal Abstraction Learning for Multi-Modal Grounded Planning (CALM) is proposed, a framework that enhances planning agents with the ability to discover and exploit causal regularities across tasks.
PerfRec (Preference-aware Flow for Recommendation), a flow-matching offline RL framework that learns an expressive behavioral policy and distills it into an efficient one-step policy, is proposed and experiments show that PerfRec improves recommendation performance over strong offline RL baselines.
Self-supervised Causal Effects Estimation is proposed, a novel framework that integrates causal priors with self-supervised learning to construct balanced and predictive representations for causal effects estimation that consistently outperforms state-of-the-art methods.
Recent advances in multimodal embodied agents have enabled long-horizon planning in visually rich environments via natural language. Yet, their generalization remains brittle when task instructions deviate from familiar examples, exposing a reliance on surface imitation rather than structural understanding. We propose...
This work presents RegionSLM, a region-aware SLM designed to explicitly connect the question to its supporting regions, and curates ReDoc, a region-supervised corpus with 105k documents and 350k question-answer pairs obtained via a question-guided two-step filtering procedure.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.