AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
Author
Nanyang Technological University, Singapore
We have 8 of 80 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.
A central capability of embodied agents is to accomplish complex objectives through sequences of interdependent tasks. Yet existing visual goal-conditioned policies underlying these agents are typically evaluated on isolated interactions where the target is already visible, and thus do not capture the conditions that a...
Rubric-based reinforcement learning extends reward-driven optimization to open-ended tasks by assigning partial credit to individual response requirements. However, rubric judges can assign a high criterion score even when the information or action it requires is absent from the response, a failure mode we term Vacuous...
Continual test-time adaptation (CTTA) adapts a source model to an unlabeled test stream whose distribution may change over time. Existing TTA methods often assess prediction reliability using confidence or entropy, which primarily reflect the model's self-certainty for the current sample. In CTTA, accumulated target ob...
AnchorWeave is introduced, a memory-augmented video generation framework that replaces a single misaligned global memory with multiple clean local geometric memories and learns to reconcile their cross-view inconsistencies.
MedMix is a semantic-alignment framework for federated multimodal sparse MoE architectures that coordinates cross-client routing and expert specialization using modality context, and achieves the best average F1 across diverse modality heterogeneity and modality incompleteness settings.
PaperCompiler is introduced, a paper-to-code generation framework that compiles paper-grounded evidence into explicit repository-level implementation specifications that encode non-degradation requirements, ownership assignments, cross-file dependencies, and file-level constraints.
Simplax is introduced, an exact Dirichlet--categorical augmentation that couples each corrupted categorical state with an auxiliary simplex-valued variable while preserving the original uniform diffusion process as its categorical marginal.
EgoMemReason is introduced, a comprehensive benchmark for week-long egocentric video understanding through memory-driven reasoning that evaluates three complementary memory types: entity memory, tracking how object states evolve and change across days; event memory, recalling and ordering activities separated by hours...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.