AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
We have 14 of 177 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.
Vision Language Models (VLMs) excel on visual benchmarks but fail systematically on tasks requiring abstract reasoning. Existing benchmarks document this failure but cannot say \emph{why} it happens or which cognitive capability is missing. We close this gap by adopting the Relational Match-to-Sample (RMTS) paradigm fr...
This work proposes AutoRef, which optimizes the harness automatically while keeping both models frozen: a coding agent iteratively rewrites the harness code, and discovers AutoRef-Harness, which improves the open-weight FLUX.
SAIL is a framework that reframes robot imitation as an iterative refinement problem capable of scaling with test-time compute, and utilizes Monte Carlo Tree Search, where each node is a complete trajectory and edges correspond to trajectory refinements.
Large language models (LLMs), when acting as agents, are expected to take observed data in context, infer the latent state space underlying the world, and leverage it for downstream prediction. However, prior work demonstrated that LLMs struggle to use representations learned in context on a graph tracking task, where...
This work evaluates cross-embodiment transfer on RoboTwin 2.0 in a controlled setup, two bimanual robots demonstrate disjoint task sets, a policy is trained on all the demonstrations, and each robot is evaluated closed-loop on the tasks only the other demonstrated.
Multimodal Probabilistic Fusion (MMPF), a training-free auditing framework that treats each modality as an expert, estimates a task-label distribution from local neighborhood agreement and global prototype similarity, and then fuses modalities with predictive-entropy weighting in a product of experts is proposed.
DREAM is presented, a framework that generates fine-tuning data for a pretrained VLA from a captured workspace and a language instruction, without requiring a task-specific human demonstration, and whether it can serve as a scalable data-collection system for the deployment workspace.
Recent work on looped language models suggests that many reasoning problems benefit from greater computational depth rather than from additional independent parameters. Existing studies, however, focus almost exclusively on Transformer backbones, leaving open whether this principle also applies to state-space language...
Vision-language-action (VLA) models with billions of parameters now dominate the LIBERO manipulation benchmark, but the model capacity actually required by the benchmark remains unclear. We introduce MINERVA (MINimal Efficient Robotic Vision-Action policy), a family of deliberately compact visuomotor policies designed...
A training-free adaptive pruning method designed specifically for batched inference in LRMs, built on two components: periodic top-k selection over the aggregated importance scores, unaffected by the shift that aggregation induces in the activation distribution, and based on the observation that important neurons re-fi...
A taxonomy of CoT is proposed consisting of Explicit CoT, which outputs all operations without aggregation, Composed CoT, which combines multiple operations into a single step, and Implicit CoT, which omits intermediate operations.
On HealMed, performance declined most in low-resource languages, although the size of the gap varied markedly across languages and models, whereas many open-source and medically specialized models showed larger and less consistent gaps.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.