AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
Category
3,629 papers
The results reveal a pattern distinct from prior findings on long-tail vulnerability during acquisition and retention: among facts that models already answer correctly, those associated with highly connected entities are more likely to be corrupted by neighboring updates, and updates to such facts propagate errors more...
This work introduces SLOWeave, an online scheduling method that selects the largest prefill chunk predicted to finish before the earliest active decode deadline, and proves that, whenever a decode-only iteration is feasible and the cost predictor is accurate, SLOWeave maximizes immediate prefill progress among decision...
Signed Rescue Routing is introduced, a budgeted routing method that predicts these two events separately and ranks requests by their difference and shows that predicting incremental value, rather than model uncertainty, is a simple and effective objective for efficient LLM cascades.
A platform-agnostic CPU baseline is established by evaluating five open-weight models below two billion parameters and revealing a reliability-resource trade-off for edge deployment.
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work introduces Coarse-to-fine Error-aware Dynamic Attention Routing (CEDAR), a coarse-to-fine method that keeps the language model frozen while preserving global coverage and derives an output-error bound governed by within-chunk key/value dispersion and uses it to allocate a variable refinement budget.
Large language models (LLMs) are increasingly used to generate media, but whether their content perpetuates gender stereotypes is unknown: standard benchmarks rely on selection-based formats rather than long-form generation, and surveyed baselines for local gender associations are scarce outside the West. We collect ge...
This work proposes a scalable reinforcement-learning-based approach for rewriting existing source texts into instances that are more difficult to translate for MT systems, using a large language model with Group Relative Policy Optimization (GRPO) and fine-tune a large language model with Group Relative Policy Optimiza...
CONDUIT, a training-free refresh policy that unifies single- and multi-image reuse as residual-stream restoration, is proposed, building on norm-weighted attention and an accessible pre-output cached-value-norm proxy, then applies empirical image-level relevance amplification before one global selection.
LatentMD is introduced, a benchmark and evaluation protocol for diagnosing CommonMark-level fence-boundary failures in LLM-generated Markdown, enabling detection of outputs that are content-correct but boundary-broken.
The audit dataset, the quantcheck acceptance-testing tool, and disclosure reports for every confirmed defect are released, and it is argued that model registries need the acceptance gate that package registries already run.
Chimaera integrates mixture-of-experts with graph foundation models (GFM) and integrates different GFM architectures, such as graph prompts and linear GNN models, to extend existing linear GNNs to support link-level and graph-level tasks in addition to node-level tasks.
Inference energy per token drives the cost and carbon footprint of deployed transformers. It is dominated by dense matrix products that incur fused multiply-accumulate (FMA) operations and memory traffic. To reduce these computations while retaining dense tensors for high GPU throughput, we develop a methodology from f...
A Blog post by NVIDIA on Hugging Face
Data Mining & Modeling
A Blog post by Ai2 on Hugging Face
A Blog post by IBM Research on Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
A Blog post by IBM Granite on Hugging Face
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
