AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
Category
9,568 papers
As retrieval systems scale, effective and efficient reranking becomes increasingly important. However, most existing encoder- and decoder-based rerankers jointly process every query--passage pair, tightly coupling their online computation and limiting deployment efficiency and flexibility. We present KaLM-Reranker-V1,...
How unlearning effects propagate from the forget set to same-domain and distant-domain knowledge not after but before unlearning is measured to find a consistent decay pattern: collateral damage is strongest near the forget set, weakens with semantic distance, but does not disappear at domain boundaries.
GroupTravelBench is introduced, the first benchmark for multi-user, multi-turn travel planning, and a complementary evaluation framework combining rule-based outcome metrics and LLM-judge process metrics, suggesting that group-level outcome quality is a key open challenge for LLM travel-planning agents.
Co-FactChecker is proposed, a framework for human-AI collaborative claim verification that translates expert feedback into trace-edits that introduce targeted modifications to the trace, sidestepping the shortcomings of dialogue-based interaction.
Reach audiences
Advertise in front of researchers, engineers, and readers.
DeToxR (Decision-support for Toxicology with Reasoning), the first adaptation of Reinforcement Learning to emergency toxicology, is presented, which designs a robust data-fusion engine for multi-label prediction across 14 substance classes based on an LLM finetuned with Group Relative Policy Optimization (GRPO).
ConRad (Confidence Calibration for Radiology Reports), a reinforcement learning framework for fine-tuning medical LVLMs to produce calibrated verbalized confidence estimates alongside radiology reports, is introduced and substantially improves calibration and outperforms competing methods.
It is shown that sampled semantic distributions can be distilled into lightweight student models which estimate a prompt-conditioned density before the language model generates an answer token, which can serve as a general framework for distilling predictive uncertainty in complex output spaces beyond language.
Although Multimodal Large Language Models (MLLMs) have shown remarkable potential in Visual Document Retrieval (VDR) through generating high-quality multi-vector embeddings, the substantial storage overhead caused by representing a page with thousands of visual tokens limits their practicality in real-world application...
Large language models are known to hallucinate, generating linguistically plausible but incorrect answers to questions. Uncertainty quantification has been proposed as a strategy to detect such behaviour, but existing methods lack a unified framework to assess reliability at both the prompt and answer level. We introdu...
SafetyFlow is introduced, the first agent-flow system designed to automate the construction of LLM safety benchmarks, and includes the first fully automated benchmarking pipeline and a comprehensive safety benchmark.
MultiViewDx, a partly physician-validated multimodal instruction dataset for evidence-linked multi-view medical imaging diagnosis, is introduced and Controlled ablations and clinician evaluation show that both case-level multi-view organization and evidence-linked reasoning targets contribute to the gain.
An evaluation framework that measures agents' empirical and normative expectations in addition to behavioral convergence is introduced, offering designers of multi-agent systems a principled basis for selecting the social processes that sustain cooperation.
A Blog post by IBM Granite on Hugging Face
A Blog post by QVAC on Hugging Face
Natural Language Processing
Our most capable vision-language-action model enhances robot dexterity, reliability, and safety
A Blog post by Ai2 on Hugging Face
A Blog post by IBM Research on Hugging Face
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
