Category
2,658 papers
Latent Recurrent Thoughts substantially outperforms prior frozen-decoder continuous-space reasoning methods under an identical decoder, prompt, data, and training budget, and outperforms non-thinking-mode chain-of-thought prompting on the same backbone at a small fraction of its inference compute.
AgentFactory is presented, a framework that jointly optimizes both foundation models and workflow structures in agentic systems while considering multiple objectives including performance, cost, and efficiency, and establishes AgentFactory as a promising approach for developing more capable and efficient agentic system...
CARE is proposed, which grounds every rubric evolution step in a high-quality anchor response generated by a frontier model conditioned on the prompt and its rubrics, enabling two complementary mechanisms: an Adaptive branch that reactively repairs reward misspecification; and a Chase branch that proactively converts f...
The hypothesis that native SLMs must be the most sustainable edge choice is not supported universally; optimized quantized LLMs can win overall, while SLMs remain competitive through lower resource demand.
Reach audiences
Advertise in front of researchers, engineers, and readers.
The results suggest that LLMs could effectively support scalable relevance assessment in specialized Portuguese corpora when evaluated using nDCG or MRR (rank-aware metrics), but they should be avoided when relying on precision or recall.
Large language models (LLMs) are trained on corpora that contain expressions of human judgment about films, books, music, and more. Yet whether LLMs systematically reproduce evaluative hierarchies remains unclear. Prior research on cultural bias in LLMs suggests competing expectations: models may mirror the popularity...
This study traces the full decision-making pipelines of the 5 APR agents across 500 real-world repair tasks, from issue description to patch validation, and reveals that, while agents excel at simple fixes, they struggle with logic-intensive bugs.
Three building blocks toward a complete, privacy-preserving browser agent, a verified repair instrument pairing a trilingual seeded-violation benchmark with an audit-inject-verify loop, and a dual-condition protocol that measures harm as carefully as benefit are contributed.
MonitrLLM is introduced, open-source infrastructure for community-centered LLM evaluations that links full conversation transcripts to user-reported task intent and outcome assessments, treating all three as primary evaluative signals rather than optional metadata.
While multi-agent LLM pipelines show real promise for legacy code specifically, since their capacity for autonomous context reconstruction and iterative, feedback-driven refinement directly addresses the sparse documentation and thin test coverage that define legacy environments, the literature to date has been validat...
It is shown that robots can generalize effectively under dynamics uncertainties even with limited training data by leveraging a feedback mechanism, namely PhyFilter, that corrects learning outputs with physics-filtered learning residuals, and shows that physics-filtered feedback can serve as a powerful alternative to m...
While vision-language models dominate medical representation learning, unstructured text lacks the dense, quantitative diagnostic phenotypes inherent in structured clinical tables. However, existing multimodal pre-training methods underutilize this potential due to semantic-agnostic designs that treat tabular inputs as...
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.
