Category
8,786 papers
Reinforcement learning (RL) has become a widely used paradigm for improving the reasoning abilities of large language models (LLMs) and Vision-language models (VLMs). Sparse binary outcome rewards, however, score only final correctness and cannot identify which intermediate steps contributed to it; in multimodal tasks,...
This study reveals that the Deepseek-R1-Distill series models are subject to significant fluctuations caused by various factors, making their claimed performance improvements difficult to reproduce reliably.
SkillFlow demonstrates that framing skill acquisition as an information retrieval task is an effective strategy, and that the practical impact of skill-augmented agents hinges on corpus coverage and skill quality, particularly the density of runnable code and bundled artifacts.
A roundtrip benchmark that scores code descriptions by whether code regenerated from them passes the original tests is introduced, and it is shown that completeness, not length, drives a description's fidelity.
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work presents the first systematic evaluation of cultural awareness in LLMs for Haitian Creole, a language spoken by millions but severely underrepresented in digital resources, using a benchmark of culturally salient prompts curated by native speakers in a text infilling setting.
LLMs increasingly act as purchasing agents, which makes the LLM, not the user, the one choosing among the options that satisfy a request; its preferences quietly fix what gets bought and what it costs. Hotel booking is a clean instance: a high-volume choice settled on a few comparable attributes, where the pick reveals...
ViSTA is introduced, a compact adapter that incorporates irregular numerical measurements into a pretrained vision-language model's chart representations and extends pretrained language models to numerical prediction and temporal questions.
Large language model-based multi-agent debate (MAD) systems are being increasingly used as complex decision pipelines in distributed processes. However, their final synthesis phase still remains inadequately controlled. Even with detailed debate logs, summarizing models are prone to fabricating smoothly written debate...
The findings indicate that the evaluated VLMs exhibit a consistent behavioral limitation when processing typographic structures containing multiple spatial frequency layers.
Intent2Tc is presented, a closed-loop language-model-driven framework that translates business-level traffic-shaping intents into declarative sub-intents and subsequently into validated, executable Linux traffic control (tc) configurations and demonstrates the practical applicability of the proposed framework.
The results show that explicitly selecting and integrating evidence improves long-context reasoning while enabling more compact generation, and the strongest overall result among the evaluated open-source models is obtained.
Mixture of Semantic Attention Regimes (MoSAR) is introduced, which learns such an adaptive, controlled-decay geometry over query--key interactions, suggesting that it is not only adaptive, but also amenable to low-cost approximation at inference time.
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations appeared first on Microsoft Research.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
A new computational approach reveals how cells communicate to assemble into tissues. This could accelerate stem cell engineering, improve disease models, and inform therapies.
Zero-knowledge proofs can verify computing results without rerunning workloads or exposing sensitive data. Magnetar helps bring them into the mainstream with support for standard programming languages, major speed gains, and quantum-resistant security. The post Proof-based general-purpose computing with Magnetar appeared first on Microsoft Research.
A new language-processing tool could help identify the highest-risk individuals from natural language, enabling swifter interventions.
A Blog post by Liquid AI on Hugging Face
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
