Category
8,786 papers
CUSP makes magnitude, timing, mechanism, movement, modes, and textual evidence compatible views of one lexical history compatible with a large corpus of US court opinions.
FAVoR (Federated Authorial Voice Retention), an author-style residual mechanism for federated PEFT, improves author-style retention over standard and personalized federated PEFT baselines and is supported by component ablations, external verification, and cold-start transfer.
A training-free ST2P pipeline that integrates both lexical and acoustic information at inference time is proposed that outperforms all baselines, including a trained ST2P model and commercial multimodal LLMs.
This work proposes ToolSearcher, a novel RL framework for effective multi-turn search and fine-grained optimization in large-scale tool selection, which introduces category-constrained tool discrimination to improve the model's ability to distinguish functionally similar tools.
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work argues that literary interpretation offers a useful setting for studying cultural referencing and reuse: how texts invoke, repeat, and transform earlier expressions across historical and linguistic contexts and proposes linking evidence-centered benchmarks, evaluation that preserves scholarly disagreement, an...
Large language models (LLMs) are increasingly used to assess long-form medical videos, but their effectiveness may depend on whether transcripts are provided in full or compressed through summarization, retrieval, or claim screening. This study examines how such transcript compression affects LLM-based veracity classif...
Difference-in-differences (DID) studies are widely used to evaluate climate policy, but assessing the evidence supporting their identification assumptions remains challenging. We introduce ARGUS, a structured language-model pipeline that audits reported evidence against an eleven-dimension assumption-implication-eviden...
This work proposes an LLM-as-a-judge approach to measure perturbation strength in a unified manner across input and CoT perturbations and suggests that judgments about a model's self-consistency is fair only within the same perturbation type.
I-Parakeet is an integer-only implementation of NVIDIA's Parakeet-CTC (0.6B parameters) that runs on a smartphone NPU without any floating-point operator or CPU fallback, and introduces a minimax-optimized Swish approximation that minimizes the maximum error of the Swish output.
This work finds that utilizing chat templates renders the model more compliant with harmful queries compared to a non-chat template, and shows that using a non-chat template during distillation better preserves the base student's internal representations, while chat template distillation induces a larger representation...
Tandem speech-to-speech architectures couple a responsive speech frontend with an asynchronous text backend. In KAME, a large language model (LLM) serves as the backend, supplying candidate responses as guidance to the speech frontend while the user is still speaking. Ordinary conversation recordings capture the eventu...
SEA-CLIP-Tiny is introduced, a compact multilingual text-vision embedding model for Southeast Asia with fewer than 50M parameters that adapts a CLIP-KD-style framework to Southeast Asian multilingual settings through regional data curation and multilingual teacher guidance.
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.
