Category
3,524 papers
NepEduBench, an initial benchmark foropen-source Small Language Models (SLMs) covering English, Nepali, and Romanized Nepali. Built from Nepal’s official Grade 6–10 Social Studies textbooks, it combines a parallel core of 318 lessons per language (the same lessons in all three languages), language-specific instruction...
(c) 2026 Pranay Mahendrakar. Licensed under CC BY 4.0. Two literatures make claims about what happens when a language model trains on data that resembles its own distribution. One asks whether reinforcement learning forgets a model's prior capabilities less than supervised fine-tuning does, and answers yes: on-policy R...
(c) 2026 Pranay Mahendrakar. Licensed under CC BY 4.0. Two literatures make claims about what happens when a language model trains on data that resembles its own distribution. One asks whether reinforcement learning forgets a model's prior capabilities less than supervised fine-tuning does, and answers yes: on-policy R...
Prefix adders are fundamental arithmetic circuits, but their design space grows exponentially with bit-width, posing significant optimization challenges. Previous works face limitations in performance, generalization, and scalability. To address these challenges, we propose PrefixAgent , a large language model (LLM)-po...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Background Healthy lifestyle management is essential for chronic disease prevention and long-term care. However, evidence linking lifestyle behaviors, biological mechanisms, and health outcomes is dispersed across diverse biomedical sources. This fragmentation makes it difficult for health professionals to efficiently...
Almost every language model in service was trained by one family of software. That concentration makes a question hard to settle: how much of what is known about training a language model describes language models, and how much describes that software? Settling it needs a second implementation able to carry a model thr...
HistoRAG is presented, a question answering assistant that answers from one regional collection and cites a volume and a page for every fact, at a far smaller cost per question than a graph based retrieval system.
A modular, predictor agnostic, tool-augmented framework that equips a small VLM with geometric tools: 3D object detection, metric depth estimation, and deterministic solvers for distance, size and bearing, matching a scripted pipeline on three of four tasks.
A pipeline for building an open-taxonomy semantic annotation of source code using a code-specialised Large Language Model, and a calibrated quality-assurance protocol that quantifies annotation precision by combining a small human gold set with an LLM-as-a-judge filter are presented.
Results show that BLV-focused post-training improves both accessibility-specific spatial grounding and general visual-text reasoning, and is substantially outperforms the baseline across various benchmarks.
We present ChunkRank, an open-source Python library that derives chunk boundaries from a target model's tokenizer and context window, and selects an answer among candidates produced independently per chunk. It ships a validated registry of 90 models across 15 providers and six answer-selection methods, and needs only t...
Understanding how Large Language Models (LLMs) encode linguistic structures remains a fundamental challenge in interpretability research. While diagnostic classifiers (or"probes") are widely used for this task, they face significant methodological criticism: training auxiliary classifiers introduces capacity confounds...
A Blog post by IBM Granite on Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Gemini 4 Carbon is our strongest model with state-of-the-art cybersecurity and long horizon capabilities.
A Blog post by Liquid AI on Hugging Face
Genie 4: our new world model unlocking unprecedented realism in real-time simulation.
Generative AI
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
