Category
3,629 papers
The Hash-Atlas network is proposed, which reformulates 3D scene editing as operations on 2D atlas images, thereby achieving a workflow decoupling of the 2D editing and 3D reconstruction processes.
This work proposes AutoMedImg, a multi-agent framework for fully automated medical image processing code generation that achieves zero human intervention, with Dice scores of up to 0.90 for segmentation tasks and 99% accuracy for classification.
An automated scoring approach in which an evolutionary algorithm derives a small set of interpretable maturity indicators, each scored from sentence-completion responses by a domain-fine-tuned language model, supports automated ego-development scoring at agreement levels comparable to trained raters, and the indicators...
A defensive capability analysis for JavaScript libraries that soundly reports every exercised capability for code executed under a lightweight protected runtime, complementing the static analysis with a lightweight runtime enforcement mechanism that blocks those patterns.
Reach audiences
Advertise in front of researchers, engineers, and readers.
Switch Distillation is proposed, a simple mid-training objective that distills on tokens where the teacher is confident, using teacher predictive entropy as a lightweight routing signal, and otherwise falls back to cross-entropy, which consistently outperforms existing distillation objectives across teacher sizes.
This work proposes VerTox, the first framework to formulate corpus poisoning as a verifiable reward-guided reinforcement learning (RLVR) problem, and produces adversarial documents that frequently rank higher than target documents across major neural ranking architectures, as well as a proprietary commercial embedding...
The results show that learnable subword tokenisation can improve sample-efficiency for BabyLM pretraining and analyse the subword learning dynamics of the models and find that tokenisation gradually converges on subword units that balance morphological alignment and fine-grained segmentation.
A single-file solver organized as a cheapest-first cascade is presented, which combines coefficient tests over structured algebra families, bounded finite-model search, an explicit central-groupoid witness, and several infinite-carrier witnesses and makes no completeness or comparative-superiority claim.
Global stable rankings can still leave individual near-tie orderings sensitive to benchmark composition, and sub-one-point leaderboard gaps should be accompanied by evidence that the implied ordering is composition-robust.
Post-training quantization (PTQ) is widely used to reduce the cost of serving large language models (LLMs), but its accuracy cost is uneven and is often tuned per model. We study where quantization damage occurs and how to allocate a small additional precision budget. Using causal mixed-precision intervention as ground...
CRAFT, which stands for Cold-start Reasoning Alignment Alignment via Fine-Tuning, is proposed, a data-centric method to autonomously generate a verified dataset of (input, trace, label) triplets, requiring substantially less compute and wall-clock time than GRPO-based methods.
CrisBench, a 1,200-question benchmark of lifecycle reasoning that combines a controlled formal setting with programs executed against Cordis, a runtime that manages component dependencies and cleanup, and asks models to identify affected components, predict state after a specified teardown order, and determine which co...
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.
