Paper page - Multi-Agent Computer Use
…We propose a general multi-agent setup in which a manager model decomposes computer use tasks as a directed acyclic graph (DAG), encoding relevant dependencies and goals for subagents. At each iteration…
Search
Paper page - Precision Is Not Faithfulness: Coverage-Aware Evaluation of Grounded Generation with a Complete Oracle
…model-free regex extractor and a cross-family LLM extractor, system-level Spearman 1.0), and give a verifier-guided generation method that improves precision and recall without references. We release the…
Paper page - FastKernels: Benchmarking GPU Kernel Generation in Production
…We release FastKernels as a stepping stone toward kernel agents whose benchmark gains translate directly into production throughput improvements. Code is available at https://github.com/Snowflake-AI-Research/ fastkernels View arXiv…
Paper page - Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops
…We audit 1,968 tasks across five terminal-agent benchmarks and find 323 (16%) hackable by frontier models given only the task description. This corrupts both leaderboard rankings and RL training signal…
Paper page - The TTS-STT Flywheel: Synthetic Entity-Dense Audio Closes the Indic ASR Gap Where Commercial and Open-Source Systems Fail
…All three beta models fall below pre-registered EHR targets (0.75 for Te, 0.65 for Hi/Ta); we report honestly. A native-human-recorded sanity check (n=20 Telugu) confirms…
Paper page - Chain of Evidence: Pixel-Level Visual Attribution for Iterative Retrieval-Augmented Generation
…Datasets, models & code released — happy to discuss! 👇 This is an automated message from the Librarian Bot . I found the following papers similar to this paper. The following papers were recommended by the…
Paper page - SVGS: Enhancing Gaussian Splatting Using Primitives with Spatially Varying Colors
…In practice, it means that one Gaussian can model much richer local appearance , capture sharper details, and reconstruct challenging regions more faithfully. SVGS supports several ways to model these spatially varying functions…
Timm ❤️ Transformers: Use any timm model with transformers
…tunes have the id2label, though I was told at release time it should be producing label_names... Do you have a public model I could look at? You're using the example…
Paper page - Implicit Preference Alignment for Human Image Animation
…Theoretically grounded in implicit reward maximization , IPA aligns the model by maximizing the likelihood of self-generated high-quality samples while penalizing deviations from the pretrained prior. Furthermore, we introduce a Hand…
Paper page - InterLV-Search: Benchmarking Interleaved Multimodal Agentic Search
…interleaved multimodal search, with the best model below 50% overall accuracy, highlighting challenges in visual evidence seeking , search control , and multimodal evidence integration. We release the benchmark data and evaluation code at…