NPCBench evaluates whether medical AI models can integrate subspecialty knowledge with multimodal evidence and maintain ...

A benchmark for temporal reasoning over patient timelines: given a question about when something happened in one patient's record, retrieve the passages that support the correct answer rather than ...

How to use GrootTeam/Groot-19B-A3B-261023-GGUF with Transformers: # Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image ...

100 short videos (at most 180 s), each with one multiple-choice question and the responses of five open-source video reasoning models (Video-Thinker, Open-o3 Video, VideoChat-R1, VideoChat-R1.5, ...

An audio-guided framework restores facial details in AI-generated videos by combining reference-guided flow modeling with audio synchronization to resolve lip and dental ambiguity. Low-quality facial ...

LIBERO spatial, object, goal and 10 suites: 1,695 successful replay episodes, 274,008 frames, 10 Hz. Derived from LIBERO demonstrations for layout-conditioned robot policy training. GT and DA3 share ...

How to use free5knuckles/my_awesome_eli5_clm-model with Transformers: # Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text ...

Private artifact package for resuming frozen MATH-to-Omni-MATH experiments from Ever2after/PGM, source commit 9ec705a56bf815eafa0fa84ef4a154a6d1946080. The archive ...

A synthetic-data framework builds end-to-end OCR for low-resource scripts using unannotated text and digital fonts, achieving high accuracy on Kashmiri without manual image annotation.

Face image quality assessment methods vary widely in detecting diffusion-based and other morphing attacks, with performance depending heavily on attack type and dataset, and high quality scores for ...

Empirical study shows continual harness self-evolution across software engineering tasks causes severe catastrophic forgetting, with performance on earlier datasets dropping sharply after later ...

Lab2Sim introduces a benchmark for converting science videos into interactive virtual experiments, and EduVideo2Code improves apparatus fidelity by encoding procedures as state machines for verified ...