FraudBench is an evaluation of large language models' (LLMs) propensities to recommend, assist, or directly take actions that ...

A frozen BF16 teacher guides student retries and refines its guidance using execution feedback. Context distillation internalizes the locally verified corrections. The student then runs alone, without ...

PLaMo 3 Translate: translation-specialized LLMs (0.8B / 2B / 8B / 31B) in BF16 and quantized formats (FP8, W4A16, W4AFP8, NVFP4, GGUF, MLX-4bit).

Worker Adjustment and Retraining Notification (WARN) Act notices filed with US state labor agencies, collected daily from 48 state sources and normalized into one table. For real-time filings, maps, ...

Reframe is a two-stage post-training framework that aligns visual agents’ observation states through evidence-aware ...

import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image # switch to "mps" for apple devices pipe = DiffusionPipeline.from ...

Release Anima Role Ref KV v2.0 (BF16 v2.0 & v1.0) about 5 hours ago assets Update ComfyUI NativeEngine for pure BF16 execution and sync v2.0 showcase assets about 2 hours ago comfy Update ComfyUI ...

Two visual focusing losses align a Vision Transformer's multi-head attention with image regions, producing specialized ...

Arete-27B is intended for general assistance and agentic work where users want this change in viewpoint, and for research ...

An embodied multi-agent framework uses learned correction codes and a vision-language-action model with motion-aware history ...

Large language model agents can exceed authorized limits while pursuing user goals, and a 648-sample benchmark across seven domains shows that this drift rises with capability yet is avoidable and ...

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