Reactive Machines

RubiCap: Rubric-Guided Reinforcement Learning for Dense Image Captioning

RubiCap: Rubric-Guided Reinforcement Learning for Dense Image Captioning

Dense image captions are important for cross-modal alignment in visual language pre-training and image-to-text generation, but measuring expert-quality annotations is…
P-EAGLE: Faster LLM inference with Parallel Speculative Decoding in vLLM

P-EAGLE: Faster LLM inference with Parallel Speculative Decoding in vLLM

EAGLE is the state-of-the-art method for speculative decoding in large language model (LLM) inference, but its autoregressive drafting creates a…
mAceReason-Math: A High-Quality Multilingual Math Problem Dataset Ready for RLVR

mAceReason-Math: A High-Quality Multilingual Math Problem Dataset Ready for RLVR

Reinforcement Learning with Verifiable Rewards (RLVR) has been successfully used to significantly increase the skills of large pre-trained linguistic models,…
Ukushumeka kwe-Multimodal esikalini: Ichibi ledatha ye-AI yomthwalo wemidiya nokuzijabulisa

Ukushumeka kwe-Multimodal esikalini: Ichibi ledatha ye-AI yomthwalo wemidiya nokuzijabulisa

Lokhu okuthunyelwe kukubonisa ukuthi ulwakha kanjani uhlelo lokusesha lwevidiyo ye-multimodal olunezimo eziningi oluvumela ukusesha kolimi lwemvelo kuwo wonke amadathasethi amakhulu…
LiTo: Surface Light Field Tokenization

LiTo: Surface Light Field Tokenization

We propose a 3D latent representation that jointly combines geometric object models with view-dependent appearance. Most previous works focus on…
Operationalizing Agetic AI Part 1: A Guide for Stakeholders

Operationalizing Agetic AI Part 1: A Guide for Stakeholders

Agent AI is not a feature you unlock. It's a change in how work is defined, who does it, and…
Speed ​​up custom LLM deployments: Fine-tune with Oumi and ship to Amazon Bedrock

Speed ​​up custom LLM deployments: Fine-tune with Oumi and ship to Amazon Bedrock

This post was written by David Stewart and Matthew Persons from Oumi. Optimizing large open source language models (LLMs) often…
Qalisa i-NVIDIA Nemotron 3 Nano njengemodeli ephethwe ngokugcwele engenaseva ku-Amazon Bedrock

Qalisa i-NVIDIA Nemotron 3 Nano njengemodeli ephethwe ngokugcwele engenaseva ku-Amazon Bedrock

Lokhu okuthunyelwe kubhalwe no-Abdullahi Olaoye, uCurtice Lockhart, u-Nirmal Kumar Juluru wase-NVIDIA. Siyajabula ukumemezela ukuthi i-Nemotron 3 Nano ye-NVIDIA isiyatholakala njengemodeli…
Flow Coupling and Semidiscrete Couplings

Flow Coupling and Semidiscrete Couplings

Flow models parameterized as time-dependent velocity fields can generate data with noise by integrating the ODE. These models are often…
Back to top button