Все публикации

0:12:11

#205 Chameleon: Plug-and-Play Compositional Reasoning with LLMs

0:15:37

ReAct: Synergizing Reasoning and Acting in Language Models

0:20:26

Video #203 GPTQ: Accurate Post-Training Quantization For Generative Pre-Trained Transformers

0:14:02

Video #202 MoE-LLaVA: Mixture of Experts for Large Vision-Language Models

0:14:06

Video #201: MultiTabQA: Generating Tabular Answers for Multi-Table QA

0:11:21

Video #200: PALO: A Polyglot Large Multimodal Model for 5B People

0:16:23

CALM: LLM Augmented LLMs

0:15:39

XTR: ConteXtualized Token Retriever

0:13:05

PLLaVA: Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning

0:17:11

YOCO: Decoder-Decoder Architectures for LLMs

0:19:29

KAN: Kolmogorov-Arnold Networks

0:11:54

LLMLingua: Compressing Prompts for Accelerated Inference of LLMs

0:13:42

LaMP: Personalization Benchmark for LLMs

0:09:18

LaMini-LM: A diverse herd of distilled models from large-scale instructions

0:59:26

Mamba: Linear-Time Sequence Modeling with Selective State Spaces

0:29:26

CircuitVQA: A VQA Dataset for Electrical Circuit Images

0:29:04

OAK: Enriching Doc Representations using Auxiliary Knowledge for XC

0:07:15

OLMo

0:10:34

OpenAI's gpt4o

0:05:48

Apple's OpenELM models

0:18:07

Supporting Infinite Context Length using TransformerFAM

0:12:14

Infini attention and Infini Transformer

0:26:59

MEGALODON: Efficient LLM Pretraining and Inference with Unlimited Context Length

0:25:26

Microsoft VASA-1: Lifelike Audio Driven Talking Faces Generated in Real Time