Все публикации

0:56:40

Randall Balestriero - The Fair Language Paradox

0:35:38

Panayiotis Panayiotou - Curricula for Learning Robust Policies

0:55:51

Patrick (Tsung-Han) Wu - Visual Haystacks: Answering Harder Questions About Sets of Images

0:48:11

Cohere For AI - Roads to Research: Paths to Graduate Studies

0:56:24

Cong Lu - The AI Scientist

0:56:08

Dr. Shaina Raza - MBIAS: Mitigating Bias in Large Language Models While Retaining

0:43:05

Ziqi Wang - Enabling Language Models to Implicitly Learn Self-Improvement

0:54:55

Joao Guilherme Madeira Araújo - Consistency of hyper-parameter selection in value-based Deep RL

1:03:05

Arthur Conmy - Mechanistic Interpretability Research Frontiers

0:55:01

Fabio Pizzati - SynthCLIP: Are we ready for a fully synthetic CLIP training?

0:22:44

Dhruv Jain - LLM Agents for Tool Planning in Real-World Scenarios

0:59:10

Maya - Multimodal Multilingual Model

0:58:16

Amanuel Mersha - DynamicViT: Making Vision Transformer Faster Throuhh Layer Skipping

0:56:47

Xiang Yue - Measuring Multimodal Reasoning with the MMMU Benchmarks

0:05:22

C4AI Expedition Aya: Mechanistically Understanding Aya for Safety Steering

0:06:14

C4AI Expedition Aya: Multi Agent Aya for Workforce

0:09:21

C4AI Expedition Aya: SafeAya: Multilingual Adversarial Robustness

0:05:26

C4AI Expedition Aya: Enhancing Sinhala NLP

0:05:08

C4AI Expedition Aya: Multilingual Machine Generated Text Portion Detection

0:04:54

C4AI Expedition Aya: StAyaL: Multilingual Style Transfer

0:07:10

C4AI Expedition Aya: Identifying mislabelled samples in the Aya dataset

0:06:39

C4AI Expedition Aya: DistAYA

0:03:47

C4AI Expedition Aya: MCM: Multilingual LLM Capability For Crisis Management

0:05:12

C4AI Expedition Aya : Speechaya