Lyte (Yassine Ennaour)

upvoted a paper 3 days ago

Chameleon: Mixed-Modal Early-Fusion Foundation Models

Paper • 2405.09818 • Published 5 days ago • 67

upvoted 3 papers 6 days ago

upvoted a collection 10 days ago

Pretrained Text-Generation Models Below 250M Parameters

Collection

Great candidates for fine-tuning targeting Transformers.js, ordered by number of parameters. • 7 items • Updated 7 days ago • 6

upvoted a paper 17 days ago

Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models

Paper • 2405.01535 • Published 18 days ago • 92

upvoted 8 papers 18 days ago

InstantFamily: Masked Attention for Zero-shot Multi-ID Image Generation

Paper • 2404.19427 • Published 20 days ago • 65

Capabilities of Gemini Models in Medicine

Paper • 2404.18416 • Published 22 days ago • 21

Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models

Paper • 2404.18796 • Published 21 days ago • 62

Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting

Paper • 2404.18911 • Published 21 days ago • 26

KAN: Kolmogorov-Arnold Networks

Paper • 2404.19756 • Published 20 days ago • 92

Is Bigger Edit Batch Size Always Better? -- An Empirical Study on Model Editing with Llama-3

Paper • 2405.00664 • Published 19 days ago • 16

Octopus v4: Graph of language models

Paper • 2404.19296 • Published 21 days ago • 89

A Careful Examination of Large Language Model Performance on Grade School Arithmetic

Paper • 2405.00332 • Published 20 days ago • 24

upvoted 2 papers 21 days ago

AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs

Paper • 2404.16873 • Published 29 days ago • 25

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

Paper • 2404.16994 • Published 25 days ago • 30

upvoted 2 papers 24 days ago

Layer Skip: Enabling Early Exit Inference and Self-Speculative Decoding

Paper • 2404.16710 • Published 25 days ago • 55

How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites

Paper • 2404.16821 • Published 25 days ago • 49

upvoted 3 papers 26 days ago

Pegasus-v1 Technical Report

Paper • 2404.14687 • Published 28 days ago • 29

Multi-Head Mixture-of-Experts

Paper • 2404.15045 • Published 27 days ago • 53

OpenELM: An Efficient Language Model Family with Open-source Training and Inference Framework

Paper • 2404.14619 • Published 28 days ago • 120

upvoted 2 papers 27 days ago

The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions

Paper • 2404.13208 • Published about 1 month ago • 37

Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Paper • 2404.14219 • Published 28 days ago • 230

upvoted a paper 28 days ago

TextSquare: Scaling up Text-Centric Visual Instruction Tuning

Paper • 2404.12803 • Published Apr 19 • 27

upvoted 21 papers about 1 month ago

Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing

Paper • 2404.12253 • Published Apr 18 • 51

OpenBezoar: Small, Cost-Effective and Open Models Trained on Mixes of Instruction Data

Paper • 2404.12195 • Published Apr 18 • 11

Long-form music generation with latent diffusion

Paper • 2404.10301 • Published Apr 16 • 23

MeshLRM: Large Reconstruction Model for High-Quality Mesh

Paper • 2404.12385 • Published Apr 18 • 24

Dynamic Typography: Bringing Words to Life

Paper • 2404.11614 • Published Apr 17 • 40

Scaling Instructable Agents Across Many Simulated Worlds

Paper • 2404.10179 • Published Mar 13 • 23

ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback

Paper • 2404.07987 • Published Apr 11 • 46

Rho-1: Not All Tokens Are What You Need

Paper • 2404.07965 • Published Apr 11 • 79

Learn Your Reference Model for Real Good Alignment

Paper • 2404.09656 • Published Apr 15 • 80

Video2Game: Real-time, Interactive, Realistic and Browser-Compatible Environment from a Single Video

Paper • 2404.09833 • Published Apr 15 • 27

Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length

Paper • 2404.08801 • Published Apr 12 • 62

TransformerFAM: Feedback attention is working memory

Paper • 2404.09173 • Published Apr 14 • 42

Natural language guidance of high-fidelity text-to-speech with synthetic annotations

Paper • 2402.01912 • Published Feb 2 • 7

RULER: What's the Real Context Size of Your Long-Context Language Models?

Paper • 2404.06654 • Published Apr 9 • 32

Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention

Paper • 2404.07143 • Published Apr 10 • 92

Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMs

Paper • 2404.05719 • Published Apr 8 • 57

Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence

Paper • 2404.05892 • Published Apr 8 • 28

OmniFusion Technical Report

Paper • 2404.06212 • Published Apr 9 • 73

LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders

Paper • 2404.05961 • Published Apr 9 • 62

CantTalkAboutThis: Aligning Language Models to Stay on Topic in Dialogues

Paper • 2404.03820 • Published Apr 4 • 20

AutoWebGLM: Bootstrap And Reinforce A Large Language Model-based Web Navigating Agent

Paper • 2404.03648 • Published Apr 4 • 22

upvoted 3 papers 2 months ago

Design2Code: How Far Are We From Automating Front-End Engineering?

Paper • 2403.03163 • Published Mar 5 • 92

Learning to Decode Collaboratively with Multiple Language Models

Paper • 2403.03870 • Published Mar 6 • 17

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

Paper • 2403.03507 • Published Mar 6 • 172

upvoted 7 papers 3 months ago

Genie: Generative Interactive Environments

Paper • 2402.15391 • Published Feb 23 • 67

Mixtures of Experts Unlock Parameter Scaling for Deep RL

Paper • 2402.08609 • Published Feb 13 • 34

BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of data

Paper • 2402.08093 • Published Feb 12 • 52

WebLINX: Real-World Website Navigation with Multi-Turn Dialogue

Paper • 2402.05930 • Published Feb 8 • 35

LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation

Paper • 2402.05054 • Published Feb 7 • 24

BiLLM: Pushing the Limit of Post-Training Quantization for LLMs

Paper • 2402.04291 • Published Feb 6 • 48

Grandmaster-Level Chess Without Search

Paper • 2402.04494 • Published Feb 7 • 62

upvoted 5 papers 4 months ago

StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback

Paper • 2402.01391 • Published Feb 2 • 41

PokéLLMon: A Human-Parity Agent for Pokémon Battles with Large Language Models

Paper • 2402.01118 • Published Feb 2 • 28

EVA-GAN: Enhanced Various Audio Generation via Scalable Generative Adversarial Networks

Paper • 2402.00892 • Published Jan 31 • 9

OWSM v3.1: Better and Faster Open Whisper-Style Speech Models based on E-Branchformer

Paper • 2401.16658 • Published Jan 30 • 12

BlockFusion: Expandable 3D Scene Generation using Latent Tri-plane Extrapolation

Paper • 2401.17053 • Published Jan 30 • 29

Yassine Ennaour

AI & ML interests

Organizations

Lyte's activity