Victor Mustar's picture

Victor Mustar PRO

victor

·

victormustar

AI & ML interests

Building the UX of this website

Articles

Inference for PROs

Organizations

victor's activity

upvoted a collection 8 days ago

SmolLM2

State-of-the-art compact LLMs for on-device applications: 1.7B, 360M, 135M • 8 items • Updated 4 days ago • 159

upvoted an article 10 days ago

Article

Code a simple RAG from scratch

By

•

10 days ago

• 7

upvoted 2 papers 11 days ago

Breaking the Memory Barrier: Near Infinite Batch Size Scaling for Contrastive Loss

Paper • 2410.17243 • Published 17 days ago • 86

ROCKET-1: Master Open-World Interaction with Visual-Temporal Context Prompting

Paper • 2410.17856 • Published 16 days ago • 48

upvoted 2 papers 16 days ago

SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree

Paper • 2410.16268 • Published 18 days ago • 65

FrugalNeRF: Fast Convergence for Few-shot Novel View Synthesis without Learned Priors

Paper • 2410.16271 • Published 18 days ago • 80

upvoted 2 collections 17 days ago

steiner-preview

Reasoning models trained on synthetic data using reinforcement learning. • 3 items • Updated 19 days ago • 23

Granite 3.0 Language Models

A series of language models trained by IBM licensed under Apache 2.0 license. We release both the base pretrained and instruct models. • 8 items • Updated 4 days ago • 86

upvoted 5 papers 21 days ago

HumanEval-V: Evaluating Visual Understanding and Reasoning Abilities of Large Multimodal Models Through Coding Tasks

Paper • 2410.12381 • Published 24 days ago • 41

VidEgoThink: Assessing Egocentric Video Understanding Capabilities for Embodied AI

Paper • 2410.11623 • Published 24 days ago • 46

Movie Gen: A Cast of Media Foundation Models

Paper • 2410.13720 • Published 22 days ago • 86

MobA: A Two-Level Agent System for Efficient Mobile Task Automation

Paper • 2410.13757 • Published 22 days ago • 30

MixEval-X: Any-to-Any Evaluations from Real-World Data Mixtures

Paper • 2410.13754 • Published 22 days ago • 74

upvoted a paper 24 days ago

HelpSteer2-Preference: Complementing Ratings with Preferences

Paper • 2410.01257 • Published Oct 2 • 19

upvoted a collection 24 days ago

Llama-3.1-Nemotron-70B

SOTA models on Arena Hard and RewardBench as of 1 Oct 2024. • 6 items • Updated 24 days ago • 128

upvoted 4 papers 25 days ago

Aria: An Open Multimodal Native Mixture-of-Experts Model

Paper • 2410.05993 • Published Oct 8 • 107

WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agents

Paper • 2410.07484 • Published 30 days ago • 48

Baichuan-Omni Technical Report

Paper • 2410.08565 • Published 29 days ago • 82

DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data

Paper • 2405.14333 • Published May 23 • 34

upvoted a paper 29 days ago

GLEE: A Unified Framework and Benchmark for Language-based Economic Environments

Paper • 2410.05254 • Published Oct 7 • 80