SmolLM2 Collection State-of-the-art compact LLMs for on-device applications: 1.7B, 360M, 135M β’ 8 items β’ Updated 4 days ago β’ 159
Breaking the Memory Barrier: Near Infinite Batch Size Scaling for Contrastive Loss Paper β’ 2410.17243 β’ Published 17 days ago β’ 86
ROCKET-1: Master Open-World Interaction with Visual-Temporal Context Prompting Paper β’ 2410.17856 β’ Published 16 days ago β’ 48
SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree Paper β’ 2410.16268 β’ Published 18 days ago β’ 65
FrugalNeRF: Fast Convergence for Few-shot Novel View Synthesis without Learned Priors Paper β’ 2410.16271 β’ Published 18 days ago β’ 80
steiner-preview Collection Reasoning models trained on synthetic data using reinforcement learning. β’ 3 items β’ Updated 19 days ago β’ 23
Granite 3.0 Language Models Collection A series of language models trained by IBM licensed under Apache 2.0 license. We release both the base pretrained and instruct models. β’ 8 items β’ Updated 4 days ago β’ 86
HumanEval-V: Evaluating Visual Understanding and Reasoning Abilities of Large Multimodal Models Through Coding Tasks Paper β’ 2410.12381 β’ Published 24 days ago β’ 41
VidEgoThink: Assessing Egocentric Video Understanding Capabilities for Embodied AI Paper β’ 2410.11623 β’ Published 24 days ago β’ 46
MobA: A Two-Level Agent System for Efficient Mobile Task Automation Paper β’ 2410.13757 β’ Published 22 days ago β’ 30
MixEval-X: Any-to-Any Evaluations from Real-World Data Mixtures Paper β’ 2410.13754 β’ Published 22 days ago β’ 74
HelpSteer2-Preference: Complementing Ratings with Preferences Paper β’ 2410.01257 β’ Published Oct 2 β’ 19
Llama-3.1-Nemotron-70B Collection SOTA models on Arena Hard and RewardBench as of 1 Oct 2024. β’ 6 items β’ Updated 24 days ago β’ 128
Aria: An Open Multimodal Native Mixture-of-Experts Model Paper β’ 2410.05993 β’ Published Oct 8 β’ 107
WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agents Paper β’ 2410.07484 β’ Published 30 days ago β’ 48
DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data Paper β’ 2405.14333 β’ Published May 23 β’ 34
GLEE: A Unified Framework and Benchmark for Language-based Economic Environments Paper β’ 2410.05254 β’ Published Oct 7 β’ 80