Célian Dumont

pcruz99's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 1 day ago

DynaFlow: Learning Free-Form Multi-Agent Orchestration

Paper • 2610.34467 • Published 4 days ago • 200

liked a model 1 day ago

google/gemma-4-26B-A4B

Image-Text-to-Text • 26B • Updated Jul 15 • 55.3k • • 452

liked 2 models 6 days ago

prism-ml/Ternary-Bonsai-27B-mlx-2bit

Text Generation • 27B • Updated Jul 14 • 976k • 218

tencent/HY-MT1.5-1.8B

Translation • 2B • Updated Jan 1 • 5.75k • • 1.2k

upvoted 3 papers 6 days ago

Making MLLM Latents Matter: Factor-Aware Predictive Learning for Cinematic Video Generation

Paper • 2610.30926 • Published 6 days ago • 204

Jeva: System One Models from First Principles

Paper • 2610.18773 • Published 16 days ago • 443

StreamEval: Evaluating Interactive Streaming Video Generation Models

Paper • 2610.28402 • Published 9 days ago • 865

liked 9 models 7 days ago

Qwen/Qwen1.5-1.8B-Chat-GPTQ-Int8

Text Generation • 2B • Updated Apr 30, 2024 • 238 • 9

google/siglip2-large-patch16-384

Zero-Shot Image Classification • 0.9B • Updated Feb 21, 2025 • 31.6k • 10

google/deplot

Visual Question Answering • 0.3B • Updated Sep 6, 2023 • 16.4k • 329

nvidia/Qwen3-32B-NVFP4

Text Generation • 17B • Updated Sep 9, 2025 • 7.77k • 26

google/t5-3b-ssm-nq

Text Generation • Updated Jan 24, 2023 • 411 • 6

facebook/mms-tts-tam

Text-to-Speech • 36.3M • Updated Feb 19, 2024 • 7.39k • 18

Qwen/Qwen3-VL-4B-Thinking

Image-Text-to-Text • 4B • Updated Oct 15, 2025 • 21.2k • • 131

nvidia/speakerverification_en_titanet_large

Updated Nov 14, 2023 • 98.4k • 137

nvidia/esm2_t48_15B_UR50D

Fill-Mask • 15B • Updated Apr 8 • 557 • 12

upvoted 4 papers 9 days ago

Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers

Paper • 2605.06169 • Published May 7 • 93

Self-Supervised Visual On-Policy Distillation

Paper • 2608.14144 • Published Aug 14 • 168

RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation

Paper • 2607.06558 • Published Jul 7 • 77

Demystifying Agent Skills: Why They Work-Until They Don't

Paper • 2608.14036 • Published Aug 14 • 168