J C

dark-pen's activity

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

upvoted 2 papers 1 day ago

Rewiring Experts on the Fly:Continuous Rerouting for Better Online Adaptation in Mixture-of-Expert models

Paper • 2510.14853 • Published Oct 16 • 4

How Far Are We from Genuinely Useful Deep Research Agents?

Paper • 2512.01948 • Published 10 days ago • 52

upvoted 3 collections 1 day ago

AIMv2

Collection

A collection of AIMv2 vision encoders that supports a number of resolutions, native resolution, and a distilled checkpoint. • 19 items • Updated Aug 25 • 82

AndesVL

Collection

AndesVL is a suite of mobile-optimized Multimodal Large Language Models (MLLMs) with 0.6B to 4B parameters. • 8 items • Updated Oct 15 • 12

Qwen-Image-Pruning

Collection

Pluggable Pruning with Contiguous Layer Distillation for Diffusion Transformers • 7 items • Updated 20 days ago • 5

upvoted 3 papers 1 day ago

Improved Visual-Spatial Reasoning via R1-Zero-Like Training

Paper • 2504.00883 • Published Apr 1 • 67

Selective Underfitting in Diffusion Models

Paper • 2510.01378 • Published Oct 1 • 2

Distribution Matching Variational AutoEncoder

Paper • 2512.07778 • Published 3 days ago • 22

upvoted a collection 1 day ago

SAE

Collection

6 items • Updated 1 day ago • 1

upvoted a paper 1 day ago

Native Parallel Reasoner: Reasoning in Parallelism via Self-Distilled Reinforcement Learning

Paper • 2512.07461 • Published 3 days ago • 68

upvoted a paper 3 days ago

DraCo: Draft as CoT for Text-to-Image Preview and Rare Concept Generation

Paper • 2512.05112 • Published 7 days ago • 11

upvoted a collection 3 days ago

MMSearch

Collection

Webpage of MMSearch: https://mmsearch.github.io/ • 2 items • Updated Sep 25, 2024 • 1

upvoted 2 papers 3 days ago

FineVision: Open Data Is All You Need

Paper • 2510.17269 • Published Oct 20 • 69

xGen-MM (BLIP-3): A Family of Open Large Multimodal Models

Paper • 2408.08872 • Published Aug 16, 2024 • 101

upvoted a paper 4 days ago

ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration

Paper • 2511.21689 • Published 15 days ago • 100

upvoted a paper 5 days ago

TTSDS -- Text-to-Speech Distribution Score

Paper • 2407.12707 • Published Jul 17, 2024 • 2

upvoted a collection 5 days ago

DiCoW

Collection

DiCoW (Diarization-Conditioned Whisper) is a collection of speaker-aware ASR models developed by BUT-FIT, extending OpenAI’s Whisper. • 6 items • Updated Oct 17 • 2

upvoted 2 papers 5 days ago

AR-GRPO: Training Autoregressive Image Generation Models via Reinforcement Learning

Paper • 2508.06924 • Published Aug 9 • 3

MultiLevel Variational MultiScale (ML-VMS) framework for large-scale simulation

Paper • 2510.23004 • Published Oct 27 • 1

upvoted a paper 7 days ago

Mathesis: Towards Formal Theorem Proving from Natural Languages

Paper • 2506.07047 • Published Jun 8 • 6