Chroma

Chroma111's activity

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

upvoted 2 collections 1 day ago

MOSS Transcribe

Collection

A unified multimodal large language model for end-to-end speaker-attributed, time-stamped transcription. • 4 items • Updated 1 day ago • 10

Agents-A1-abliterated

Collection

2 items • Updated 1 day ago • 1

upvoted 15 papers 1 day ago

SkillOpt-Lite: Better and Faster Agent Self-evolution via One Line of Vibe

Paper • 2607.03451 • Published 9 days ago • 26

Multi-Turn Agentic Scientific Literature Search via Workflow Induction

Paper • 2607.00597 • Published 11 days ago • 28

PhotoQuilt: Training-Free Arbitrary-Resolution Photomosaics via Bootstrapped Tiled Denoising

Paper • 2606.30968 • Published 13 days ago • 27

Multi-Block Diffusion Language Models

Paper • 2606.29215 • Published 12 days ago • 39

Vision as Unified Multimodal Generation

Paper • 2607.06560 • Published 5 days ago • 44

Vision Pretraining for Dense Spatial Perception

Paper • 2607.05247 • Published 6 days ago • 42

Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition

Paper • 2601.16211 • Published 10 days ago • 48

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence

Paper • 2607.07675 • Published 4 days ago • 47

Video-Oasis: Rethinking Evaluation of Video Understanding

Paper • 2603.29616 • Published 10 days ago • 51

Gemma 4 Technical Report

Paper • 2607.02770 • Published 10 days ago • 57

Dual Latent Memory in Vision-Language-Action Models for Robotic Manipulation

Paper • 2607.07608 • Published 4 days ago • 51

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

Paper • 2607.06558 • Published 5 days ago • 76

Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning

Paper • 2607.07708 • Published 4 days ago • 83

RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation

Paper • 2607.06559 • Published 5 days ago • 89

Vidu S1: A Real-Time Interactive Video Generation Model

Paper • 2607.03118 • Published 9 days ago • 120

upvoted a collection 1 day ago

NVFP4

Collection

Dynamic Unsloth NVFP4 Quants. Faster and more accurate. • 3 items • Updated about 1 hour ago • 20

upvoted a paper 1 day ago

Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling

Paper • 2607.02980 • Published 9 days ago • 64

upvoted a paper 2 days ago

Nemotron-Labs-3-Puzzle-75B-A9B: Compressing Hybrid MoE LLMs

Paper • 2607.04371 • Published 7 days ago • 5