Chroma

Chroma111's activity

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

upvoted a paper about 7 hours ago

SemanTok: Predictable Semantic Tokens for Efficient Autoregressive Video Generation

Paper • 2610.00686 • Published 3 days ago • 4

upvoted a collection about 7 hours ago

Swift 27B

Collection

Swift 1.0, UkisAI's original reasoning-efficient model: 58% fewer thinking tokens than Qwen3.8-27B. BF16 weights and every quant. • 5 items • Updated 8 days ago • 2

upvoted an article about 8 hours ago

view article

Article

Open-sourcing AstaBrief, the fast report-generation model in Asta

• 

allenai

•

about 8 hours ago

• 8

upvoted a collection about 8 hours ago

AstaBrief

Collection

All datasets and model checkpoints from the training process of AstaBrief • 5 items • Updated about 9 hours ago • 2

upvoted a collection about 13 hours ago

Decision models

Collection

GGUF decision models for the /v1/systemone API in llama.cpp • 6 items • Updated about 10 hours ago • 11

upvoted a paper about 16 hours ago

Better Supervision Is Nearby: Neighborhood On-Policy Self-Distillation

Paper • 2609.39687 • Published 3 days ago • 7

upvoted a paper about 17 hours ago

In-Place Tokenizer Expansion for Pre-trained LLMs

Paper • 2607.15232 • Published Jul 16 • 2

upvoted 2 papers about 21 hours ago

Adaptive Reward Routing: Dynamic Multi-Reward Optimization for Joint Audio-Video Diffusion via Forward-Process RL

Paper • 2609.37200 • Published 4 days ago • 117

4Director: Controlling Video World Models with Rigid 3D Geometry

Paper • 2610.02160 • Published 2 days ago • 21

upvoted 2 articles about 22 hours ago

view article

Article

autotrust/JEV-27B-VL: a decision model that learned to see without a single image of training

• 

autotrust

•

3 days ago

• 3

view article

Article

autotrust/JEV-27B: fast, calibrated decisions and full reasoning from one open model

• 

autotrust

•

6 days ago

• 11

upvoted 9 papers about 23 hours ago

OSWorld-Science: A Benchmark of Computer Use Agents for Learning and Using Scientific Software

Paper • 2609.39903 • Published 3 days ago • 39

DyRAD: Radar Novel View Synthesis for Dynamic Driving Scenes

Paper • 2609.39841 • Published 3 days ago • 35

It's Not What the Image Shows: Irrelevant Context Destabilises VLM Judges Without Informing Them

Paper • 2609.37863 • Published 4 days ago • 36

TERRA: Terrain-Aware Reconstruction, Retargeting and Control for Musculoskeletal Locomotion

Paper • 2609.38653 • Published 4 days ago • 33

DC-SAE: Deep Compression Semantic Autoencoder for Faster Diffusion Convergence

Paper • 2609.39222 • Published 3 days ago • 36

LANTERN: Illuminating Hidden Mathematical Knowledge in Language Models

Paper • 2609.32264 • Published 7 days ago • 43

Agent Error Dataset: Scaling 50,000 Error--Diagnosis Pairs for Failure Analysis and Error-Aware Post-Training

Paper • 2609.40111 • Published 3 days ago • 46

Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering

Paper • 2609.38177 • Published 4 days ago • 59

More Choices, Fewer Decisions: Ordinal-Scale Bias in JEV-like Direct-Decision Models

Paper • 2609.38827 • Published 3 days ago • 52