Models
Datasets
Spaces
Buckets new
Docs
Enterprise
Pricing
- Website
- Community
- Solutions
Log In
Sign Up

Collections

Discover the best community collections!

Collections including paper arxiv:2604.04921

WTF GENIUS PAPERS

Papers that made me appreciate my major and my life a little more. obs=Observation, innov=Innovation. Most papers are abt improving tiny models.

about 18 hours ago

Continuous Latent Diffusion Language Model

Paper • 2605.06548 • Published 26 days ago • 80
Scaling Latent Reasoning via Looped Language Models

Paper • 2510.25741 • Published Oct 29, 2025 • 231
Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach

Paper • 2502.05171 • Published Feb 7, 2025 • 156
Pretraining Language Models to Ponder in Continuous Space

Paper • 2505.20674 • Published May 27, 2025 • 3

TriAttention: Efficient Long Reasoning with Trigonometric KV Compression

Paper • 2604.04921 • Published Apr 6 • 114

TriAttention: Efficient Long Reasoning with Trigonometric KV Compression

Paper • 2604.04921 • Published Apr 6 • 114
deepseek-ai/DeepSeek-V4-Pro

Text Generation • 862B • Updated 27 days ago • 5.83M • • 4.54k

Mobile-O: Unified Multimodal Understanding and Generation on Mobile Device

Paper • 2602.20161 • Published Feb 23 • 23
A Very Big Video Reasoning Suite

Paper • 2602.20159 • Published Feb 23 • 525
Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model

Paper • 2603.21986 • Published Mar 23 • 125
AURA: Always-On Understanding and Real-Time Assistance via Video Streams

Paper • 2604.04184 • Published Apr 5 • 51

YOLO-Master: MOE-Accelerated with Specialized Transformers for Enhanced Real-time Detection

Paper • 2512.23273 • Published Dec 29, 2025 • 15
A 58-Addition, Rank-23 Scheme for General 3x3 Matrix Multiplication

Paper • 2512.21980 • Published Dec 26, 2025 • 3
Step-DeepResearch Technical Report

Paper • 2512.20491 • Published Dec 23, 2025 • 88
SAM Audio: Segment Anything in Audio

Paper • 2512.18099 • Published Dec 19, 2025 • 25

Efficient Training on Multiple Consumer GPUs with RoundPipe

Paper • 2604.27085 • Published Apr 29 • 47
TriAttention: Efficient Long Reasoning with Trigonometric KV Compression

Paper • 2604.04921 • Published Apr 6 • 114

Turboquant/Triattention

Ver isso mais tarde pra acelerar meus modelos de LLM / Imagem?

TriAttention: Efficient Long Reasoning with Trigonometric KV Compression

Paper • 2604.04921 • Published Apr 6 • 114

CarePilot: A Multi-Agent Framework for Long-Horizon Computer Task Automation in Healthcare

Paper • 2603.24157 • Published Mar 25 • 10
TriAttention: Efficient Long Reasoning with Trigonometric KV Compression

Paper • 2604.04921 • Published Apr 6 • 114
Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

Paper • 2604.24763 • Published Apr 27 • 71

Papers I'm going to read

LTX-2: Efficient Joint Audio-Visual Foundation Model

Paper • 2601.03233 • Published Jan 6 • 180
MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head

Paper • 2601.07832 • Published Jan 12 • 53
Motion Attribution for Video Generation

Paper • 2601.08828 • Published Jan 13 • 72
Post-LayerNorm Is Back: Stable, ExpressivE, and Deep

Paper • 2601.19895 • Published Jan 27 • 27

Meta-Awareness Enhances Reasoning Models: Self-Alignment Reinforcement Learning

Paper • 2510.03259 • Published Sep 26, 2025 • 57
Hybrid Reinforcement: When Reward Is Sparse, It's Better to Be Dense

Paper • 2510.07242 • Published Oct 8, 2025 • 30
First Try Matters: Revisiting the Role of Reflection in Reasoning Models

Paper • 2510.08308 • Published Oct 9, 2025 • 24
Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward

Paper • 2510.03222 • Published Oct 3, 2025 • 76

WTF GENIUS PAPERS

Papers that made me appreciate my major and my life a little more. obs=Observation, innov=Innovation. Most papers are abt improving tiny models.

about 18 hours ago

Continuous Latent Diffusion Language Model

Paper • 2605.06548 • Published 26 days ago • 80
Scaling Latent Reasoning via Looped Language Models

Paper • 2510.25741 • Published Oct 29, 2025 • 231
Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach

Paper • 2502.05171 • Published Feb 7, 2025 • 156
Pretraining Language Models to Ponder in Continuous Space

Paper • 2505.20674 • Published May 27, 2025 • 3

Efficient Training on Multiple Consumer GPUs with RoundPipe

Paper • 2604.27085 • Published Apr 29 • 47
TriAttention: Efficient Long Reasoning with Trigonometric KV Compression

Paper • 2604.04921 • Published Apr 6 • 114

TriAttention: Efficient Long Reasoning with Trigonometric KV Compression

Paper • 2604.04921 • Published Apr 6 • 114

Turboquant/Triattention

Ver isso mais tarde pra acelerar meus modelos de LLM / Imagem?

TriAttention: Efficient Long Reasoning with Trigonometric KV Compression

Paper • 2604.04921 • Published Apr 6 • 114

TriAttention: Efficient Long Reasoning with Trigonometric KV Compression

Paper • 2604.04921 • Published Apr 6 • 114
deepseek-ai/DeepSeek-V4-Pro

Text Generation • 862B • Updated 27 days ago • 5.83M • • 4.54k

CarePilot: A Multi-Agent Framework for Long-Horizon Computer Task Automation in Healthcare

Paper • 2603.24157 • Published Mar 25 • 10
TriAttention: Efficient Long Reasoning with Trigonometric KV Compression

Paper • 2604.04921 • Published Apr 6 • 114
Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

Paper • 2604.24763 • Published Apr 27 • 71

Mobile-O: Unified Multimodal Understanding and Generation on Mobile Device

Paper • 2602.20161 • Published Feb 23 • 23
A Very Big Video Reasoning Suite

Paper • 2602.20159 • Published Feb 23 • 525
Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model

Paper • 2603.21986 • Published Mar 23 • 125
AURA: Always-On Understanding and Real-Time Assistance via Video Streams

Paper • 2604.04184 • Published Apr 5 • 51

Papers I'm going to read

LTX-2: Efficient Joint Audio-Visual Foundation Model

Paper • 2601.03233 • Published Jan 6 • 180
MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head

Paper • 2601.07832 • Published Jan 12 • 53
Motion Attribution for Video Generation

Paper • 2601.08828 • Published Jan 13 • 72
Post-LayerNorm Is Back: Stable, ExpressivE, and Deep

Paper • 2601.19895 • Published Jan 27 • 27

YOLO-Master: MOE-Accelerated with Specialized Transformers for Enhanced Real-time Detection

Paper • 2512.23273 • Published Dec 29, 2025 • 15
A 58-Addition, Rank-23 Scheme for General 3x3 Matrix Multiplication

Paper • 2512.21980 • Published Dec 26, 2025 • 3
Step-DeepResearch Technical Report

Paper • 2512.20491 • Published Dec 23, 2025 • 88
SAM Audio: Segment Anything in Audio

Paper • 2512.18099 • Published Dec 19, 2025 • 25

Meta-Awareness Enhances Reasoning Models: Self-Alignment Reinforcement Learning

Paper • 2510.03259 • Published Sep 26, 2025 • 57
Hybrid Reinforcement: When Reward Is Sparse, It's Better to Be Dense

Paper • 2510.07242 • Published Oct 8, 2025 • 30
First Try Matters: Revisiting the Role of Reflection in Reasoning Models

Paper • 2510.08308 • Published Oct 9, 2025 • 24
Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward

Paper • 2510.03222 • Published Oct 3, 2025 • 76

Previous
1
2
Next

Company

TOS Privacy About Careers

Website

Models Datasets Spaces Pricing Docs