Collection by 
4 days ago
Collections
Discover the best community collections!
Collections including paper arxiv:2605.12500
Collection by 
about 3 hours ago
-
Code as Agent Harness
Paper • 2605.18747 • Published • 210 -
SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture
Paper • 2605.12500 • Published • 191 -
From Context to Skills: Can Language Models Learn from Context Skillfully?
Paper • 2604.27660 • Published • 166 -
PhysBrain 1.0 Technical Report
Paper • 2605.15298 • Published • 143
Collection by 
12 days ago
Collection by 
8 days ago
-
ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling
Paper • 2603.25746 • Published • 155 -
TAPS: Task Aware Proposal Distributions for Speculative Sampling
Paper • 2603.27027 • Published • 144 -
Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models
Paper • 2603.25716 • Published • 156 -
LongCat-Next: Lexicalizing Modalities as Discrete Tokens
Paper • 2603.27538 • Published • 147
Collection by 
7 days ago
-
EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters
Paper • 2402.04252 • Published • 31 -
Vision Superalignment: Weak-to-Strong Generalization for Vision Foundation Models
Paper • 2402.03749 • Published • 15 -
ScreenAI: A Vision-Language Model for UI and Infographics Understanding
Paper • 2402.04615 • Published • 45 -
EfficientViT-SAM: Accelerated Segment Anything Model Without Performance Loss
Paper • 2402.05008 • Published • 24
Collection by 
11 days ago
-
SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture
Paper • 2605.12500 • Published • 191 -
From Context to Skills: Can Language Models Learn from Context Skillfully?
Paper • 2604.27660 • Published • 166 -
Stream-R1: Reliability-Perplexity Aware Reward Distillation for Streaming Video Generation
Paper • 2605.03849 • Published • 125 -
ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration
Paper • 2605.03042 • Published • 124
Collection by 
13 days ago
Collection by 4 days ago
Collection by 7 days ago
-
EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters
Paper • 2402.04252 • Published • 31 -
Vision Superalignment: Weak-to-Strong Generalization for Vision Foundation Models
Paper • 2402.03749 • Published • 15 -
ScreenAI: A Vision-Language Model for UI and Infographics Understanding
Paper • 2402.04615 • Published • 45 -
EfficientViT-SAM: Accelerated Segment Anything Model Without Performance Loss
Paper • 2402.05008 • Published • 24
Collection by about 3 hours ago
-
Code as Agent Harness
Paper • 2605.18747 • Published • 210 -
SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture
Paper • 2605.12500 • Published • 191 -
From Context to Skills: Can Language Models Learn from Context Skillfully?
Paper • 2604.27660 • Published • 166 -
PhysBrain 1.0 Technical Report
Paper • 2605.15298 • Published • 143
Collection by 11 days ago
-
SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture
Paper • 2605.12500 • Published • 191 -
From Context to Skills: Can Language Models Learn from Context Skillfully?
Paper • 2604.27660 • Published • 166 -
Stream-R1: Reliability-Perplexity Aware Reward Distillation for Streaming Video Generation
Paper • 2605.03849 • Published • 125 -
ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration
Paper • 2605.03042 • Published • 124
Collection by 12 days ago
Collection by 13 days ago
Collection by 8 days ago
-
ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling
Paper • 2603.25746 • Published • 155 -
TAPS: Task Aware Proposal Distributions for Speculative Sampling
Paper • 2603.27027 • Published • 144 -
Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models
Paper • 2603.25716 • Published • 156 -
LongCat-Next: Lexicalizing Modalities as Discrete Tokens
Paper • 2603.27538 • Published • 147