Collection by 
about 9 hours ago
Collections
Discover the best community collections!
Collections including paper arxiv:2605.27365
Collection by 
3 days ago
-
FAN: Fourier Analysis Networks
Paper • 2410.02675 • Published • 29 -
Tensor Product Attention Is All You Need
Paper • 2501.06425 • Published • 91 -
Scalable-Softmax Is Superior for Attention
Paper • 2501.19399 • Published • 25 -
EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling
Paper • 2502.09509 • Published • 9
Collection by 
2 days ago
Collection by 
3 days ago
Collection by 
1 day ago
-
LTX-2: Efficient Joint Audio-Visual Foundation Model
Paper • 2601.03233 • Published • 180 -
MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head
Paper • 2601.07832 • Published • 53 -
Motion Attribution for Video Generation
Paper • 2601.08828 • Published • 72 -
Post-LayerNorm Is Back: Stable, ExpressivE, and Deep
Paper • 2601.19895 • Published • 27
Collection by 
3 days ago
-
Warp-as-History: Generalizable Camera-Controlled Video Generation from One Training Video
Paper • 2605.15182 • Published • 39 -
STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?
Paper • 2605.06527 • Published • 44 -
Learning to Build the Environment: Self-Evolving Reasoning RL via Verifiable Environment Synthesis
Paper • 2605.14392 • Published • 8 -
World Action Models: The Next Frontier in Embodied AI
Paper • 2605.12090 • Published • 67
Collection by 
2 days ago
-
MolmoAct2: Action Reasoning Models for Real-world Deployment
Paper • 2605.02881 • Published • 345 -
LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding
Paper • 2605.27365 • Published • 118 -
Continuous Latent Diffusion Language Model
Paper • 2605.06548 • Published • 80
Collection by 
2 days ago
Collection by 
3 days ago
-
Fast-SAM3D: 3Dfy Anything in Images but Faster
Paper • 2602.05293 • Published • 2 -
Stroke of Surprise: Progressive Semantic Illusions in Vector Sketching
Paper • 2602.12280 • Published • 34 -
CADEvolve: Creating Realistic CAD via Program Evolution
Paper • 2602.16317 • Published • 30 -
SketchDynamics: Exploring Free-Form Sketches for Dynamic Intent Expression in Animation Generation
Paper • 2601.20622 • Published • 2
Collection by 
about 23 hours ago
-
YOLO-Master: MOE-Accelerated with Specialized Transformers for Enhanced Real-time Detection
Paper • 2512.23273 • Published • 15 -
A 58-Addition, Rank-23 Scheme for General 3x3 Matrix Multiplication
Paper • 2512.21980 • Published • 3 -
Step-DeepResearch Technical Report
Paper • 2512.20491 • Published • 88 -
SAM Audio: Segment Anything in Audio
Paper • 2512.18099 • Published • 25
Collection by about 9 hours ago
Collection by 3 days ago
-
Warp-as-History: Generalizable Camera-Controlled Video Generation from One Training Video
Paper • 2605.15182 • Published • 39 -
STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?
Paper • 2605.06527 • Published • 44 -
Learning to Build the Environment: Self-Evolving Reasoning RL via Verifiable Environment Synthesis
Paper • 2605.14392 • Published • 8 -
World Action Models: The Next Frontier in Embodied AI
Paper • 2605.12090 • Published • 67
Collection by 3 days ago
-
FAN: Fourier Analysis Networks
Paper • 2410.02675 • Published • 29 -
Tensor Product Attention Is All You Need
Paper • 2501.06425 • Published • 91 -
Scalable-Softmax Is Superior for Attention
Paper • 2501.19399 • Published • 25 -
EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling
Paper • 2502.09509 • Published • 9
Collection by 2 days ago
-
MolmoAct2: Action Reasoning Models for Real-world Deployment
Paper • 2605.02881 • Published • 345 -
LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding
Paper • 2605.27365 • Published • 118 -
Continuous Latent Diffusion Language Model
Paper • 2605.06548 • Published • 80
Collection by 2 days ago
Collection by 2 days ago
Collection by 3 days ago
Collection by 3 days ago
-
Fast-SAM3D: 3Dfy Anything in Images but Faster
Paper • 2602.05293 • Published • 2 -
Stroke of Surprise: Progressive Semantic Illusions in Vector Sketching
Paper • 2602.12280 • Published • 34 -
CADEvolve: Creating Realistic CAD via Program Evolution
Paper • 2602.16317 • Published • 30 -
SketchDynamics: Exploring Free-Form Sketches for Dynamic Intent Expression in Animation Generation
Paper • 2601.20622 • Published • 2
Collection by 1 day ago
-
LTX-2: Efficient Joint Audio-Visual Foundation Model
Paper • 2601.03233 • Published • 180 -
MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head
Paper • 2601.07832 • Published • 53 -
Motion Attribution for Video Generation
Paper • 2601.08828 • Published • 72 -
Post-LayerNorm Is Back: Stable, ExpressivE, and Deep
Paper • 2601.19895 • Published • 27
Collection by about 23 hours ago
-
YOLO-Master: MOE-Accelerated with Specialized Transformers for Enhanced Real-time Detection
Paper • 2512.23273 • Published • 15 -
A 58-Addition, Rank-23 Scheme for General 3x3 Matrix Multiplication
Paper • 2512.21980 • Published • 3 -
Step-DeepResearch Technical Report
Paper • 2512.20491 • Published • 88 -
SAM Audio: Segment Anything in Audio
Paper • 2512.18099 • Published • 25