Teiji Takagi
softmaximalist
AI & ML interests
None yet
Recent Activity
updated a collection about 4 hours ago
Vision updated a collection about 4 hours ago
Vision updated a collection about 4 hours ago
lang-modelOrganizations
lang-model
-
DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation
Paper • 2607.05147 • Published • 49 -
Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning
Paper • 2609.03430 • Published • 170 -
LFM2 Technical Report
Paper • 2511.23404 • Published • 72 -
Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills
Paper • 2609.02749 • Published • 537
Vision
-
VGGT-Det: Mining VGGT Internal Priors for Sensor-Geometry-Free Multi-View Indoor 3D Object Detection
Paper • 2603.00912 • Published • 40 -
Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation
Paper • 2609.08084 • Published • 43 -
Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving
Paper • 2609.00111 • Published • 377
safety
lang-model
-
DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation
Paper • 2607.05147 • Published • 49 -
Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning
Paper • 2609.03430 • Published • 170 -
LFM2 Technical Report
Paper • 2511.23404 • Published • 72 -
Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills
Paper • 2609.02749 • Published • 537
abstract/latent
Vision
-
VGGT-Det: Mining VGGT Internal Priors for Sensor-Geometry-Free Multi-View Indoor 3D Object Detection
Paper • 2603.00912 • Published • 40 -
Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation
Paper • 2609.08084 • Published • 43 -
Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving
Paper • 2609.00111 • Published • 377