Efficient Reasoning on the Edge
Paper • 2603.16867 • Published • 9
AI & ML interests
None defined yet.
Recent Activity
View all activity
taesiri
submitted 4
papers to Daily Papers about 8 hours ago
MolmoB0T: Large-Scale Simulation Enables Zero-Shot Manipulation
Paper • 2603.16861 • Published • 1
OneWorld: Taming Scene Generation with 3D Unified Representation Autoencoder
Paper • 2603.16099 • Published • 1
WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation
Paper • 2603.16871 • Published • 41
taesiri
submitted a
paper to Daily Papers about 9 hours ago
taesiri
submitted 3
papers to Daily Papers 1 day ago
taesiri
submitted 5
papers to Daily Papers 2 days ago
Visual-ERM: Reward Modeling for Visual Equivalence
Paper • 2603.13224 • Published • 21
VQQA: An Agentic Approach for Video Evaluation and Quality Improvement
Paper • 2603.12310 • Published • 7
Spend Less, Reason Better: Budget-Aware Value Tree Search for LLM Agents
Paper • 2603.12634 • Published • 6
From Sparse to Dense: Multi-View GRPO for Flow Models via Augmented Condition Space
Paper • 2603.12648 • Published • 11
daVinci-Env: Open SWE Environment Synthesis at Scale
Paper • 2603.13023 • Published • 28
taesiri
submitted 5
papers to Daily Papers 5 days ago
One Model, Many Budgets: Elastic Latent Interfaces for Diffusion Transformers
Paper • 2603.12245 • Published • 17
WeEdit: A Dataset, Benchmark and Glyph-Guided Framework for Text-centric Image Editing
Paper • 2603.11593 • Published • 24
Multi-Task Reinforcement Learning for Enhanced Multimodal LLM-as-a-Judge
Paper • 2603.11665 • Published • 4
Understanding by Reconstruction: Reversing the Software Development Process for LLM Pretraining
Paper • 2603.11103 • Published • 8
Tiny Aya: Bridging Scale and Multilingual Depth
Paper • 2603.11510 • Published • 6
taesiri
submitted 2
papers to Daily Papers 6 days ago