PRISM: Demystifying Retention and Interaction in Mid-Training Paper • 2603.17074 • Published 2 days ago
LaDe: Unified Multi-Layered Graphic Media Generation and Decomposition Paper • 2603.17965 • Published about 24 hours ago • 4
Unified Spatio-Temporal Token Scoring for Efficient Video VLMs Paper • 2603.18004 • Published about 24 hours ago • 5
MolmoB0T: Large-Scale Simulation Enables Zero-Shot Manipulation Paper • 2603.16861 • Published 2 days ago • 2
OneWorld: Taming Scene Generation with 3D Unified Representation Autoencoder Paper • 2603.16099 • Published 3 days ago • 1
WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation Paper • 2603.16871 • Published 2 days ago • 51
EvoClaw: Evaluating AI Agents on Continuous Software Evolution Paper • 2603.13428 • Published 7 days ago • 13
Code-A1: Adversarial Evolving of Code LLM and Test LLM via Reinforcement Learning Paper • 2603.15611 • Published 3 days ago • 10
VQQA: An Agentic Approach for Video Evaluation and Quality Improvement Paper • 2603.12310 • Published 7 days ago • 7
Spend Less, Reason Better: Budget-Aware Value Tree Search for LLM Agents Paper • 2603.12634 • Published 7 days ago • 6
From Sparse to Dense: Multi-View GRPO for Flow Models via Augmented Condition Space Paper • 2603.12648 • Published 7 days ago • 11
The Curse and Blessing of Mean Bias in FP4-Quantized LLM Training Paper • 2603.10444 • Published 8 days ago • 10