FilmFlow: Agentic System for 3D Virtual Film Cinematography Paper • 2610.30753 • Published 4 days ago • 31
VideoJev: System One Model for Video Understanding and Interaction Paper • 2610.18615 • Published 13 days ago • 342
VisionWeave: Weaving Elastic Visual Representations as a Native Capability of MLLMs Paper • 2610.07987 • Published 20 days ago • 73
Investigating the Role of Reasoning-Language Alignment in Monolingual Retrieval-Augmented Generation Paper • 2610.03136 • Published 24 days ago • 7
MotorMind: Scaffolding General Vision Language Models for Zero-Shot Robot Manipulation Paper • 2609.38078 • Published 27 days ago • 116
Think Before You Link: Rarity, Reasoning, and Retrieval in Multilingual Entity Linking Paper • 2609.10745 • Published Sep 9 • 23
A*-Thought-V2: Efficient Latent Reasoning via Geometric Dynamics of LLM Paper • 2609.07821 • Published Sep 7 • 15
Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training Paper • 2609.07108 • Published Sep 7 • 35