The authors present WeVisOne-VL, a vision-language model that unifies object-level and pixel-level perception through structured next-token prediction. They add a lightweight pixel decoder to the VLM via a special <OBJ> token to output instance-level pixel masks, and train it with three-stage curriculum SFT followed by mixed-task RL.
arXiv:2610.31329
The authors present FilmFlow, an agentic framework that turns natural-language instructions or reference videos into explicit camera trajectories for dynamic 3D scenes. A Director agent composes high-level camera motions from concurrent atomic operations (translation, rotation, framing), supported by Interpreter, Scout, and Critic agents. They also release CinemaBench, with 150 Blender scenes, 750 text-directed tasks, and 60 reference videos.
arXiv:2610.30753
The authors present IQuest-Q1, a sparse Mixture-of-Experts agentic foundation model with 320B total parameters (15B activated). It is built through three stages: stable pre-training with a two-stage coding-weighted curriculum, fine-grained mid-training with progressive context extension, and multi-scaffold, multi-version post-training that combines SFT, domain-specialized RL, and MOPD, followed by model merging.
arXiv:2610.30949
The authors propose PACE, a post-hoc four-bit quantizer for the recurrent states of linear-attention language models. PACE rounds the state only every few generated tokens, buffering the intermediate tokens, and shares one quantization scale per column because large gated-delta state entries align in columns; heads that retain error longest are kept at eight bits.
arXiv:2610.29545