← Back to all news
arXiv Computer Vision By Chaoyu Li, Arka Sadhu, Yuliang Li, Hyo Jin Kim, Yuning Chai, Pooyan Fazli

EgoP$^{2}$C: Internalizing Plan-Perceive-Compose for Spatial Reasoning in Egocentric Video

Read the original on arXiv Computer Vision →

EgoP$^{2}$C is a new framework that internalizes a plan‑perceive‑compose workflow within a single vision‑language model for spatial reasoning in egocentric video. It trains specialized Planner and Perception teachers via Dual‑LoRA adapters, then fine‑tunes a mixture‑of‑experts student under their supervision, using a segment‑level multi‑teacher on‑policy distillation to guide evidence‑seeking, stopping, and answer composition. The resulting student models, built on Qwen3‑VL‑8B and SenseNova‑SI‑1.3‑8B, outperform their base models by 9.2 and 7.5 percentage points on three benchmarks, while cutting inference FLOPs by about 66% and speeding up inference 1.29–1.49×.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Computer Vision
Sep 16

EgoPathBench: Evaluating Zero-Shot Egocentric Waypoint Decision-Making in Vision-Language Models

EgoPathBench is a new dataset and benchmark that tests zero‑shot egocentric waypoint decision‑making in vision‑language models. Each task presents an egocentric RGB image, a natural‑language goal, and numbered visible waypoints, and models must return traversable candidates or an ordered route. The benchmark evaluates candidate feasibility, edge legality, and goal arrival under point‑agent or embodied geometry, covering 31,852 training, 1,345 validation, and 1,111 benchmark questions. "whyItMatters":"The benchmark reveals that current VLMs perform poorly on integrated navigation tasks, highlighting a gap in spatial intelligence that can be addressed by fine‑tuning with the released training data."

By Yang Zhao, Zhuo Chen, Xubo Yang
llmsagentsroboticsfine-tuningmultimodalbenchmarks
More like this →
arXiv Computer Vision
Sep 30

Spatial-OPSD: Self-Improving Spatial Reasoning via Label-Free Self-Distillation

Spatial-OPSD is a label‑free self‑improvement framework for vision‑language models that leverages spatial priors such as depth, 3D relations, and camera geometry to provide dense token‑level supervision. During training, a privileged teacher uses these priors while the student learns from only the original visual‑language input, and a recursive round‑wise scheme allows repeated self‑improvement without moving the teacher. Across four VLM families, one round of Spatial‑OPSD improves the five‑benchmark average, and three rounds push a strong spatially specialized model to the open‑source frontier, achieving the highest average among open models and best results on three of five spatial reasoning benchmarks.

By Zhenyu Liu, Zhangquan Chen, Keyi Chen, Mingze Sun, Xiang An, Haodong Jing, Ruqi Huang
llmsroboticsefficiencymultimodalbenchmarks
More like this →
arXiv AI
Aug 5

SpatialCLI: Learning to Reason With Spatial Tools, Then Without Them

arXiv:2607. 27703v2 Announce Type: replace Abstract: Vision-language models (VLMs) are increasingly used in embodied agents to interpret visual inputs, reason about spatial relationships, and make task-level decisions based on that reasoning.

By Yang Zhou, Zixuan Huang, Sunzhu Li, Zhuo Yang, Chen Zhang, Shunian Chen, Caijun Yan, Jianyao Xu, Shunyu Liu, Weijie Fu, Peiliang Li, Xiaozhi Chen, Yuxiang Cai
llmsagentscomputer-visionreinforcement-learningroboticsfine-tuningmultimodalbenchmarks
More like this →