Pixelis: Reasoning in Pixels, from Seeing to Acting
Most vision-language systems are static observers: they describe pixels, do not act, and cannot safely improve under shift. This passivity limits generalizable, physically grounded visual intelligence. Learning through action, not static description, is essential beyond curated data. We present Pixelis, a pixel-space agent that operates directly on images and videos via a compact set of executable operations (zoom/crop, segment, track, OCR, temporal localization) and learns from its consequences. Pixelis trains in three phases: (1) Supervised Fine-Tuning learns a pixel-tool grammar from Chain-of-Thought-Action traces with a masked imitation loss that upweights operation/argument tokens and auxiliary heads to stabilize pixel-grounded arguments; (2) Curiosity-Coherence Reward Fine-Tuning optimizes a dual-drive objective marrying prediction-error curiosity with adjacent-step coherence and a mild efficiency prior under a KL anchor, yielding short, valid, structured toolchains; (3) Pixel Test-Time RL performs label-free adaptation by retrieving neighbors, voting over complete trajectories rather than answers, and updating toward short, high-fidelity exemplars while constraining drift with a KL-to-EMA safety control. Across six public image and video benchmarks, Pixelis yields consistent improvements: the average relative gain is +4.08% over the same 8B baseline (peaking at +6.03% on VSI-Bench), computed as (ours-baseline)/baseline, while producing shorter, auditable toolchains and maintaining in-corridor KL during test-time learning. Acting within pixels, rather than abstract tokens, grounds multimodal perception in the physical world, linking visual reasoning with actionable outcomes, and enables embodied adaptation without external feedback.
Code (0)
등록된 구현이 없습니다.
Tasks
Visual ReasoningSimilar Papers 제목 키워드 기반
The Expense of Seeing: Attaining Trustworthy Multimodal Reasoning Within the Monolithic Paradigm
The rapid proliferation of Vision-Language Models (VLMs) is often framed as enabling unified multimodal knowledge discovery but rests on an under-examined assumption: that current VLMs faithfully synthesise multimodal da…
Multimodal ReasoningSeeing without Pixels: Perception from Camera Trajectories
Can one perceive a video's content without seeing its pixels, just from the camera trajectory-the path it carves through space? This paper is the first to systematically investigate this seemingly implausible question. T…
Camera Pose EstimationContrastive LearningResponsibility in Extensive Form Games
Two different forms of responsibility, counterfactual and seeing-to-it, have been extensively discussed in the philosophy and AI in the context of a single agent or multiple agents acting simultaneously. Although the gen…
counterfactualFormPhilosophyBad Seeing or Bad Thinking? Rewarding Perception for Multimodal Reasoning
Achieving robust perception-reasoning synergy is a central goal for advanced Vision-Language Models (VLMs). Recent advancements have pursued this goal via architectural designs or agentic workflows. However, these approa…
Reinforcement LearningMultimodal ReasoningSeeing Culture: A Benchmark for Visual Reasoning and Grounding
Multimodal vision-language models (VLMs) have made substantial progress in various tasks that require a combined understanding of visual and textual content, particularly in cultural understanding tasks, with the emergen…
Visual Question AnsweringVisual Reasoning