Video multimodal large language models support language guided video segmentation, but they often show spatio temporal inconsistencies, e.g., jitter, drift, and identity switches. These failures are more common when targets are partly hidden or when similar objects appear nearby.One likely reason is that current training lacks explicit spatial priors, which makes it difficult to maintain stable spatial identity and shape over time. We present PhysMLLMs, a training-stage prior injection architecture that injects physics-inspired spatial continuity priors into Video MLLMs. PhysMLLMs is designed to encourage more stable object-centered representations by aligning the student global visual representation with a frozen teacher model during training. Our core mechanism, Global Representation Prior Alignment (REPA-Global), distills global visual representations from a frozen DINOv2 teacher using an offline embedding cache and a scheduled distillation plan. This design keeps inference unchanged and does not add inference time cost. Across multiple video benchmarks, PhysMLLMs improves video segmentation mask quality and cross-frame consistency, with larger gains on challenging cases involving small targets, fast motion, occlusion, distractors, and reasoning queries. On single-frame referring image segmentation and representative general VLM benchmarks, PhysMLLMs maintains comparable performance, demonstrating that the injected spatial prior improves video consistency without compromising image-level grounding or general multimodal capability. These results suggest that physics-inspired spatial prior injection can improve temporal stability while preserving general capability. The code is available at https://github.com/tusu-code/20260121-icml2026-2.git.
Part-level affordance grounding has advanced the localization of functional object regions associated with elemental actions. Extending this capability to complex tasks calls for connecting the semantic roles of participating objects with task-state-aligned visual observations and multi-step planning. We introduce EgoAfford, a benchmark designed to connect these three aspects. Given an egocentric observation and a high-level tabletop task, a model must generate the remaining plan and segment the functional regions of up to three components of the next action: the direct object, instrument, and destination. EgoAfford comprises approximately 15.5k human-verified images from 2,000 generated multi-step scenes, organized as semantically aligned, task-complete image series, together with EgoAfford-Real, 102 manually captured images spanning 26 tasks. We further present EgoLens, a 3B multimodal large language model with role-specific mask decoders, as an in-domain reference model for this joint task. Evaluations of recent referring-segmentation MLLMs, commercial-VLM--SAM2 pipelines, and EgoLens highlight the complementary challenges of next-step inference and action-role-conditioned part grounding. EgoLens establishes strong reference performance on both generated and manually captured observations. Together, EgoAfford and EgoLens provide a foundation for jointly studying perception and planning in multi-step tabletop tasks. Our project page is available at: https://egoafford.github.io
Penglei Sun, Yehua Huang, Zhuoli Tao +8cs.CV cs.AI
Language-guided aerial perception aims to understand user-specified tiny targets in complex unmanned aerial vehicle (UAV) scenes. In real UAV deployment, the UAV must respond while it flies, so such perception runs in an online streaming manner, where frames arrive sequentially and the model responds to each one without access to future frames. However, applying current Multimodal Large Language Models (MLLMs) to this setting raises two challenges. First, targets viewed from the air are often tiny, yet the visual compression in existing MLLMs treats all regions equally and discards their fine-grained details. Second, understanding a continuous stream requires past-frame context, yet retaining the entire history is infeasible on resource-constrained onboard hardware, whereas discarding it causes the target to drift or disappear. We address the tiny object and streaming challenges from both data and method perspectives. From the data perspective, we present \textbf{DroneEyes}, the \textbf{first} pixel-level and open-vocabulary referring-segmentation dataset for tiny aerial targets, comprising $2,140$ high-definition videos and $176,623$ pairs across Object Description and Referring Expression tasks, with dense per-frame masks. From the method perspective, we propose \textbf{SkyAnchor}, an MLLM with two designs to the above challenges: a Semantics-Aware Token Router that preserves small-target under a reduced visual-token budget, and a Hierarchical Memory Bank that keeps the target consistently understood on streams.
This paper explores multi-turn visual reasoning and observes that MLLMs repeatedly fail to localize the target, leading to long, redundant trajectories. We attribute this failure to the entanglement of reasoning and perception within a single model, the MLLM reasons and localizes simultaneously, and inaccurate localization triggers additional reasoning turns that bloat the trajectory. To solve this problem, we propose PixelEyes, a multi-turn visual reasoning agent that explicitly decouples reasoning from perception, i.e., the reasoner decides what to look for, while a specialized perception tool answers where it is. Specifically, PixelEyes introduces 1) Mask-guided Visual Search. A referring segmentation model is invoked to provide mask-precise localization, freeing the reasoner from the need to compensate for imprecise grounding. 2) Semantic-region Breadth-first Search (BFS). To eliminate redundant loops caused by repeatedly cropping incorrect sub-regions, we organize exploration as a breadth-first search over semantic regions. To internalize these capabilities, we construct the PixelEyes-6K dataset by resynthesizing expert trajectories from existing data. This explicitly embeds our mask-guided search and BFS logic into the model. We further introduce Pinpoint-Bench, a zero-hint visual search benchmark, i.e., no location cues are provided in the question, with instance-level masks and bounding boxes that separate localization failures from reasoning failures, enabling fine-grained analysis of failure modes such as inattentional blindness. Recent state-of-the-art MLLMs and visual reasoning agents leave large headroom on Pinpoint-Bench, demonstrating its quality and difficulty. Code and models are open-sourced.
Referring Remote Sensing Image Segmentation (RRSIS) seeks to localize and segment the target object or region specified by a natural language expression in a remote sensing image. While existing RRSIS models have benefited from large-scale foundation models, they predominantly rely on full fine-tuning. These approaches are computationally intensive and may weaken the generalization ability of pre-trained models, as extensive fine-tuning on significantly smaller downstream datasets can distort the well-structured feature representations learned during large-scale pre-training. Although Parameter-Efficient Tuning (PET) offers a potential alternative, existing PET frameworks primarily focus on single-modal optimization, failing to capture the complex cross-modal dependencies required for multimodal reasoning, while simultaneously struggling to bridge the substantial domain gap between natural scenes and aerial imagery. To address these limitations, we propose a novel framework, Semantic-driven Scale and Spatial Selection for Efficient Cross-modal Alignment (S4ECA), which enables effective and efficient cross-modal interaction through parameter-efficient adaptation. Specifically, we design a dual-encoder adapter architecture. The textual adapter employs learnable queries to distill highly semantic language proxies from word-level embeddings, facilitating early grounding. Simultaneously, the visual adapter refines hierarchical feature representations through a multi-scale dense extractor, followed by a language-guided scale and spatial selection mechanism that dynamically emphasizes relevant visual contexts, ensuring precise cross-modal alignment. By updating only 2.4% of the backbone parameters, our proposed model achieves state-of-the-art performance on the RRSIS-D and RefSegRS datasets, demonstrating superior efficiency and precision in complex aerial scenarios.
Recent advances in 3D multimodal large language models (3D-MLLMs) have enabled unified solutions for 3D scene understanding tasks, including visual question answering, captioning, and referring segmentation. However, existing 3D-MLLMs remain largely object-centric, limiting their ability to model fine-grained part structures that are essential for embodied interaction with 3D environments. In this work, we present PAR3D, a unified part-aware 3D-MLLM framework that enables models to understand, reason about, and ground both objects and their parts in 3D scenes. To enable training and evaluation of part-aware 3D scene understanding, we introduce ScenePart, a synthetic 3D scene dataset with part-level annotations and language instructions. We further develop Part-Aware 3D Representation Learning to enrich 3D visual representations with fine-grained part-level semantics, and propose Hierarchical Segmentation Query Generation to ground part targets via hierarchical object-part queries. Extensive experiments show that our method substantially improves part-level question answering and referring segmentation, while also achieving strong performance across object-level vision-language tasks.