UniCompress is a deployment-oriented framework that transforms multi-task vision‑language expertise into a single compact, adapter‑free model suitable for edge intelligence. Starting from a BF16 Qwen3‑VL‑4B teacher, it builds an asymmetric INT2 student using GPTQ initialization and teacher‑guided quantization recovery, jointly compressing both the vision encoder and language backbone. Evaluated on four embodied tasks, UniCompress cuts weight storage from 8.9 GB to 2.1 GB (≈76% reduction) while improving the INT2 macro task score by 34.3 percentage points over GPTQ‑INT2 and staying within 0.9 points of the BF16 teacher.
arXiv:2609.24526v2 Announce Type: replace Abstract: Physical AI requires models to ground visual and linguistic understanding in real-world environments while accounting for environmental constraints...
arXiv:2609.24526v1 Announce Type: new Abstract: Physical AI requires models to ground visual and linguistic understanding in real-world environments while accounting for environmental constraints and...
The paper introduces VLAct, a Vision‑Language‑Action model that focuses on representation‑centric continued pre‑training rather than merely scaling robot data. VLAct is trained on diverse, multi‑embodiment robot data and preserves a broad VLM prior while encouraging shared action semantics across embodiments. Experiments across simulation, real‑world, and unseen‑embodiment settings show that VLAct consistently outperforms existing industrial VLA systems, achieving high success rates with only a modest compute budget and open‑source data.
VisionWeave introduces elastic visual representation weaving, a native capability for multimodal large language models that learns where and at what granularity to encode visual information. The method combines a gated spatial pooler for coarse representations with a granularity router that allocates content‑adaptive token usage, trained end‑to‑end on large‑scale data. Experiments on Qwen3.5‑4B and Qwen3.8‑27B show that VisionWeave can save 43.0% of tokens while preserving 98.9% of performance across eight benchmarks, and delivers significant throughput gains and latency reductions when deployed on the SGLang serving engine.
arXiv:2601. 03309v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models, which integrate pretrained large Vision-Language Models (VLM) into their policy backbone, are gaining significant attention for their promising generalization capabilities.
arXiv:2606. 14752v1 Announce Type: cross Abstract: Modern Vision-Language-Action (VLA) models must bridge pretrained vision-language reasoning and precise continuous robot control.
Building capable embodied agents requires not only multimodal perception and understanding, but also agentic capabilities for reasoning about actions, adapting to evolving situations, and interacting with the physical world. In this report, we introduce Hy-Embodied-VLM-1.
arXiv:2608. 11739v1 Announce Type: cross Abstract: The prevailing recipe for Vision-Language-Action (VLA) models couples a pretrained VLM with a separately trained flow-matching action expert.
arXiv:2608. 06756v1 Announce Type: new Abstract: Vision-language models are increasingly serving as the reasoning core of embodied agents.
arXiv:2609.23974v1 Announce Type: new Abstract: Foundation models are endowing autonomous systems with greater intelligence, enabling a more comprehensive understanding of the environment through vis...
Foundation models are endowing autonomous systems with greater intelligence, enabling a more comprehensive understanding of the environment through visual perception. A representative example is Human...
COMET is a task‑agnostic continual learning framework for vision‑language models that addresses modal‑consistency drift, representation‑space interference, and per‑task capacity shortfall. It uses a frozen teacher for feature reference, Tri‑Affinity Distillation to preserve image‑image, text‑text, and image‑text geometry, and Student‑Aware Cross‑Expert Distillation to align new experts with prior ones, while a contextual bandit and reconstruction router manage capacity and inference. Experiments on the X‑TAIL benchmark show that each component improves continual learning performance, demonstrating that separating feature reference, expert shaping, routing, and capacity control enables effective multimodal adaptation.