arXiv AI September 4, 2026 By Javier del Pino (SperidLabs), Salvador Rodr\'iguez (SperidLabs), Alejandro Garabito (SperidLabs), Javier \'Alvarez (SperidLabs), Chema Garabito (SperidLabs)

ENEAS: Embedding-guided Neural Ensemble for Adaptive Segmentation

Read the original on arXiv AI →

ENEAS is a unified, text‑promptable method that simultaneously provides precise instance tracking and high‑quality segmentation, and enables open‑concept discovery of any instance named by a text query. It extends the SeC architecture with a text‑prompting adapter and temporal memory to maintain targets through disappearance and avoid drifting, while a semantic verification layer combines visual embedding matching with conditional VLM refinement to filter ontological errors. Designed for 3D reconstruction, ENEAS delivers robust semantic tracking and segmentation across videos, libraries, and unordered collections, distinguishing true instances from look‑alike doppelgangers.

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 AI.

arXiv AI

4d ago

GoDeep: Annotation-Free Open-Vocabulary 3D Scene Understanding via Language-Space Lifting

GoDeep is an annotation‑free method for open‑vocabulary 3D scene understanding that uses a vision‑language model solely as a translator to generate structured, entity‑level descriptions of each image. These descriptions are projected and aggregated in a language‑only embedding space, eliminating the need for a 3D training corpus or domain‑specific encoder. The approach achieves competitive performance on ScanNet++ and a cultural heritage benchmark, accurately localizes out‑of‑vocabulary objects, and offers explainable, point‑level predictions.

By Thodoris Betsas, Anastasios Doulamis, Andreas Georgopoulos

llms rag computer-vision multimodal benchmarks

arXiv Computer Vision

Aug 28

Retrieval Heads Meet Vision: Uncovering How VLMs Locate and Extract Visual Information

The paper introduces Visual Retrieval Heads (VRHs), a small fraction of attention heads in vision‑language models that are causally responsible for grounding text descriptions to image regions. By recasting head‑scoring methods and evaluating across eleven VLMs and five benchmarks, the authors show that masking the top 20 VRHs can drop grounding accuracy by up to 80 percentage points, while random masking has little effect. VRHs generalize across various visual reference tasks, preserve output format while corrupting localization, and transfer causally across models sharing an LLM backbone.

By Chanho Park, Daehyeon Choi, Jihyun Lee, Minhyuk Sung

llms fine-tuning multimodal benchmarks

arXiv AI

Jun 19

QueryGaussian: Scalable and Training-Free Open-Vocabulary 3D Instance Retrieval

arXiv:2606. 19733v1 Announce Type: cross Abstract: Efficiently retrieving specific 3D instances from large-scale scenes via natural language prompts remains a formidable challenge in multimedia analysis.

By Xiuyuan Zhu, Ke Lu, Zijie Yang, Chao Yue, Jian Xue, Dongming Zhang

rag computer-vision efficiency benchmarks

arXiv AI

Jul 7

Generative Semantic Multi-Object Tracking: A Large-Scale Benchmark and an MLLM-Driven Reasoning Framework

arXiv:2601. 06550v3 Announce Type: replace-cross Abstract: Semantic Multi-Object Tracking (SMOT) is evolving from purely geometric localization toward comprehensive video understanding.

By Pan Liao, Feng Yang, Di Wu, Jinwen Yu, Wang Zhao, Dingwen Zhang

llms multimodal benchmarks safety

arXiv AI

Jun 2

An Open-Source Benchmark and Baseline for Multi-temporal Referring Segmentation

arXiv:2606. 00987v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) have shown strong visual understanding and language-guided grounding abilities, yet their capacity for multi-temporal visual reasoning remains underexplored.

By Bingyu Li, Da Zhang, Tao Huo, Zhiyuan Zhao, Junyu Gao, Xuelong Li

llms agents computer-vision fine-tuning multimodal benchmarks

arXiv AI

Jul 31

TraceCLIP: Recovering Local Semantics from Patch-to-CLS Contributions

arXiv:2607. 26107v1 Announce Type: cross Abstract: Dense vision-language understanding, including object localization, region recognition, and open-vocabulary semantic segmentation, requires associating language concepts with spatially grounded visual regions.

By Xinran Liu, Shouqian Shi, Yutong Chen, Ge Wang, Xin-Wei Yao, Sheng Zhong

rag computer-vision multimodal benchmarks safety

One email a morning, machine-written

Related stories

GoDeep: Annotation-Free Open-Vocabulary 3D Scene Understanding via Language-Space Lifting

Retrieval Heads Meet Vision: Uncovering How VLMs Locate and Extract Visual Information

QueryGaussian: Scalable and Training-Free Open-Vocabulary 3D Instance Retrieval

Generative Semantic Multi-Object Tracking: A Large-Scale Benchmark and an MLLM-Driven Reasoning Framework

An Open-Source Benchmark and Baseline for Multi-temporal Referring Segmentation

TraceCLIP: Recovering Local Semantics from Patch-to-CLS Contributions