arXiv:2602. 23353v2 Announce Type: replace-cross Abstract: The Platonic Representation Hypothesis posits that neural networks trained on different modalities converge toward a shared statistical model of the world.
arXiv:2606. 23885v1 Announce Type: cross Abstract: Representation alignment has emerged as an effective approach to improve Multimodal Large Language Models (MLLMs) by regularizing their internal representations toward those of an external vision encoder.
The paper introduces AURORA, a hyperbolic vision‑language framework that separates angular alignment from radial ordering. Angular alignment captures semantic similarity while a novel Radial‑Angular Order Cone (RAOC) models hierarchical entailment based on parent‑child radial gaps. The approach includes norm regularization to prevent radial degeneration and is evaluated on large image‑text datasets, outperforming both Euclidean and hyperbolic baselines in zero‑shot classification, retrieval, hierarchical reasoning, and compositional understanding.
arXiv:2606. 29464v1 Announce Type: cross Abstract: Vision-language dataset distillation (VLDD) compresses a large image-text paired dataset into a small set of synthetic pairs that can efficiently train contrastive vision-language models under strict data and compute budgets.
RankAlign introduces a rank-based normalization technique for aligning vision and language representations without cross-modal supervision. By converting within-modality similarity kernels into ordinal relational representations, it preserves the relative ordering of similarities while remaining invariant to strictly increasing reparameterizations. The method offers theoretical guarantees for exact and partial ordinal agreement and shows improved, more stable class-level correspondence recovery across various frozen encoders and datasets, even under label corruption and domain shift.
arXiv:2610.02718v1 Announce Type: cross Abstract: Vision-language models such as CLIP exhibit strong semantic generalization, but remain limited in fine-grained visual perception. A recent work named...
arXiv:2602. 07026v3 Announce Type: replace-cross Abstract: Despite the success of multimodal contrastive learning in aligning visual and linguistic representations, a persistent geometric anomaly, the Modality Gap, remains: embeddings of distinct modalities expressing identical semantics occupy systematically offset regions.
The paper introduces TopoBench-180, a human‑verified benchmark of 180 structural diagrams with canonical graph annotations, and TopoAgent, a perception‑to‑reasoning framework that extracts graph topology from diagrams using large vision‑language models. TopoAgent combines grounded perception, global structural priors, node inventory construction, local‑to‑global relation reasoning, and consistency enforcement to progressively build the target graph. Experiments demonstrate that TopoAgent surpasses strong baselines, particularly in edge extraction, thereby advancing multimodal structured understanding for diagram‑to‑graph tasks.
arXiv:2606. 14172v1 Announce Type: new Abstract: Multimodal Attributed Graphs (MAGs) model real-world entities by coupling graph topology with heterogeneous attributes such as text and images.
arXiv:2604. 04050v2 Announce Type: replace-cross Abstract: Flow-matching methods for 3D shape assembly learn point-wise velocity fields that transport parts toward assembled configurations, yet they receive no explicit guidance about which cross-part interactions should drive the motion.
The paper investigates the Platonic Representation Hypothesis, which posits that more capable models converge toward shared representations. By distinguishing relational structure (which samples are related) from metric geometry (quantitative relations like distances), the authors develop a controlled $2 imes2$ framework to evaluate both aspects at local and global scales. Their findings show that relational structure consistently converges across vision‑language and video‑text models, while metric geometry converges much more weakly, a pattern that persists even when using a Riemannian metric approximation.
arXiv:2603. 26798v2 Announce Type: replace-cross Abstract: Vision-language model (VLM) encoders such as CLIP enable strong retrieval and zero-shot classification in a shared image-text embedding space, yet the semantic organization of this space is rarely inspected.