arXiv:2505. 18227v4 Announce Type: replace-cross Abstract: In Transformer architectures, tokens\textemdash discrete units derived from raw data\textemdash are formed by segmenting inputs into fixed-length chunks.
arXiv:2607. 25527v1 Announce Type: cross Abstract: Unifying visual understanding and generation in one model holds immense promise, but remains challenging and expensive due to heavy compute and data demands and conflicts between the visual features needed for these two capabilities.
arXiv:2609.40362v1 Announce Type: new Abstract: We present Multimodal Flow, a fully continuous generative model of language and vision. Most unified multimodal models either model both language and q...
arXiv:2505.10202v2 Announce Type: replace Abstract: Large Language Models (LLMs) have achieved remarkable success but face significant computational and memory challenges, particularly due to their e...
MoEMB introduces a mixture‑of‑experts (MoE) approach to scale universal multimodal embeddings (UME) without increasing the size of the output vector or relying on autoregressive decoding. By expanding encoder capacity along the expert axis, MoEMB achieves state‑of‑the‑art performance on MMEB‑V2 and MRMR benchmarks with only 3 B active parameters, outperforming TTE‑based methods that use more than four times as many active parameters and require significantly more compute. The paper also presents the first comprehensive study of adaptive computation for MoE‑based embeddings, exploring training‑time and inference‑time strategies to further improve efficiency for large‑scale retrieval and recommendation systems.
The paper introduces M2Tok, a Multi-head Multi-codebook Action Tokenizer that reduces reconstruction loss for continuous action signals by decomposing latent features into multiple heads and assigning independent codebooks to each. This design expands representational expressivity, leading to lower reconstruction error and higher success rates in Vision‑Language‑Action models evaluated on RoboTwin, Simpler‑Env, and zero‑shot real‑world tasks. Ablation studies confirm the effectiveness of both multi‑head and multi‑codebook mechanisms.
arXiv:2508. 20330v5 Announce Type: replace Abstract: Combinatorial optimization problems are ubiquitous in science and engineering.
arXiv:2508. 00956v3 Announce Type: replace-cross Abstract: User representation learning serves as a fundamental pillar for personalized services on large-scale web platforms.
arXiv:2606. 00324v1 Announce Type: cross Abstract: Multimodal LLMs use dedicated encoders to bridge non-language modalities (vision encoders for images, depth models for audio codec tokens) because raw token embeddings alone cannot capture modality-specific structure.
RGSQ introduces a Riemannian geometry‑aware post‑training quantization method for large vision‑language models, treating quantization as a reconstruction problem under a Fisher‑Riemannian metric. It identifies modality‑specific sensitive directions via manifold mappings and applies geometry‑aligned rotations and whitening to steer low‑bit perturbations toward loss‑insensitive axes. Experiments on diverse VLM benchmarks show RGSQ delivers the best accuracy and stability in extremely low‑bit settings, outperforming existing VLM‑aware baselines by up to 5.9% and single‑modality methods by up to 8.6%.
The paper introduces ${M}^2$Tok, a Multi-head Multi-codebook Action Tokenizer that reduces reconstruction loss in discrete action tokenization for Vision‑Language‑Action models. By decomposing latent action features into multiple heads and assigning independent codebooks to each, the tokenizer expands representational expressivity and improves policy performance. Experiments on RoboTwin, Simpler‑Env, and zero‑shot real‑world tasks show superior reconstruction fidelity and higher success rates compared to prior methods.
arXiv:2606. 30319v1 Announce Type: cross Abstract: Modeling the bidirectional correspondence between external sensory stimuli and internal neural activity has emerged as a critical frontier in neuroscience.