representation-alignment

Tag

Cards List
#representation-alignment

Fusion is not one-size-fits-all: Cross-Modal Representation Alignment for Time-to-Event Modeling

arXiv cs.AI ↗ · 2026-06-16 Cached

Introduces a foundation model–driven framework for cross-modal representation alignment between CT imaging and longitudinal EHR data for time-to-event prediction, evaluating fusion strategies on pulmonary embolism and cardiovascular disease cohorts.

0 favorites 0 likes
#representation-alignment

MaskAlign: Token-Subset Representation Alignment for Efficient Diffusion Training

Hugging Face Daily Papers ↗ · 2026-06-07 Cached

MaskAlign proposes a token-subset representation alignment method that improves diffusion transformer training by reducing reliance on complete token sets and maintaining stable alignment under perturbations.

0 favorites 0 likes
#representation-alignment

Improving Relative Representations with Learned Anchors and Whitened Inner Products

arXiv cs.LG ↗ · 2026-06-01 Cached

This paper proposes improvements to Relative Representations by learning robust semantic anchors and using a geometry-aware similarity metric, enabling nearly lossless information transfer and stable zero-shot communication between independently trained models of varying architectures.

0 favorites 0 likes
#representation-alignment

Representation Alignment Rests on Linear Structure

arXiv cs.LG ↗ · 2026-05-29 Cached

This paper investigates the Platonic Representation Hypothesis, proposing that alignment arises from linear structure in representations, and introduces a statistical framework of signal, bias, and noise.

0 favorites 0 likes
#representation-alignment

LoMo: Local Modality Substitution for Deeper Vision-Language Fusion

Hugging Face Daily Papers ↗ · 2026-05-28 Cached

LoMo proposes a data curation method that reformulates single-modality prompts into interleaved multimodal sequences to improve cross-modal representation alignment in vision-language models, achieving consistent gains on multiple benchmarks.

0 favorites 0 likes
#representation-alignment

Don't Retrain, Align: Adapting Autoregressive LMs to Diffusion LMs via Representation Alignment

arXiv cs.LG ↗ · 2026-05-11 Cached

This paper introduces Repr-Align, a method to adapt autoregressive language models into diffusion language models via representation alignment, achieving up to 4x training acceleration without retraining representations from scratch.

0 favorites 0 likes
#representation-alignment

Anisotropic Modality Align

Hugging Face Daily Papers ↗ · 2026-05-08 Cached

This paper proposes AnisoAlign, a framework that addresses the modality gap in multimodal models by applying anisotropic geometric correction to enable effective unpaired modality alignment.

0 favorites 0 likes
#representation-alignment

TextLDM: Language Modeling with Continuous Latent Diffusion

Hugging Face Daily Papers ↗ · 2026-05-08 Cached

This paper introduces TextLDM, a method that adapts visual latent diffusion transformers for language modeling by mapping discrete tokens to continuous latents. It demonstrates that this approach, enhanced by representation alignment, matches GPT-2 performance and unifies visual and text generation architectures.

0 favorites 0 likes
#representation-alignment

UniSD: Towards a Unified Self-Distillation Framework for Large Language Models

Hugging Face Daily Papers ↗ · 2026-05-07 Cached

This paper introduces UniSD, a unified self-distillation framework for adapting large language models that integrates mechanisms for supervision reliability, representation alignment, and training stability. Experimental results show that UniSD improves performance over base models and existing baselines across multiple benchmarks.

0 favorites 0 likes
#representation-alignment

MMCORE: MultiModal COnnection with Representation Aligned Latent Embeddings

Hugging Face Daily Papers ↗ · 2026-04-21 Cached

MMCORE introduces a unified multimodal image generation and editing framework that aligns VLM semantic embeddings with diffusion conditioning, achieving state-of-the-art fidelity without costly fusion or from-scratch training.

0 favorites 0 likes
← Previous
← Back to home

Submit Feedback