arXiv Machine Learning September 11, 2026 By Gaurav Sarkar, Syed Affan Daimi, Jay Gala, Subarna Tripathi

SG-Blend: Learning an Interpolation Between Improved Swish and GELU for Robust Neural Representations

Read the original on arXiv Machine Learning →

SG-Blend introduces a per‑layer adaptive activation that interpolates between a bias‑corrected, parametric Swish variant (SSwish) and GELU, using a learnable blend coefficient, sharpness, and zero‑centering bias. The method adds only three scalars per feed‑forward block and, on BERT‑style IMDB classification, matches peak accuracy while reducing seed‑to‑seed variance by 42 %. It also achieves the lowest validation perplexity on WikiText103 and generalizes to computer vision and other domains.

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 Machine Learning.

arXiv AI

Jun 6

Predict and Reconstruct: Joint Objectives for Self-Supervised Language Representation Learning

arXiv:2606. 05173v1 Announce Type: cross Abstract: Masked language modelling (MLM) has been the dominant pre-training objective for text encoders since BERT, yet it encourages representations that are strongly anchored to surface-form token identity rather than deeper semantic structure.

By Aimen Boukhari

rag diffusion benchmarks

arXiv AI

Aug 11

LF${}^{2}$AR: Accounting for Layerwise Dynamics to Improve Multimodal Adaptation of Language Models

arXiv:2503. 06211v3 Announce Type: replace-cross Abstract: Text-pretrained language models (LMs) encode rich world knowledge, but adapting them to process and generate perceptual modalities such as audio and images while effectively leveraging that knowledge remains challenging.

By Santiago Cuervo, Adel Moumen, Yanis Labrak, Sameer Khurana, Antoine Laurent, Mickael Rouvier, Phil Woodland, Ricard Marxer

llms multimodal benchmarks safety

arXiv AI

Jul 1

Gradient Smoothing: Coupling Layer-wise Updates for Improved Optimization

arXiv:2606. 30813v1 Announce Type: cross Abstract: Deep neural networks with repeated architectural blocks, such as transformers, often exhibit structured relationships across layers that emerge during training.

By Haoming Meng, Anton Sugolov, Vardan Papyan

llms diffusion computer-vision reinforcement-learning

Hugging Face Trending Papers

Jul 26

PathSelect: Sequential Token Selection for Whole Slide Pathology

Gigapixel Whole-Slide Images (WSIs) present a fundamental computational bottleneck for vision-language models (VLMs) due to extreme sequence lengths. Existing approaches predominantly rely on spatial sampling or training-free pruning, which risk diluting weak but informative signals, leading to the loss of critical diagnostic evidence due to the spatially diffuse nature of pathological cues.

llms efficiency multimodal

arXiv Computer Vision

Sep 10

Isotropic Embedding Perturbations for Robust Vision Language Encoders

arXiv:2609.10292v1 Announce Type: new Abstract: Data augmentation is fundamental to training modern deep vision and multimodal models. While individual methods, such as RandAug, CutMix, Mixup, RandEr...

By Hyesong Choi, Daeun Kim, Song Park, Taekyung Kim, Byeongho Heo, Sangdoo Yun, Dongbo Min, Dongyoon Han

llms rag diffusion multimodal safety

arXiv Machine Learning

Jul 2

MMLoP: Multi-Modal Low-Rank Prompting for Efficient Vision-Language Adaptation

arXiv:2602. 21397v2 Announce Type: replace-cross Abstract: Prompt learning has become a dominant paradigm for adapting vision-language models (VLMs) such as CLIP to downstream tasks without modifying pretrained weights.

By Sajjad Ghiasvand, Haniyeh Ehsani Oskouie, Mahnoosh Alizadeh, Ramtin Pedarsani

llms rag multimodal benchmarks safety

One email a morning, machine-written

Related stories

Predict and Reconstruct: Joint Objectives for Self-Supervised Language Representation Learning

LF${}^{2}$AR: Accounting for Layerwise Dynamics to Improve Multimodal Adaptation of Language Models

Gradient Smoothing: Coupling Layer-wise Updates for Improved Optimization

PathSelect: Sequential Token Selection for Whole Slide Pathology

Isotropic Embedding Perturbations for Robust Vision Language Encoders

MMLoP: Multi-Modal Low-Rank Prompting for Efficient Vision-Language Adaptation