arXiv AI June 9, 2026 By Xingyu Ren, Youran Sun, Haoyu Liang

Correcting Mean Bias in Text Embeddings: A Refined Renormalization with Training-Free Improvements on MMTEB

arXiv:2511. 11041v2 Announce Type: replace-cross Abstract: We find that current sentence-embedding models produce outputs with a consistent bias: every embedding $e$ decomposes as $\tilde e + \mu$, where the mean $\mu$ is near-identical across all sentences.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv Machine Learning

Aug 7

Decoupling Perception from Description: Computation-Grounded Representation Alignment between Multivariate Time Series and Language

arXiv:2608. 05238v1 Announce Type: new Abstract: Training multimodal models to align time series with language runs into a self-supervision trap.

By Xinran Feng, Yi Xie, Chao Zhang, Ruikun Li, Wanyun Ling, Ziyue Li, Chenxi Liu

llms multimodal benchmarks safety

arXiv Machine Learning

Aug 6

When More Becomes Less: Position-Dependent Repetition Effects in Language Models

arXiv:2608. 04021v1 Announce Type: cross Abstract: Cloze-style probes that vary how often a target token appears implicitly assume that more copies of a target affect prediction the same way regardless of where the readout slot sits.

By Han-yu Wang

llms benchmarks

arXiv AI

Jun 26

Reconstruction Alignment Improves Unified Multimodal Models

arXiv:2509. 07295v4 Announce Type: replace-cross Abstract: Unified multimodal models (UMMs) unify visual understanding and generation within a single architecture.

By Ji Xie, Trevor Darrell, Luke Zettlemoyer, XuDong Wang

rag diffusion multimodal benchmarks safety

arXiv AI

Jul 17

Introspection Fine-Tuning (IFT): Training Small LLMs to Introspect

arXiv:2607. 14111v1 Announce Type: cross Abstract: Can small language models detect and report on perturbations their own internal activations?

By Ely Hahami, Ishaan Sinha, Lavik Jain

llms fine-tuning benchmarks safety

arXiv AI

Jul 21

CoCurve: Cross-Module Co-Pruning Curvature for Training-Free Structured LLM Pruning

arXiv:2607. 17568v1 Announce Type: cross Abstract: Structured pruning compresses large language models (LLMs) by removing whole computational units, such as attention heads and feed-forward (FFN) channel groups.

By Zhiren Gong, Zihao Zeng, Zijie Wang, Tiantong Wang, Chau Yuen, Wei Yang Bryan Lim

llms fine-tuning efficiency benchmarks

arXiv AI

Jun 24

When Language Overwrites Vision: Over-Alignment and Geometric Debiasing in Vision-Language Models

arXiv:2605. 08245v4 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) increasingly power high-stakes applications, from medical imaging to autonomous systems, yet they routinely hallucinate, confidently describing content not present in the input.

By Harshvardhan Saini, Samyak Jha, Yiming Tang, Dianbo Liu

llms rag agents fine-tuning multimodal benchmarks safety

Related stories

Decoupling Perception from Description: Computation-Grounded Representation Alignment between Multivariate Time Series and Language

When More Becomes Less: Position-Dependent Repetition Effects in Language Models

Reconstruction Alignment Improves Unified Multimodal Models

Introspection Fine-Tuning (IFT): Training Small LLMs to Introspect

CoCurve: Cross-Module Co-Pruning Curvature for Training-Free Structured LLM Pruning

When Language Overwrites Vision: Over-Alignment and Geometric Debiasing in Vision-Language Models