arXiv Machine Learning August 18, 2026 By Kin Ian Lo

The Limits of Binding in Dual Encoders

Read the original on arXiv Machine Learning →

arXiv:2608. 15971v1 Announce Type: new Abstract: Dual-encoder models such as CLIP score an image-caption pair by a single inner product of two independently computed unit vectors, and fail at binding, often scoring near chance when asked to distinguish "a red car and a blue dog" from "a blue car and a red dog".

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

arXiv AI

Jun 3

Beyond Encoder Accumulation: Measuring Encoder Roles in Multi-Encoder VLMs

arXiv:2606. 03879v1 Announce Type: cross Abstract: As foundation models scale toward fusing more heterogeneous visual streams, understanding how diverse encoders interact under joint training becomes a prerequisite for principled design.

By Wei Ding, Yudong Zhang, Ruobing Xie, Xingwu Sun, Jiansheng Chen, Yu Wang

llms multimodal benchmarks

arXiv Machine Learning

Jun 2

Capability and Robustness Cannot Both Be Free: An Information-Theoretic Bound for Vision-Language-Action Models

arXiv:2605. 25889v4 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models reach high success rates on clean inputs but collapse under small adversarial perturbations: a $16/255$ PGD attack drops OpenVLA-7B's LIBERO success from $95\%$ to under $5\%$.

By Jianwei Tai

multimodal safety

arXiv AI

Jul 28

Cheap Probes Predict Expensive Training in 3D-CT Vision--Language Models

arXiv:2607. 22771v1 Announce Type: cross Abstract: Picking the frozen image encoder for a 3D~CT vision--language model (VLM), together with the token-compression scheme on top of it, is a search over many candidates.

By Renjie Liang

llms rag fine-tuning multimodal benchmarks

arXiv AI

Jul 7

Input Pathways Shape Few-Shot, Not Zero-Shot, Binding in Tiny Transformers: A Fully-Enumerable Study

arXiv:2607. 04926v1 Announce Type: cross Abstract: How does the way information reaches a transformer -- as symbolic tokens, a clean per-factor "oracle" code, or an entangled perceptual vector -- shape whether it binds that information compositionally?

By Yoshiyuki Ootani

llms safety

arXiv AI

Aug 13

Low-Interaction-Rank Learning: Unifying Multiplicative Dual-Encoder Heads

arXiv:2608. 11661v1 Announce Type: cross Abstract: A multiplicative dual-encoder network computes a real-valued output for a pair of inputs as the inner product of their separate encodings.

By Zijian Zhao, Sen Li

llms multimodal

arXiv Machine Learning

Jul 28

The Entropic Bound for Transformers: Why Static Rank Fails and Attention-Native Rank Recovers

arXiv:2607. 23050v1 Announce Type: new Abstract: Neural scaling laws describe how loss decreases as models, data, and compute grow, but they do not answer a prior question: for a fixed task, what is the minimum model capacity required to solve it?

By Byeong Hoon Yoon

llms safety

Related stories

Beyond Encoder Accumulation: Measuring Encoder Roles in Multi-Encoder VLMs

Capability and Robustness Cannot Both Be Free: An Information-Theoretic Bound for Vision-Language-Action Models

Cheap Probes Predict Expensive Training in 3D-CT Vision--Language Models

Input Pathways Shape Few-Shot, Not Zero-Shot, Binding in Tiny Transformers: A Fully-Enumerable Study

Low-Interaction-Rank Learning: Unifying Multiplicative Dual-Encoder Heads

The Entropic Bound for Transformers: Why Static Rank Fails and Attention-Native Rank Recovers