The paper introduces Conditional Predictive Sufficient Statistics (CPSS) as a formal way to capture useful visual representations that preserve latent factors shared with future data while discarding noise. It shows that predicting the next image patch embedding with a cosine loss approximates maximum likelihood under a von Mises-Fisher model, and that stop‑gradient alone does not enforce sufficiency. Experiments on MNIST and CIFAR‑10 with small causal Transformers demonstrate that CPSS readouts outperform intermediate blocks, while removing stop‑gradient collapses embedding rank even when the pretext loss appears perfect.
A useful visual representation is a statistic of the observed past that retains the latent factors shared with the future and discards patch-private noise. We formalize this requirement as a condition...
arXiv:2609.38485v1 Announce Type: new Abstract: Unified multimodal models (UMMs) train image understanding and autoregressive image generation on shared parameters, and the two objectives are known t...
arXiv:2608. 25138v1 Announce Type: new Abstract: Stochastic masking, cropping, or modality removal makes deterministic reconstruction an incomplete target: one observation can admit many clean completions.
arXiv:2608. 12939v1 Announce Type: new Abstract: Joint-embedding predictive architectures (JEPAs) learn world models that predict in a compact latent space rather than in pixels, reducing the pressure to model nuisance appearance.
arXiv:2608. 04879v1 Announce Type: new Abstract: Vision Transformers (ViTs) achieve strong image-recognition performance, but their parameter count grows linearly with depth when each block is independently parameterized.
arXiv:2608.23253v1 Announce Type: cross Abstract: Vision-language models typically encode an image into hundreds of visual tokens, incurring substantial inference latency and GPU memory overhead. Exi...
arXiv:2604. 21395v3 Announce Type: replace-cross Abstract: Ordinary supervised training minimises the task loss and then stops.
arXiv:2608. 19376v1 Announce Type: cross Abstract: Split-conformal prediction provides marginal coverage under exchangeability and is increasingly used as an abstention layer for zero-shot vision-language models (VLMs).
arXiv:2604.05819v2 Announce Type: replace-cross Abstract: Interpreting the decisions of complex computer vision models is crucial to establish trust and accountability, especially in safety-critical...
arXiv:2607. 18088v1 Announce Type: new Abstract: Standard evaluation of many recognition systems contains distribution shift by construction, since benchmarks place disjoint conditions in the training and test splits.
arXiv:2609.00868v1 Announce Type: cross Abstract: Vision-language models are evaluated by aggregate accuracy on multimodal benchmarks, a practice that implicitly assumes the model uses its visual inp...
The paper investigates why multimodal large language models (MLLMs) struggle with vision‑centric tasks when visual evidence conflicts with pretrained language knowledge. Using image reconstruction and a new WhatIfVis benchmark, the authors show that MLLMs preserve coarse‑grained visual attributes but fail to consistently use them, and that supervised fine‑tuning and activation patching can improve controllability of visual context sensitivity. The study demonstrates that the main bottleneck lies in the models’ inability to reliably regulate their reliance on visual evidence rather than in visual perception itself.