برچسب: بینایی ماشین

Enterprise AI Assistant Compliance Under Pressure

PACT examines whether enterprise AI assistants continue following rules under urgency, user pressure, and tempting shortcuts—and shows that correct answers in calm conditions are not enough for operational…

SIEVE: Selective Unlearning in Vision-Language Models via Attention-Value Suppression

SIEVE suppresses attention values for forget examples and matches them to a reference model for retain examples, reducing recovery of sensitive image–question–answer associations. Reported MLLMU-Bench results also show…

MOLE: Mixture of Latent Experts for Complementary Visual Reasoning

MOLE is designed to reduce redundancy in latent visual reasoning through selective visual routing and expert-specific latent transformations.

In Video Safety, “Unsafe” Is Not a Sufficient Answer

A close reading of a preprint on multi-label video safety detection and controlling false-positive versus false-negative errors during training.

Disentangling Spatial Reasoning Failures with Composable Video Operators

This paper introduces CROSS, a training-free library for explicit geometric computations in video spatial reasoning. By separating perception, evidence sufficiency, measurement choice, and coordinate conventions, the authors report…

Controlling Errors in Multi-label Video Safety Detection with ATPO

This paper introduces ATPO, a method for making the precision–recall trade-off controllable in multi-label unsafe-video detection. Experiments on two benchmarks show that its adaptive reward outperforms static rewards,…

Sphere Encoder 2: Image Generation with Rotation in a Spherical Latent Space

This paper introduces Sphere Encoder 2, a single-stage autoencoder for image generation that improves ImageNet samples by covering the equatorial region of its spherical latent space and separating…

When the Same Reward Teaches Different Visual Skills

This preprint argues that improved visual-benchmark scores need not come from learning from images; task design must make visual evidence necessary for reward.

VISTA: Lossless Visual Memory for Multimodal Agents

VISTA is a visual harness that lets multimodal models retrieve and re-examine past frames at their original detail. The authors report that this design substantially improves the underlying…

Turning 2D Vision-Language Models into 3D Programmers with Iterative Feedback

3D-Prog proposes using 2D vision-language models for 3D tasks without retraining through coordinate framing and execution feedback; this is a preprint with unverified independent review, and runtime cost,…