Dynamic watermarking detects replay attacks in vision controllers
RL policy balances watermark energy against control distortion on UR5 robot.
Stories per day · 30 days
2 RSS
Relatedagents1bci1deepseek1detection1ensembles1inference-time1language-models1long-context1medical-device1mixture-of-experts1model-release1neuralink1neural-thickets1openrouter1prima1replay1robotics1stargardt1
9 stories, newest first · one card per story
Stories tagged #vision
Neural Thickets gains traced to output diversity rather than weight experts
Perturb-Select-Vote on frozen models matches or beats full-weight perturbations on most reasoning tasks and helps vision under domain shift.
DeepSeek: DeepSeek v4.1 Flash 1017
DeepSeek's October 17 V4.1 Flash snapshot is a 552B MoE with native vision and 1M context.
12
Hide and Seek: HIDE Concepts to SEEK explanations for black box models
Hide and Seek attributes concepts in black-box vision models without weights or labeled concept datasets.
speridlabs/iris-3b — new model trending #30 on Hugging Face
Sperid Labs released Iris-3B, a 3-billion-parameter pixel-space image model that also does depth and upscaling.
7
How Far Are We from Removing the Visual Encoder? Scaling Laws for Encoder-Free Multimodal Pretraining
Scaling laws suggest encoder-free multimodal models catch encoder-based ones near 10^22 FLOPs as the visual prior matters less.
VisionHOPE: Visual Backbones as Self-Modifying Learning Systems
VisionHOPE introduces a self-modifying visual backbone where memory content and learning rules co-evolve per image, with competitive ImageNet, COCO, and ADE20K results.
VDiff-Bench: A Challenging Benchmark for Fine-Grained Image Difference Identification
VDiff-Bench, a 1,756-question benchmark, shows multimodal LLMs struggle with fine-grained image-difference identification, scoring as low as 8.7% on low-level changes.
Tri-PvP: Exposing Modality Bias in Omni-Modal Large Language Models through Perceptual-Propositional Evidence Conflicts
Tri-PvP is a new benchmark revealing robust modality bias in omni-modal LLMs, with vision favoring perceptual signals and audio favoring propositional ones.