Vision-language models achieve at most 61.9% accuracy on identifying image distortion types and severities, falling short of human majority-vote performance at 65.7%.
Visual instruction tuning
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
Multimodal LLMs act as training-free similarity estimators for instance-level image retrieval by converting next-token probabilities from image-pair prompts into scores, combined with efficient indexing for scalability.
SSL-R1 reformulates visual SSL tasks into verifiable puzzles to supply rewards for RL post-training of MLLMs, yielding gains on multimodal benchmarks without external supervision.
DexWild co-trains dexterous robot policies on in-the-wild human hand interactions recorded with a low-cost system and limited robot data, achieving 68.5% success in unseen environments and 5.8x better cross-embodiment generalization.
citing papers explorer
-
DistortBench: Benchmarking Vision Language Models on Image Distortion Identification
Vision-language models achieve at most 61.9% accuracy on identifying image distortion types and severities, falling short of human majority-vote performance at 65.7%.
-
Indexing Multimodal Language Models for Large-scale Image Retrieval
Multimodal LLMs act as training-free similarity estimators for instance-level image retrieval by converting next-token probabilities from image-pair prompts into scores, combined with efficient indexing for scalability.
-
SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models
SSL-R1 reformulates visual SSL tasks into verifiable puzzles to supply rewards for RL post-training of MLLMs, yielding gains on multimodal benchmarks without external supervision.
-
DexWild: Dexterous Human Interactions for In-the-Wild Robot Policies
DexWild co-trains dexterous robot policies on in-the-wild human hand interactions recorded with a low-cost system and limited robot data, achieving 68.5% success in unseen environments and 5.8x better cross-embodiment generalization.