VLMs across families and scales show anchoring to discrete slant angles in zero-shot and prompted settings rather than human-like graded texture-based slant perception.
In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3years
2026 3representative citing papers
HyLaR interleaves discrete text generation with continuous visual latent representations and optimizes them via a decoupled RL algorithm using vMF distributions, improving fine-grained visual reasoning.
ESC uses emotional cues triggered by an external verifier to enable training-free self-correction in VLMs, improving reliability on safety, hallucination, and reasoning benchmarks.
citing papers explorer
-
Anchored, Not Graded: Vision-Language Models Fail at Slant-from-Texture Perception
VLMs across families and scales show anchoring to discrete slant angles in zero-shot and prompted settings rather than human-like graded texture-based slant perception.
-
HyLaR: Hybrid Latent Reasoning with Decoupled Policy Optimization
HyLaR interleaves discrete text generation with continuous visual latent representations and optimizes them via a decoupled RL algorithm using vMF distributions, improving fine-grained visual reasoning.
-
ESC: Emotional Self-Correction for Reliable Vision-Language Models
ESC uses emotional cues triggered by an external verifier to enable training-free self-correction in VLMs, improving reliability on safety, hallucination, and reasoning benchmarks.