Looks the Same, Answers Differently: Flip-Direction Steering for Robust Vision-Language Reasoning

arXiv:2609.28851 · cs.CV · Submitted 2026-09-23 · Read on arXiv

cs.CV

Submitted: 2026-09-23

Updated: 2026-09-23

Comments: 27 pages

Code: https://github.com/meta-llama/llama-models

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Steering — 36× in this paper · explained in 2 episodes
• Benchmark — 22× in this paper · explained in 2 episodes
• Accuracy — 13× in this paper · explained in 1 episode
• Robustness — 11× in this paper · explained in 5 episodes
• Calibration — 9× in this paper · explained in 7 episodes
• Trace — 8× in this paper · explained in 2 episodes
• Ablation — 7× in this paper · explained in 1 episode
• Computer Vision and Pattern Recognition — 6× in this paper
• Hallucination — 6× in this paper · explained in 3 episodes
• Consistency — 5× in this paper · explained in 3 episodes
• Benchmarking — 4× in this paper · explained in 3 episodes
• Adaptation — 3× in this paper · explained in 1 episode
• Alignment — 3× in this paper · explained in 1 episode
• In International Conference on Learning Representations — 2× in this paper
• Vision-Language Models (VLMs) — 2× in this paper · explained in 6 episodes
• AUC — 1× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Activation Addition — 1× in this paper · explained in 1 episode
• Adversarial Attacks — 1× in this paper · explained in 1 episode
• Adversarial Robustness — 1× in this paper · explained in 3 episodes
• CVF International Conference on Computer Vision — 1× in this paper
• Conference on Computer and Robot Vision — 1× in this paper
• Decode — 1× in this paper · explained in 2 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Hallucination Mitigation — 1× in this paper · explained in 2 episodes
• Hysteresis — 1× in this paper · explained in 3 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• Provenance — 1× in this paper · explained in 3 episodes
• Reconstruction Error — 1× in this paper · explained in 2 episodes
• Visual Grounding — 1× in this paper · explained in 2 episodes

Sources

• Qwen3-VL Technical Report
• Robo2VLM: Visual Question Answering from Large-Scale In-the-Wild Robot Manipulation Datasets
• GMAI-MMBench: A Comprehensive Multimodal Evaluation Benchmark Towards General Medical AI
• MedMNIST-C: Comprehensive benchmark and improved classifier robustness by simulating realistic image corruptions
• Gemma 3 Technical Report
• Questioning the Stability of Visual Question Answering
• Benchmarking Large Multimodal Models against Common Corruptions

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models